RECOD Titans participation at the ISBI 2017 challenge - Part 3

The official command line tool for interacting with the ISIC Archive.

Attention Deeplabv3+: Multi-level Context Attention Mechanism for Skin Lesion Segmentation

U-Net-based Models for Skin Lesion Segmentation: More Attention and Augmentation

Instructions for the removal of duplicate image files from within individual ISIC datasets and across all ISIC datasets.

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

Official implementation of "Deeply Supervised Skin Lesions Diagnosis with Stage and Branch Attention"

Skin lesion classification, using Keras and the ISIC 2020 dataset

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

Source code and experiments for the paper: "Dark Corner on Skin Lesion Image Dataset: Does it matter?"

ISIC Challenge submission platform.

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

Melanoma Segmentation and Classification Package involving training evaluating and comparing with already trained models

ISIC Challenge - Lesion Segmentation task solved using the U-Net model building from scratch

My machine learning notebooks. Feel free to use for your purposes.

RECOD Titans @ SIIM-ISIC Melanoma Classification

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

Skin Lesion Classifier using the ISIC 2018 Task 3 Dataset.

ISIC2019 skin lesion classification (binary & multi-class) as well as segmentation pipelines using VGG16_BN and visual attention blocks. The project features improving the results found in the literature by implementing an ensemble architecture. This project was developed for "Computer Aided Diagnosis - CAD" course for MAIA masters program.