Table 1.

Examples of studies utilizing various types of AI architectures for data acquisition/preprocessing and predictive model development.

Topic	Author/year (reference)	Title	Aim of AI use	AI architecture(s)
AI for data acquisition and preprocessing	Ungan et al. (2022)28	Metastatic melanoma treated by immunotherapy: discovering prognostic markers from radiomics analysis of pretreatment CT with feature selection and classification	Feature selection and classification	SVM, Boruta, RF, LR, k-NN
	Zhao et al. (2021)18	Lung segmentation and automatic detection of COVID-19 using radiomic features from chest CT images	Segmentation	V-Net
	Xu et al. (2024)14	Synthesis of virtual monoenergetic images from kilovoltage peak images using wavelet loss enhanced CycleGAN for improving radiomics features reproducibility	Image generation	GAN
	Gitto et al. (2024)35	X-rays radiomics-based ML classification of atypical cartilaginous tumour and high-grade chondrosarcoma of long bones	Class imbalance correction	ADASYN
	Rich et al. (2021)34	Radiomics Predicts for Distant Metastasis in Locally Advanced Human Papillomavirus-Positive Oropharyngeal Squamous Cell Carcinoma	Class imbalance correction	synthetic minority over-sampling technique (SMOTE), ADASYN, and borderline SMOTE
	Ziegelmayer et al. (2020)40	Deep Convolutional Neural Network-Assisted Feature Extraction for Diagnostic Discrimination and Feature Visualization in Pancreatic Ductal Adenocarcinoma (PDAC) versus Autoimmune Pancreatitis (AIP)	Deep radiomics extraction	CNN, RF
AI for radiomics model development	Lee et al. (2022)59	Radiomic ML for predicting prognostic biomarkers and molecular subtypes of breast cancer using tumour heterogeneity and angiogenesis properties on MRI	Classification	naïve Bayes, linear regression, ANN, Decision Tree, RF
	Zhou et al. (2024)50	CT-Based Radiomics Analysis of Different ML Models for Discriminating the Risk Stratification of Pheochromocytoma and Paraganglioma: A Multicenter Study	Risk stratification (classification)	MLPs, SVM, RFs, k-NN
	Currie et al. (2019)79	Intelligent Imaging: Radiomics and ANN in Heart Failure	Risk stratification (classification)	ANN
	Klontzas et al. (2021)56	Radiomics and ML Can Differentiate Transient Osteoporosis from Avascular Necrosis of the Hip	Classification	XGboost, CatBoost and SVM
	Sakai et al. (2020)66	MRI Radiomic Features to Predict IDH1 Mutation Status in Gliomas: A Machine Learning Approach using Gradient Tree Boosting	Classification	XGBoost
	Chiari-Correia et al. (2023)78	A 3D Radiomics-Based ANN Model for Benign Versus Malignant Vertebral Compression Fracture Classification in MRI	Classification	MLP neural network with a back-propagation algorithm
	Sushentsev et al. (2023)84	Time series radiomics for the prediction of prostate cancer progression in patients on active surveillance	Classification using time series data	LSTM RNN
	Usuzaki et al. (2024)89	Identifying key factors for predicting O6-Methylguanine-DNA methyltransferase status in adult patients with diffuse glioma: a multimodal analysis of demographics, radiomics, and MRI by variable Vision Transformer	Classification using multimodal data	Vision transformer (vViT)