Spaces:
Sleeping
Sleeping
Jason Adrian
commited on
Commit
·
70a8ae4
1
Parent(s):
727fc3c
add index.html and other resources
Browse files
figures/Original-ResNet-18-Architecture.png
ADDED
|
figures/ResNet-18.png
ADDED
|
figures/resnet-residual-block-for-resnet18-from-scratch-using-pytorch.png
ADDED
|
figures/resnet18-basic-blocks-1.png
ADDED
|
index.html
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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><strong>Body Part Classification</strong></title>
|
| 9 |
+
</head>
|
| 10 |
+
<body>
|
| 11 |
+
<div class="container">
|
| 12 |
+
<h1 class="title"><strong> Body Part Classification</strong></h1>
|
| 13 |
+
<h2 class="subtitle"><strong>Kalbe Digital Lab</strong></h2>
|
| 14 |
+
<section class="overview">
|
| 15 |
+
<div class="grid-container">
|
| 16 |
+
<h3 class="overview-heading"><span class="vl">Overview</span></h3>
|
| 17 |
+
<p class="overview-content">
|
| 18 |
+
The Body Part Classification program serves the critical purpose of categorizing body parts from DICOM x-ray scans into five distinct classes: abdominal, adult chest, pediatric chest, spine, and others. This program trained using ResNet18 model.
|
| 19 |
+
</p>
|
| 20 |
+
</div>
|
| 21 |
+
<div class="grid-container">
|
| 22 |
+
<h3 class="overview-heading"><span class="vl">Dataset</span></h3>
|
| 23 |
+
<div>
|
| 24 |
+
<p class="overview-content">
|
| 25 |
+
The program has been meticulously trained on a robust and diverse dataset, specifically <a href="https://vindr.ai/datasets/bodypartxr" target="_blank">VinDrBodyPartXR Dataset.</a>.
|
| 26 |
+
<br/>
|
| 27 |
+
This dataset is introduced by Vingroup of Big Data Institute which include 16,093 x-ray images that are collected and manually annotated. It is a highly valuable resource that has been instrumental in the training of our model.
|
| 28 |
+
</p>
|
| 29 |
+
<ul>
|
| 30 |
+
<li>Objective: Body Part Identification</li>
|
| 31 |
+
<li>Task: Classification</li>
|
| 32 |
+
<li>Modality: Grayscale Images</li>
|
| 33 |
+
</ul>
|
| 34 |
+
</div>
|
| 35 |
+
</div>
|
| 36 |
+
<div class="grid-container">
|
| 37 |
+
<h3 class="overview-heading"><span class="vl">Model Architecture</span></h3>
|
| 38 |
+
<div>
|
| 39 |
+
<p class="overview-content">
|
| 40 |
+
The model architecture of ResNet18 to train x-ray images for classifying body part.
|
| 41 |
+
</p>
|
| 42 |
+
<img class="content-image" src="file/figures/ResNet-18.png" alt="model-architecture" width="425" height="115" style="vertical-align:middle" />
|
| 43 |
+
</div>
|
| 44 |
+
</div>
|
| 45 |
+
</section>
|
| 46 |
+
<h3 class="overview-heading"><span class="vl">Demo</span></h3>
|
| 47 |
+
<p class="overview-content">Please select or upload a body part x-ray scan image to see the capabilities of body part classification with this model</p>
|
| 48 |
+
</div>
|
| 49 |
+
</body>
|
| 50 |
+
</html>
|
style.css
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
* {
|
| 2 |
+
box-sizing: border-box;
|
| 3 |
+
}
|
| 4 |
+
|
| 5 |
+
body {
|
| 6 |
+
font-family: 'Source Sans Pro', sans-serif;
|
| 7 |
+
font-size: 16px;
|
| 8 |
+
}
|
| 9 |
+
|
| 10 |
+
.container {
|
| 11 |
+
width: 100%;
|
| 12 |
+
margin: 0 auto;
|
| 13 |
+
}
|
| 14 |
+
|
| 15 |
+
.title {
|
| 16 |
+
font-size: 24px !important;
|
| 17 |
+
font-weight: 600 !important;
|
| 18 |
+
letter-spacing: 0em;
|
| 19 |
+
text-align: center;
|
| 20 |
+
color: #374159 !important;
|
| 21 |
+
}
|
| 22 |
+
|
| 23 |
+
.subtitle {
|
| 24 |
+
font-size: 24px !important;
|
| 25 |
+
font-style: italic;
|
| 26 |
+
font-weight: 400 !important;
|
| 27 |
+
letter-spacing: 0em;
|
| 28 |
+
text-align: center;
|
| 29 |
+
color: #1d652a !important;
|
| 30 |
+
padding-bottom: 0.5em;
|
| 31 |
+
}
|
| 32 |
+
|
| 33 |
+
.overview-heading {
|
| 34 |
+
font-size: 24px !important;
|
| 35 |
+
font-weight: 600 !important;
|
| 36 |
+
letter-spacing: 0em;
|
| 37 |
+
text-align: left;
|
| 38 |
+
}
|
| 39 |
+
|
| 40 |
+
.overview-content {
|
| 41 |
+
font-size: 14px !important;
|
| 42 |
+
font-weight: 400 !important;
|
| 43 |
+
line-height: 30px !important;
|
| 44 |
+
letter-spacing: 0em;
|
| 45 |
+
text-align: left;
|
| 46 |
+
}
|
| 47 |
+
|
| 48 |
+
.content-image {
|
| 49 |
+
width: 100% !important;
|
| 50 |
+
height: auto !important;
|
| 51 |
+
}
|
| 52 |
+
|
| 53 |
+
.vl {
|
| 54 |
+
border-left: 5px solid #1d652a;
|
| 55 |
+
padding-left: 20px;
|
| 56 |
+
color: #1d652a !important;
|
| 57 |
+
}
|
| 58 |
+
|
| 59 |
+
.grid-container {
|
| 60 |
+
display: grid;
|
| 61 |
+
grid-template-columns: 1fr 2fr;
|
| 62 |
+
gap: 20px;
|
| 63 |
+
align-items: flex-start;
|
| 64 |
+
margin-bottom: 0.7em;
|
| 65 |
+
}
|
| 66 |
+
|
| 67 |
+
.grid-container:nth-child(2) {
|
| 68 |
+
align-items: center;
|
| 69 |
+
}
|
| 70 |
+
|
| 71 |
+
@media screen and (max-width: 768px) {
|
| 72 |
+
.container {
|
| 73 |
+
width: 90%;
|
| 74 |
+
}
|
| 75 |
+
|
| 76 |
+
.grid-container {
|
| 77 |
+
display: block;
|
| 78 |
+
}
|
| 79 |
+
|
| 80 |
+
.overview-heading {
|
| 81 |
+
font-size: 18px !important;
|
| 82 |
+
}
|
| 83 |
+
}
|