Skip to content

Commit

Permalink
add_html
Browse files Browse the repository at this point in the history 
Change-Id: I5a7b05ba83471f674d879772cf7552df07cb9eae
  • Loading branch information
@fishneck
fishneck committed Apr 25, 2024
1 parent 09fce9f commit 055b56d
Show file tree
Hide file tree
Showing 10 changed files with 55 additions and 72 deletions.
Binary file added docs/images/COBRA-Overview-KneeOA.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/COBRA-Overview-Stroke.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/Confounding_factors_object_color.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/Data-KneeOA.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/Data-StrokeRehab.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/Mean_confidence.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/Result-KneeOA.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/Result-Stroke-Sensor.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/images/Result-Stroke-Video.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
127 changes: 55 additions & 72 deletions docs/index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
-->
<html>
<head>
<title>Editorial by HTML5 UP</title>
<title>COnfidence-Based chaRacterization of Anomalies (COBRA)</title>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=no" />
<link rel="stylesheet" href="assets/css/main.css" />
Expand All @@ -22,66 +22,49 @@

<!-- Header -->
<header id="header">
<a href="index.html" class="logo"><strong>Editorial</strong> by HTML5 UP</a>
<a href="index.html" class="logo"> COnfidence-Based chaRacterization of Anomalies (<strong>COBRA</strong>)</a>
<ul class="icons">
<li><a href="#" class="icon brands fa-twitter"><span class="label">Twitter</span></a></li>
<li><a href="#" class="icon brands fa-facebook-f"><span class="label">Facebook</span></a></li>
<li><a href="#" class="icon brands fa-snapchat-ghost"><span class="label">Snapchat</span></a></li>
<li><a href="#" class="icon brands fa-instagram"><span class="label">Instagram</span></a></li>
<li><a href="#" class="icon brands fa-medium-m"><span class="label">Medium</span></a></li>
<li><a href="#" class="icon brands fa-github"><span class="label">Github</span></a></li>
</ul>
</header>

<!-- Banner -->
<section id="banner">
<div class="content">
<header>
<h1>Hi, I’m Editorial<br />
by HTML5 UP</h1>
<p>A free and fully responsive site template</p>
<h1>Quantifying Impairment and Disease Severity <br />
Using AI Models Trained on Healthy Subjects</h1>
<p>Boyang Yu, Aakash Kaku, Kangning Liu, Avinash Parnandi, Emily Fokas, Anita Venkatesan, Natasha Pandit, Rajesh Ranganath, Heidi Schambra and Carlos Fernandez-Granda</p>
</header>
<p>Aenean ornare velit lacus, ac varius enim ullamcorper eu. Proin aliquam facilisis ante interdum congue. Integer mollis, nisl amet convallis, porttitor magna ullamcorper, amet egestas mauris. Ut magna finibus nisi nec lacinia. Nam maximus erat id euismod egestas. Pellentesque sapien ac quam. Lorem ipsum dolor sit nullam.</p>
<p>Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a novel framework, COnfidence-Based chaRacterization of Anomalies (COBRA), to address this challenge, which leverages AI models trained exclusively on healthy subjects. The models are designed to predict a clinically-meaningful attribute of the healthy patients. When presented with data where the attribute is affected by the medical condition of interest, the models experience a decrease in confidence that can be used to quantify deviation from the healthy population. COBRA was applied to quantification of upper-body motion impairment in stroke patients, and severity of knee osteoarthritis from magneticresonance imaging scans.</p>
<ul class="actions">
<li><a href="#" class="button big">Learn More</a></li>
</ul>
</div>
<span class="image object">
<img src="images/pic10.jpg" alt="" />
<img src="images/COBRA-Overview-Stroke.png" alt="" />
</span>
</section>

