ABSTRACT
Large-scale and systematic research and development of various CAD schemes were begun in the early 1980s at the Kurt Rossmann Laboratories for Radiologic Image Research
Kunio Doi
1.1 Introduction 1 1.2 Early Development of CAD Schemes 1
1.2.1 Strategies for Research and Development of CAD 2 1.2.2 Initial CAD Schemes for the Detection of Lesions 3
1.3 Computer-Aided Diagnosis and Automated Computer Diagnosis 3 1.3.1 Historical View on Computer Analysis of Medical Information and Images 3 1.3.2 Clear Distinction between CAD and Computer Diagnosis 4 1.3.3 Evaluation of Performances for CAD and Computer Diagnosis 5
1.4 Brief Summary of Recent CAD Research 5 1.5 Eect of Computer Output on Radiologists’ Performance 6
1.5.1 Eect of Computer Output on the Detection of Lesions 7 1.5.2 Eect of Computer Output on Dierential Diagnosis 7
1.6 Potential Usefulness of Similar Images in Support of CAD 8 1.7 Prototype and First Commercial CAD Systems in the Early Phase 9 1.8 Reevaluation of Reading Methods for CAD in the PACS Environment 12 1.9 Conclusion 12 References 12
in the Department of Radiology at the University of Chicago. Prior to and since that time, we have been engaged in some basic research on the eects of digital images on radiologic diagnosis (Ishida et al., 1982, 1983, 1984; Giger and Doi, 1984a,b, 1985; MacMahon et al., 1984, 1985, 1986; Fujita et al., 1985, 1986; Loo et al., 1985; Giger et al., 1986a,b; Kume et al., 1986; Ohara et al., 1986), and many investigators have become involved in research and development of some aspects of picture archiving and communication system (PACS) (Huang, 2010, 2011). Although PACS would be useful and advantageous in the management of radiologic images in radiology departments and might be benecial economically to hospitals, it seemed unlikely at that time that PACS would bring a signicant clinical benet to radiologists. erefore, we thought that a major benet of digital images must be realized in radiologists’ daily work. Of course, radiologists’ daily work consists of image reading and radiologic diagnosis. us, we came to the question, “how can radiologists’ diagnosis be helped by the benets of digital images?” is led immediately to the concept of computer-aided diagnosis.
