Automated seeded lesion segmentation on digital mammograms

• Published in: IEEE transactions on medical imaging Vol. 17; no. 4; pp. 510 - 517
• Main Authors: Kupinski, M.A., Giger, M.L.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.08.1998; Institute of Electrical and Electronics Engineers
• Subjects: Algorithm design and analysis; Algorithms; Biological and medical sciences; Breast Neoplasms - diagnostic imaging; Computer aided diagnosis; Data mining; Database systems; Digital signal processing; Genital system. Mammary gland; Humans; Image segmentation; Investigative techniques, diagnostic techniques (general aspects); Lesions; Mammography - methods; Medical sciences; Partitioning algorithms; Performance analysis; Probability distribution; Probability distributions; Radiodiagnosis. Nmr imagery. Nmr spectrometry; Radiographic Image Enhancement - methods; Radiology; Shape; Testing; Human; Radiodiagnosis; Segmentation; Image processing; Mammography; Digital image; Malignant tumor; Medical screening; Automated processing; Mammary gland diseases; Radial gradient; Female; Mammary gland; Computer aid
• ISSN: 0278-0062
• DOI: 10.1109/42.730396

Segmenting lesions is a vital step in many computerized mass-detection schemes for digital (or digitized) mammograms. The authors have developed two novel lesion segmentation techniques-one based on a single feature called the radial gradient index (RGI) and one based on simple probabilistic models to segment mass lesions, or other similar nodular structures, from surrounding background. In both methods a series of image partitions is created using gray-level information as well as prior knowledge of the shape of typical mass lesions. With the former method the partition that maximizes the RGI is selected. In the latter method, probability distributions for gray-levels inside and outside the partitions are estimated, and subsequently used to determine the probability that the image occurred for each given partition. The partition that maximizes this probability is selected as the final lesion partition (contour). The authors tested these methods against a conventional region growing algorithm using a database of biopsy-proven, malignant lesions and found that the new lesion segmentation algorithms more closely match radiologists' outlines of these lesions. At an overlap threshold of 0.30, gray level region growing correctly delineates 62% of the lesions in the authors' database while the RGI and probabilistic segmentation algorithms correctly segment 92% and 96% of the lesions, respectively.