Latest / What's Your Problem? / Scanning Every Muscle to Help Olympians Get Stronger

Transcript

Scanning Every Muscle to Help Olympians Get Stronger · What's Your Problem?

• 0:08
  Speaker 1: Hushkin, what's one surprising thing your work has taught you
• 0:19
  Speaker 1: about elite athletes?
• 0:22
  Speaker 2: I never thought I would see muscles that were so
• 0:25
  Speaker 2: developed they broke our scale. Wow.
• 0:31
  Speaker 1: Yeah, like it was just too big the machine, the
• 0:34
  Speaker 1: AI couldn't figure out what it is.
• 0:35
  Speaker 2: Well, no, the AI found it, but we are like
• 0:38
  Speaker 2: our kind of rating system.
• 0:40
  Speaker 1: Wow. Was there a particular athlete or a particular sport
• 0:43
  Speaker 1: or particular muscle?
• 0:44
  Speaker 2: What?
• 0:44
  Speaker 1: What? What muscle broke the scale?
• 0:47
  Speaker 2: Uh? The gluteus maximus breaks it A.
• 0:49
  Speaker 1: Fair kidding fantastic.
• 0:53
  Speaker 2: Yes, it's a pain in my butt.
• 0:56
  Speaker 1: Like because it's too big.
• 0:58
  Speaker 2: Yeah, it's just so big.
• 1:06
  Speaker 1: I'm Jacob Goldstein and this is what's your Problem? This
• 1:09
  Speaker 1: month a bunch of Pushkin podcasts are coming out with
• 1:12
  Speaker 1: Olympics inspired shows. Revisionist History has a series about America's
• 1:17
  Speaker 1: decision to participate in Hitler's Berlin Olympics in nineteen thirty six.
• 1:23
  Speaker 1: The Happiness Lab has an interview with a coach who
• 1:26
  Speaker 1: coaches coaches and here on What's Your Problem, We're going
• 1:30
  Speaker 1: to be talking with people who are working at the
• 1:32
  Speaker 1: frontiers of technology to help elite athletes perform better. For example,
• 1:39
  Speaker 1: today my guest is Sylvia Blemker. She's a professor of
• 1:43
  Speaker 1: biomechanical engineering at the University of Virginia, and she's the
• 1:47
  Speaker 1: co founder of a company called Springbok Analytics. Sylvia's problem
• 1:52
  Speaker 1: is this, how do you combine MRI scans and artificial
• 1:55
  Speaker 1: intelligence to generate new insights that can help both elite
• 1:59
  Speaker 1: athletes and people suffering from diseases that affect the muscles.
• 2:04
  Speaker 1: Springbox clients include medical researchers, Olympic athletes, major League baseball,
• 2:09
  Speaker 1: and several professional basketball and soccer teams. You'll hear about
• 2:13
  Speaker 1: all that on the show, but first we're going to
• 2:16
  Speaker 1: pick up where we left off in the conversation. We
• 2:20
  Speaker 1: were discussing the extraordinarily large muscles of elite athletes, and
• 2:25
  Speaker 1: then Sylvia told me something even more surprising.
• 2:30
  Speaker 2: The other thing is that they have some tiny muscles too, Huh.
• 2:33
  Speaker 1: Like they have like smaller than a normal person's muscle.
• 2:36
  Speaker 2: Much smaller.
• 2:37
  Speaker 1: Huh.
• 2:38
  Speaker 2: They put their muscle where they need it.
• 2:40
  Speaker 1: What's an example, Like what muscle is tiny and what
• 2:42
  Speaker 1: kind of athletes?
• 2:44
  Speaker 2: Calf muscles are small in most fast athletes huh? And
• 2:49
  Speaker 2: ether you look at a sprinter or like a running back.
• 2:53
  Speaker 1: It's just all quad no calf, all.
• 2:57
  Speaker 2: Like thigh no calf, yeah, THI And it kind of
• 3:00
  Speaker 2: makes sense because you know, if you're trying to run fast,
• 3:03
  Speaker 2: you wouldn't want to put a lot of mass like
• 3:04
  Speaker 2: at the end of your leg. It's like as a
• 3:07
  Speaker 2: lot of inertia to like move your leg.
• 3:09
  Speaker 1: Huh.
• 3:09
  Speaker 2: Because you know, the muscles are important for sprinting, that's
• 3:12
  Speaker 2: the interesting thing, but they just don't they're small, very.
• 3:16
  Speaker 1: H huh uh huh. So I'm particularly interested at this
• 3:20
  Speaker 1: moment in the sports piece of what you do. I'm curious,
• 3:27
  Speaker 1: by the way. Do you work with any Olympic teams
• 3:31
  Speaker 1: or Olympic athletes? Yeah?
• 3:33
  Speaker 2: Yeah, We've actually been working with several different Olympic athletes.
• 3:39
  Speaker 2: The ones that probably that come to mind most are
• 3:42
  Speaker 2: multiple players on the US women's national soccer team.
• 3:46
  Speaker 1: Oh cool, tell me, like, tell me the story of
• 3:48
  Speaker 1: that of that work. So they came to you, what
• 3:52
  Speaker 1: did what did they what do they want when they
• 3:54
  Speaker 1: came to you? Like, how did that? How did that begin?
• 3:57
  Speaker 2: They came to us along with their team. So the
• 4:01
  Speaker 2: technology we provide, you know, an athlete could understand it,
• 4:04
  Speaker 2: but really with their team to help them figure out
• 4:07
  Speaker 2: how to keep athletes healthy.
• 4:10
  Speaker 1: So what did they what did they say? What did
• 4:12
  Speaker 1: they say when they came to.
• 4:14
  Speaker 2: So, for example, one athlete that's coming to mind had
• 4:20
  Speaker 2: a known imbalance side to side that based on a
• 4:25
  Speaker 2: history of injury, and they really wanted to know where
• 4:28
  Speaker 2: that imbalance was coming from.
• 4:30
  Speaker 1: So the woman had had hurt one of her legs,
• 4:33
  Speaker 1: and that leg was even after she came back, that
• 4:35
  Speaker 1: leg was weaker essentially than the other. I mean, is
• 4:38
  Speaker 1: that the sort of gross you know, macro.
• 4:41
  Speaker 2: Way, Yeah, exactly, that's a that's a nice way to
• 4:43
  Speaker 2: put it.
• 4:43
  Speaker 1: Yeah, And and they wanted a sort of finder like, okay,
• 4:47
  Speaker 1: but we can see that, but what's going on on
• 4:49
  Speaker 1: the inside, like muscle by muscle tell us that, yes.
