The final project of "Applying AI to 3D Medical Imaging Data" from "AI for Healthcare" nanodegree - Udacity.

Overview

Quantifying Hippocampus Volume for Alzheimer's Progression

Background

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that results in impaired neuronal (brain cell) function and eventually, cell death. AD is the most common cause of dementia. Clinically, it is characterized by memory loss, inability to learn new material, loss of language function, and other manifestations.

For patients exhibiting early symptoms, quantifying disease progression over time can help direct therapy and disease management.

A radiological study via MRI exam is currently one of the most advanced methods to quantify the disease. In particular, the measurement of hippocampal volume has proven useful to diagnose and track progression in several brain disorders, most notably in AD. Studies have shown a reduced volume of the hippocampus in patients with AD.

The hippocampus is a critical structure of the human brain (and the brain of other vertebrates) that plays important roles in the consolidation of information from short-term memory to long-term memory. In other words, the hippocampus is thought to be responsible for memory and learning (that's why we are all here, after all!)

Hippocampus
Source: Life Science Databases (LSDB). Hippocampus. Images are from Anatomography maintained by Life Science Databases (LSDB). (2010). CC-BY-SA 2.1jp. Link

Humans have two hippocampi, one in each hemisphere of the brain. They are located in the medial temporal lobe of the brain. Fun fact - the word "hippocampus" is roughly translated from Greek as "horselike" because of the similarity to a seahorse observed by one of the first anatomists to illustrate the structure, but you can also see the comparison in the following image.

Seahorse & Hippocampus
Source: Seress, Laszlo. Laszlo Seress' preparation of a human hippocampus alongside a sea horse. (1980). CC-BY-SA 1.0. Link

According to Nobis et al., 2019, the volume of hippocampus varies in a population, depending on various parameters, within certain boundaries, and it is possible to identify a "normal" range taking into account age, sex and brain hemisphere.

You can see this in the image below where the right hippocampal volume of women across ages 52 - 71 is shown.

Nomogram - Female, Right Hippocampus Volume, Corrected for Head Size
Source: Nobis, L., Manohar, S.G., Smith, S.M., Alfaro-Almagro, F., Jenkinson, M., Mackay, C.E., Husain, M. Hippocampal volume across age: Nomograms derived from over 19,700 people in UK Biobank. Neuroimage: Clinical, 23(2019), pp. 2213-1582.

There is one problem with measuring the volume of the hippocampus using MRI scans, though - namely, the process tends to be quite tedious since every slice of the 3D volume needs to be analyzed, and the shape of the structure needs to be traced. The fact that the hippocampus has a non-uniform shape only makes it more challenging. Do you think you could spot the hippocampi in this axial slice below?

Axial slice of an MRI image of the brain

As you might have guessed by now, we are going to build a piece of AI software that could help clinicians perform this task faster and more consistently.

You have seen throughout the course that a large part of AI development effort is taken up by curating the dataset and proving clinical efficacy. In this project, we will focus on the technical aspects of building a segmentation model and integrating it into the clinician's workflow, leaving the dataset curation and model validation questions largely outside the scope of this project.

What You Will Build

In this project you will build an end-to-end AI system which features a machine learning algorithm that integrates into a clinical-grade viewer and automatically measures hippocampal volumes of new patients, as their studies are committed to the clinical imaging archive.

Fortunately you won't have to deal with full heads of patients. Our (fictional) radiology department runs a HippoCrop tool which cuts out a rectangular portion of a brain scan from every image series, making your job a bit easier, and our committed radiologists have collected and annotated a dataset of relevant volumes, and even converted them to NIFTI format!

You will use the dataset that contains the segmentations of the right hippocampus and you will use the U-Net architecture to build the segmentation model.

After that, you will proceed to integrate the model into a working clinical PACS such that it runs on every incoming study and produces a report with volume measurements.

The Dataset

We are using the "Hippocampus" dataset from the Medical Decathlon competition. This dataset is stored as a collection of NIFTI files, with one file per volume, and one file per corresponding segmentation mask. The original images here are T2 MRI scans of the full brain. As noted, in this dataset we are using cropped volumes where only the region around the hippocampus has been cut out. This makes the size of our dataset quite a bit smaller, our machine learning problem a bit simpler and allows us to have reasonable training times. You should not think of it as "toy" problem, though. Algorithms that crop rectangular regions of interest are quite common in medical imaging. Segmentation is still hard.

The Programming Environment

You will have two options for the environment to use throughout this project:

Udacity Workspaces

These are setup environments that contains all you need from the Local Environment section below that you can run directly on your web browser.

Local Environment

If you would like to run the project locally, you would need a Python 3.7+ environment with the following libraries for the first two sections of the project:

In the 3rd section of the project we will be working with three software products for emulating the clinical network. You would need to install and configure:

  • Orthanc server for PACS emulation
  • OHIF zero-footprint web viewer for viewing images. Note that if you deploy OHIF from its github repository, at the moment of writing the repo includes a yarn script (orthanc:up) where it downloads and runs the Orthanc server from a Docker container. If that works for you, you won't need to install Orthanc separately.
  • If you are using Orthanc (or other DICOMWeb server), you will need to configure OHIF to read data from your server. OHIF has instructions for this: https://docs.ohif.org/configuring/data-source.html
  • In order to fully emulate the Udacity workspace, you will also need to configure Orthanc for auto-routing of studies to automatically direct them to your AI algorithm. For this you will need to take the script that you can find at section3/src/deploy_scripts/route_dicoms.lua and install it to Orthanc as explained on this page: https://book.orthanc-server.com/users/lua.html
  • DCMTK tools for testing and emulating a modality. Note that if you are running a Linux distribution, you might be able to install dcmtk directly from the package manager (e.g. apt-get install dcmtk in Ubuntu)

You can look at the rubric for this project here. Let's get started!

