Evaluation of Clinical Breast MR Imaging Performed with Prototype Computer-aided Diagnosis Breast MR Imaging Workstation: Reader Study

Evaluation of Clinical Breast MR Imaging Performed with Prototype Computer-aided Diagnosis Breast MR Imaging Workstation: Reader Study
Akiko Shimauchi, Maryellen L. Giger, Neha Bhooshan, Li Lan, Lorenzo L. Pesce, John K. Lee, Hiroyuki Abe, and Gillian M. Newstead
Radiology 2011; 258 696-704

Link to Journal

Use of a diagnostic computer aid for dynamic contrast-enhanced MR imaging has the potential to improve radiologists' performance in differentiating between benign and malignant breast lesions

Computer-aided Classification of Breast Masses: Performance and Interobserver Variability of Expert Radiologists versus Residents

Computer-aided Classification of Breast Masses: Performance and Interobserver Variability of Expert Radiologists versus Residents
Swatee Singh, Jeff Maxwell, Jay A. Baker, Jennifer L. Nicholas, and Joseph Y. Lo
Radiology 2011; 258 73-80

Link to Journal

Our study demonstrates that a computer-aided diagnosis model can potentially provide accurate classification of breast lesions for both radiology residents and experienced breast imagers with 3-17 years of experience

Interpretation Time of Computer-aided Detection at Screening Mammography

Interpretation Time of Computer-aided Detection at Screening Mammography
Philip M. Tchou, Tamara Miner Haygood, E. Neely Atkinson, Tanya W. Stephens, Paul L. Davis, Elsa M. Arribas, William R. Geiser, and Gary J. Whitman
Radiology 2010;257 40-46


Link to Journal

The time added to radiologists' interpretations of screening mammograms by the use of computer-aided detection is an important consideration in the assessment of the efficiency of digital mammography interpretation

The additional time required to review CAD images represented a 19% increase in the mean interpretation time without CAD.

CAD requires a considerable time investment for digital screening mammography but may provide less measurable benefits in terms of confidence of the radiologists

Mammographic Features of Breast Cancers at Single Reading with Computer-aided Detection and at Double Reading in a Large Multicenter Prospective Trial of Computer-aided Detection: CADET II

Mammographic Features of Breast Cancers at Single Reading with Computer-aided Detection and at Double Reading in a Large Multicenter Prospective Trial of Computer-aided Detection: CADET II
Jonathan J. James, Fiona J. Gilbert, Matthew G. Wallis, Maureen G. C. Gillan, Susan M. Astley, Caroline R. M. Boggis, Olorunsola F. Agbaje, Adam R. Brentnall, and Stephen W. Duffy
Radiology 2010;256 379-386

Link to Journal

Purpose: To evaluate the mammographic features of breast cancer that favor lesion detection with single reading and computer-aided detection (CAD) or with double reading

Results: A total of 227 cancers were detected in 28 204 women. A total of 170 cases were recalled with both reading regimens. Lesion types were masses (66%), microcalcifications (25%), parenchymal deformities (6%), and asymmetric densities (3%). The ability of the reading regimens to correctly prompt the reader to recall cases varied significantly by lesion type (P < .001). More parenchymal deformities were recalled with double reading, whereas more asymmetric densities were recalled with single reading with CAD. There was no difference in the ability of either reading regimen to prompt the reader to correctly recall masses or microcalcifications. CAD correctly prompted 100% of microcalcifications, 87% of mass lesions, 80% of asymmetric densities, and 50% of parenchymal deformities. CAD correctly marked 93% of spiculated masses compared with 80% of ill-defined masses (P = .054). There was a significant trend for cancers detected with double reading to occur only in women with a denser mammographic background pattern (P = .02). Size had no effect on lesion detection.

Conclusion: Readers using either single reading with CAD or double reading need to be aware of the strengths and weaknesses of reading regimens to avoid missing the more challenging cancer cases

Computer-aided US Diagnosis of Breast Lesions by Using Cell-based Contour Grouping

Computer-aided US Diagnosis of Breast Lesions by Using Cell-based Contour Grouping
Jie-Zhi Cheng, Yi-Hong Chou, Chiun-Sheng Huang, Yeun-Chung Chang, Chui-Mei Tiu, Kuei-Wu Chen, and Chung-Ming Chen
Radiology 2010; 255 746-754

Link to Journal

We present an efficient computer-aided diagnostic algorithm with an automatic segmentation approach where the lesion boundaries determined by using the cell-based contour grouping (CBCG) algorithms were shown to be close to the manually delineated boundaries, and the morphologic features determined from these CBCG-generated boundaries gave a high differentiation performance

Cancerous Breast Lesions on Dynamic Contrast-enhanced MR Images: Computerized Characterization for Image-based Prognostic Markers

