Automatic detection and classification of hypodense hepatic lesions on contrast-enhanced venous-phase CT

• Published in: Medical physics (Lancaster) Vol. 31; no. 9; p. 2584
• Main Authors: Bilello, Michel, Gokturk, Salih Burak, Desser, Terry, Napel, Sandy, Jeffrey, Jr, R Brooke, Beaulieu, Christopher F
• Format: Journal Article
• Language: English
• Published: United States 01.09.2004
• Subjects: Algorithms; Artificial Intelligence; Cluster Analysis; Computer Simulation; Contrast Media - administration & dosage; Hepatic Veins - diagnostic imaging; Humans; Information Storage and Retrieval - methods; Injections, Intravenous; Liver Diseases - classification; Liver Diseases - diagnostic imaging; Liver Neoplasms - classification; Liver Neoplasms - diagnostic imaging; Male; Middle Aged; Numerical Analysis, Computer-Assisted; Pattern Recognition, Automated - methods; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Tomography, X-Ray Computed - methods
• ISSN: 0094-2405
• DOI: 10.1118/1.1782674

The objective of this work was to develop and validate algorithms for detection and classification of hypodense hepatic lesions, specifically cysts, hemangiomas, and metastases from CT scans in the portal venous phase of enhancement. Fifty-six CT sections from 51 patients were used as representative of common hypodense liver lesions, including 22 simple cysts, 11 hemangiomas, 22 metastases, and 1 image containing both a cyst and a hemangioma. The detection algorithm uses intensity-based histogram methods to find central lesions, followed by liver contour refinement to identify peripheral lesions. The classification algorithm operates on the focal lesions identified during detection, and includes shape-based segmentation, edge pixel weighting, and lesion texture filtering. Support vector machines are then used to perform a pair-wise lesion classification. For the detection algorithm, 80% lesion sensitivity was achieved at approximately 0.3 false positives (FP) per slice for central lesions, and 0.5 FP per slice for peripheral lesions, giving a total of 0.8 FP per section. For 90% sensitivity, the total number of FP rises to about 2.2 per section. The pair-wise classification yielded good discrimination between cysts and metastases (at 95% sensitivity for detection of metastases, only about 5% of cysts are incorrectly classified as metastases), perfect discrimination between hemangiomas and cysts, and was least accurate in discriminating between hemangiomas and metastases (at 90% sensitivity for detection of hemangiomas, about 28% of metastases were incorrectly classified as hemangiomas). Initial implementations of our algorithms are promising for automating liver lesion detection and classification.