Graphical Oracles to Assess Computer-Aided Diagnosis Systems: A Case Study in Mammogram Masses and Calcifications Detection

Author(s)

Goncalves, Vagner Mendonca ; Delamaro, Marcio E. ; Nunes, Fatima L. S. ; Paiva, AC ; Conci, A ; Braz, G ; Almeida, JDS ; Fernandes, LAF

• Document type: Journal article
• Source: PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING (IWSSIP), 27TH EDITION; v. N/A, p. 6-pg., 2020-01-01.

Abstract

Computer-Aided Diagnosis (CAD) systems provide a second opinion to health professionals about the possible existence of an anomaly. Evaluation of CAD systems is a challenge and most of the traditional metrics requires the constant participation of experts. This paper presents an approach for evaluating CAD systems using concepts of Content-Based Image Retrieval and graphical oracles. After implementing feature descriptors and selecting three similarity functions, two metrics are proposed to measure the efficiency of CAD systems. A case study was conducted considering three simulated CAD systems to detect masses and calcifications in mammographic images. The results indicated that the our approach is as robust as traditional metrics with respect to performance evaluation. However, our approach is more flexible than traditional metrics because evaluators can choose the more adequate features to assess a particular CAD system. (AU)

• FAPESP's process: 10/01496-1 - Application of CBIR for evaluating computer-aided diagnosis systems.
• Grantee: Vagner Mendonça Gonçalves
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• FAPESP's process: 19/06937-0 - Study and development of software testing techniques and their applications
• Grantee: Márcio Eduardo Delamaro
• Support Opportunities: Regular Research Grants