ISIC 2018 Leaderboards
| Rank 17 total | Team 17 unique teams | Approach | Manuscript | Used External Data 1 yes | Primary Metric Value Jaccard Index | |
|---|---|---|---|---|---|---|
| 1 |
NMN_team
NMN_team
|
attributes_ensembleALL_miliaReplaced_withSegmentation | description |
public_off
No
|
0.307 | |
|
|
||||||
| 2 |
Le-Health
Le-Health
|
Multi-level feature fusion in Pyramid Scene Parsing Network | description |
public_off
No
|
0.276 | |
|
|
||||||
| 3 |
RECOD Titans
RECOD Titans
|
Average of 4 Deep-Learning Models without Thresholding | description |
public_off
No
|
0.238 | |
|
|
||||||
| 4 |
Mammoth
Mammoth
|
Unet without validation | description |
public_off
No
|
0.231 | |
|
|
||||||
| 5 |
Weill Cornell Medicine
Weill Cornell Medicine
|
Three-step Unet with weighted average ensemble | description |
public_off
No
|
0.209 | |
|
|
||||||
| 6 |
PA_Tech
PA_Tech
|
a patch-based deep convolutional neural network based on U-net | description |
public_off
No
|
0.207 | |
|
|
||||||
| 7 |
Andrey Sorokin
Andrey Sorokin
|
Mask-RCNN with SGD | description |
public_off
No
|
0.202 | |
|
|
||||||
| 8 |
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Scie
Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Scie
|
Automated Visual‐attention‐guided Approach with ROI‐unifying DCNNs | description |
public_off
No
|
0.194 | |
|
|
||||||
| 9 |
Università degli Studi di Modena e Reggio Emilia (AImage Lab .zip)
Università degli Studi di Modena e Reggio Emilia (AImage Lab .zip)
|
Adapted Deep Labelling for Semantic Image Segmentation (DeepLab) | description |
public_off
No
|
0.178 | |
|
|
||||||
| 10 |
Multimedia Processing Group
Multimedia Processing Group
|
CNN softmax areanorm classweights | description |
public_off
No
|
0.170 | |
|
|
||||||
| 11 |
Asmaa Aljuhani and Abhishek Kumar @ OSU
Asmaa Aljuhani and Abhishek Kumar @ OSU
|
Skin lesion attribute detection using full sized images in Mask R-CNN | description |
public_off
No
|
0.169 | |
|
|
||||||
| 12 |
imsight
imsight
|
Automatic Skin Lesion Attribute Detection using DCNN | description |
public_off
No
|
0.153 | |
|
|
||||||
| 13 |
Tencent Youtu Lab
Tencent Youtu Lab
|
Automatic Skin Lesion Attribute Detection with Deep Networks | description |
public_off
No
|
0.146 | |
|
|
||||||
| 14 |
AI Toulouse
AI Toulouse
|
Using GrassNet segmentation and training seperately 5 attributes | description |
public_off
No
|
0.128 | |
|
|
||||||
| 15 |
NTHU CVLab
NTHU CVLab
|
Deep learning with GCN model | description |
public_off
No
|
0.104 | |
|
|
||||||
| 16 |
The Homeboy's
The Homeboy's
|
Patch based processing for feature segmentation | description |
public_off
No
|
0.100 | |
|
|
||||||
| 17 |
University of York
University of York
|
Multitask learning, single CNN for all three tasks, segmentation via FCN | description |
public
Yes
|
0.086 | |
|
|
||||||