• 4:53
  Speaker 2: Exactly, that's precisely what we do. We go on the
• 4:55
  Speaker 2: inside because on the outside you see perhaps that her
• 5:01
  Speaker 2: knee extents or quads seem weaker on one side than
• 5:04
  Speaker 2: the other. But there's four quads, quadre steps, four muscles,
• 5:09
  Speaker 2: and so it's not clear which of those muscles are
• 5:11
  Speaker 2: actually the culprit for that imbalance and in what way.
• 5:15
  Speaker 1: Good So this is their question, and then what happens next?
• 5:20
  Speaker 2: So This first step is an MRI scan, and so
• 5:24
  Speaker 2: with these athletes or teams, we have ways to connect
• 5:32
  Speaker 2: them with an MRI machine, whether it be through an
• 5:35
  Speaker 2: imaging center that they partner with, or we've even actually
• 5:39
  Speaker 2: brought MRI mobile trucks to sites to make it.
• 5:45
  Speaker 1: Like players run off the field and get an MRI
• 5:48
  Speaker 1: and go back and keep playing. Yeah, yeah, kind yeah, yeah.
• 5:51
  Speaker 2: It helps just with the timing of things. But so
• 5:54
  Speaker 2: first we connect them there, so it takes about ten minutes.
• 5:58
  Speaker 2: Then they send those pictures up into the cloud into
• 6:03
  Speaker 2: our server and then we crunched through it and then
• 6:06
  Speaker 2: we send back a report on their muscles. We also
• 6:10
  Speaker 2: have what we call it interactive Viewer, and it's presented
• 6:14
  Speaker 2: in the form of a three D model. Three dimensional model,
• 6:18
  Speaker 2: so you actually see your own legs, the muscles and bones,
• 6:22
  Speaker 2: your own muscles and bones that we've identified from the
• 6:26
  Speaker 2: images going through a process called segmentation where we find
• 6:31
  Speaker 2: all the muscles and bones and then we reconstruct them,
• 6:33
  Speaker 2: so it's kind of like a digital twin of that
• 6:35
  Speaker 2: person that they can see on their computer. And so
• 6:38
  Speaker 2: along with it or a number or all these metrics
• 6:41
  Speaker 2: that helps them understand their balance. The development or strength
• 6:47
  Speaker 2: of the muscles and the health of the muscles.
• 6:50
  Speaker 1: So tell me about this report, they get like, what
• 6:52
  Speaker 1: does it? What does it say?
• 6:55
  Speaker 2: So the basis of that is actually a lot of
• 6:57
  Speaker 2: research that we did over many years, because you need
• 7:01
  Speaker 2: to understand where somebody falls relative to a normal essentially
• 7:06
  Speaker 2: to give them. Essentially, we have a scoring system for
• 7:09
  Speaker 2: the muscles and that's based on comparing with a large
• 7:13
  Speaker 2: data set of healthy individuals. And so we know for
• 7:18
  Speaker 2: a given person, based on their sex, age, height and weight,
• 7:24
  Speaker 2: how big we expect all the muscles to be. And
• 7:27
  Speaker 2: that's through a lot of previous research. So then we
• 7:30
  Speaker 2: can say, okay, here's where you land each particular muscle
• 7:34
  Speaker 2: compared to this nor what we call a normative database,
• 7:38
  Speaker 2: so we call it a spring box score.
• 7:40
  Speaker 1: Do you do it for every muscle in the leg.
• 7:42
  Speaker 2: Or we do it? So our primary product that we
• 7:46
  Speaker 2: started with was every muscle in the legs essentially from
• 7:50
  Speaker 2: belly to feet, no muscle left behind. They're all important.
• 7:54
  Speaker 1: How many muscles are there.
• 7:56
  Speaker 2: Thirty five per leg?
• 7:58
  Speaker 1: So seven okay, okay, yeah, more than I would have guessed,
• 8:01
  Speaker 1: but a lot. Yeah, all important, okay. So, and so
• 8:08
  Speaker 1: it's basically, how strong and healthy is every one of
• 8:12
  Speaker 1: those seventy muscles relative to baseline?
• 8:16
  Speaker 2: Right, And then the asymmetry comes where you can compare
• 8:20
  Speaker 2: side to side. So for each of the thirty five
• 8:22
  Speaker 2: muscles that they exist on each leg, we can say
• 8:25
  Speaker 2: which side is bigger, which side is smaller, and by
• 8:28
  Speaker 2: how much? And then we also have normative values for
• 8:31
  Speaker 2: that because we're all just slightly asymmetric.
• 8:34
  Speaker 1: Uh huh, And presumably some muscles are more asymmetric than others,
• 8:38
  Speaker 1: And so you want to know kind of how how
• 8:41
  Speaker 1: asymmetric relative to baseline is this particular pair of muscles exactly? Yeah,
• 8:47
  Speaker 1: And and so in the in the case of this
• 8:50
  Speaker 1: uh soccer player who came to you who you know,
• 8:54
  Speaker 1: knew knew she had some kind of problem with her
• 8:56
  Speaker 1: quadriceps on one side, but didn't know what was going on.
• 8:59
  Speaker 1: What did you find?
• 9:01
  Speaker 2: We found some imbalances, and actually not just in those muscles.
• 9:06
  Speaker 2: It turns out that, you know, it's all connected. So
• 9:11
  Speaker 2: if you have a weakness or an imbalance and one
• 9:14
  Speaker 2: set of muscles, usually some other set of muscles are
• 9:17
  Speaker 2: compensating in someone.
• 9:18
  Speaker 1: Yeah, well, it's like when you like mess up. Even
• 9:21
  Speaker 1: if you're just a recreational athlete, right Like, if you
• 9:24
  Speaker 1: mess up something, you mess up your ankle, then you
• 9:26
  Speaker 1: start walking funny, and then like your back hurts because
• 9:29
  Speaker 1: you're walking funny. Right Like, that is a very anecdotally
• 9:32
  Speaker 1: apparent thing.
• 9:33
  Speaker 2: Yeah, yeah, we all know that, but that you know
• 9:35
  Speaker 2: it shows through in the skin. But the thing is
• 9:37
  Speaker 2: that it's not very intuitive from the outside which muscles
• 9:41
  Speaker 2: have been affected, how they've compensated, and it looks different
• 9:45
  Speaker 2: for every single person.
• 9:46
  Speaker 1: Huh.
• 9:47
  Speaker 2: So that's why the report is very valuable because for
• 9:50
  Speaker 2: that person, they know exactly which muscles are the ones
• 9:54
  Speaker 2: that they really need to target, both the ones that
• 9:56
  Speaker 2: they already thought maybe were an issue, but then all
• 9:59
  Speaker 2: the other ones that showed up and they didn't really realize.
