Enhance mist.html with comprehensive project details

Added detailed sections on architecture, overview, open-source tools, patents, publications, and contact information for the MIST framework.

Author: vishwaparekh

research/mist.html

@@ -0,0 +1,75 @@
+---
+layout: default
+title: MIST
+---
+
+<section class="hero">
+  <h1>MIST: Medical Image Streaming Toolkit</h1>
+  <p class="subtitle">A unified framework for intelligent, progressive, and resource-efficient medical image streaming.</p>
+  <div class="btn-container">
+      <a href="https://doi.org/10.1007/s10278-024-01173-z" class="btn">Journal Paper (JIIM 2024)</a>
+      <a href="https://openreview.net/forum?id=IIuULGCHLY&noteId=IIuULGCHLY" class="btn">Conference Paper (MIDL 2025)</a>
+      <a href="https://patentscope.wipo.int/search/en/detail.jsf?docId=WO2024233969" class="btn">Patent</a>
+      <a href="https://github.com/BioIntelligence-Lab/MIST" class="btn">GitHub</a>
+    </div>
+</section>
+
+<section id="architecture">
+    <h2>Architecture</h2>
+    <p class="center">A schematic representation of MIST's hierarchical and adaptive streaming pipeline.</p>
+    <img src="https://raw.githubusercontent.com/BioIntelligence-Lab/MIST/main/assets/overview.png" alt="MIST Architecture Overview" class="diagram">
+  </section>
+
+  <section id="overview">
+<p><strong>MIST</strong> and <strong>ISLE</strong> represent two complementary frameworks addressing the challenges of large-scale medical imaging datasets and AI-driven inference systems.</p>
+<h2>Overview</h2>
+<h3>MIST: Medical Imaging Streaming Toolkit</h3>
+<ul class="highlights">
+<li><strong>Challenge:</strong> Large-scale imaging datasets require significant storage and bandwidth, limiting accessibility for AI research and clinical deployment.</li>
+<li><strong>MIST Solution:</strong> A format-agnostic database enabling streaming of medical images at multiple resolutions and formats from a single high-resolution copy.</li>
+<li><strong>Evaluation:</strong> Tested across eight diverse datasets (CT, MRI, X-ray) covering multiple modalities and file formats.</li>
+<li><strong>Results:</strong> Reduced storage and bandwidth requirements without impacting image quality or downstream deep learning performance.</li>
+<li><strong>Impact:</strong> Creates a data-efficient, format-agnostic platform that reduces barriers to AI research in medical imaging.</li>
+</ul>
+
+
+<h3>ISLE: Intelligent Streaming for AI Inference</h3>
+<ul class="highlights">
+<li><strong>Motivation:</strong> Growing adoption of AI systems in radiology is increasing demands for bandwidth and computational resources.</li>
+<li><strong>ISLE Framework:</strong> An intelligent streaming method inspired by video-on-demand platforms to deliver only the resolution needed for AI inference using progressive encoding.</li>
+<li><strong>Results (Classification):</strong> Reduced transmission by ≥90% and decoding time by ≥87%</li>
+<li><strong>Results (Segmentation):</strong> Reduced transmission by ≥77% and decoding time by ≥89%</li>
+<li><strong>Performance:</strong> No impact on diagnostic performance (all P > 0.05).</li>
+<li><strong>Impact:</strong> Improves data and computational efficiency for AI deployment in clinical environments without compromising diagnostic accuracy.</li>
+</ul>
+</section>
+
+  <section id="opensource">
+    <h2>Open-Source Tools</h2>
+    <table>
+      <tr><th>Component</th><th>Description</th><th>Repository</th></tr>
+      <tr><td>MIST</td><td>Core streaming and dataset management framework</td><td><a href="https://github.com/BioIntelligence-Lab/MIST">GitHub</a></td></tr>
+      <tr><td>IntelligentStreaming</td><td>AI-aware streaming for real-time inference</td><td><a href="https://github.com/BioIntelligence-Lab/IntelligentStreaming">GitHub</a></td></tr>
+      <tr><td>OpenJPHpy</td><td>Python interface for HTJ2K codec</td><td><a href="https://github.com/BioIntelligence-Lab/openjphpy">GitHub</a></td></tr>
+    </table>
+  </section>
+
+  <section id="patent">
+    <h2>Patents</h2>
+    <p><strong>Patent:</strong> <a href="https://patents.google.com/patent/WO2024233969A1/en?oq=WO2024233969A1">WO2024233969A1</a> — <em>Systems and methods for high-throughput analysis for graphical data</em></p> 
+    <p><strong>Filed by:</strong> University of Maryland Baltimore <br>
+       <strong>Inventors:</strong> Vishwa S. Parekh, Pranav Kulkarni, Adway Kanhere, Paul H. Yi, Eliot L. Siegel</p>
+  </section>
+
+  <section id="publications">
+    <h2>Publications</h2>
+    <p>Kulkarni P., Kanhere A., Siegel E.L., Yi P.H., Parekh V.S. <em>ISLE: An Intelligent Streaming Framework for High-Throughput AI Inference in Medical Imaging.</em> <strong>Journal of Imaging Informatics in Medicine. 2024 Dec;37(6):3250-63. <a href="https://doi.org/10.1007/s10278-024-01173-z">DOI</a></p>
+    <p>Kulkarni P., Kanhere A., Siegel E., Yi P., Parekh V.S. <em>Towards Resource-Efficient Streaming of Large-Scale Medical Image Datasets for Deep Learning.</em> <strong>Medical Imaging with Deep Learning (MIDL)</strong> (2025). <a href="https://openreview.net/forum?id=IIuULGCHLY&noteId=IIuULGCHLY">OpenReview</a></p>
+  </section>
+
+  <section id="contact">
+    <h2>Contact</h2>
+    <p class="center"><strong>Dr. Vishwa S. Parekh</strong><br>
+    UTHealth Houston<br>
+    <a href="mailto:vishwa.s.parekh@uth.tmc.edu">vishwa.s.parekh@uth.tmc.edu</a></p>
+  </section>