<!-- Section -->
<section>
<header class="major">
<h2>Erat lacinia</h2>
<h2>Clinical Applications</h2>
</header>
<div class="features">
<article>
<span class="icon fa-gem"></span>
<span class="icon fa-user-plus"></span>
<div class="content">
<h3>Portitor ullamcorper</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<h3>Stroke Impairment</h3>
<p>The quantification of impairment in stroke patients was carried out using the publicly available StrokeRehab dataset. StrokeRehab contains wearable-sensor data and video data from a cohort of 29 healthy individuals and 51 stroke patients performing multiple trials of 9 rehabilitation activities.</p>
</div>
</article>
<article>
<span class="icon solid fa-paper-plane"></span>
<span class="icon solid fa-wheelchair"></span>
<div class="content">
<h3>Sapien veroeros</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
</div>
</article>
<article>
<span class="icon solid fa-rocket"></span>
<div class="content">
<h3>Quam lorem ipsum</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
</div>
</article>
<article>
<span class="icon solid fa-signal"></span>
<div class="content">
<h3>Sed magna finibus</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<h3>Knee Osteoarthritis Severity</h3>
<p>The quantification of knee osteoarthritis (OA) severity was carried out using the publicly available OAI-ZIB dataset. This dataset provides 3D MRI scans of 101 healthy right knees and 378 right knees affected by knee osteoarthritis (OA), a long-term degenerative joint condition.</p>
</div>
</article>
</div>
Expand All @@ -90,53 +73,61 @@ <h3>Sed magna finibus</h3>
<!-- Section -->
<section>
<header class="major">
<h2>Ipsum sed dolor</h2>
<h2>Results</h2>
</header>
<div class="posts">
<article>
<a href="#" class="image"><img src="images/pic01.jpg" alt="" /></a>
<h3>Interdum aenean</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<a href="#" class="image"><img src="images/Data-StrokeRehab.jpg" alt="" /></a>
<h3>Stroke - StrokeRehab data</h3>
<p>StrokeRehab contains wearable-sensor data and video data from a cohort of 29 healthy individuals and 51 stroke patients performing multiple trials of 9 rehabilitation activities. The impairment level of each patient was quantified via the Fugl-Meyer assessment (FMA). The FMA score is a number between 0 (maximum impairment) and 66 (healthy) equal to the sum of itemized scores (each from 0 to 2) for 33 upper body mobility assessments carried out in-clinic by a trained expert.</p>
<ul class="actions">
<li><a href="#" class="button">More</a></li>
</ul>
</article>
<article>
<a href="#" class="image"><img src="images/Data-KneeOA.jpg" alt="" /></a>
<h3>Knee OA - OAI-ZIB data</h3>
<p>OAI-ZIB provides 3D MRI scans of 101 healthy right knees and 378 right knees affected by knee osteoarthritis (OA), a long-term degenerative joint condition. Each knee is labeled with the corresponding Kellgren-Lawrence (KL) grades, retrieved from the NIH Osteoarthritis Initiative collection. The KL grade quantifies OA severity on a scale from 0 (healthy) to 4 (severe).</p>
<ul class="actions">
<li><a href="#" class="button">More</a></li>
</ul>
</article>
<article>
<a href="#" class="image"><img src="images/pic02.jpg" alt="" /></a>
<h3>Nulla amet dolore</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<a href="#" class="image"><img src="images/Mean_confidence.png" alt="" /></a>
<h3>Averaging model confidence yields a discriminative characterization score</h3>
<p>The average confidence is higher for the healthy subjects. The means of the distributions (dashed lines) are clearly separated. This motivates the definition of the COBRA score as the mean confidence averaged over multiple data points associated to the subject.</p>
<ul class="actions">
<li><a href="#" class="button">More</a></li>
</ul>
</article>
<article>
<a href="#" class="image"><img src="images/pic03.jpg" alt="" /></a>
<h3>Tempus ullamcorper</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<a href="#" class="image"><img src="images/Result-Stroke-Sensor.png" alt="" /></a>
<h3>High correlation with Stroke clinical assessments</h3>
<p>An independent assessment performed in-clinic by trained experts was shown to be strongly correlated with the COBRA score for wearable sensor data (ρ = 0.845, 95% CI [0.743,0.908]) </p>
<ul class="actions">
<li><a href="#" class="button">More</a></li>