• 10:03
  Speaker 1: And so in the case of this soccer player, was
• 10:05
  Speaker 1: it like one particular quadrcep on one side that was
• 10:09
  Speaker 1: like the core thing and you could figure out which
• 10:11
  Speaker 1: one it was.
• 10:12
  Speaker 2: There was a few mess It wasn't just that. I
• 10:14
  Speaker 2: think there were at least one calf muscle and then
• 10:18
  Speaker 2: some in especially in the deep hip, those were impacted.
• 10:23
  Speaker 2: So yeah, it kind of shows up everywhere.
• 10:26
  Speaker 1: And so you have this essentially diagnosis, right, a very
• 10:30
  Speaker 1: sort of fine grained kind of diagnosis. Do you also
• 10:33
  Speaker 1: have a have a prescription? Do you have sort of
• 10:36
  Speaker 1: particular kinds of training to address these very fine grained things,
• 10:41
  Speaker 1: or do you leave that to the trainers or whoever?
• 10:44
  Speaker 2: We leave that to the trainers, because I think that
• 10:47
  Speaker 2: it's also important to have all the other information about
• 10:49
  Speaker 2: the athlete. We're not arguing that it replaces everything else.
• 10:53
  Speaker 2: And people pair it with lots of different other types
• 10:57
  Speaker 2: of measurements depending on the application or in the setting,
• 11:02
  Speaker 2: Like some people pair it with let's say, metrics of
• 11:06
  Speaker 2: jump performance. I'm shifting over to basketball here, but that's
• 11:11
  Speaker 2: just one that came to mind, where you can look
• 11:12
  Speaker 2: at the asymmetry about how how an athlete jumps, but
• 11:16
  Speaker 2: then you can also compare it to the asymmetry of
• 11:18
  Speaker 2: their muscles and get some insight. So it definitely, you know,
• 11:23
  Speaker 2: plugs in with a lot of other things.
• 11:25
  Speaker 1: And to what extent can trainers or you know, strength
• 11:29
  Speaker 1: coaches develop programs that are sufficiently kind of fine grained
• 11:36
  Speaker 1: to match the kind of fine grained findings you're having, right, Like,
• 11:39
  Speaker 1: for example, if you find, as I understand you did
• 11:43
  Speaker 1: that a soccer player has one particular quadricep that is weak. Like,
• 11:48
  Speaker 1: are there workouts that target a single quadricep and not
• 11:51
  Speaker 1: the others?
• 11:52
  Speaker 2: Yep, there are.
• 11:53
  Speaker 1: That's cool for whichever quadricepp you're just like, just for fun,
• 11:57
  Speaker 1: give me an example.
• 11:59
  Speaker 2: You know. One one way that it's very simple is
• 12:01
  Speaker 2: using something called biofeedback. Huh. So you can measure whether
• 12:07
  Speaker 2: you use something called EMG, which is a way to
• 12:11
  Speaker 2: measure how much electrical activity is a muscle, and then
• 12:14
  Speaker 2: you can see which muscles you're using for a given task.
• 12:17
  Speaker 2: So if you give people the feedback of which of
• 12:20
  Speaker 2: those muscles they're using and say, oh, no, you're not
• 12:23
  Speaker 2: using this one, use this one more, that actually works
• 12:27
  Speaker 2: very effectively.
• 12:27
  Speaker 1: Oh really, So you can basically use your brain if
• 12:32
  Speaker 1: you're getting the feedback to focus on which quadricep you're training.
• 12:37
  Speaker 2: Yeah, and there's other ways you can give the feedback
• 12:39
  Speaker 2: in other different ways, but yeah, our brains are very
• 12:42
  Speaker 2: good at that. Once they get feedback, they're very good
• 12:44
  Speaker 2: at learning.
• 12:46
  Speaker 1: That's cool, especially somehow to think of what elead athletes right,
• 12:49
  Speaker 1: because they are already presumably like super dialed in in
• 12:52
  Speaker 1: terms of like the relationship between their brain and their
• 12:54
  Speaker 1: body at this very elite level exactly.
• 12:57
  Speaker 2: Yeah. The other I was going to mention a lot
• 13:00
  Speaker 2: of players and teams use this not just one time,
• 13:05
  Speaker 2: but overtime. So they'll get a scan, figure out a plan,
• 13:10
  Speaker 2: work on that for maybe three months or six months,
• 13:14
  Speaker 2: and then do another scan and see how things are
• 13:16
  Speaker 2: progressing and adjust accordingly. So that's definitely another way to
• 13:21
  Speaker 2: in the long term see if what they're doing is
• 13:24
  Speaker 2: resulting in the change that they're hoping to see.
• 13:27
  Speaker 1: So, what happened with that soccer player who had the
• 13:30
  Speaker 1: weak quadricep and other related Yeah, No, I.
• 13:34
  Speaker 2: Think she's doing great, like staying healthy and and you know,
• 13:39
  Speaker 2: getting ready.
• 13:41
  Speaker 1: Yeah. So I know you can't tell us her name,
• 13:42
  Speaker 1: but will we see her in the Olympics this time? Great? So,
• 13:47
  Speaker 1: as you were talking about that, I mean there was
• 13:48
  Speaker 1: a moment where it was like, Okay, the athlete goes
• 13:51
  Speaker 1: and gets the MRI and then you get the scan.
• 13:55
  Speaker 1: You get the scan, and then you said, like, you
• 13:57
  Speaker 1: crunch through the numbers and then you make the report.
• 14:00
  Speaker 1: Ssumably you crunching through the numbers is like the result
• 14:04
  Speaker 1: of many many years of work and kind of the
• 14:06
  Speaker 1: core of what your company does. So I want to
• 14:08
  Speaker 1: talk a little bit more about that and kind of
• 14:10
  Speaker 1: how you how you got here, Like how did you
• 14:15
  Speaker 1: come to start the company?
• 14:16
  Speaker 2: Mm hmm? How long do I have a while?
• 14:22
  Speaker 1: I mean it's not you know, it's not the radio,
• 14:23
  Speaker 1: it's a podcast.
• 14:25
  Speaker 2: You. I am a professor too, so I can go on.
• 14:27
  Speaker 1: Let me ask you this, What was the moment when
• 14:29
  Speaker 1: you decided to start the company?
• 14:32
  Speaker 2: I can give you one moment and then we can
• 14:36
  Speaker 2: do a.
• 14:36
  Speaker 1: Couple of moments. Yeah, that's what's what a good story is,
• 14:42
  Speaker 1: like three moments.
• 14:43
  Speaker 2: In time, right right? Three not four?
• 14:46
  Speaker 1: Four is a tricky number. We could do five, or
• 14:48
  Speaker 1: we could do one. I think I think is better.
