Investig Clin Urol.
2020 Nov;61(6):555-564. 10.4111/icu.20200086.
Expert-level segmentation using deep learning for volumetry of polycystic kidney and liver
- Shin TY
1,2 - Kim H3
- Lee JH1
- Choi JS2
- Min HS4
- Cho H4
- Kim K5
- Kang G2
- Kim J2
- Yoon S5
- Park H2
- Hwang YU6
- Kim HJ7
- Han M7
- Bae E8
- Yoon JW3
- Rha KH9
- Lee YS10
- Affiliations
-
- 1Synergy A.I. Co.Ltd., Chuncheon, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
- 2Department of Urology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
- 3Department of Internal Medicine, Division of Nephrology, Hallym University Chuncheon Sacred Heart Hospital, Hallym University College of Medicine, Chuncheon, Korea
- 4Tomocube, Inc., Daejeon, Korea
- 5Schulich School of Medicine & Dentistry, The University of Western, Ontario, London, ON, Canada
- 6Department of Radiology, Inje University Ilsan Paik Hospital, Goyang, Korea
- 7Department of Internal Medicine, Pusan National University Hospital, Busan, Korea
- 8Department of Internal Medicine, Gyeongsang National University Changwon Hospital, Gyeongsang National University College of Medicine, Changwon, Korea
- 9Department of Urology, Urological Science Institute, Yonsei University College of Medicine, Seoul, Korea
- 10Department of Urology, Hallym University Sacred Heart Hospital, Hallym University Collge of Medicine, Anyang, Korea
- KMID: 2508186
- DOI: http://doi.org/10.4111/icu.20200086
Abstract
- Purpose
Volumetry is used in polycystic kidney and liver diseases (PKLDs), including autosomal dominant polycystic kidney disease (ADPKD), to assess disease progression and drug efficiency. However, since no rapid and accurate method for volumetry has been developed, volumetry has not yet been established in clinical practice, hindering the development of therapies for PKLD. This study presents an artificial intelligence (AI)-based volumetry method for PKLD.
Materials and Methods
The performance of AI was first evaluated in comparison with ground-truth (GT). We trained a V-net-based convolutional neural network on 175 ADPKD computed tomography (CT) segmentations, which served as the GT and were agreed upon by 3 experts using images from 214 patients analyzed with volumetry. The dice similarity coefficient (DSC), interobserver correlation coefficient (ICC), and Bland–Altman plots of 39 GT and AI segmentations in the validation set were compared. Next, the performance of AI on the segmentation of 50 random CT images was compared with that of 11 PKLD specialists based on the resulting DSC and ICC.
Results
The DSC and ICC of the AI were 0.961 and 0.999729, respectively. The error rate was within 3% for approximately 95% of the CT scans (error<1%, 46.2%; 1%≤error<3%, 48.7%). Compared with the specialists, AI showed moderate performance. Furthermore, an outlier in our results confirmed that even PKLD specialists can make mistakes in volumetry.
Conclusions
PKLD volumetry using AI was fast and accurate. AI performed comparably to human specialists, suggesting its use may be practical in clinical settings.
- Full Text Links
-
- Actions
-
Cited
- CITED
-
- Close
- Share
-
- Similar articles
-
- Deep Learning in Dental Radiographic Imaging
- Three-dimensional (3D) auto-segmentation of vascular structures and hepatic sectional parenchyme of living liver donors using computed tomographic angiography: a deep learning model for automatic 3D volumetry
- Deep Learning-Based Lumen and Vessel Segmentation of Intravascular Ultrasound Images in Coronary Artery Disease
- Deep Learning Algorithm for Automated Segmentationand Volume Measurement of the Liver and Spleen UsingPortal Venous Phase Computed Tomography Images
- Ultrasonography of polycystic kidney
