Deep learning-enabled medical computer vision (2021-01-08T00:00:00.000000Z)

TL;DR

Recent progress in the development of modern computer vision techniques—powered by deep learning—for medical applications, focusing on medical imaging, medical video, and clinical deployment is surveyed.

Abstract

A decade of unprecedented progress in artificial intelligence (AI) has demonstrated the potential for many fields—including medicine—to benefit from the insights that AI techniques can extract from data. Here we survey recent progress in the development of modern computer vision techniques—powered by deep learning—for medical applications, focusing on medical imaging, medical video, and clinical deployment. We start by briefly summarizing a decade of progress in convolutional neural networks, including the vision tasks they enable, in the context of healthcare. Next, we discuss several example medical imaging applications that stand to benefit—including cardiology, pathology, dermatology, ophthalmology–and propose new avenues for continued work. We then expand into general medical video, highlighting ways in which clinical workflows can integrate computer vision to enhance care. Finally, we discuss the challenges and hurdles required for real-world clinical deployment of these technologies.

Authors

Yun Liu

5 papers

J. Dean

3 papers

E. Topol

3 papers

TL;DR

Abstract

Authors

References171 items

Current applications and future impact of machine learning in emerging contaminants: A review

The Convergence of Human and Artificial Intelligence on Clinical Care - Part I

CT super-resolution using multiple dense residual block based GAN

Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension

Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension

Automatic detection of hand hygiene using computer vision technology

A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations.

Predicting conversion to wet age-related macular degeneration using deep learning

Deep learned tissue “fingerprints” classify breast cancers by ER/PR/Her2 status from H&E images

Expert Discussions Improve Comprehension of Difficult Cases in Medical Image Assessment

A Human-Centered Evaluation of a Deep Learning System Deployed in Clinics for the Detection of Diabetic Retinopathy

A mountable toilet system for personalized health monitoring via the analysis of excreta

COVID-19 and telemedicine: Immediate action required for maintaining healthcare providers well-being

Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF

3D Deep Learning on Medical Images: A Review

Artificial Intelligence in Dermatology: A Primer.

Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection

Video-based AI for beat-to-beat assessment of cardiac function

The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database

Evaluation of Deep Learning Models for Identifying Surgical Actions and Measuring Performance

Ethical and Legal Aspects of Ambient Intelligence in Hospitals.

Artificial intelligence in gastrointestinal endoscopy: general overview

International evaluation of an AI system for breast cancer screening

Deep neural network models for computational histopathology: A survey

Deep learning-based survival prediction for multiple cancer types using histopathology images

Reinventing the eye exam

MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports

Building an Otoscopic screening prototype tool using deep learning

Can skin cancer diagnosis be transformed by AI?

Remote Tool-Based Adjudication for Grading Diabetic Retinopathy

Using artificial intelligence on dermatology conditions in Uganda: a case for diversity in training data sets for machine learning

Dissecting racial bias in an algorithm used to manage the health of populations

Deep learning-based classification of mesothelioma improves prediction of patient outcome

A deep learning system for differential diagnosis of skin diseases

An augmented reality microscope with real-time artificial intelligence integration for cancer diagnosis

Artificial intelligence in digital pathology — new tools for diagnosis and precision oncology

Implementation of a cloud-based referral platform in ophthalmology: making telemedicine services a reality in eye care

Machine learning approach of automatic identification and counting of blood cells

Clinical-grade computational pathology using weakly supervised deep learning on whole slide images

Artificial Intelligence and Human Trust in Healthcare: Focus on Clinicians

Deep learning interpretation of echocardiograms

Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India.

Analyzing the role of model uncertainty for electronic health records

Intelligent ICU for Autonomous Patient Monitoring Using Pervasive Sensing and Deep Learning

Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task.

The present and future of deep learning in radiology.

Detecting Anemia from Retinal Fundus Images

Deep learning versus human graders for classifying diabetic retinopathy severity in a nationwide screening program

A computer vision system for deep learning-based detection of patient mobilization activities in the ICU

Automated Abdominal Segmentation of CT Scans for Body Composition Analysis Using Deep Learning.

A Survey of Crowdsourcing in Medical Image Analysis

A contemporary review of machine learning in otolaryngology–head and neck surgery

CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison

High-performance medicine: the convergence of human and artificial intelligence

A guide to deep learning in healthcare

Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study

Artificial intelligence and deep learning in ophthalmology

Predicting optical coherence tomography-derived diabetic macular edema grades from fundus photographs using deep learning

Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease

Fully Automated Echocardiogram Interpretation in Clinical Practice

nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation

Learning to Describe Scenes with Programs

Multimodal skin lesion classification using deep learning

Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning

Detection of Longitudinal Visual Field Progression in Glaucoma Using Machine Learning.

Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices

With an eye to AI and autonomous diagnosis

Clinically applicable deep learning for diagnosis and referral in retinal disease

Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists

Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs.

Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks

Current Applications and Future Impact of Machine Learning in Radiology.

AutoAugment: Learning Augmentation Policies from Data

DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks

Mapping of Crowdsourcing in Health: Systematic Review

Hookworm Detection in Wireless Capsule Endoscopy Images With Deep Learning