dermoscopy 开源项目推荐（44 个）

uni-medical /Project-Imaging-X

Project Imaging-X：面向基础模型开发的 1000+ 开放获取医学影像数据集综述

karthik-d /few-shot-dermoscopic-image-analysis

Skin lesion image analysis that draws on meta-learning to improve performance in low data and imbalanced data regimes.

peterlipan /MRC_VFC

The souce code of MICCAI'23 paper: Combat Long-tails in Medical Classification with Relation-aware Consistency and Virtual Features Compensation

JaspinXu /SkinDualGen

Prompt-driven diffusion for jointly generating dermoscopic images and lesion masks, with downstream classification and segmentation evaluation.

TaherGrayson24 /deep_learning_skin_cancer_detection_multi_type_isic2018

多类型ISIC 2018皮肤病变分类的深度学习流程，包含CNN、预处理、增强以及训练和推断支持🐙。

rjsayskaddu /Skin-Lesion-Classification-Analysis

Skin Lesion Classification Analysis: A Comparative Study

daorre1202 /skin-lesion-classifier-CNN

CNN ensemble for skin lesion classification — BACC 0.846 ± 0.009 · Clinical threshold calibration · ResNet-50 + DenseNet-121 + EfficientNet-B3 · ISIC 2018 Task 3

Usman-Amin-AI /DermaScope-Streamlit

Streamlit Application live to use for free forever.

OdincovMD /img2txt

Автоматическое клиническое описание дерматоскопических изображений: признаки → бакетизация → ранжирование → Qwen2.5-7B

ibrar-syed /deep_learning_skin_cancer_detection_multi_type_isic2018

使用 ISIC 数据集进行皮肤病变分类的深度学习流水线，采用多种深度学习 CNN 算法及高级预处理，包括多线程加载、数据增强和性能评估。

MoleCare /molecare-ml

Melanoma classification service and training notebooks behind the MoleCare skin-health apps. Research and education only — not a medical device.

Boatengs /skin-disease-classifier

EfficientNetB0 trained on HAM10000 across 7 skin lesion classes: 74.15% test accuracy, Grad-CAM heatmaps that show the image regions behind each prediction, and class weighted loss for imbalanced data. Live demo on Hugging Face Spaces.

salonipandagale /Skin-Lesion-Segmentation-UNet

Pixel-level skin lesion segmentation using a custom U-Net deep learning model trained on ISIC 2016 dermoscopic images.

mmu-dermatology-research /dca_artifact_removal

Source code for the paper: "Dermoscopic Dark Corner Artifacts Removal: Friend or Foe?"

Boatengs /skin-lesion-segmentation

Pixel level skin lesion segmentation with a U-Net trained from scratch on HAM10000: 0.9115 Dice score, 31M parameters, combined BCE and Dice loss. Live demo on Hugging Face Spaces.

NigusHaile /skin_lesion_v2

Deep learning for 7-class skin lesion classification using HAM10000, with ViT + LoRA, ResNet50, Grad-CAM explainability, and an interactive Streamlit dashboard.

vijaysairaj /Dermiq

derm - dermatology/skin iq - intelligence, AI

Gonzalo-A-G /dermabench

Benchmark honesto de descriptores de imagen para clasificar lesiones cutaneas dermatoscopicas (ISIC): 390 combinaciones descriptor x algoritmo, control del efecto de lote y validacion externa entre instituciones. AUC 0.741 fuera del archivo de entrenamiento.

ahmed-226 /Skin-Cancer-Detection

A computer vision and machine learning pipeline for automatic skin cancer detection from dermoscopic images. Achieves high accuracy using traditional ML techniques with preprocessing, feature extraction, and ensemble learning.

DyneStein /RiskAware-ActiveLearning

Risk-aware active learning for skin lesion classification: a dual-metric escalation policy that refers a case to a clinician when either model uncertainty or an independent malignancy-risk head crosses a calibrated threshold. 43% fewer unsafe auto-accepts in 12 of 12 configurations. Under peer review.