Laboratory for Imagery, Vision and Artificial Intelligence

boundary-loss

Official code for "Boundary loss for highly unbalanced segmentation", runner-up for best paper award at MIDL 2019. Extended version in MedIA, volume 67, January 2021.

miccai_weakly_supervised_tutorial

Code for tutorial at MICCAI 2022

SizeLoss_WSS

Code of our MIDL 2018 paper and MedIA extension: https://arxiv.org/abs/1805.04628

MedicalImageSegmentation

This repository aims at containing all the code employed at LIVIA to segment medical images. Mainly, our research focuses on bringind the expertise in deep learning and optimization techniques to the medical image analysis domain.

boxes_tightness_prior

Oral presentation at MIDL 2020 - Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision

semi_curriculum

Code for our arxiv preprint: https://arxiv.org/abs/1904.05236

miccai_2020-weakly_supervised_tutorial

Material of the MICCAI 2020 tutorial on weakly supervised learning for semantic segmentation. The updated tutorial (2021 and onwards) is available there: https://github.com/LIVIAETS/miccai_weakly_supervised_tutorial

MT-MTDA

extended_logbarrier

Code for our arxiv preprint: https://arxiv.org/abs/1904.04205

KD_UDA

TransUNet

This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.