CT-Based-COVID-19-Diagnose-by-Image-Processing-and-Deep-Learning

This project proposed the deep learning and image processing method to undertake the diagnosis on 2D CT image and 3D CT volume. The first proposed deep learning method applied 3D-UNet model to undertake the segmentation of the lung area from the raw 3D CT volume, and the image processing method can also do this part. And the second deep learning method offers the 3D CNN model to classify the COVID-19 cases normal CT volume followed by another 3D CNN model to classify the COVID-19 cases into three categories according to the infectious area. Then, the last 3D U-Net model could segment the infectious area from the confirmed cases and the slice with largest infectious area would be selected. Finally, the diagnosis report will be generated based on the previous output. The similar operation can be conducted on the 2D CT image.

CT Based COVID 19 Diagnose by Image Processing and Deep Learning

Related tags

Overview

CT-Based-COVID-19-Diagnose-by-Image-Processing-and-Deep-Learning

This is my undergraduate honour project in Hong Kong Baptist University, and thanks to my supervisor Prof. CHU Xiaowen

Project Poster

System Architecture

Diagnose Result

Owner

Deep Networks with Recurrent Layer Aggregation

PyTorch Implementation of Temporal Output Discrepancy for Active Learning, ICCV 2021

HyperPose is a library for building high-performance custom pose estimation applications.

3D-Transformer: Molecular Representation with Transformer in 3D Space

Official PyTorch Implementation of Rank & Sort Loss [ICCV2021]

rliable is an open-source Python library for reliable evaluation, even with a handful of runs, on reinforcement learning and machine learnings benchmarks.

PyTorch implementation for Partially View-aligned Representation Learning with Noise-robust Contrastive Loss (CVPR 2021)

Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification

Code for "Modeling Indirect Illumination for Inverse Rendering", CVPR 2022

City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones Code

Awesome Graph Classification - A collection of important graph embedding, classification and representation learning papers with implementations.

PyTorch implementation of "LayoutTransformer: Layout Generation and Completion with Self-attention"

Project to create an open-source 6 DoF input device

Gym Threat Defense

magiCARP: Contrastive Authoring+Reviewing Pretraining

Block-wisely Supervised Neural Architecture Search with Knowledge Distillation (CVPR 2020)

This is the unofficial code of Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data

A library for optimization on Riemannian manifolds

Denoising Normalizing Flow

This repo contains the code for the paper "Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging" that has been accepted to NeurIPS 2021.