MILK10k 2025 Leaderboards

Lesion Diagnosis
Rank 49 total Team 49 unique teams Approach Manuscript Used External Data 5 yes Primary Metric Value Dice Coefficient
1
Trần Văn Đồng - Beast Team
Independant researchers
EfficientnetV2 + customized loss v9 add milk10 -
public Yes
0.654
2
AcuvizionAI Belgium
Independent Researcher
AcuvizionAI Multi-Modal Fusion -
public_off No
0.538
3
PanDerm Team
AIM for Health Lab, Monash University
PanDerm V2 -
public_off No
0.524
4
Benjamin Bruch
Independent Researcher
EfficientNetV2 Ensemble -
public_off No
0.506
5
PikaPika
KAIST
EfficientnetV2 + Metadata MLP Fusion -
public_off No
0.505
6
PawsMakeClickClick
Kharkiv National University of Radio Electronics
Derm_v2 -
public_off No
0.504
7
Rohan Iyer
University of Minnesota
Swin-V2 + Multi-View Fusion -
public_off No
0.499
8
able_23
PEC Chandigarh
convnext_base + asl -
public_off No
0.499
9
Sabanci_VPA
Sabanci University
EfficientNet_V2 Dual V2.2 - Rare Classes -
public_off No
0.498
10
JTeam
 dual_vision -
public_off No
0.495
11
Valor
BRAC University b
Dual Swin-Transformer -
public_off No
0.491
12
BUPT
Beijing University of Posts and Telecommunications
MDCL-fold5 -
public_off No
0.491
13
Pedro Bento
 SwinV2 (tiny) - 2 epoch mid training -
public Yes
0.486
14
MDCL-SCRL-2
 MDCL-SCRL-FOLD3 -
public_off No
0.485
15
LIFE
Universidade Federal do Espírito Santo
Concatenation baseline custom loss -
public Yes
0.476
16
MDCL-SCRL
 MDCL-SCRL-FOLD1 -
public_off No
0.471
17
MDCL-SCRL-all
 ALL -
public_off No
0.471
18
Nikshay Kataria
 convnext_512 -
public_off No
0.470
19
Hongyuan Xie
Manchester Metropolitan University
Avg_Scale_Size_CNN -
public_off No
0.467
20
SkinGuard
 ResNet50 -
public_off No
0.464
21
Huvy
 Volo D1 Remix -
public Yes
0.463
22
AK
HUST
CNN -
public_off No
0.462
23
It Hurts When IP
Woxsen University
Densenet -
public_off No
0.459
24
ZY
AHU
Dual_SwinTransformer -
public_off No
0.456
25
ManuelPla
UOC
Multimodal 1.7 -
public_off No
0.453
26
milkyway
Yonsei iie4123
sampler+customloss+tta -
public_off No
0.450
27
cheesenet
 Efficientnetv2 + custom loss + dynamics -
public_off No
0.447
28
Dhruval Padia
 Ensemble -
public_off No
0.444
29
John's Lab
Independent
Vision transformer - custom head - 6 -
public_off No
0.444
30
NIH NLM AI4M
National Institutes of Health, National Library of Medicine
Multimodal-Image-Text -
public_off No
0.442
31
DBAA
Hanoi University of Science and Technology
Multimodal -
public_off No
0.440
32
CBML_UNIPI
University of Pireaus
EfficientNetV2S_DualFusion_Attention -
public_off No
0.439
33
Erdem Bozyel
 Ensemble v1 -
public Yes
0.437
34
ElaheVisionX SkinAnalytics
 EffNetV2 -
public_off No
0.436
35
Concat-four
 Concat-fold5 -
public_off No
0.436
36
Concat
 Concat-All -
public_off No
0.424
37
AIEM
Johns Hopkins University
CNN -
public_off No
0.419
38
Soland
UET
EfficientNetV2 -
public_off No
0.413
39
BUPT6
Beijing University of Posts and Telecommunications
ResNext-Pre-6 -
public_off No
0.402
40
XRAI-Keele
Keele University
Swin-v2 with concept-guided cross-attention -
public_off No
0.389
41
slemanfaiz
 ResNet optimized -
public_off No
0.384
42
BUPT3
Beijing University of Posts and Telecommunications
aa2 -
public_off No
0.323
43
BUPT5
Beijing University of Posts and Telecommunications
ResNext-OnlyImage -
public_off No
0.317
44
TestTeam
 TestModel -
public_off No
0.296
45
JMI SkinVision (Farhan khan)
Jamia Millia Islamia
Dual-EfficientNetV2 with Multi Modal Fusion -
public_off No
0.260
46
BUPT4
Beijing University of Posts and Telecommunications
ResNext-OnlyImage -
public_off No
0.239
47
skintell
 SkinTell -
public_off No
0.236
48
Judy
BUAA
resnet50 -
public_off No
0.155
49
fibers
Universitat Politècnica de Barcelona
First test -
public_off No
0.136