Source code for the paper 'Data Augmentation for Skin Lesion Analysis' — 🏆 Best Paper Award at the ISIC Skin Image Analysis Workshop @ MICCAI 2018

Implementation for MICCAI DART paper: 'Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification'

Experiments of the DAI in Healthcare project - skin lesions images use case - using Flower

This repository contains experiments using different XAI methods and ISIC2020 dataset.

This repository deals with generating 'malign' synthetic samples from 'benign' samples using CycleGAN to mitigate class imbalance and detecting Melanoma using a new balanced skin lesion image dataset.

Implementation for ICML 2022 paper: 'Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification'

Official code for our paper - "Melanoma classification from dermatoscopy images using knowledge distillation for highly imbalanced data".

Classification of malignt or benignt melanoma using the ISIC 2020 Challenge Dataset.

Melanoma classification using computer vision techniques on SIM-ISIC 2020 dataset

This is a final-year project backend primarily focused on image classification for melanoma skin cancer. I have implemented a Convolutional Neural Network (CNN) AI model for this purpose.

Melanoma Detection Tool : Website

Melanoma Detection Tool : REST APIs

The project consist in a binary classification for melanoma detection. Reference was made to the Challenge proposed the International Skin Imaging Collaboration in 2016, and in particular Task 3 (Lesion Classification), using its datasets and testing the model through the same metrics.

Ai powered web app that can analyze a picture of a skin lesion and instantly classify it into one of 7 types - including cancerous lesions like melanoma.

This repository uses Deep Learning methods to develop a neural network that can effectively detect Melanoma.

Melanoma Skin Cancer Diagnosis based on Dermoscopic Features and DNA Mutations

This project focuses on the VisioMel Challenge whose goal is predicting melanoma relapse. Recent advancements in SSL and WSL offer promising new solutions for improving the accuracy of cancer relapse detection.