KalbeDigitalLab/PathologyNucleiClassification
0
1<!DOCTYPE html>2<html>3 <head>4 <link rel="stylesheet" href="file/style.css" />5 <link rel="preconnect" href="https://fonts.googleapis.com" />6 <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />7 <link href="https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600;700&display=swap" rel="stylesheet" />8 <title>Pathology Nuclei Classification</title>9 </head>10 <body>11 <div class="container">12 <h1 class="title">Pathology Nuclei Classification</h1>13 <h2 class="subtitle">Kalbe Digital Lab</h2>14 <section class="overview">15 <div class="grid-container">16 <h3 class="overview-heading"><span class="vl">Overview</span></h3>17 <div>18 <p class="overview-content">Nuclei classification within Haematoxylin & Eosi stained histology images. Classifying nuclei cells as the following types:</p>19 <ul>20 <li>Other</li>21 <li>Inflammatory</li>22 <li>Epithelial</li>23 <li>Spindle-Shaped</li>24 </ul>25 <p class="overview-content">References: <a href="https://doi.org/10.1016/j.media.2019.101563" target="_blank">https://doi.org/10.1016/j.media.2019.101563</a></p>26 </div>27 </div>28 <div class="grid-container">29 <h3 class="overview-heading"><span class="vl">Dataset</span></h3>30 <div>31 <p class="overview-content">32 The model is trained with Colorectal Nuclear Segmentation and Phenotypes (CoNSeP) dataset33 <a href="https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet" target="_blank">https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet</a>. Images were extracted from 16 colorectal adenocarcinoma (CRA) WSIs.34 </p>35 <ul>36 <li>Target: Nuclei</li>37 <li>Task: Classification</li>38 <li>Modality: Images (Histology and Label) </li>39 </ul>40 </div>41 </div>42 <div class="grid-container">43 <h3 class="overview-heading"><span class="vl">Model Architecture</span></h3>44 <div>45 <p class="overview-content">The model is trained using DenseNet121 over CoNSep dataset.</p>46 <img class="content-image" src="file/figures/architecture.png" alt="model-architecture" />47 </div>48 </div>49 </section>50 <h3 class="overview-heading"><span class="vl">Demo</span></h3>51 <p class="overview-content">Please select or upload a nuclei histology image and label image to see Nuclei Cells Classification capabilities of this model</p>52 </div>53 </body>54</html>55