Automated detection of breast carcinomas not detected in a screening program

• Published in: Radiology Vol. 207; no. 2; p. 465
• Main Authors: te Brake, G M, Karssemeijer, N, Hendriks, J H
• Format: Journal Article
• Language: English
• Published: United States 01.05.1998
• Subjects: Algorithms; Automation; Breast Neoplasms - classification; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - prevention & control; Carcinoma - classification; Carcinoma - diagnostic imaging; Carcinoma - prevention & control; Databases as Topic; Diagnosis, Computer-Assisted; False Positive Reactions; Female; Humans; Image Processing, Computer-Assisted; Mammography - classification; Mass Screening; Neural Networks (Computer); Pattern Recognition, Automated; Radiographic Image Enhancement; Retrospective Studies; ROC Curve; Sensitivity and Specificity
• ISSN: 0033-8419
• DOI: 10.1148/radiology.207.2.9577496

To investigate the possibility of automated detection of early signs of cancer that were not detected in a breast cancer screening program. A set of 75 mammograms (in 65 women) with subtle circumscribed masses, stellate lesions, and architectural distortions that were not detected in a screening program by two radiologists was assembled and extended with 142 normal mammograms (contralateral mammograms in the same 65 women). An automated system for the detection of circumscribed masses and stellate lesions was applied to this set. In 22 (34%) of 65 cases, an early sign of cancer was detected at a specificity of one false-positive finding per image. At a specificity of three false-positive findings per image, 39 (60%) of the cancers were detected. Of the tumors that were classified as screening errors, seven (50%) were found at a specificity of 0.5 false-positive finding per image. A substantial proportion of cancers that were missed in a screening program, despite double reading, were found with this detection method at less than one false-positive finding per image.