• 14:52
  Speaker 2: Yeah. Yeah. So I'm a professor. I run a lab
• 14:56
  Speaker 2: and form my entire career. I've been fascinated with must
• 15:00
  Speaker 2: and how it works, and fascinated by something that we
• 15:05
  Speaker 2: all in like the muscle field. We call form function relationships.
• 15:10
  Speaker 2: So the idea that the way a muscle is shaped
• 15:13
  Speaker 2: and the way it's structured and how big it is
• 15:16
  Speaker 2: influences how well it works or how well it functions,
• 15:20
  Speaker 2: how strong it is, how well it behaves. And there's
• 15:22
  Speaker 2: a lot too there, and there's a lot of nuance.
• 15:24
  Speaker 2: And that's like I've spent a career studying that in
• 15:27
  Speaker 2: lots of different ways. So I've always been interested in
• 15:30
  Speaker 2: quantifying muscle and figuring out how that influence is, how
• 15:33
  Speaker 2: it works, and both in healthy people or in athletes,
• 15:36
  Speaker 2: and also in different patient populations different In particular, I
• 15:41
  Speaker 2: have an interest in movement disorders, so neuromuscular diseases that
• 15:47
  Speaker 2: lead to impairments and mobility and movement ability. So one
• 15:53
  Speaker 2: of the light bulb moments for this was the fact
• 15:56
  Speaker 2: that I'd been using MRI to study muscle in my
• 15:59
  Speaker 2: research for a long time. It's kind of a ubiquitous
• 16:03
  Speaker 2: tool or like often use tool and research. But I
• 16:09
  Speaker 2: was struck by the fact that I was hearing from,
• 16:14
  Speaker 2: in particular a surgeon collaborator, and the surgeon was telling
• 16:18
  Speaker 2: me about his work and helping kids with cerebral palsy
• 16:22
  Speaker 2: improve their movement where they had hindered movement and largely
• 16:26
  Speaker 2: because their muscles are impacted. Not only do they have
• 16:32
  Speaker 2: an impaired ability to control their muscles, but their muscles
• 16:35
  Speaker 2: end up with impairments in their structure or their form,
• 16:39
  Speaker 2: which then influences how well they work. So surgeons have
• 16:42
  Speaker 2: to go in and do surgeries to try to change that.
• 16:45
  Speaker 2: They do things like modify tendons to try to make
• 16:49
  Speaker 2: muscles less stiff, or they transfer muscles to make them
• 16:53
  Speaker 2: do a new thing. But one of the big tricky
• 16:57
  Speaker 2: parts is that oftentimes some of those muscles are very week.
• 17:00
  Speaker 2: So if they choose the wrong muscle, then they'll make
• 17:03
  Speaker 2: a weak muscle even weaker. Huh, And that's catastrophic. So
• 17:07
  Speaker 2: it's a very fine line that a surgeon has to
• 17:10
  Speaker 2: figure out and they have to go in. You know,
• 17:11
  Speaker 2: we just talked about there's thirty five muscle muscles in
• 17:14
  Speaker 2: each leg, So which of the muscles are the ones
• 17:16
  Speaker 2: that should be operated on and which ones should be avoided?
• 17:20
  Speaker 2: And so what my collaborator, a guy named doctor Mark Abel,
• 17:26
  Speaker 2: fantastic surgeon. He was telling me, Yeah, like, it's very hard,
• 17:30
  Speaker 2: and I don't he didn't have a way to see that.
• 17:32
  Speaker 2: All that he could do is look from the outside.
• 17:35
  Speaker 2: No technology could give him the information he needed to
• 17:38
  Speaker 2: figure out which muscles he should focus on and which
• 17:40
  Speaker 2: ones to.
• 17:41
  Speaker 1: Avoid, because it's not obvious by looking what's a strong
• 17:44
  Speaker 1: muscle and what's a weak one. Yeah, I guess that's
• 17:47
  Speaker 1: surprising to me on some level, Like I don't I've
• 17:52
  Speaker 1: never thought about it. But naively, I would think you
• 17:55
  Speaker 1: could look at a muscle and say it looks strong
• 17:59
  Speaker 1: or it looks weak.
• 17:59
  Speaker 2: Not right, because you just see it from the surface.
• 18:02
  Speaker 2: You don't see it on the inside. And the other challenges.
• 18:06
  Speaker 2: For every joint, there's many muscles. So like we just
• 18:10
  Speaker 2: said that quadrceps has four muscles on the back of
• 18:13
  Speaker 2: the leg, ham strings, there's three hamstrings muscles. There's other
• 18:18
  Speaker 2: muscles that are in the thigh. So you're just seeing
• 18:21
  Speaker 2: what's an impairment and the overall movement, let's say of
• 18:24
  Speaker 2: a joint. But then there could be many muscles or
• 18:27
  Speaker 2: combinations of muscles that are leading to that, and you
• 18:29
  Speaker 2: don't know when you look from the outside. Our body
• 18:32
  Speaker 2: is designed that way actually to be somewhat we call
• 18:34
  Speaker 2: it redundant. We have more muscles than we need probably,
• 18:37
  Speaker 2: but if you think about imbalances, then any one of
• 18:41
  Speaker 2: those muscles could create it create some trouble.
• 18:44
  Speaker 1: So, okay, so the surgeon describes this problem he's having,
• 18:48
  Speaker 1: and then and then what do you do?
• 18:50
  Speaker 2: So then I was thinking, well, you know, that's the
• 18:53
  Speaker 2: information that we generate all the time. When we're doing
• 18:57
  Speaker 2: our research. We take MRIs, quantify, we identify muscles, we
• 19:03
  Speaker 2: create three dimensional models of the muscles, we figure out
• 19:06
  Speaker 2: how they're working from that. But I was struck by
• 19:10
  Speaker 2: the fact that none of that was something that a
• 19:12
  Speaker 2: clinician could use, despite the fact that MRI is obviously
• 19:16
  Speaker 2: ubiquitous in healthcare. Right, yeah, you can't go to a
• 19:20
  Speaker 2: hospital without finding multiple MRIs, but there's no way to
• 19:23
  Speaker 2: use those MRIs and the way that I was using
• 19:26
  Speaker 2: them for my research, And I thought, well, that's too bad,
• 19:30
  Speaker 2: because this would be very useful to the surgeon in
• 19:33
  Speaker 2: figuring out how to treat these patients. So that was
• 19:38
  Speaker 2: one light bulb at the beginning. So a lot of
• 19:41
  Speaker 2: it was figuring out how to take something that we
• 19:43
  Speaker 2: use in research for very specific, targeted basic science questions
• 19:48
  Speaker 2: and turn it into something that is useful clinically.
