Skip to content

Commit 4843c2d

Browse files
Fujia1998Fujia1998
committed
website_v2
1 parent 0557473 commit 4843c2d

8 files changed

+320
-173
lines changed

‎contact.html

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -120,6 +120,7 @@
120120
<nav class="nav-links">
121121
<a href="index.html">Home</a>
122122
<a href="tasks.html">Tasks</a>
123+
<a href="dataset.html">Dataset</a>
123124
<a href="evaluate.html">Evaluate</a>
124125
<a href="prizes.html">Prizes</a>
125126
<a href="leaderboard.html">Leaderboard</a>

‎dataset.html

Lines changed: 262 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,262 @@
1+
<!DOCTYPE html>
2+
<html lang="en">
3+
4+
<head>
5+
<meta charset="UTF-8">
6+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
7+
<title>SegRap2025 Challenge</title>
8+
<link rel="stylesheet" href="shared.css">
9+
<style>
10+
.task-section {
11+
margin-bottom: 60px;
12+
}
13+
14+
.task-content {
15+
background: white;
16+
border-radius: 12px;
17+
padding: 20px;
18+
margin-bottom: 20px;
19+
}
20+
21+
.task-content li {
22+
color: #064b43;
23+
margin-bottom: 0.3em;
24+
line-height: 1.5;
25+
}
26+
27+
.task-overview {
28+
margin-bottom: 40px;
29+
line-height: 1.6;
30+
}
31+
32+
.evaluation-metrics {
33+
margin-top: 20px;
34+
}
35+
36+
.metric-item {
37+
margin-bottom: 20px;
38+
}
39+
40+
.metric-name {
41+
font-weight: 500;
42+
color: var(--text-primary);
43+
font-size: 20px;
44+
margin-bottom: 8px;
45+
margin-top: 0px;
46+
}
47+
48+
.metric-description {
49+
color: var(--text-secondary);
50+
font-size: 0.95em;
51+
line-height: 1.5;
52+
}
53+
54+
.news-list {
55+
list-style: none;
56+
padding: 0;
57+
margin: 0;
58+
}
59+
60+
.news-list li {
61+
position: relative;
62+
padding-left: 25px;
63+
margin-top: 1%;
64+
margin-bottom: 20px;
65+
line-height: 1.3;
66+
color: #000000;
67+
font-size: 0.95em;
68+
font-weight: 400;
69+
}
70+
71+
.news-list li::before {
72+
content: "•";
73+
position: absolute;
74+
left: 10px;
75+
color: #00bfa5;
76+
}
77+
78+
.news-list a {
79+
color: #00bfa5;
80+
text-decoration: none;
81+
font-weight: 500;
82+
transition: color 0.2s ease;
83+
}
84+
85+
.news-list a:hover {
86+
color: #00897b;
87+
}
88+
</style>
89+
</head>
90+
91+
<body>
92+
<div class="site-header">
93+
<div class="header-image" style="text-align: center;">
94+
<img src="logo_web.png" alt="SegRap Logo" style="width: 50%; height: auto;">
95+
</div>
96+
<div class="header-container">
97+
<div class="content-section">
98+
<nav class="nav-links">
99+
<a href="index.html">Home</a>
100+
<a href="tasks.html">Tasks</a>
101+
<a href="dataset.html" class="active">Dataset</a>
102+
<a href="evaluate.html">Evaluate</a>
103+
<a href="prizes.html">Prizes</a>
104+
<a href="leaderboard.html">Leaderboard</a>
105+
<a href="organizing.html">Organizing</a>
106+
<a href="contact.html">Contact</a>
107+
</nav>
108+
</div>
109+
</div>
110+
</div>
111+
112+
<main class="main-content">
113+
<!-- Overview Section -->
114+
<section id="overview" class="task-section">
115+
<h1 class="section-title">Description</h1>
116+
<div class="metric-name">Task01: GTV segmentation</div>
117+
<p class="metric-description">
118+
SegRap2025 Dataset will consist of CT images collected by Siemens CT scanners with the following
119+
scanning conditions:
120+
bulb voltage, 120 kV; current, 300 mA; scan thickness, 3.0 mm; resolution, 1024 &times; 1024 or 512
121+
&times; 512; injected contrast
122+
agent, iohexol (volume, 60~80 mL; rate, 2 mL/s; without delay). The dataset consists of clinically
123+
required non-contrast
124+
CT images (ncCT) and contrast CT images (ceCT) from patients with nasopharyngeal cancer before
125+
treatment.
126+
</p>
127+
<br>
128+
<p class="metric-description">
129+
The dataset consists of clinically required <strong>non-contrast CT images (ncCT)</strong> and
130+
<strong>contrast CT images (ceCT)</strong> from patients with nasopharyngeal cancer before
131+
treatment.
132+
</p>
133+
<ul class="news-list">
134+
<li>Training data will consist of CT images from <strong>120 patients</strong> with a
135+
corresponding
136+
label map, as well as <strong>500 unlabeled cases</strong>.</li>
137+
<li>Validation data will consist of CT images from <strong>20 patients</strong>.</li>
138+
<li>Testing data will consist of CT images from two cohorts: <strong>60 patients from internal testing
139+
cohort</strong>, and <strong>60 patients from external testing cohort</strong>.
140+
</li>
141+
</ul>
142+
<!-- <br> -->
143+
<p class="metric-description">
144+
<em>Note:</em> All GTVs were annotated individually by oncologists using MIM Software and ITKSNAP,
145+
the annotation of each organ was also stored individually. The expected output from your algorithm
146+
should be a set of label maps.
147+
</p>
148+
<br>
149+
150+
<div class="metric-name">Task02: LN CTV Segmentation</div>
151+
<p class="metric-description">
152+
SegRap2025 Dataset will consists of CT images from Sichuan Cancer Hospital are collected by a
153+
Brilliance CT Big Bore
154+
system from Philips Healthcare (Philips Healthcare, Best, the Netherlands), with the following