</ul>
</article>
<article>
<a href="#" class="image"><img src="images/pic04.jpg" alt="" /></a>
<h3>Sed etiam facilis</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<a href="#" class="image"><img src="images/Result-Stroke-Video.png" alt="" /></a>
<h3>High correlation with Stroke clinical assessments</h3>
<p>An independent assessment performed in-clinic by trained experts was shown to be strongly correlated with the COBRA score for video data (ρ = 0.746, 95% C.I [0.594, 0.847])</p>
<ul class="actions">
<li><a href="#" class="button">More</a></li>
</ul>
</article>
<article>
<a href="#" class="image"><img src="images/pic05.jpg" alt="" /></a>
<h3>Feugiat lorem aenean</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<a href="#" class="image"><img src="images/Result-KneeOA.png" alt="" /></a>
<h3>High correlation with Knee OA clinical assessments</h3>
<p>The COBRA score was applied to quantify severity of knee osteoarthritis from magneticresonance imaging scans, again achieving significant correlation with an independent clinical assessment (ρ = 0.658, 95% C.I [0.581,0.734])</p>
<ul class="actions">
<li><a href="#" class="button">More</a></li>
</ul>
</article>
<article>
<a href="#" class="image"><img src="images/pic06.jpg" alt="" /></a>
<h3>Amet varius aliquam</h3>
<p>Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<a href="#" class="image"><img src="images/Confounding_factors_object_color.png" alt="" /></a>
<h3>Controling for confounding varibles yields a better score</h3>
<p>The table-top rehabilitation activity in the stroke impairment quantification task involves dark and light-colored objects (top row). Stratifying according to object color corrects for the confounding factor, improving the correlation coefficient.</p>
<ul class="actions">
<li><a href="#" class="button">More</a></li>
</ul>
Expand Down Expand Up @@ -165,26 +156,20 @@ <h2>Menu</h2>
</header>
<ul>
<li><a href="index.html">Homepage</a></li>
<li><a href="generic.html">Generic</a></li>
<li><a href="elements.html">Elements</a></li>
<li><a href="elements.html">Code</a></li>
<li>
<span class="opener">Submenu</span>
<span class="opener">Data</span>
<ul>
<li><a href="#">Lorem Dolor</a></li>
<li><a href="#">Ipsum Adipiscing</a></li>
<li><a href="#">Tempus Magna</a></li>
<li><a href="#">Feugiat Veroeros</a></li>
<li><a href="#">Stroke</a></li>
<li><a href="#">Knee OA</a></li>
</ul>
</li>
<li><a href="#">Etiam Dolore</a></li>
<li><a href="#">Adipiscing</a></li>
<li>
<span class="opener">Another Submenu</span>
<span class="opener">Models</span>
<ul>
<li><a href="#">Lorem Dolor</a></li>
<li><a href="#">Ipsum Adipiscing</a></li>
<li><a href="#">Tempus Magna</a></li>
<li><a href="#">Feugiat Veroeros</a></li>
<li><a href="#">Stroke Wearable Sensor</a></li>
<li><a href="#">Stroke Video</a></li>
<li><a href="#">Knee OA MRI</a></li>
</ul>
</li>
<li><a href="#">Maximus Erat</a></li>
Expand Down Expand Up @@ -220,20 +205,18 @@ <h2>Ante interdum</h2>
<!-- Section -->
<section>
<header class="major">
<h2>Get in touch</h2>
<h2>Related Publication</h2>
</header>
<p>Sed varius enim lorem ullamcorper dolore aliquam aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin sed aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.</p>
<p>Quantifying Impairment and Disease Severity Using AI Models Trained on Healthy Subjects</p>
<ul class="contact">
<li class="icon solid fa-envelope"><a href="#">information@untitled.tld</a></li>
<li class="icon solid fa-phone">(000) 000-0000</li>
<li class="icon solid fa-home">1234 Somewhere Road #8254<br />
Nashville, TN 00000-0000</li>
<li class="icon solid fa-envelope"><a href="#">boy.yu@nyu.edu</a></li>
<li class="icon solid bookmark-o"> Boyang Yu, Aakash Kaku, Kangning Liu*, Avinash Parnandi, Emily Fokas, Anita Venkatesan, Natasha Pandit, Rajesh Ranganath, Heidi Schambra and Carlos Fernandez-Granda</li>
</ul>
</section>

<!-- Footer -->
<footer id="footer">
<p class="copyright">&copy; Untitled. All rights reserved. Demo Images: <a href="https://unsplash.com">Unsplash</a>. Design: <a href="https://html5up.net">HTML5 UP</a>.</p>
<p class="copyright">&copy; All rights reserved. Demo Images: <a href="https://unsplash.com">Unsplash</a>. Design: <a href="https://html5up.net">HTML5 UP</a>.</p>
</footer>

</div>
Expand Down

0 comments on commit 055b56d

Please sign in to comment.