Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
read the original abstract
This work summarizes the results of the largest skin image analysis challenge in the world, hosted by the International Skin Imaging Collaboration (ISIC), a global partnership that has organized the world's largest public repository of dermoscopic images of skin. The challenge was hosted in 2018 at the Medical Image Computing and Computer Assisted Intervention (MICCAI) conference in Granada, Spain. The dataset included over 12,500 images across 3 tasks. 900 users registered for data download, 115 submitted to the lesion segmentation task, 25 submitted to the lesion attribute detection task, and 159 submitted to the disease classification task. Novel evaluation protocols were established, including a new test for segmentation algorithm performance, and a test for algorithm ability to generalize. Results show that top segmentation algorithms still fail on over 10% of images on average, and algorithms with equal performance on test data can have different abilities to generalize. This is an important consideration for agencies regulating the growing set of machine learning tools in the healthcare domain, and sets a new standard for future public challenges in healthcare.
This paper has not been read by Pith yet.
Forward citations
Cited by 35 Pith papers
-
AMUSE: Anytime Muon with Stable Gradient Evaluation
AMUSE is a new optimizer integrating Muon orthogonalization with Schedule-Free averaging via adaptive interpolation for schedule-free anytime training that improves Pareto frontiers on vision and LLM tasks.
-
ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning
ConceptSeg-R1 uses Meta-GRPO meta-RL to learn transferable rules from visual demonstrations and apply them via concept translation for generalized concept segmentation across CI, CD, and CR levels.
-
Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image Segmentation
Patch-MoE Mamba introduces patch-ordered hierarchical scanning and an MoE-based directional fusion module to improve Mamba segmentation models on polyp and skin lesion datasets.
-
MedCore: Boundary-Preserving Medical Core Pruning for MedSAM
MedCore achieves 60% parameter and 58.4% FLOP reduction on MedSAM with Dice 0.9549 and preserved boundary metrics via dual-intervention pruning and a new boundary leverage principle.
-
Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning
LoRA adapters fix collapsed visual CLS token attention in CLIP for superior cross-domain few-shot learning, and the new Semantic Probe framework revives prompt methods to reach state-of-the-art on four benchmarks.
-
XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity
XTinyU-Net identifies the smallest stable U-Net configuration using a Jacobian sensitivity metric on unlabeled images at initialization, achieving comparable accuracy to full models with 400-1600 times fewer parameters.
-
Principle-Guided Supervision for Interpretable Uncertainty in Medical Image Segmentation
PriUS enforces uncertainty estimates in segmentation models via evidential learning to match image contrast, corruption levels, and shape complexity, yielding more consistent uncertainty on ACDC, ISIC, and WHS dataset...
-
S2M-Net: Spectral-Spatial Mixing for Medical Image Segmentation with Morphology-Aware Adaptive Loss
S2M-Net achieves state-of-the-art Dice scores on 16 medical datasets across 8 modalities using a 4.7M-parameter spectral-spatial mixer and morphology-aware adaptive loss, outperforming transformers with 3.5-6x fewer p...
-
Adversarial Robustness in One-Stage Learning-to-Defer
Develops the first adversarial robustness framework for one-stage learning-to-defer, including cost-sensitive surrogate losses and theoretical consistency guarantees for classification and regression.
-
Rethinking Noise-Robust Training for Frozen Vision Foundation Models: A Cross-Dataset Benchmark with a Case Study of Small-Loss Failure
Large-scale benchmark of noisy-label methods on frozen VFMs reveals no universal winner, with ELR and CUFIT performing differently, and demonstrates small-loss assumption failure via 53-61% loss overlap under asymmetr...
-
Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation
HERA is a select-regularize-calibrate framework adapting frozen vision foundation models for cross-domain few-shot semantic segmentation via hierarchical layer selection with ETR, prior-guided regularization, and pixe...
-
Towards Fine-Grained and Verifiable Concept Bottleneck Models
A verifiable CBM framework grounds concepts in localized image patches, achieving comparable accuracy to standard CBMs on medical benchmarks while enabling direct inspection of concept correctness.
-
Keyed Nonlinear Transform: Lightweight Privacy-Enhancing Feature Sharing for Medical Image Analysis
KNT applies key-conditioned nonlinear obfuscation to split-inference features, cutting re-identification AUC from 0.635 to 0.586 with 0.15 ms overhead and under 1 pp accuracy loss.
-
Geometry-aware Prototype Learning for Cross-domain Few-shot Medical Image Segmentation
GeoProto enriches appearance prototypes with geometric offsets from an ordinal shape branch to improve cross-domain few-shot medical image segmentation.
-
XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity
A Jacobian sensitivity curve computed at initialization identifies the narrowest U-Net configuration that avoids performance collapse, matching nnU-Net accuracy with 400-1600x fewer parameters on six medical datasets.
-
Probing Intrinsic Medical Task Relationships: A Contrastive Learning Perspective
TaCo contrastively embeds semantic, generative, and transformation tasks from medical imaging into a joint space to reveal which tasks cluster, blend, or remain distinct.