155+
scanning conditions: bulb
156+
voltage at 120 kV, current ranging from 275 to 375 mA, slice thickness of 3.0 mm, and full
157+
resolution of 512 &times; 512. An
158+
injected contrast agent, iohexol, was used during the ceCT examination. Similarly, CT images from
159+
Sichuan Provincial
160+
People's Hospital, The First Affiliated Hospital of University of Science and Technology of China
161+
and Southern Medical
162+
University were acquired using a Somatom Definition AS 40 system from Siemens Healthcare (Siemens
163+
Healthcare, Forcheim,
164+
Germany), with the following conditions: bulb voltage ranging from 120 to140 kV, current ranging
165+
from 280 to 380 mA,
166+
slice thickness of 3.0 mm, and full resolution of 512 &times; 512. CT images from Daguan Hospital of
167+
Chengdu Jinjiang were
168+
acquired using a Somatom Definition AS 40 system from Siemens Healthcare (Siemens Healthcare,
169+
Forcheim, Germany), with
170+
the following conditions: bulb voltage 120 kV, current ranging from 200 to 250 mA, slice thickness
171+
of 2.5 mm, and full
172+
resolution of 512 &times; 512.
173+
</p>
174+
<br>
175+
<p class="metric-description">
176+
The dataset consists of clinically required <strong>non-contrast CT images (ncCT)</strong> and/or
177+
<strong>contrast CT images (ceCT)</strong> from patients with nasopharyngeal cancer before
178+
treatment.
179+
</p>
180+
<ul class="news-list">
181+
182+
<li>Training data will consist of CT images from <strong>262 patients from five cohorts</strong>
183+
(150 paired CT, 32 ncCT and 80 ceCT) with
184+
a corresponding label map, as well as <strong>500 unlabeled cases</strong>.</li>
185+
<li>Validation data will consist of <strong>40 patients from external testing
186+
cohort</strong>: <em>20 with paired CT</em>, <em>10 with only ncCT</em>, and <em>10 with
187+
only ceCT</em>.
188+
</li>
189+
<li>Testing data will consist of <strong>100 patients from external testing
190+
cohort</strong>: <em>40 with paired CT</em>, <em>30 with only ncCT</em>, and <em>30 with
191+
only ceCT</em>.</li>
192+
</ul>
193+
<!-- <br> -->
194+
<p class="metric-description">
195+
<em>Note:</em> All LN CTVs were annotated individually by oncologists using MIM Software and
196+
ITKSNAP, the annotation of each organ was
197+
also stored individually. The expected output from your algorithm should be a set of label maps.
198+
</p>
199+
<br>
200+
201+
<h2 class="section-title">Download</h2>
202+
<div class="task-content">
203+
<div class="metric-name">Task01: GTV Segmentation</div>
204+
<p class="metric-description">
205+
The training data (with labels) and validation data (without lables) can be downloaded at: <a
206+
href="https://drive.google.com/drive/folders/115mzmNlZRIewnSR2QFDwW_-RkNM0LC9D">GoogleDrive</a>
207+
and <a
208+
href="https://pan.baidu.com/s/1KYH4j5CQO_qx7wg7GkkR7Q?pwd=2023#list/path=%2F">BaiduNetDisk</a>.
209+
The unzipped password is <em>segrap2023@uestc</em>.
210+
</p>
211+
<br>
212+
213+
<div class="metric-name">Task02: LN CTV Segmentation</div>
214+
<p class="metric-description">
215+
The training data (with labels) can be downloaded at: <a
216+
href="https://figshare.com/articles/dataset/LNCTVSeg-DataSet_zip/26793622?file=48684664">here</a>,
217+
and the unzipped passowrd is <em>lnctvseg@uestc</em>.
218+
<br>
219+
The validation data (without labels) can be
220+
downloaded at: <a
221+
href="https://drive.google.com/file/d/1vcEX4aLnwi32c10ronFbdxMy49JDhjtQ/view?usp=sharing">GoogleDrive</a>
222+
and <a href="https://pan.baidu.com/s/18ZKqRBOWR0BWFQ9Z6HXv2w?pwd=2025">BaiduNetDisk</a>.
223+
<br>
224+
</p>
225+
<br>
226+
227+
<div class="metric-name">Supplementary unlabeled data</div>
228+
<p class="metric-description">
229+
A total of 500 <strong>unlabeled images</strong> are provided at: <a
230+
href="https://drive.google.com/file/d/1pfYGXHg62gV-77LYv-U-9_hdQh81KYHb/view?usp=sharing">GoogleDrive</a>
231+
and <a href="https://pan.baidu.com/s/1JzayTGV-EBuXYeiLhGlfew?pwd=2025">BaiduNetDisk</a>.
232+
Participants
233+
may explore
234+
self-supervised or semi-supervised learning strategies to enhance model generalizability.
235+
</p>
236+
<br>
237+
238+
<div class="metric-name">Note</div>
239+
<ul class="news-list">
240+
<li>Please fill out the <a
241+
href="https://drive.google.com/file/d/1KvEB41N4PvYyAAha--xDrCbvUEWg9Ljm/view?usp=sharing">EndUserAgreement</a>,
242+
and email a scan of the signed document to <em>[email protected]</em>. Then, we will provide
243+
you with the unzipped password for the Task02 validation set and Supplementary unlabeled data.
244+
</li>
245+
<li>SegRap2025 focuses on the GTV and LN CTV segmentation. Participants are encouraged to leverage
246+
<strong>OAR anatomical information</strong> to support GTV segmentation, but segmentation of
247+
OARs are not necessary.
248+
</li>
249+
<li>The use of <strong>foundation models</strong> is permitted, but additional external data are not
250+
allowed.
251+
</li>
252+
</ul>
253+
<br>
254+
</div>
255+
256+
</section>
257+
258+
259+
</main>
260+
</body>
261+
262+
</html>

