Source code for the MICCAI 2016 Paper "Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworks and 3D Conditional Random Fields"
Code for MICCAI 2016 paper : Automatic liver and lesions segmentation using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields
PyTorch implementation of MICCAI 2018 paper "Liver Lesion Detection from Weakly-labeled Multi-phase CT Volumes with a Grouped Single Shot MultiBox Detector"
Liver cancer is one of the most dangerous diseases and is one of causes leading of death. The application of science and technology in the diagnosis and identification of cancerous tissues of the liver plays a very important role. This assists the doctor in planning and treating the patient. In this paper, we study the application of convolutional neural networks (CNN) in the determination of cancerous tissues of the human liver. The training are performed on a 3D CT image dataset of the body segment containing the liver. We then run the results into a train model, on which experiments are performed with different test samples.
This is the Solution for the competition https://dphi.tech/challenges/sds-bit-mesra-ml-contest-on-liver-disease-prediction/192/leaderboard/private/ where our team Dataminers was able to achieve 21st position outs in private lea of 120 teamderboard, We explored a lot of imputational and interpolation methods for the mising data and built the whole pipeline in PyTorch. Our task was to predict the Stage of the patient according to their medical reports.
