Diffuse boundary extraction of breast masses on ultrasound by leak plugging

• Published in: Medical physics (Lancaster) 2005-11, Vol.32 (11), p.3318-3328
• Main Authors: Cary, T. W., Conant, E. F., Arger, P. H., Sehgal, C. M.
• Format: Article
• Language: English
• Subjects: ALGORITHMS; BIOMEDICAL RADIOGRAPHY; biomedical ultrasonics; Breast - pathology; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - therapy; cancer; CARCINOMAS; Computer aided diagnosis; Computer Simulation; DIAGNOSIS; Diagnosis, Computer-Assisted; Female; Humans; Image Enhancement; Image Interpretation, Computer-Assisted - methods; Image Processing, Computer-Assisted; Image scanners; Imaging, Three-Dimensional; Iteration theory; MAMMARY GLANDS; Mammography; MASS RESOLUTION; Medical image segmentation; Medical imaging; Models, Statistical; Numerical Analysis, Computer-Assisted; Overflows; Pattern Recognition, Automated; Phantoms, Imaging; POROUS MATERIALS; Radiographic Image Interpretation, Computer-Assisted; RADIOLOGY AND NUCLEAR MEDICINE; Regression Analysis; Reproducibility of Results; Signal Processing, Computer-Assisted; Time Factors; Tissues; tumours; ULTRASONOGRAPHY; Ultrasonography, Mammary - methods; User-Computer Interface
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1118/1.2012967

We propose a semiautomated seeded boundary extraction algorithm that delineates diffuse region boundaries by finding and plugging their leaks. The algorithm not only extracts boundaries that are partially diffuse, but in the process finds and quantifies those parts of the boundary that are diffuse, computing local sharpness measurements for possible use in computer-aided diagnosis. The method treats a manually drawn seed region as a wellspring of pixel “fluid” that flows from the seed out towards the boundary. At indistinct or porous sections of the boundary, the growing region will leak into surrounding tissue. By changing the size of structuring elements used for growing, the algorithm changes leak properties. Since larger elements cannot leak as far from the seed, they produce compact, less detailed boundary approximations; conversely, growing from smaller elements results in less constrained boundaries with more local detail. This implementation of the leak plugging algorithm decrements the radius of structuring disks and then compares the regions grown from them as they increase in both area and boundary detail. Leaks are identified if the outflows between grown regions are large compared to the areas of the disks. The boundary is plugged by masking out leaked pixels, and the process continues until one-pixel-radius resolution. When tested against manual delineation on scans of 40 benign masses and 40 malignant tumors, the plugged boundaries overlapped and correlated well in area with manual tracings, with mean overlap of 0.69 and area correlation R 2 of 0.86, but the algorithm’s results were more reproducible.