Owner
Omar Laham
Bioinformatician and Healthcare AI Engineer
Omar Laham
Easy to use and customizable SOTA Semantic Segmentation models with abundant datasets in PyTorch

Semantic Segmentation Easy to use and customizable SOTA Semantic Segmentation models with abundant datasets in PyTorch Features Applicable to followin

sithu3 530 Jan 05, 2023
This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).

TransFG: A Transformer Architecture for Fine-grained Recognition Official PyTorch code for the paper: TransFG: A Transformer Architecture for Fine-gra

Ju He 307 Jan 03, 2023
The repository is for safe reinforcement learning baselines.

Safe-Reinforcement-Learning-Baseline The repository is for Safe Reinforcement Learning (RL) research, in which we investigate various safe RL baseline

172 Dec 19, 2022
Sign-to-Speech for Sign Language Understanding: A case study of Nigerian Sign Language

Sign-to-Speech for Sign Language Understanding: A case study of Nigerian Sign Language This repository contains the code, model, and deployment config

16 Oct 23, 2022
PyTorch implementation of MulMON

MulMON This repository contains a PyTorch implementation of the paper: Learning Object-Centric Representations of Multi-object Scenes from Multiple Vi

NanboLi 16 Nov 03, 2022
PyTorch implementation of Super SloMo by Jiang et al.

Super-SloMo PyTorch implementation of "Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation" by Jiang H., Sun

Avinash Paliwal 2.9k Jan 03, 2023
An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

CPC_audio This code implements the Contrast Predictive Coding algorithm on audio data, as described in the paper Unsupervised Pretraining Transfers we

8 Nov 14, 2022
DeepStochlog Package For Python

DeepStochLog Installation Installing SWI Prolog DeepStochLog requires SWI Prolog to run. Run the following commands to install: sudo apt-add-repositor

KU Leuven Machine Learning Research Group 17 Dec 23, 2022
Filtering variational quantum algorithms for combinatorial optimization

Current gate-based quantum computers have the potential to provide a computational advantage if algorithms use quantum hardware efficiently.

1 Feb 09, 2022
Graph Convolutional Networks for Temporal Action Localization (ICCV2019)

Graph Convolutional Networks for Temporal Action Localization This repo holds the codes and models for the PGCN framework presented on ICCV 2019 Graph

Runhao Zeng 318 Dec 06, 2022
A cross-document event and entity coreference resolution system, trained and evaluated on the ECB+ corpus.

A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution. Introduction This repo contains experimental code derived from

2 May 09, 2022
More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval

More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval, CVPR 2021. Ayan Kumar Bhunia, Pinaki nath Chowdh

Ayan Kumar Bhunia 22 Aug 27, 2022
Privacy as Code for DSAR Orchestration: Privacy Request automation to fulfill GDPR, CCPA, and LGPD data subject requests.

Meet Fidesops: Privacy as Code for DSAR Orchestration A part of the greater Fides ecosystem. โšก Overview Fidesops (fee-dez-รคps, combination of the Lati

Ethyca 44 Dec 06, 2022
A Fast and Stable GAN for Small and High Resolution Imagesets - pytorch

A Fast and Stable GAN for Small and High Resolution Imagesets - pytorch The official pytorch implementation of the paper "Towards Faster and Stabilize

Bingchen Liu 455 Jan 08, 2023
Very large and sparse networks appear often in the wild and present unique algorithmic opportunities and challenges for the practitioner

Sparse network learning with snlpy Very large and sparse networks appear often in the wild and present unique algorithmic opportunities and challenges

Andrew Stolman 1 Apr 30, 2021
Semantic Segmentation in Pytorch

PyTorch Semantic Segmentation Introduction This repository is a PyTorch implementation for semantic segmentation / scene parsing. The code is easy to

Hengshuang Zhao 1.2k Jan 01, 2023
a minimal terminal with python ๐Ÿ˜Ž๐Ÿ˜‰

Meterm a terminal with python ๐Ÿ˜Ž How to use Clone Project: $ git clone https://github.com/motahharm/meterm.git Run: in Terminal: meterm.exe Or pip ins

Motahhar.Mokfi 5 Jan 28, 2022
Multimodal Descriptions of Social Concepts: Automatic Modeling and Detection of (Highly Abstract) Social Concepts evoked by Art Images

MUSCO - Multimodal Descriptions of Social Concepts Automatic Modeling of (Highly Abstract) Social Concepts evoked by Art Images This project aims to i

0 Aug 22, 2021
FluidNet re-written with ATen tensor lib

fluidnet_cxx: Accelerating Fluid Simulation with Convolutional Neural Networks. A PyTorch/ATen Implementation. This repository is based on the paper,

JoliBrain 50 Jun 07, 2022
Matlab Python Heuristic Battery Opt - SMOP conversion and manual conversion

SMOP is Small Matlab and Octave to Python compiler. SMOP translates matlab to py

Tom Xu 1 Jan 12, 2022