Automatic detection and classification of hypodense hepatic lesions on contrast-enhanced venous-phase CT
Michel Bilello1, Salih Burak Gokturk, Terry Desser
1Department of Computer Science, Stanford University, Stanford, California 94305, USA. bilello@rad.upenn.edu
Insights
This study developed algorithms to detect and classify liver lesions like cysts, hemangiomas, and metastases on CT scans. The automated methods show promise for improving diagnostic accuracy in radiology.
Area of Science:
- Medical Imaging
- Radiology
- Computer-Aided Diagnosis
Background:
- Accurate detection and classification of hypodense hepatic lesions are crucial for patient management.
- Distinguishing between liver cysts, hemangiomas, and metastases on CT scans can be challenging.
Purpose of the Study:
- To develop and validate algorithms for automated detection and classification of hypodense liver lesions.
- To specifically differentiate between simple cysts, hemangiomas, and metastases using CT scans.
Main Methods:
- Utilized 56 CT scans from 51 patients representing common hypodense liver lesions.
- Employed intensity-based histogram methods and liver contour refinement for lesion detection.
- Applied shape-based segmentation, edge weighting, texture filtering, and support vector machines for classification.
Main Results:
- Detection algorithm achieved 80% sensitivity with 0.8 false positives per section.
- Classification demonstrated good discrimination between cysts and metastases, and perfect discrimination between hemangiomas and cysts.
- Discrimination between hemangiomas and metastases was less accurate, with 28% misclassification at 90% hemangioma sensitivity.
Conclusions:
- The developed algorithms show promising results for automating the detection and classification of hepatic lesions.
- Further refinement may improve accuracy, particularly in differentiating hemangiomas from metastases.
Abstract:
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.
Related Concept Videos
01:20Venous Thrombosis II: Clinical Manifestations and Diagnostic Studies
01:28Imaging Studies for Cardiovascular System V: CT