‎evaluate.html

Lines changed: 20 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -148,6 +148,7 @@
148148
<nav class="nav-links">
149149
<a href="index.html">Home</a>
150150
<a href="tasks.html">Tasks</a>
151+
<a href="dataset.html">Dataset</a>
151152
<a href="evaluate.html" class="active">Evaluate</a>
152153
<a href="prizes.html">Prizes</a>
153154
<a href="leaderboard.html">Leaderboard</a>
@@ -170,31 +171,17 @@ <h1 class="section-title">Evaluate and Ranking</h1>
170171
For the first phase (validation phase), the participants are required to submit the output of their
171172
algorithms as a single compressed zip file to the organization team. The submitted zip files should
172173
be formatted like the one below. Make sure the results in the submitted zip file all be matched with
173-
the validation images one-to-one, which contains 2 predictions for task1 and 6 predictions for task2
174-
for each case. Otherwise, the results are considered invalid submissions and no score will be
175-
generated.
174+
the validation images one-to-one (2 classes for Task01 and 6 classes for Task02). Otherwise, the
175+
results are considered invalid submissions and no score will be generated.
176176
</p>
177177
<div class="tree">
178-
<ul> results/
179-
<ul>
180-
<li>SegRap_0001
181-
<ul>
182-
<li>GTVnx.nii.gz</li>
183-
<li>GTVnd.nii.gz</li>
184-
</ul>
185-
</li>
186-
<li>…
187-
<ul>
188-
<li>GTVnx.nii.gz</li>
189-
<li>GTVnd.nii.gz</li>
190-
</ul>
191-
</li>
192-
<li>SegRap_xxxx
193-
<ul>
194-
<li>GTVnx.nii.gz</li>
195-
<li>GTVnd.nii.gz</li>
196-
</ul>
197-
</li>
178+
<ul> team_name/
179+
<ul> Task0*_results/
180+
<ul>
181+
<li>SegRap_0001.nii.gz</li>
182+
<li>......</li>
183+
<li>SegRap_xxxx.nii.gz</li>
184+
</ul>
198185
</ul>
199186
</ul>
200187
</div>
@@ -227,20 +214,18 @@ <h1 class="section-title">Evaluate and Ranking</h1>
227214
<div class="evaluate-content">
228215
<div class="metric-name">Ranking</div>
229216
<p class="metric-description">
230-
Firstly, for each organ, we calculate the average DSC and NSD across all the patients respectively.
231-
Secondly, each
232-
participant will be ranked based on the organ-level DSC and NSD; each participant will have 2
233-
&times; 2 or 6 &times; 2 rankings.
234-
Finally, average all these rankings and then normalize them by the number of teams. At the same
235-
time, we will take the
236-
statistical ranking. (Allow equal teams if there is no significant difference).</p>
217+
Firstly, for each cohort (set), we calculate the average DSC and NSD across all the patients for
218+
each class, respectively. Secondly, each participant will be ranked based on the class-level DSC and
219+
NSD, with 2 &times; 2 or 6 &times; 2 rankings. Then, rankings for all classes are averaged in each
220+
cohort (set). Finally, rankings for all cohorts (sets) are averaged and then normalized by the
221+
number of teams. At the same time, we will take the statistical ranking. (Allow equal teams if there
222+
is no significant difference).</p>
237223
<br>
238224
<p class="metric-description">
239-
In addition, if the submissions have some missing results on test cases, the corresponding organ's
240-
DSC and NSD will be
241-
set to 0 and 0 for ranking. For example, a test case missed an organ and the ranking value of this
242-
organ in average DSC
243-
and NSD will degrade.
225+
In addition, if the submissions have some missing results on test cases, the corresponding class's
226+
DSC and NSD will be set to 0 and 0 for ranking. For example, a test case missed a class and the
227+
ranking value of this
228+
class in average DSC and NSD will degrade.
244229
</p>
245230
</div>
246231
</section>

