Open-Source Enterprise AI
Deep learning frameworks have significantly improved the development and deployment of medical imaging AI, helping researchers use computer vision to perform accurate early detection, medical classification, and advanced, automated 3D segmentation for medical imaging analysis. When these models are taken to the clinical environment, they can help clinicians streamline imaging workflows, uncover hidden insights, improve productivity, and connect multimodal patient information for deeper patient understanding.
Neurology
Neurology is the specialty within the medical field pertaining to nerves and the nervous system. Neurologists diagnose and treat diseases of the brain, spinal cord, peripheral nerves, muscles, autonomic nervous system, and blood vessels. Much of neurology is consultative, as neurologists treat patients suffering from strokes, Alzheimer’s disease, seizure disorders, and spinal cord disorders.
Neurology offers several subspecialties, including the following:
- Brain injury medicine
- Child neurology
- Clinical neurophysiology
- Endovascular surgical neuroradiology
- Hospice and palliative medicine
- Neurodevelopmental disabilities
- Neuromuscular medicine
- Pain medicine
- Sleep medicine
- Vascular neurology
(definition from here)
Research Papers & Articles
- Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks - Nature Medicine - 2020
- A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain - 2018
- High-precision automated reconstruction of neurons with flood-filling networks - 2018
- Machine learning in neurology: what neurologists can learn from machines and vice versa - 2018
- AI and Neuroscience: A virtuous circle
- Artificial Intelligence and Neurology - 2016
Open-source
- MNE: Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python
- nilearn: machine learning for neuroimaging in Python
- visbrain: brain data visualization in Python
Datasets
- Allen Brain Atlas
- BrainCloud
- The Human Connectome Project
- UCI - EEG Database Data Set
- MRI Lesion Segmentation in Multiple Sclerosis Database
- Multiple sclerosis lesion segmentation
- EEG Challenge Datasets on Kaggle
- American Epilepsy Society Seizure Prediction Challenge
- UPenn and Mayo Clinic's Seizure Detection Challenge
- Grasp-and-Lift EEG Detection
- Parkinsons Data Set
- Parkinsons Telemonitoring Data Set
- Parkinson Speech Dataset with Multiple Types of Sound Recordings Data Set
- Parkinson's Disease Classification Data Set
Radiology
Physicians specializing in diagnostic radiology are trained to diagnose illnesses in patients through the use of x-rays, radioactive substances, sound waves in ultrasounds, or the body’s natural magnetism in magnetic resonance images (MRIs).
They can also pursue a subspecialty in the following areas:
- Abdominal radiology
- Breast imaging
- Cardiothoracic radiology
- Cardiovascular radiology
- Chest radiology
- Emergency radiology
- Endovascular surgical neuroradiology
- Gastrointestinal radiology
- Genitourinary radiology
- Head and neck radiology
- Interventional radiology
- Musculoskeletal radiology
- Neuroradiology
- Nuclear radiology
- Pediatric radiology
- Radiation oncology
- Vascular and interventional radiology
(defintion from here)
Research Papers
- COVID-19 Classification of X-ray Images Using Deep Neural Networks
- Using reinforcement learning to personalize AI-accelerated MRI scans
- Deep Learning for Automated Recognition of Covid-19 from Chest X-ray Images
- DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction
- COVID-FACT: A Fully-Automated Capsule Network-based Framework for Identification of COVID-19 Cases from Chest CT scans
Open-source
- OpenREM - OpenREM is a free, open source application for patient radiation dose monitoring. The software is capable of importing and displaying data from a wide variety of x-ray dose related sources with filtering, charts and analysis. The software also enables easy export of the data in a form that is suitable for further analysis by suitably qualified medical physics personnel.
Datasets
Center for Invivo Microscopy (CIVM), Embrionic and Neonatal Mouse (H&E, MR) user guide
The Open Access Series of Imaging Studies (OASIS) - The Open Access Series of Imaging Studies (OASIS) is a project aimed at making neuroimaging data sets of the brain freely available to the scientific community. By compiling and freely distributing neuroimaging data sets, we hope to facilitate future discoveries in basic and clinical neuroscience.
The Mammographic Image Analysis Society (MIAS) mini-database
Mammography Image Databases 100 or more images of mammograms with ground truth
NLM HyperDoc Visible Human Project color, CAT and MRI image samples - over 30 images
ABIDE: The Autism Brain Imaging Data Exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Function MRI images for 539 individuals suffering from ASD and 573 typical controls. These 1112 datasets are composed of structural and resting state functional MRI data along with an extensive array of phenotypic information.
CT Colongraphy for Colon Cancer CT scan for diagnosing of colon cancer. Includes data for patients without polyps, 6-9mm polyps, and greater than 10 mm polyps.
INbreast - Database for Digital Mammography
Cardiovascular Health
Cardiology is a branch of medicine that deals with the disorders of the heart as well as some parts of the circulatory system. The field includes medical diagnosis and treatment of congenital heart defects, coronary artery disease, heart failure, valvular heart disease and electrophysiology. Physicians who specialize in this field of medicine are called cardiologists, a specialty of internal medicine. Pediatric cardiologists are pediatricians who specialize in cardiology. Physicians who specialize in cardiac surgery are called cardiothoracic surgeons or cardiac surgeons, a specialty of general surgery.
(definition from Wikipedia)
Research Papers & Articles
- Getting to the Heart of it: How Deep Learning is Transforming Cardiac Imaging - 2018
- Artificial Intelligence in Cardiology - 2018
- Cardiac imaging: working towards fully-automated machine analysis & interpretation - 2017
- A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre, 2020
Open-source
Datasets
- Cardiac MRI dataset
- Congenital Heart Disease (CHD)
- SPECT - Heart Dataset
- Stanford’s South African Heart Disease Dataset
- Sunnybrook Cardiac Data
- UCI - Heart Disease Dataset
- EchoNet-Dynamic - A Large New Cardiac Motion Video Data Resource for Medical Machine Learning, from Stanford. Overview:
- Multi-Ethnic Study of Atherosclerosis (MESA) - Multi-Ethnic Study of Atherosclerosis (MESA) is an NHLBI-sponsored 6-center collaborative longitudinal investigation of factors associated with the development of subclinical cardiovascular disease and the progression of subclinical to clinical cardiovascular disease in 6,814 black, white, Hispanic, and Chinese-American men and women initially ages 45-84 at baseline in 2000-2002.
- Heart Disease Data Set