CT Colonography with Computer-aided Detection as a Second Reader: Observer Performance Study 1

National Institute of Biomedical Imaging and Bioengineering/Center for Devices and Radiological Health Joint Laboratory for the Assessment of Medical Imaging Systems, U.S. Food and Drug Administration, Rockville, MD, USA.
Radiology (Impact Factor: 6.87). 01/2008; 246(1):148-56. DOI: 10.1148/radiol.2453062161
Source: PubMed


To evaluate the effect of computer-aided detection (CAD) as second reader on radiologists' diagnostic performance in interpreting computed tomographic (CT) colonographic examinations by using a primary two-dimensional (2D) approach, with segmental, unblinded optical colonoscopy as the reference standard.
This HIPAA-compliant study was IRB-approved with written informed consent. Four board-certified radiologists analyzed 60 CT examinations with a commercially available review system. Two-dimensional transverse views were used for initial polyp detection, while three-dimensional (3D) endoluminal and 2D multiplanar views were available for problem solving. After initial review without CAD, the reader was shown CAD-identified polyp candidates. The readers were then allowed to add to or modify their original diagnoses. Polyp location, CT Colonography Reporting and Data System categorization, and reader confidence as to the likelihood of a candidate being a polyp were recorded before and after CAD reading. The area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity were estimated for CT examinations with and without CAD readings by using multireader multicase analysis.
Use of CAD led to nonsignificant average reader AUC increases of 0.03, 0.03, and 0.04 for patients with adenomatous polyps 6 mm or larger, 6-9 mm, and 10 mm or larger, respectively (P > or = .25); likewise, CAD increased average reader sensitivity by 0.15, 0.16, and 0.14 for those respective groups, with a corresponding decrease in specificity of 0.14. These changes achieved significance for the 6 mm or larger group (P < .01), 6-9 mm group (P < .02), and for specificity (P < .01), but not for the 10 mm or larger group (P > .16). The average reading time was 5.1 minutes +/- 3.4 (standard deviation) without CAD. CAD added an average of 3.1 minutes +/- 4.3 (62%) to each reading (supine and prone positions combined); average total reading time, 8.2 minutes +/- 5.8.
Use of CAD led to a significant increase in sensitivity for detecting polyps in the 6 mm or larger and 6-9 mm groups at the expense of a similar significant reduction in specificity.

11 Reads
  • Source
    • "The standalone performance of CADe schemes was evaluated by a number of investigators [18] [19] [20] [21] [22]. Observer performance studies were performed to show the usefulness of CADe schemes [17] [23]. However, it has not yet been clear whether CADe would improve radiologists' performance in the detection of " difficult " polyps which were " missed " by radiologists in a multicenter clinical trial. "
    [Show abstract] [Hide abstract]
    ABSTRACT: To investigate the actual usefulness of computer-aided detection (CADe) of polyps as a second reader, we conducted a free-response observer performance study with radiologists in the detection of "difficult" polyps in CT colonography (CTC) from a multicenter clinical trial. The "difficult" polyps were defined as the ones that had been "missed" by radiologists in the clinical trial or rated "difficult" in our retrospective review. Our advanced CADe scheme utilizing massive-training artificial neural networks (MTANNs) technology was sensitive and specific to the "difficult" polyps. Four board-certified abdominal radiologists participated in this observer study. They were instructed, first without and then with our CADe, to indicate the location of polyps and their confidence level regarding the presence of polyps. Our database contains 20 patients with 23 polyps including 14 false-negative (FN) and 7 "difficult" polyps and 10 negative patients. With CADe, the average by-polyp sensitivity of radiologists was improved from 53 to 63% at a statistically significant level (P=0.037). Thus, our CADe scheme utilizing the MTANN technology improved the diagnostic performance of radiologists, including expert readers, in the detection of "difficult" polyps in CTC.
    Proceedings of SPIE - The International Society for Optical Engineering 03/2013; 8670. DOI:10.1117/12.2008284 · 0.20 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: CT virtual colonoscopy (VC) is a modern diagnostics method which enables 3D view of walls and internal space of the colon as a result of reconstruction of helical CT images. Its role in diagnosis of pathologies of the colon systematically increases, and in many medical centers of the world is carried out as a screening test in patients with high risk of colon cancer. The key for the proper interpretation of this procedure is the patients preparation for the examination and the experience of evaluating radiologist. Common causes of the misinterpretation are technical errors linked with improper patients preparation (fecal mass and fluid attenuation). Protocol of the examination differs in screening and in diagnostic examination. Full evaluation includes the evaluation of toposcan, axial images (which are always reference images), multiplanar reconstructions and 3D options amongst the others navigator type reconstructions. Novelty in this field, which improves the proper evaluation, is the computer aided diagnosis (CAD). Virtual colonoscopy is safe and well tolerated in patients diagnostic method which permits early detection of pre cancer pathologies with specificity and sensitivity similar to classical colonoscopy, but also enables the possibility of evaluating extra colon lesions. This method can be an reasonable alternative for classical colonoscopy in screening and should take place of double contrast barium enema in evaluating the patient with probable colon cancer or polyps.

Show more