harit-pc commited on
Commit
f4ebd61
·
1 Parent(s): bdd19ae

Update index file

Browse files
Files changed (1) hide show
  1. index.html +50 -42
index.html CHANGED
@@ -1,46 +1,54 @@
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>Bilateral View Hypercomplex Breast Classification</title>
9
- </head>
10
- <body>
11
- <div class="container">
12
- <h1 class="title">MedSAM: Segment Anything in Medical Images</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
- <p class="overview-content">
18
- MedSAM, a foundation model for universal medical image segmentation. MedSAM is adapted from the SAM model on an unprecedented scale, with more than one million medical image-mask pairs.
19
- <br />
20
- Reference: <a href="https://arxiv.org/abs/2304.12306" target="_blank">https://arxiv.org/abs/2204.05798</a>
21
- </p>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  </div>
23
- <div class="grid-container">
24
- <h3 class="overview-heading"><span class="vl">Dataset</span></h3>
25
- <div>
26
- <p class="overview-content">The model is trained using a diverse and large-scale medical image segmentation dataset with 1,090,486 medical image-mask pairs, covering 15 imaging modalities, over 30 cancer types, and a multitude of imaging protocols.</p>
27
- <ul>
28
- <li>Target: Capturing a broad spectrum of anatomies and lesions across different modalities.</li>
29
- <li>Task: Segmentation</li>
30
- <li>Modality: Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Endoscopy, Ultrasound, Pathology, Fundus, Dermoscopy, Mammography, and Optical Coherence Tomography (OCT).</li>
31
- </ul>
32
- </div>
33
  </div>
34
- <div class="grid-container">
35
- <h3 class="overview-heading"><span class="vl">Model Architecture</span></h3>
36
- <div>
37
- <p class="overview-content">Parameterized Hypercomplex ResNets-18 Variants (PHYResNet).</p>
38
- <img class="content-image" src="file/figures/medsam.png" alt="model-architecture" />
39
- </div>
40
- </div>
41
- </section>
42
- <h3 class="overview-heading"><span class="vl">Demo</span></h3>
43
- <p class="overview-content">Please select the example below or upload 2 pairs of mammography exam result.</p>
44
- </div>
45
- </body>
46
- </html>
 
1
  <!DOCTYPE html>
2
  <html>
3
+
4
+ <head>
5
+ <link rel="stylesheet" href="file/style.css" />
6
+ <link rel="preconnect" href="https://fonts.googleapis.com" />
7
+ <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin />
8
+ <link href="https://fonts.googleapis.com/css2?family=Source+Sans+Pro:wght@400;600;700&display=swap"
9
+ rel="stylesheet" />
10
+ <title>Bilateral View Hypercomplex Breast Classification</title>
11
+ </head>
12
+
13
+ <body>
14
+ <div class="container">
15
+ <h1 class="title">MedSAM: Segment Anything in Medical Images</h1>
16
+ <h2 class="subtitle">Kalbe Digital Lab</h2>
17
+ <section class="overview">
18
+ <div class="grid-container">
19
+ <h3 class="overview-heading"><span class="vl">Overview</span></h3>
20
+ <p class="overview-content">
21
+ MedSAM, a foundation model for universal medical image segmentation. MedSAM is adapted from the SAM
22
+ model on an unprecedented scale, with more than one million medical image-mask pairs.
23
+ <br />
24
+ Reference: <a href="https://arxiv.org/abs/2304.12306"
25
+ target="_blank">https://arxiv.org/abs/2204.05798</a>
26
+ </p>
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">The model is trained using a diverse and large-scale medical image
32
+ segmentation dataset with 1,090,486 medical image-mask pairs, covering 15 imaging modalities,
33
+ over 30 cancer types, and a multitude of imaging protocols.</p>
34
+ <ul>
35
+ <li>Target: Capturing a broad spectrum of anatomies and lesions across different modalities.
36
+ </li>
37
+ <li>Task: Segmentation</li>
38
+ <li>Modality: Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Endoscopy, Ultrasound,
39
+ Pathology, Fundus, Dermoscopy, Mammography, and Optical Coherence Tomography (OCT).</li>
40
+ </ul>
41
  </div>
42
+ </div>
43
+ <!-- <div class="grid-container">
44
+ <h3 class="overview-heading"><span class="vl">Model Architecture</span></h3>
45
+ <div>
46
+ <p class="overview-content">Segment Anything (MedSAM).</p>
47
+ <img class="content-image" src="./figures/medsam.png" alt="model-architecture" />
 
 
 
 
48
  </div>
49
+ </div>
50
+ </section>
51
+ </div>
52
+ </body>
53
+
54
+ </html>