• 19:52
  Speaker 1: And again this is like my ignorance, Like I might
• 19:55
  Speaker 1: have thought, well, you could just do an MRI and
• 19:58
  Speaker 1: see how big or not big the muscles are, and
• 20:02
  Speaker 1: infer from how big or not big the muscles are,
• 20:05
  Speaker 1: how strong or not strong they are. And that sounds straightforward,
• 20:11
  Speaker 1: but clearly it's not, like, why is it harder than that?
• 20:16
  Speaker 2: So a couple of reasons. One is going taking the
• 20:20
  Speaker 2: MRI pictures and figuring out how big the muscles is
• 20:23
  Speaker 2: a very challenging problem. So in order to accurately get
• 20:27
  Speaker 2: how big the muscles are, you have to essentially generate
• 20:31
  Speaker 2: its shape in three dimensions, so you have to get
• 20:33
  Speaker 2: the whole length of the muscle, and so you do
• 20:37
  Speaker 2: that off of multiple MRI pictures. So the MRI essentially
• 20:40
  Speaker 2: kind of takes pictures through the body at multiple different
• 20:45
  Speaker 2: slices we call them, going from you know, the abdomen
• 20:50
  Speaker 2: all the way down to the feet, sort of going
• 20:52
  Speaker 2: cross sectionally we call it. And so we usually have
• 20:56
  Speaker 2: over two hundred images. So in each image you have
• 21:00
  Speaker 2: to find each muscle, and so for any given image
• 21:03
  Speaker 2: there's probably at least fifteen muscles or more.
• 21:09
  Speaker 1: So it wasn't like you could just push the like
• 21:11
  Speaker 1: show me the muscles button on the MRI and it
• 21:14
  Speaker 1: would show you the muscles.
• 21:15
  Speaker 2: Like.
• 21:15
  Speaker 1: Nobody had done that, and there was no obvious way
• 21:18
  Speaker 1: to do it, certainly not for a surgeon. Ordering a
• 21:21
  Speaker 1: standard MRON just didn't exist.
• 21:24
  Speaker 2: It did not exist.
• 21:25
  Speaker 1: So okay, so you realize this, what happens? How do
• 21:30
  Speaker 1: you make it happen?
• 21:32
  Speaker 2: So, you know, one of our first tasks was to
• 21:34
  Speaker 2: figure out how to get many muscles. So one of
• 21:38
  Speaker 2: the things that we had done on the research side
• 21:41
  Speaker 2: is really focus on a couple of muscles, but I
• 21:44
  Speaker 2: knew for this application that wasn't going to work. We
• 21:46
  Speaker 2: have to be able to identify any muscle. That was
• 21:49
  Speaker 2: really the problem is that like you don't know which
• 21:52
  Speaker 2: one's the problem, so you don't know which one to
• 21:54
  Speaker 2: look at. So you got to look at all of them.
• 21:56
  Speaker 2: And then the next task was to figure out all
• 21:59
  Speaker 2: those muscles and figure out a process to go from
• 22:01
  Speaker 2: the you know, identifying each and every muscle and each
• 22:04
  Speaker 2: and every image. So it's called developing an atlas.
• 22:08
  Speaker 1: And is that an AI problem?
• 22:12
  Speaker 2: So now we have an AI, and it's the type
• 22:14
  Speaker 2: of AI as supervised learning, where they can you essentially
• 22:18
  Speaker 2: train the computer to do what the person would do.
• 22:22
  Speaker 2: But in order to do that, you need to do
• 22:23
  Speaker 2: what the person would do first. And so we did
• 22:28
  Speaker 2: that all manually at first, in order to generate one
• 22:32
  Speaker 2: of these reports. At first, it took us about fifty
• 22:36
  Speaker 2: hours per person.
• 22:39
  Speaker 1: Just going through image after image after image and saying
• 22:42
  Speaker 1: this is this muscle, that is that muscle exactly.
• 22:45
  Speaker 2: So we needed to develop that. But the other piece
• 22:48
  Speaker 2: we needed is this back to this normative database I
• 22:51
  Speaker 2: talked about, because if I just told you how big
• 22:55
  Speaker 2: your muscle is in milli leaders in volume, what are
• 22:58
  Speaker 2: you going to do with that information?
• 23:00
  Speaker 1: Like, oh, great, and nobody knew And it's interesting. It's
• 23:03
  Speaker 1: one of those things you always think, oh, surely there's
• 23:05
  Speaker 1: some data in the world that everybody knows X. But
• 23:08
  Speaker 1: so you're saying, nobody knew what was the kind of
• 23:10
  Speaker 1: medium size of a particular quadricept for whatever, a healthy
• 23:15
  Speaker 1: twelve year old boy or whatever. Nobody knew that at
• 23:17
  Speaker 1: that time. Well, all of.
• 23:18
  Speaker 2: The information up until then, for the most part, was
• 23:22
  Speaker 2: based on dissecting cadavers.
• 23:24
  Speaker 1: Uh huh.
• 23:25
  Speaker 2: Was based on taking cadavers and dissecting muscles, weighing the muscles.
• 23:33
  Speaker 2: And you know, one of the big challenges with that
• 23:35
  Speaker 2: is usually cadavers are older adults, and so they're not
• 23:40
  Speaker 2: really representative of a younger, healthy population. And I will
• 23:46
  Speaker 2: tell you at that time that that was a lot
• 23:48
  Speaker 2: of work and we had I had people saying, like,
• 23:50
  Speaker 2: why are you doing that. Uh, like that seems like
• 23:54
  Speaker 2: a waste of time. That's crazy. You know, I had
• 23:58
  Speaker 2: this vision and I trusted that it was going to
• 24:01
  Speaker 2: turn into something at least useful to the research community,
• 24:04
  Speaker 2: and you know, I'm thankful that we stuck with it.
• 24:08
  Speaker 1: There's lots more to come on the show, including but
• 24:11
  Speaker 1: not limited to the work Sylvia and her colleagues are
• 24:14
  Speaker 1: doing with major league pitchers, college football players, and patients
• 24:18
  Speaker 1: with degenerative muscle disease. Sylvia and her colleagues trained an
• 24:33
  Speaker 1: AI model to do what had previously taken a human
• 24:37
  Speaker 1: fifty hours for every person who got scanned, and they
• 24:41
  Speaker 1: expanded from working with patients with cerebral palsy to working
• 24:45
  Speaker 1: with elite athletes. Today, their clients include not just Olympic athletes,
• 24:51
  Speaker 1: but teams in the NBA and the Premier League. Also,
• 24:54
  Speaker 1: she told me they're working on a project with Major
• 24:57
  Speaker 1: League Baseball.
• 24:58
  Speaker 2: Yeah, so we're working with the MLB studying pictures and
• 25:02
  Speaker 2: we're getting essentially a normative database, whole body scan of pictures.
