Multiview-based computer-aided detection scheme for breast masses

• Published in: Medical physics (Lancaster) Vol. 33; no. 9; pp. 3135 - 3143
• Main Authors: Zheng, Bin, Leader, Joseph K., Abrams, Gordon S., Lu, Amy H., Wallace, Luisa P., Maitz, Glenn S., Gur, David
• Format: Journal Article
• Language: English
• Published: United States American Association of Physicists in Medicine 01-09-2006
• Subjects: Algorithms; Artificial Intelligence; biological organs; BIOMEDICAL RADIOGRAPHY; Breast Neoplasms - diagnostic imaging; Cancer; CHEST; Computer aided diagnosis; computer-aided detection; digital mammography; Female; Humans; Image analysis; Image detection systems; image matching; IMAGE PROCESSING; Imaging, Three-Dimensional - methods; Information Storage and Retrieval - methods; MAMMARY GLANDS; Mammography; Mammography - methods; mass detection; medical image processing; Medical imaging; Muscles; neural nets; NEURAL NETWORKS; PACS; Pattern Recognition, Automated - methods; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Radiologists; RADIOLOGY AND NUCLEAR MEDICINE; Reproducibility of Results; Retrospective Studies; SENSITIVITY; Sensitivity and Specificity; Skin; Testing procedures; mass detection; computer-aided detection; digital mammography; image matching
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1118/1.2237476

In this study, we developed and tested a new multiview-based computer-aided detection (CAD) scheme that aims to maintain the same case-based sensitivity level as a single-image-based scheme while substantially increasing the number of masses being detected on both ipsilateral views. An image database of 450 four-view examinations (1800 images) was assembled. In this database, 250 cases depicted malignant masses, of which 236 masses were visible on both views and 14 masses were visible only on one view. First, we detected suspected mass regions depicted on each image in the database using a single-image-based CAD. For each identified region (with detection
score
⩾
0.55
), we then identified a matching strip of interest on the ipsilateral view based on the projected distance to the nipple along the centerline. By lowering CAD operating threshold inside the matching strip, we searched for a region located inside the strip and paired it with the original region. A multifeature-based artificial neural network scored the likelihood of the paired “matched” regions representing true-positive masses. All single (unmatched) regions except for those either with very high detection scores
(
⩾
0.85
)
or those located near the chest wall that cannot be matched on the other view were discarded. The original single-image-based CAD scheme detected 186 masses (74.4% case-based sensitivity) and 593 false-positive regions. Of the 186 identified masses, 91 were detected on two views (48.9%) and 95 were detected only on one view (51.1%). Of the false-positive detections, 54 were paired on the ipsilateral view inside the corresponding matching strips and the remaining 485 were not, which represented 539 case-based false-positive detections (0.3 per image). Applying the multiview-based CAD scheme, the same case-based sensitivity was maintained while cueing 169 of 186 masses (90.9%) on both views and at the same time reducing the case-based false-positive detection rate by 23.7% (from 539 to 411). The study demonstrated that the new multiview-based CAD scheme could substantially increase the number of masses being cued on two ipsilateral views while reducing the case-based false-positive detection rate.