ISIC 2018 - Skin Lesion Classification for Melanoma Detection

Yuval and nosound models and write-up for Kaggle's competition "SIIM-ISIC Melanoma Classification"

Testing the consistency of binary classification performance scores reported in papers

Fully automatic skin lesion segmentation using the Berkeley wavelet transform and UNet algorithm.

Matthews Correlation Coefficient Loss implementation for image segmentation.

Skin Lesion Detector using HAM10000 dataset with Chainer / ChainerCV

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

Fully supervised binary classification of skin lesions from dermatoscopic images using multi-color space moments/texture features and Support Vector Machines/Random Forests.

Skin lesion classification, using Keras and the ISIC 2020 dataset

Skin lesion segmentation using a new ensemble deep network model and an incremental learning approach

PyTorch model that uses triplet loss to find the image with most similar skin condition

Analysis of the dermoscopic image processing pipeline toward optimally segmenting skin lesion regions and classifying lesion types using adversarial and generative deep learning.

[CIBM'2021] Knowledge Distillation approach towards Melanoma Detection

Skin caner detection application with convolutional neural network utilizing skin lesion images

ISIC Archive API v2 download images by ISIC ID

A collection of publicly available skin lesion datasets

RECOD Titans @ SIIM-ISIC Melanoma Classification

Machine Learning 2 Course Project at RKMVERI, 2021. Published at The Imaging Science Journal (2023), Paper: https://www.tandfonline.com/doi/full/10.1080/13682199.2023.2174657

Code and experimental results for an ensemble deep learning study on the HAM10000 skin lesion dataset