Table 2.

A summary of work done on CAD diagnosis

Article	Study objective	Results	Study conclusion	Contributor
Review article	(i) Adoption and implementation of CAD during breast cancer screening	(i) There is a trade off between the facilitators and barriers for CAD use	(i) The cost-effectiveness of CAD has not been well established for breast cancer screening in various populations	Masud et al., 2019 [15]
	(ii) to describe barriers and facilitators for CAD use	(ii) Facilitators for CAD use improved breast cancer detection rates, increased profitability of breast imaging, and time saved by replacing double reading	(ii) Research is needed on how to best facilitate CAD in radiology practices in order to optimize patient outcomes, and the views of radiologists
Original research	(i) To evaluate the diagnostic performance of the CAD system in full-field digital MM for detecting breast cancer when used by dedicated breast radiologist (BR) and radiology resident (RR)	(i) Sensitivity improved with CAD use in the BR and RR groups (from 81.10 to 84.29% for BR and 75.38 to 77.95% for RR)	(i) CAD was helpful for dedicated BRs to improve their diagnostic performance and for RRs to improve the sensitivity in a screening setting	Jung et al., 2014 [19]
	(ii) To investigate the benefit of CAD application		(ii) CAD could be essential for radiologists by decreasing reading time without decreasing diagnostic performance
Original research	(i) To evaluate a commercial tomosynthesis cCAD system in an independent, multicenter dataset	(i) Use of the CAD system showed per-lesion sensitivity of 89% (99 of 111; 95% confidence interval	(i) A digital breast tomosynthesis CAD system can allow detection of a large percentage of breast cancers manifesting as masses and microcalcification clusters, with an acceptable false-positive rate	Meyer-Base et al. 2021 [44]
		(ii) 62 of 72 lesions detected were masses	(ii) Further studies with larger datasets acquired with equipment from multi-parametric imaging and breast cancer radiomics
		(iii) Overall, 37 of 39 microcalcification clusters (95% sensitivity, 95% confidence interval: 81%, 99%) and 79 of 89 masses (89% sensitivity, 95% confidence interval: 80%, 94%) were detected with the CAD system
Original research	(i) To evaluate the value of the CAD program applied to diagnostic breast ultrasonography (US) based on operator experience	(i) Out of 100 breast masses, 41 (41%) were malignant and 59 (59%) were benign	(i) CAD is a useful additional diagnostic tool for breast US in all radiologists, with benefits differing depending on the radiologist’s level of experience	Park et al., 2019 [55]
		(ii) compared with the experienced radiologists, the less experienced radiologists had significantly improved negative predictive value (86.7–94.7% vs 53.3–76.2%, respectively)	(ii) CAD improved the inter-observer agreement and showed acceptable agreement in the characterization of breast masses
		(iii) experienced radiologists had significantly improved specificity (52.5 and 54.2% vs 66.1 and 66.1%) and positive predictive value (55.6 and 58.5% vs 64.9 and 64.9%, respectively) with CAD assistance (all P < 0.05)
Original research	To develop a breast CADx methodology that addresses the efficiency of pre-trained convolutional neural networks (CNNs) and using preexisting handcrafted CADx features	(i) From ROC analysis, the fusion-based method demonstrates, imaging modalities with statistical significant improvements	(i) A novel breast CADx methodology that can be used to more effectively characterize breast lesions in comparison to existing methods	Antropova et al., 2017 [56]
		(ii) AUC compared to previous breast cancer CADx methods in the task showed distinguishing result between malignant and benign lesions
Original research	To analyze the cost-effectiveness of adding computer-aided detection (CAD) to a screening MM program	(i) Cost-effectiveness was expressed as the marginal cost per year of life saved (MCYLS)	(i) The cost-effectiveness of CAD is dependent on the magnitude of the increase in cancer detection rates with CAD	Lindfors et al., 2006 [57]
		(ii) CAD to a mammographic screening program resulted in a MCYLS of $19,058 and yields a linear increase in MCYLS	(ii) It is also affected by the stage distribution of cancers diagnosed with CAD
			(iii) MCYLS is greater for CAD added to screening versus screening MM alone but is within the accepted cost-effective range
Original research	(i) To investigate the efficacy of CAD for MRI in tumor extent, lymph node status, and multifocality breast cancers	(i) MRI with CAD had the highest area under the receiver operating characteristic curve (AUC  =  0.888)	(i) CAD for breast MRI can be a feasible method of evaluating tumor extent and multifocality in invasive breast cancer patients	Song et al., 2015 [58]
	(ii) To compare CAD detection for MRI with other breast-imaging modalities