• 25:05
  Speaker 1: And is that partly because like pitchers mess up their
• 25:09
  Speaker 1: arms so badly? Is that kind of the motivation there, Yes.
• 25:12
  Speaker 2: There's definitely a lot of issue with with injury and surgery.
• 25:17
  Speaker 2: And so the idea here is that by taking these scans,
• 25:21
  Speaker 2: we can really figure out where there might be weaknesses
• 25:25
  Speaker 2: and sort of potential areas for mitigating the injuries.
• 25:30
  Speaker 1: So when you do work for a whole team, like
• 25:34
  Speaker 1: say the Bulls, you know, a basketball team, an NBA team, Like,
• 25:38
  Speaker 1: what's the nature of that of that work? What do
• 25:40
  Speaker 1: you do for a team like that?
• 25:42
  Speaker 2: Yeah, we're they will do a baseline of the whole
• 25:46
  Speaker 2: team and.
• 25:47
  Speaker 1: They basically tailor the athletes training presumably strength training in
• 25:52
  Speaker 1: particular on a muscle by muscle basis, based on the
• 25:57
  Speaker 1: reports that you're sending them.
• 25:59
  Speaker 2: Correct.
• 25:59
  Speaker 1: Yeah, yeah, And I mean you can imagine like better
• 26:03
  Speaker 1: performance being one outcome. Reduced risk of injury seems plausible, right,
• 26:10
  Speaker 1: Like it seems obvious that like a big asymmetry could
• 26:14
  Speaker 1: make you more likely to be injured. I mean, are
• 26:16
  Speaker 1: you at a point now where you can predict the
• 26:19
  Speaker 1: risk of injury?
• 26:22
  Speaker 2: That's like a whole can of worms.
• 26:24
  Speaker 1: I won't say, I mean, is that interesting to you?
• 26:28
  Speaker 1: Or is that like too much? Or yeah?
• 26:30
  Speaker 2: No, no, no, this is something we think about a lot,
• 26:34
  Speaker 2: and let me I want to so first, I'll tell
• 26:38
  Speaker 2: you why it's a can of worms. Yeah yeah, And
• 26:40
  Speaker 2: I'll tell you what project.
• 26:42
  Speaker 1: Tell me about the can. We'll look at it from
• 26:43
  Speaker 1: the outside of.
• 26:44
  Speaker 2: It, so from the cannon. Like, there's a lot of
• 26:46
  Speaker 2: technologies out there that will say that they're predicting injury risk.
• 26:50
  Speaker 2: They'll give you numbers, and they're just not based on anything,
• 26:55
  Speaker 2: and so I don't know, it's there's.
• 26:58
  Speaker 1: A lot of the yeah.
• 27:02
  Speaker 2: Yeah, yeah, yeah. So that's not what we're about, Like,
• 27:05
  Speaker 2: we're about like providing actual things that matter. And so
• 27:10
  Speaker 2: the question is like can you do do these muscle scans?
• 27:16
  Speaker 2: Do they correlate with injury likelihood in some way? And
• 27:20
  Speaker 2: so we actually have a project to address that very question.
• 27:24
  Speaker 2: It's actually funded by the NFL. Uh. We're actually in
• 27:28
  Speaker 2: that project. We're working with college teams called college football
• 27:34
  Speaker 2: teams baselining entire rosters at the beginning of the season
• 27:39
  Speaker 2: and then tracking hamstring injuries and then if a if
• 27:43
  Speaker 2: an athlete gets injured, they come back for a scan
• 27:46
  Speaker 2: at the time of injury and then return to sport.
• 27:50
  Speaker 2: And so one of our questions is based on the
• 27:53
  Speaker 2: baseline scan, can we predict who's more likely to get
• 27:57
  Speaker 2: an injury, an initial injury index injury, and then then
• 28:01
  Speaker 2: the secondary question is can we predict who will be
• 28:04
  Speaker 2: re injured? I was saying that we often pairt people
• 28:07
  Speaker 2: pair it with other things. In this project, we're always
• 28:09
  Speaker 2: also doing that. Each athlete is getting an assessment of
• 28:13
  Speaker 2: their sprint mechanics, so kind of the biomechanics of how
• 28:17
  Speaker 2: they run, and then also assessment of their strength of
• 28:22
  Speaker 2: their hamstring muscles, so like kind of measured strength. Obviously
• 28:25
  Speaker 2: you can't do that when they have an injury, of course,
• 28:28
  Speaker 2: but you can you know when they're healthy.
• 28:30
  Speaker 1: So that biomechanics piece seems like something that has been
• 28:33
  Speaker 1: developing in parallel with your work, also driven by computer vision, right, that,
• 28:40
  Speaker 1: like markerless motion captures, seems like a big world that
• 28:47
  Speaker 1: that overlaps with your world some Yeah, So tell me
• 28:52
  Speaker 1: about your work with female athletes versus male athletes and
• 28:55
  Speaker 1: how that plays a role.
• 28:59
  Speaker 2: Yeah, I will say probably the biggest thing that we've
• 29:02
  Speaker 2: been focused on is making sure that our data addresses that.
• 29:07
  Speaker 2: So our normative database is uh separated by sex, so
• 29:13
  Speaker 2: and it is different because like women aren't small men, right,
• 29:19
  Speaker 2: So it's important that we have that basis to compare
• 29:22
  Speaker 2: that's like for women and not comparing to some average
• 29:27
  Speaker 2: or primarily male data sets. So that's that's one huge
• 29:30
  Speaker 2: important thing is that it's it's compared to the normative
• 29:34
  Speaker 2: values for the female population. And then in terms of
• 29:41
  Speaker 2: like working with the female athletes, I think, you know,
• 29:43
  Speaker 2: one of the big ones is is really just ability
• 29:46
  Speaker 2: to personalize and provide this like really accurate detailed assessment
• 29:53
  Speaker 2: of their of their bodies. And you know, a lot
• 29:57
  Speaker 2: of the you know, knowledge about like appropriate body composition
• 30:02
  Speaker 2: historically has been based on studies and men, and but
• 30:06
  Speaker 2: then we're applying them to women and making us feel
• 30:09
  Speaker 2: really bad about ourselves. So really motivated to move away
• 30:14
  Speaker 2: from that and sort of acknowledge the muscular physiology and
• 30:18
  Speaker 2: anatomy of the female and also the female athlete to
• 30:22
  Speaker 2: really understand understand that. You know, I think one thing
• 30:26
  Speaker 2: obviously that we've seen is, you know, acl injuries are
• 30:30
  Speaker 2: more common in women than men, and examining how these
• 30:35
  Speaker 2: like recovery profiles look on how they differ between men
• 30:39
  Speaker 2: and women. That's something that we're observing and seeing how
• 30:42
  Speaker 2: those things shake out. But we're motivated by really providing
• 30:46
  Speaker 2: that information that's specific to women.