‎index.html

Lines changed: 7 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -143,6 +143,7 @@
143143
<nav class="nav-links">
144144
<a href="index.html" class="active">Home</a>
145145
<a href="tasks.html">Tasks</a>
146+
<a href="dataset.html">Dataset</a>
146147
<a href="evaluate.html">Evaluate</a>
147148
<a href="prizes.html">Prizes</a>
148149
<a href="leaderboard.html">Leaderboard</a>
@@ -197,11 +198,11 @@ <h1 class="section-title">Abstract</h1>
197198
<h1 class="section-title">Important Dates</h1>
198199
<ul class="news-list">
199200
<li><strong>Registration opens</strong>: May 1st (12:00 AM GMT), 2025</li>
200-
<li><strong>Release of training data</strong>: May 10th (12:00 AM GMT), 2025</li>
201-
<li><strong>Release of validation data</strong>: June 30th (12:00 AM GMT), 2025</li>
202-
<li><strong>Docker and short paper submission opens</strong>: Aug. 10th (12:00 AM GMT), 2025</li>
203-
<li><strong>Submission deadline</strong>: Aug. 31st (12:00 AM GMT), 2025</li>
204-
<li><strong>Announcement of final results</strong>: Sep. 23th and 27th, 2025</li>
201+
<li><strong>Release of training and validation data</strong>: May 10th (12:00 AM GMT), 2025</li>
202+
<li><strong>Validation results evaluation</strong>: June 30th ~ Aug. 10th (12:00 AM GMT), 2025</li>
203+
<li><strong>Docker and short paper submission</strong>: Aug. 10th ~ Aug. 31st (12:00 AM
204+
GMT), 2025</li>
205+
<li><strong>Announcement of final results</strong>: Sep. 23th, 2025</li>
205206
</ul>
206207
</section>
207208

@@ -233,4 +234,4 @@ <h1 class="section-title">References</h1>
233234
</main>
234235
</body>
235236

236-
</html>
237+
</html>

‎leaderboard.html

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -38,6 +38,7 @@
3838
<nav class="nav-links">
3939
<a href="index.html">Home</a>
4040
<a href="tasks.html">Tasks</a>
41+
<a href="dataset.html">Dataset</a>
4142
<a href="evaluate.html">Evaluate</a>
4243
<a href="prizes.html">Prizes</a>
4344
<a href="leaderboard.html" class="active">Leaderboard</a>

‎organizing.html

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -132,6 +132,7 @@
132132
<nav class="nav-links">
133133
<a href="index.html">Home</a>
134134
<a href="tasks.html">Tasks</a>
135+
<a href="dataset.html">Dataset</a>
135136
<a href="evaluate.html">Evaluate</a>
136137
<a href="prizes.html">Prizes</a>
137138
<a href="leaderboard.html">Leaderboard</a>

0 commit comments

Comments
 (0)