Automation of CT-Based Liver Segmentation Is Accurate and Saves Time
By MedImaging International staff writers Posted on 11 May 2015 |
A new study published in the April 20, 2015, online issue of the Journal Academic Radiology, has compared a new semi-automated liver segmentation method with a manual volume measurement tool for assessing the total liver volume using Computed Tomography (CT).
The researchers from the University of Montreal (UdeM; Montreal, Quebec, Canada) compared the repeatability and agreement of the two methods intended for preoperative planning. The semi-automated segmentation method is based on variational interpolation, and 3-D minimal path surface segmentation. Contrast-enhanced CT images, in venous phase, were used to segment total and sub-segmental liver volumes.
The retrospective study included 41 subjects all of whom underwent liver CT for preoperative planning, and presented with pathologies such as colorectal cancer metastases, hepatocellular carcinoma, and benign liver lesions. Two image analysts made independent semi-automated segmentations, and two additional analysts performed manual segmentations. The repeatability and agreement of both methods were evaluated using Intraclass Bland–Altman analysis, and Correlation Coefficients (ICC).
The results of the study showed that semi-automated segmentation method can shorten interaction time significantly compared to manual segmentation, while still providing the same high level of repeatability and agreement.
Related Links:
University of Montreal
The researchers from the University of Montreal (UdeM; Montreal, Quebec, Canada) compared the repeatability and agreement of the two methods intended for preoperative planning. The semi-automated segmentation method is based on variational interpolation, and 3-D minimal path surface segmentation. Contrast-enhanced CT images, in venous phase, were used to segment total and sub-segmental liver volumes.
The retrospective study included 41 subjects all of whom underwent liver CT for preoperative planning, and presented with pathologies such as colorectal cancer metastases, hepatocellular carcinoma, and benign liver lesions. Two image analysts made independent semi-automated segmentations, and two additional analysts performed manual segmentations. The repeatability and agreement of both methods were evaluated using Intraclass Bland–Altman analysis, and Correlation Coefficients (ICC).
The results of the study showed that semi-automated segmentation method can shorten interaction time significantly compared to manual segmentation, while still providing the same high level of repeatability and agreement.
Related Links:
University of Montreal
Latest Radiography News
- Novel Breast Imaging System Proves As Effective As Mammography
- AI Assistance Improves Breast-Cancer Screening by Reducing False Positives
- AI Could Boost Clinical Adoption of Chest DDR
- 3D Mammography Almost Halves Breast Cancer Incidence between Two Screening Tests
- AI Model Predicts 5-Year Breast Cancer Risk from Mammograms
- Deep Learning Framework Detects Fractures in X-Ray Images With 99% Accuracy
- Direct AI-Based Medical X-Ray Imaging System a Paradigm-Shift from Conventional DR and CT
- Chest X-Ray AI Solution Automatically Identifies, Categorizes and Highlights Suspicious Areas
- AI Diagnoses Wrist Fractures As Well As Radiologists
- Annual Mammography Beginning At 40 Cuts Breast Cancer Mortality By 42%
- 3D Human GPS Powered By Light Paves Way for Radiation-Free Minimally-Invasive Surgery
- Novel AI Technology to Revolutionize Cancer Detection in Dense Breasts
- AI Solution Provides Radiologists with 'Second Pair' Of Eyes to Detect Breast Cancers
- AI Helps General Radiologists Achieve Specialist-Level Performance in Interpreting Mammograms
- Novel Imaging Technique Could Transform Breast Cancer Detection
- Computer Program Combines AI and Heat-Imaging Technology for Early Breast Cancer Detection