Table 3.

CV applications in healthcare.

Areas	Citations	Image Type	Deep Model	Application
Medical imaging and diagnosis	[98,99,100,101,102,103]	CT, F-FDG PET/CT, Chest X-rays	Mask-RCNN, CNN, Transformer, SVM, random forest, k-nearest neighbor	Lung cancer, tuberculosis
	[104,105,106]	Iris, cellular retinal, fundus	Binarytree, Random Forest, SVM, neural network, CNN	Changes in vision related to diabetes
	[107,108,109]	HD microscope	Vision transformer, CNN	Cervical cancer
	[97,110,111,112,113,114,115,116,117,118,119]	Mammogram, whole slide images, hematoxylin, eosin	YOLO, CNN, random forest, SVM, decision tree, Naïve Bayes, Logistic linear classifier, Linear discriminant classifier, Fischer’s Linear Discriminant analysis, k-nearest neighbor, Autoencoders	Breast cancer, data augmentation
	[120,121,122,123]	Dermoscopic image	CNN, Gated recurrent unit	Skin cancer detection/segmentation
	[124,125,126,127]	Endoscopic images, hematoxylin & eosin, whole-slide images	CNN, transformer, U-net	Colorectal, gastrointestinal cancer
	[128,129,130,131,132,133]	Chest X-rays	CNN, transformer, logistic regression	COVID-19 diagnosis Age estimation in unidentified patients
	[134]	Whole slide images	Vision transformer	Subtyping of papillary renal cell carcinoma
	[25,29,30,98,127,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151]	MRI, Histogram, CT, X-ray, ultrasound, PET	CNN, Naïve Bayes, Random Forest, Neural Networks, SVM, k-nearest neighbor, Decision Tree, logistic function, Naive Bayes, Fuzzy k-means	Cancers (brain, bladder, breast, liver, lung, pancreas, prostate, other), CT reconstruction, Alzheimer’s Disese, intracranial hemorrhage
	[152,153,154,155]	Dual energy X-Ray absorptiometry (DEXA) X-ray	SVM YOLOv8.0, Detectron2, several others (see systematic review)	Lumbar spine fractures Pediatric fractures Overall fracture identification
Delirium	[156]	Surveillance images	CNN, k-nearest neighbors	Delirium monitoring
Pain, Agitation, Stress, Level of sedation	[157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180]	Surveillance images, depth image, face images, pain datasets	YOLO, Mask-RCNN, CNN, CDBN, SVM, LSTM, LMM, Neural Network	Activity recognition, detection of pain and discomfort, stress, automated facial analysis for grimacing, agitation, eye localization, depression, anxiety, stress levels, AU
Patient deterioration	[181,182]	Color videos	Logistic/linear Regression	Deterioration prediction using AUs
Mechanical ventilation	[183,184,185]	Chest X-rays, ICU videos	U-net, YOLO, TL, Feature descriptor	Need for mechanical ventilation, detect and recognize ventilation objects and positioning, estimate lung volume
Mobility	[186,187]	ICU video images	CNN, YOLOv2	Patient mobilization activities in ICU, NIMS
Patient safety	[188,189,190,191,192,193,194,195]	Surgical videos, depth images, video recordings	OpenPose, Yolo, CNN, Mask-RCNN	Surgical team behavioral analysis, patient mobilization activities, hand hygiene, ICU staff monitoring, assessing situational awareness
Surgical assistance	[194,196,197,198,199]	Surgical activity images, OR videos	CNN	Robot-assisted surgery, situational awareness in OR
Neurological, neurodevelopmental, psychiatric disorders	[142,162,174,178,200,201,202,203,204,205,206,207,208,209],	Whole-body video recording, MRI, PET, patient images	Detectron2, OpenPose, CNN, k-nearest neighbor, SVM, K-SVD, Bayesian Networks	Analysis of gain synchrony, balance, Infant neuromotor risk, neurodegenerative disease, behavioral analysis in ASD and ADHD, facial expression in depression, facial weakness
Remote monitoring, telemedicine	[210,211]	Surveillance images	Deep reinforcement learning, CNN	In-home elbow rehabilitation
Data security and privacy	[114,212,213,214]	X-rays, MRI	CNN, Fuzzy CNN	Privacy protections for deep learning algorithms containing medical data
Fall detection	[215,216,217,218,219]	Surveillance images	Gaussian Mixture Model, CNN Segmentation, AlphaPose, OpenPose, LSTM	Human fall detection
Hospital scene recognition	[192,220,221,222,223,224,225,226]	Indoor images of ICU, hospital, nursing home; pediatric ICU videos	YOLO, CNN, SVM, CATS	ICU and hospital indoor object detection, hand hygiene, ICU activity measurement

Table 3 describes the varying uses of CV technology in healthcare and outlines the image captures, machine learning models used, and the focus area. This is not an exhaustive list. Abbreviations: AU: action unit; ASD: autism spectrum disorder; CATS: Clinical Activity Tracking System; CNN: Convolutional Neural Network; NIMS: Non-Invasive Mobility Sensor; OR: operating room.