Hierarchical probabilistic 3D U-Net, with attention mechanisms (—𝘈𝘵𝘵𝘦𝘯𝘵𝘪𝘰𝘯 𝘜-𝘕𝘦𝘵, 𝘚𝘌𝘙𝘦𝘴𝘕𝘦𝘵) and a nested decoder structure with deep supervision (—𝘜𝘕𝘦𝘵++). Built in TensorFlow 2.5. Configured for voxel-level clinically significant prostate cancer detection in multi-channel 3D bpMRI scans.
Decoder architecture based on the UNet++. Combining residual bottlenecks with depthwise convolutions and attention mechanisms, it outperforms the UNet++ in a coronary artery segmentation task, while being significantly more computationally efficient.
This repository contains the image classification followed by semantic segmentation of Chest X-Rays to detect a clinical condition called Pneumothorax.
The repository contains the reproduction of UNetPluPlus, introduced by Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang; upon the dataset obtained from the KITS19 Kidney Tumor Segmentation Challenge.
Brain tumor segmentation using UNet++ Architecture . Implementation of the paper titled - UNet++: A Nested U-Net Architecture for Medical Image Segmentation @ https://arxiv.org/abs/1807.10165
