[MICCAI 2023] DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation

FixCaps: An Improved Capsules Network for Diagnosis of Skin Cancer，DOI: 10.1109/ACCESS.2022.3181225

[ICML 2023] Official repository of paper: Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat

The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions.

This repo includes classifier trained to distinct 7 type of skin lesions

PyTorch code to reproduce the key experiments and results presented in the paper: ELMAGIC: Energy-Efficient Lean Model for Reliable Medical Image Generation and Classification Using Forward Forward Algorithm.

Multiclass skin cancer detection using explainable AI for checking the models' robustness

Data quality analysis of DermaMNIST (MedMNIST), HAM10000, and Fitzpatrick17k datasets

Cross-platform smartphone app capable of detecting skin cancer lesions using Computer Vision.

This is a project that I worked on with my colleagues in the 6th Semester of my B.tech. In this project, we present a fully automatic method for skin lesion segmentation by leveraging UNet and FCN that is trained end to-end. For Skin lesion disease classification, we use a customized convolutional neural net. Designing a novel loss function base…

HAM10000 image dataset classification using Pytorch and Scikit Learn

Notebooks of pre trained models using the HAM10000 dataset

Convolutional neural network capable of identifying skin lesions (based on the skin lesion image data set HAM10000).

[MICCAI 2025] CENet: Context Enhancement Network for Medical Image Segmentation

This repository contains a deep learning model for skin cancer classification using the InceptionV3 architecture. The model was trained on the HAM10000 dataset and is designed with computational efficiency in mind. It was developed to be able to run on a CPU.

This project uses TensorFlow to implement a Convolutional Neural Network (CNN) for image classification. The goal is to classify skin lesion images into different categories. The dataset used is HAM10000, which contains skin lesion images with associated metadata. The actual accuracy of the model is 90%. 🚀🚀

Discover DermaScan: A full-stack web app with MobileNetV2-based skin lesion classifier using Harvard's Ham10000 Dataset for precise dermatological diagnosis.

Terminal application to perform skin lesion segmentation & classification

Website for Skin cancer detection based on HAM10000 | Dropbox Integration

This project is designed for classifying various skin diseases using the HAM10000 dataset. It leverages a trained model, explains predictions using LIME, and provides multiple interfaces for users, including a server, a graphical user interface, a command-line interface, and an API.