-
RABC-Net: Reliability-Aware Annotation-Free Skin Lesion Segmentation for Low-Resource Dermoscopy
RABC-Net achieves 86.58% DICE and 79.47% JAC on skin lesion segmentation across ISIC-2017, ISIC-2018, and PH2 using only pseudo-labels and no manual masks for training or adaptation.
-
Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detection
A single model trained on one normal sample per dataset from nine heterogeneous medical sources achieves state-of-the-art anomaly detection in one-shot universal, full-shot universal, one-shot specialized, and full-sh...
-
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
ViSurf unifies SFT and RLVR for LVLMs in one training stage by injecting ground-truth labels into rollouts and applying novel reward controls, outperforming standalone and two-stage baselines on diverse benchmarks.
-
Cross-Domain Few-Shot Segmentation via Ordinary Differential Equations over Time Intervals
FSS-TIs models cross-domain few-shot segmentation as an ODE process with Fourier-based spectral perturbations to create domain-agnostic features and enable effective fine-tuning on limited support samples.
-
Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
AML outperforms cross-validated baselines including CNNs on 50-2000 example image datasets and is comparable to XGBoost/LightGBM on tabular data using only training data and no task-dependent hyperparameters.
-
Rad-VLSM: A Cross-Modal Framework with Semantics-Assisted Prompting for Medical Segmentation and Diagnosis
Rad-VLSM is a cross-modal two-stage framework that converts semantic guidance from BLIP-2 into box prompts for SAM-based lesion segmentation and then uses the resulting masks as spatial priors in a visual-radiomics fu...
-
SemiGDA: Generative Dual-distribution Alignment for Semi-Supervised Medical Image Segmentation
SemiGDA aligns feature and semantic distributions via dual encoders and skip adapters to boost semi-supervised medical image segmentation.
-
MambaLiteUNet: Cross-Gated Adaptive Feature Fusion for Robust Skin Lesion Segmentation
MambaLiteUNet integrates Mamba into U-Net with adaptive fusion, local-global mixing, and cross-gated attention modules to reach 87.12% IoU and 93.09% Dice on skin lesion datasets while cutting parameters by 93.6%.
-
Improved Anomaly Detection in Medical Images via Mean Shift Density Enhancement
A new Mean Shift Density Enhancement procedure applied to self-supervised embeddings yields state-of-the-art anomaly detection AUC and average precision on seven medical imaging datasets.
-
Bias-constrained multimodal intelligence for equitable and reliable clinical AI
BiasCareVL is a bias-aware vision-language framework trained on 3.44 million medical samples that outperforms prior methods on clinical tasks like diagnosis and segmentation while aiming for equitable performance unde...
-
Risk-Calibrated Learning: Minimizing Fatal Errors in Medical AI
Risk-Calibrated Learning reduces critical error rates in medical AI by 20-92% across four imaging datasets by embedding a severity matrix into the optimization.
-
M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model
M-IDoL learns modality-specific and diverse representations by maximizing inter-modality entropy and minimizing intra-modality uncertainty through information decomposition in MoE subspaces.
-
CLIP-SVD: Efficient and Interpretable Vision-Language Adaptation via Singular Values
CLIP-SVD performs parameter-efficient adaptation of CLIP by fine-tuning singular values from SVD of weight matrices, reporting SOTA few-shot accuracy on 21 datasets plus a language-based interpretability analysis.
-
Task-Distributionally Robust Data-Free Meta-Learning
The paper proposes a trustworthy DFML framework that mitigates task-distribution shift and corruption via synthetic task reconstruction, historical task replay through interpolation, and automatic filtering of untrust...
-
Entropy-Guided Self-Supervised Learning for Medical Image Classification
Ensemble of ImageNet-pretrained and entropy-guided MAE-pretrained ConvNeXt-Tiny models achieves state-of-the-art results on four medical imaging datasets including BUSI, ISIC 2018, Kvasir, and COVID.
-
Med-DisSeg: Dispersion-Driven Representation Learning for Fine-Grained Medical Image Segmentation
Med-DisSeg uses a dispersive loss on batch representations plus adaptive multi-scale decoding to achieve state-of-the-art fine-grained segmentation on five medical imaging datasets.
-
Improving Model Safety by Targeted Error Correction
A dual GBDT error classifier reduces dangerous misclassifications by 12-34% on medical and animal image datasets with under 2% added latency.
-
DMDSC: A Dynamic-Margin Deep Simplex Classifier for Open-Set Recognition on Medical Image Datasets
DMDSC adapts simplex-classifier margins dynamically according to label frequency to tighten clustering on rare medical classes and improve open-set rejection on imbalanced imaging datasets.
-
Attention Is not Everything: Efficient Alternatives for Vision
A survey that taxonomizes non-Transformer vision models and evaluates their practical trade-offs across efficiency, scalability, and robustness.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.