• 30:49
  Speaker 1: So what are some of the non sports things you're
• 30:53
  Speaker 1: working on, things you're trying to figure out.
• 30:55
  Speaker 2: Yeah, I mean, one that's I'm really interested in is
• 31:01
  Speaker 2: this area that we're applying to in clinical trials for
• 31:04
  Speaker 2: muscle disease. So we've been working in a specific muscle
• 31:09
  Speaker 2: disease called fascioscapulo humoral muscular district f SHD, which is
• 31:15
  Speaker 2: a slowly progressing muscle disease genetic and basis, and so
• 31:22
  Speaker 2: eventually people with f SHD need a wheelchair. Just life
• 31:26
  Speaker 2: is very difficult, and so it's pretty devastating. But the
• 31:30
  Speaker 2: other exciting thing is there are some new treatments out there,
• 31:33
  Speaker 2: some in particular gene therapies coming online. And now the
• 31:37
  Speaker 2: challenges do they work because the problem is in these
• 31:41
  Speaker 2: diseases because they're pretty slowly progressing. If you want to
• 31:45
  Speaker 2: see if a drug is helping somebody, it's very hard
• 31:50
  Speaker 2: to see that in a slowly progressing.
• 31:51
  Speaker 1: Right and the clinical manifestations are hard to pick up.
• 31:55
  Speaker 1: If it makes your muscles shrink more slowly, it's going
• 32:00
  Speaker 1: to be hard to see.
• 32:01
  Speaker 2: It's very hard to see, especially from like rudimentary measures.
• 32:04
  Speaker 2: But with the MRIs. We've been able to provide this
• 32:07
  Speaker 2: really detailed insight about the disease date of each muscle
• 32:11
  Speaker 2: and how it's progressing over time. And so you know,
• 32:15
  Speaker 2: one of our goals is to really lean in on
• 32:17
  Speaker 2: IS and help figure out exactly how people should look
• 32:21
  Speaker 2: at all this data and figure out if a drug
• 32:24
  Speaker 2: is working or not. It's really profoundly important because without that,
• 32:28
  Speaker 2: these these clinical trials just won't move forward.
• 32:32
  Speaker 1: What else are you sort of still trying to figure out?
• 32:37
  Speaker 2: So we talked about predicting injury but having all the
• 32:42
  Speaker 2: data needed to show like if you do if your
• 32:45
  Speaker 2: scan looks like this, and if you do this, you
• 32:47
  Speaker 2: will be able to improve your jump high by height.
• 32:50
  Speaker 1: By that, yeah, you'll be able to throw a fastball
• 32:53
  Speaker 1: two miles an hour faster. Like that would be wildly valuable.
• 32:57
  Speaker 2: That would be very and we do have data in
• 32:59
  Speaker 2: our search. We were able to show that these muscle
• 33:04
  Speaker 2: scores correlate with performance metrics such as jump, hide, and speed.
• 33:09
  Speaker 2: So we for sure see that The question is then
• 33:12
  Speaker 2: the spin on like observing how how that plays out,
• 33:15
  Speaker 2: Like if you then strengthen the appropriate muscles, how how
• 33:20
  Speaker 2: much faster do you get? And you just need more
• 33:22
  Speaker 2: and more data to really like to go after that.
• 33:26
  Speaker 2: But that's one thing that I'm fascinated by. One of
• 33:29
  Speaker 2: the other interesting ones, Can I go off on a tangent.
• 33:32
  Speaker 1: Anything you want?
• 33:35
  Speaker 2: One of our research partners that's interested in how muscles
• 33:38
  Speaker 2: adapt to strength training and different interventions and what influences
• 33:42
  Speaker 2: that had a really interesting finding that I think is
• 33:46
  Speaker 2: quite profound but also obvious. So everybody if there, if
• 33:50
  Speaker 2: they're targeted training their quadrceps and hamstrings, those muscles got bigger,
• 33:56
  Speaker 2: that makes sense, but in a fair number of the people,
• 33:59
  Speaker 2: some muscles got smaller. And then you know, he had
• 34:04
  Speaker 2: done some controlling and in documentation of nutrition intake, and
• 34:10
  Speaker 2: he found that people that had higher caloric and protein
• 34:15
  Speaker 2: intake had less of that effect.
• 34:19
  Speaker 1: So all that, all the Jim bros. Telling you to
• 34:21
  Speaker 1: eat a lot of protein are validated by this guy's study.
• 34:25
  Speaker 2: Yeah, yeah, but they're not. It's not necessarily to make
• 34:27
  Speaker 2: that muscle that you're working bigger so you don't lose
• 34:29
  Speaker 2: the other muscles.
• 34:30
  Speaker 1: Uh huh. That's a good one. And was he using
• 34:35
  Speaker 1: your scans to figure out that?
• 34:37
  Speaker 2: Yeah? Yeah, he was using our scans and and the
• 34:39
  Speaker 2: thing that was cool. Is that Normally in research you
• 34:42
  Speaker 2: wouldn't bother looking at those other muscles. You would just
• 34:45
  Speaker 2: look at the ones that were targeted, right, because those
• 34:47
  Speaker 2: are the ones that you just think about. But by
• 34:49
  Speaker 2: getting the entire extent of the of all the muscles,
• 34:52
  Speaker 2: you see these impacts that you wouldn't necessarily.
• 34:55
  Speaker 1: Have known, Like he wasn't even looking for it.
• 34:58
  Speaker 2: Yeah, it's it's quite profound because somebody's strength training recovering
• 35:02
  Speaker 2: from an injury. That really means like that, the nutritional
• 35:06
  Speaker 2: elements important because you could be strengthening some muscles but
• 35:11
  Speaker 2: weakening others if you're not. If you're not, you know,
• 35:13
  Speaker 2: playing your cards right there.
• 35:18
  Speaker 1: We'll be back in a minute with the lightning round.
• 35:21
  Speaker 1: M h, I want to finish with the lightning round.
• 35:33
  Speaker 1: I won't take too long. It'll be fun.
• 35:35
  Speaker 2: Okay, what I don't know what that is?
• 35:38
  Speaker 1: Well, you'll find out right now.
• 35:41
  Speaker 2: Does this have to be fast?
• 35:44
  Speaker 1: I could call it the random round? Okay, I like
• 35:47
  Speaker 1: that random. Have you scanned yourself?
• 35:52
  Speaker 2: Yes? Well times? Oh of course that's what kind of thing.
• 35:58
  Speaker 2: Probably I've been in an MRI machine, I don't know,
• 36:00
  Speaker 2: maybe a hundred times.
• 36:01
  Speaker 1: Like it's not radiation. Right, it's not like an X ray.