Cancerous Breast Lesions on Dynamic Contrast-enhanced MR Images: Computerized Characterization for Image-based Prognostic Markers
Neha Bhooshan, Maryellen L. Giger, Sanaz A. Jansen, Hui Li, Li Lan, and Gillian M. Newstead
Radiology 2010;254 680-690

Link to Journal

Study results show that our MR imaging computer-aided diagnosis algorithm, with use of a combination of computer-extracted MR imaging kinetic and morphologic features, has the potential to be extended to two prognostic tasks: (a) classification of noninvasive (ductal carcinoma in situ) versus invasive (invasive ductal carcinoma [IDC]) lesions and (b) further classification of IDC lesions into lesions with positive lymph nodes (LNs) and lesions with negative LNs.

Breast US Computer-aided Diagnosis System: Robustness across Urban Populations in South Korea and the United States

Breast US Computer-aided Diagnosis System: Robustness across Urban Populations in South Korea and the United States
Nicholas P. Gruszauskas, Karen Drukker, Maryellen L. Giger, Ruey-Feng Chang, Charlene A. Sennett, Woo Kyung Moon, and Lorenzo L. Pesce
Radiology 2009;253 661-671

Link to Journal

In general, the breast US computer-aided diagnosis system appears to be effective across different patient populations, but further investigation is warranted

Breast Cancer Screening Results 5 Years after Introduction of Digital Mammography in a Population-based Screening Program

Breast Cancer Screening Results 5 Years after Introduction of Digital Mammography in a Population-based Screening Program
Nico Karssemeijer, Adriana M. Bluekens, David Beijerinck, Jan J. Deurenberg, Matthijs Beekman, Roelant Visser, Ruben van Engen, Annemieke Bartels-Kortland, and Mireille J. Broeders
Radiology 2009;253 353-358

Link to Journal

With the FFDM-CAD combination, detection performance is at least as good as that with SFM. The detection of ductal carcinoma in situ and microcalcification clusters improved with FFDM using CAD, while the recall rate increased.

Results indicate that with full-field digital mammography (FFDM) using computer-aided diagnosis (CAD) and double reading, the detection is as good as that with screen-film mammography, and detection of clustered microcalcifications and ductal carcinoma in situ is improved with FFDM using CAD

Can Computer-aided Detection Be Detrimental to Mammographic Interpretation?

Can Computer-aided Detection Be Detrimental to Mammographic Interpretation?
Liane E. Philpotts
Radiology 2009;253 17-22

Link to Journal


Understanding of the limitations of computer-aided detection is important for those interpreting mammograms; this cautious approach to the use of computer-aided detection should help optimize this presently imperfect system and minimize the possible detrimental effects

The Preponderance of Evidence Supports Computer-aided Detection for Screening Mammography

The Preponderance of Evidence Supports Computer-aided Detection for Screening Mammography
Robyn L. Birdwell
Radiology 2009;253 9-16

Link to Journal

Having a system to aid the human eye that does not take vacations, is not vulnerable to fatigue or environmental distractions, is without, emotion, and is designed specifically to assist the very human eye to "look over here" seems like a good idea

Computer-aided Detection Evaluation Methods Are Not Created Equal

Computer-aided Detection Evaluation Methods Are Not Created Equal
Robert M. Nishikawa and Lorenzo L. Pesce
Radiology 2009;251 634-636

Link to Journal

For the evaluation of computer-aided detection, longitudinal studies (historical controls) are inherently different from cross-sectional studies (sequential reading) when cancer detection rate is used as an end point in a screening program

Breast US Computer-aided Diagnosis Workstation: Performance with a Large Clinical Diagnostic Population

Breast US Computer-aided Diagnosis Workstation: Performance with a Large Clinical Diagnostic Population
Karen Drukker, Nicholas P. Gruszauskas, Charlene A. Sennett, and Maryellen L. Giger
Radiology 2008;248 392-397

Link to Journal

The computer performance was largely unaffected by the inclusion of large numbers of lesions that did not undergo biopsy in the analysis, achieving overall good lesion characterization performance at area under the receiver operating characteristic curve value of 0.90

Computer-aided Detection in Full-Field Digital Mammography: Sensitivity and Reproducibility in Serial Examinations

Seung Ja Kim, Woo Kyung Moon, Nariya Cho, Joo Hee Cha, Sun Mi Kim, and Jung-Gi Im
Radiology 2007;246 71-80
http://radiology.rsnajnls.org/cgi/content/abstract/246/1/71?etoc

When a computer-aided detection system was applied to initial and short-term follow-up digital mammograms, sensitivities were, respectively, 91% and 89% for masses and 100% and 100% for microcalcifications; overall false-positive mark rates were 0.29 mark per image and 0.27 mark per image at initial and follow-up digital mammography, respectively