Table 3 State of the art AI—based models for cancer diagnosis by radiology images analysis
Refs. | Approach | Modality | Brief Description |
|---|---|---|---|
Ejaz et al. (2021) | Unsupervised learning | Echo | Identified diastolic dysfunction patients' left atrial and ventricular strain clusters |
Iftikhar et al. (2017b) | Supervised learning | Echocardiography Imaging | Complications were predicted using clinical and echocardiographic factors |
Ragab et al. (2022b) | Support Vector Machine (SVM) | SPECT | Using a support vector machine technique, improved SPECT to identify coronary artery disease |
Ece et al. (2022) | Deep learning | CT | Analyzed the performance of automated and manual assessments of the architecture and functions of the left and right sides of the heart |
Zabihollahy et al. (2018) | Machine learning | MRI | RVR reconstruction using echocardiography and cardiac MRI was more accurate than straight cardiac MRI |
Bustin et al. (2020) | Deep learning | MRI | Evaluated ventricular contours with hand tracing |
Dhasarathan et al. (2023) | Deep learning | X-ray | Simple CapsNet |