CAD: How it works, how to use it, performance

Abstract

a b s t r a c tComputer-aided diagnosis (CAD) systems are software algorithms designed to assist radiologists (or other practitioners) in solving a diagnostic problem by using a visual prompt (or "CAD mark") to direct the observer towards potential pathology. CT colonography is a recent arrival to CAD, but could represent one of its most fruitful applications in the future. In contrast to other organs, where a variety of different pathologies are equally represented, significant colorectal pathologies other than polyps and cancer are relatively uncommon. As we shall see, this simplifies the diagnostic task for artificial intelligence developers and also for radiologists who, ultimately, must make the final decision.This review aims to present the current state-of-the-art for CAD applied to CT colonography. A brief overview of the technical essentials and of the diagnostic performance of CAD in isolation, is followed by an explanation of how CAD is used in day-to-day practice. The last section will deal with the most controversial issues affecting CAD performance in clinical practice, with a focus on the interaction between human and artificial intelligence.

Teleradiology based CT colonography to screen a population group of a remote island; at average risk for colorectal cancer

“…We believe that 3D interpretation is crucial to obtain good results, although there is no clear scientific evidence for this. Furthermore, according to literature, CAD could also have a positive influence on the results of CTC [20].…”

Autoflight in Ultrasonography:Practice Corner

“…However, high price tags and inconsistent performance have limited the implementation and use of CAD systems (5-7). Of particular concern is the low positive predictive value of CAD marks, which can lead to needless additional tests and procedures (5).…”

A comparison of material decomposition techniques for dual-energy CT colonography

“…Further, CTC with the combination of computer-aided diagnosis (CAD) [6] may help detect small polyps [7], which are otherwise difficult to detect. While CAD has been reported to be able to detect lesions with high sensitivity [8–9], the success of this technique depends highly on the quality of the input image. The presence of artifacts such as beam-hardening artifacts is known to severely affect the detection performance [10].…”