• 36:04
  Speaker 1: You could do it every day.
• 36:05
  Speaker 2: As much as you want.
• 36:06
  Speaker 1: Yeah, what'd you learn?
• 36:09
  Speaker 2: So I actually used it? You know, I've learned lots
• 36:13
  Speaker 2: over the years, but I will tell you one anecdote.
• 36:15
  Speaker 2: I have a hip replacement. I have a genetic condition
• 36:21
  Speaker 2: that leads to early arthritis. And so I was before
• 36:26
  Speaker 2: I got my hip replacement, I got a scan. I
• 36:28
  Speaker 2: knew I was getting weak, but holy cow, was I
• 36:31
  Speaker 2: really weak on that side. What was profound was how
• 36:36
  Speaker 2: weak my hip flexers were very weak. And I you know,
• 36:41
  Speaker 2: I think a lot of times people talk about hip
• 36:42
  Speaker 2: flexures being tight, and that's kind of what I thought
• 36:46
  Speaker 2: was happening. I felt pain and I felt like I
• 36:49
  Speaker 2: was having a lot of tightness, but it was actually
• 36:52
  Speaker 2: weakness and they were like super small on both sides,
• 36:57
  Speaker 2: but really especially on the on the side that was
• 36:59
  Speaker 2: effect it. So that was one thing that I worked
• 37:03
  Speaker 2: on a lot.
• 37:04
  Speaker 1: Do that genetic condition you have, did that influence your
• 37:07
  Speaker 1: your work and all your decision to go into the field.
• 37:13
  Speaker 2: I mean it's like loosely maybe because my dad had
• 37:17
  Speaker 2: the same thing, which actually caused him to go blind. Oh,
• 37:21
  Speaker 2: it has like a multiple different issues, and so I
• 37:23
  Speaker 2: think that at an early age got me interested in
• 37:27
  Speaker 2: medicine and disabilities and like helping helping people, so that
• 37:35
  Speaker 2: that might be broadly speaking, I didn't and I knew
• 37:37
  Speaker 2: I had some eye problems. I didn't know the genetic thing.
• 37:40
  Speaker 2: We didn't discover that till later.
• 37:41
  Speaker 1: But huh. Interesting. What's the most underrated muscle in the
• 37:47
  Speaker 1: human body?
• 37:48
  Speaker 2: Hmm, that's a hard one. So I have a few
• 37:56
  Speaker 2: favorite muscles.
• 37:57
  Speaker 1: Okay, what's your favorite muscle?
• 37:58
  Speaker 2: Yeah, so the so muscle so as major it's it's
• 38:02
  Speaker 2: a hip flexer, okay, but it also it's really cool
• 38:05
  Speaker 2: it actually it's also a back lower back muscle, so
• 38:09
  Speaker 2: it attaches to the lumbar vertebrae. But then it also
• 38:13
  Speaker 2: crosses the front of your hip. It's really hard to
• 38:16
  Speaker 2: find because it's like really back deep in your hip.
• 38:19
  Speaker 2: It goes right over your.
• 38:20
  Speaker 1: Your in the middle of your body kind of yeah,
• 38:24
  Speaker 1: right in the middle.
• 38:25
  Speaker 2: It kind of connects everything, sort of connects your lower
• 38:28
  Speaker 2: extremity to the rest of your body in some ways.
• 38:31
  Speaker 1: Okay, last one, why do you hate astrophysicist Barbie?
• 38:40
  Speaker 2: I don't hate anything. I mean, well, it's too perfect.
• 38:47
  Speaker 2: It's kind of like this, you know idea that like, oh,
• 38:51
  Speaker 2: you know, you can, you can inspire girls to go
• 38:54
  Speaker 2: into science by showing them that Barbie does too. But
• 38:57
  Speaker 2: Barbie's like fictitious, so it kind of tells you that,
• 39:02
  Speaker 2: like it like promotes the idea of perfectionism in society
• 39:07
  Speaker 2: but definitely in girls. And you know, what we really
• 39:10
  Speaker 2: want to promote is almost the opposite of that is
• 39:13
  Speaker 2: taking risks and and not worrying about being perfect and
• 39:18
  Speaker 2: just doing something that matters to you. So yeah, I
• 39:22
  Speaker 2: don't know. I mean, I don't hate it. I had
• 39:24
  Speaker 2: Barbies when I was a kid, but I just it
• 39:26
  Speaker 2: kind of.
• 39:27
  Speaker 1: Like wrote you wrote a whole column about it.
• 39:34
  Speaker 2: That was I was very proud of that. Yeah, no,
• 39:38
  Speaker 2: and really that, you know, the astrophysicist part, honestly was
• 39:41
  Speaker 2: more of a hook. The article I had written already
• 39:45
  Speaker 2: before that Astrophysicist Barbie came to be. It was about
• 39:49
  Speaker 2: the issue of perfectionism and how that dissuades girls to
• 39:55
  Speaker 2: go into stem and research.
• 39:58
  Speaker 1: Well, a good hook is important, and you found.
• 40:03
  Speaker 2: Yeah.
• 40:07
  Speaker 1: Sylvia Bleimker is a professor at the University of Virginia
• 40:10
  Speaker 1: and the co founder of Springbok analytics. Next week on
• 40:14
  Speaker 1: What's Your Problem, I'll be talking to Jimmy Buffy. He
• 40:18
  Speaker 1: is using AI to bring the insights of biomechanics to
• 40:21
  Speaker 1: professional athletes. Jimmy told me that before the advent of AI,
• 40:26
  Speaker 1: when biomechanics experts tried to work with athletes, it could
• 40:30
  Speaker 1: be somewhat awkward. So You've got like a picture in
• 40:33
  Speaker 1: his underwear with a bunch of little metal balls, Take
• 40:36
  Speaker 1: them and they're like, just pitch like you always pitched right.
• 40:39
  Speaker 3: And the state of the art for tracking it was
• 40:41
  Speaker 3: an awful experience for the people you.
• 40:43
  Speaker 2: Were trying to track.
• 40:45
  Speaker 1: So what changes?
• 40:46
  Speaker 3: The big inflection point was computer vision, basically using artificial
• 40:50
  Speaker 3: intelligence to identify where those joints are in a camera image,
• 40:55
  Speaker 3: rather than needing to paste those reflective markers.
• 41:00
  Speaker 1: Today's show was produced by Gabriel Hunter Chang, edited by
• 41:04
  Speaker 1: Lydia Jean Kott, and engineered by Sarah Bugero. You can
• 41:08
  Speaker 1: email us at Problem at Pushkin dot FM. I'm Jacob Goldstein.
• 41:13
  Speaker 1: We'll be back next week with another episode of What's
• 41:15
  Speaker 1: Your Problem.