IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease
Purpose: To develop and integrate interactive features with automatic methods for accurate liver cyst segmentation in patients with autosomal dominant polycystic kidney and liver disease (ADPKD). Methods: SmartClick and antiSmartClick were developed using iterative region growth guided by spatial an...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Tomography |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2379-139X/8/1/37 |
| _version_ | 1827652496908091392 |
|---|---|
| author | Collin Li Dominick Romano Sophie J. Wang Hang Zhang Martin R. Prince Yi Wang |
| author_facet | Collin Li Dominick Romano Sophie J. Wang Hang Zhang Martin R. Prince Yi Wang |
| author_sort | Collin Li |
| collection | DOAJ |
| description | Purpose: To develop and integrate interactive features with automatic methods for accurate liver cyst segmentation in patients with autosomal dominant polycystic kidney and liver disease (ADPKD). Methods: SmartClick and antiSmartClick were developed using iterative region growth guided by spatial and intensity connections and were integrated with automated level set (LS) segmentation and graphical user interface, forming an intelligent rapid interactive segmentation (IRIS) tool. IRIS and LS segmentations of liver cysts on <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>T</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula> weighted images of patients with ADPKD (<i>n</i> = 17) were compared with manual segmentation as ground truth (GT). Results: Compared to manual GT, IRIS reduced the segmentation time by more than 10-fold. Compared to automated LS, IRIS reduced the mean liver cyst volume error from 42.22% to 13.44% (<i>p</i> < 0.001). IRIS segmentation agreed well with manual GT (79% dice score and 99% intraclass correlation coefficient). Conclusion: IRIS is feasible for fast, accurate liver cyst segmentation in patients with ADPKD. |
| first_indexed | 2024-03-09T20:56:15Z |
| format | Article |
| id | doaj.art-337773c3db4c4b85966d57693f10e0ac |
| institution | Directory Open Access Journal |
| issn | 2379-1381 2379-139X |
| language | English |
| last_indexed | 2024-03-09T20:56:15Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tomography |
| spelling | doaj.art-337773c3db4c4b85966d57693f10e0ac2023-11-23T22:19:48ZengMDPI AGTomography2379-13812379-139X2022-02-018144745610.3390/tomography8010037IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney DiseaseCollin Li0Dominick Romano1Sophie J. Wang2Hang Zhang3Martin R. Prince4Yi Wang5Department of Radiology, MRI Research Institute, Weill Cornell Medicine, New York, NY 10065, USADepartment of Radiology, MRI Research Institute, Weill Cornell Medicine, New York, NY 10065, USADepartment of Radiology, MRI Research Institute, Weill Cornell Medicine, New York, NY 10065, USADepartment of Radiology, MRI Research Institute, Weill Cornell Medicine, New York, NY 10065, USADepartment of Radiology, MRI Research Institute, Weill Cornell Medicine, New York, NY 10065, USADepartment of Radiology, MRI Research Institute, Weill Cornell Medicine, New York, NY 10065, USAPurpose: To develop and integrate interactive features with automatic methods for accurate liver cyst segmentation in patients with autosomal dominant polycystic kidney and liver disease (ADPKD). Methods: SmartClick and antiSmartClick were developed using iterative region growth guided by spatial and intensity connections and were integrated with automated level set (LS) segmentation and graphical user interface, forming an intelligent rapid interactive segmentation (IRIS) tool. IRIS and LS segmentations of liver cysts on <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mi>T</mi><mn>2</mn></msub></mrow></semantics></math></inline-formula> weighted images of patients with ADPKD (<i>n</i> = 17) were compared with manual segmentation as ground truth (GT). Results: Compared to manual GT, IRIS reduced the segmentation time by more than 10-fold. Compared to automated LS, IRIS reduced the mean liver cyst volume error from 42.22% to 13.44% (<i>p</i> < 0.001). IRIS segmentation agreed well with manual GT (79% dice score and 99% intraclass correlation coefficient). Conclusion: IRIS is feasible for fast, accurate liver cyst segmentation in patients with ADPKD.https://www.mdpi.com/2379-139X/8/1/37liver cystlesion segmentationintelligent rapid interactive segmentation |
| spellingShingle | Collin Li Dominick Romano Sophie J. Wang Hang Zhang Martin R. Prince Yi Wang IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease Tomography liver cyst lesion segmentation intelligent rapid interactive segmentation |
| title | IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease |
| title_full | IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease |
| title_fullStr | IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease |
| title_full_unstemmed | IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease |
| title_short | IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease |
| title_sort | iris intelligent rapid interactive segmentation for measuring liver cyst volumes in autosomal dominant polycystic kidney disease |
| topic | liver cyst lesion segmentation intelligent rapid interactive segmentation |
| url | https://www.mdpi.com/2379-139X/8/1/37 |
| work_keys_str_mv | AT collinli irisintelligentrapidinteractivesegmentationformeasuringlivercystvolumesinautosomaldominantpolycystickidneydisease AT dominickromano irisintelligentrapidinteractivesegmentationformeasuringlivercystvolumesinautosomaldominantpolycystickidneydisease AT sophiejwang irisintelligentrapidinteractivesegmentationformeasuringlivercystvolumesinautosomaldominantpolycystickidneydisease AT hangzhang irisintelligentrapidinteractivesegmentationformeasuringlivercystvolumesinautosomaldominantpolycystickidneydisease AT martinrprince irisintelligentrapidinteractivesegmentationformeasuringlivercystvolumesinautosomaldominantpolycystickidneydisease AT yiwang irisintelligentrapidinteractivesegmentationformeasuringlivercystvolumesinautosomaldominantpolycystickidneydisease |