Automatic Segmentation with Detection of Local Segmentation Failures in Cardiac MRI

Overview

Journal Sci Rep

Specialty Science

Date 2020 Dec 11

PMID 33303782

Citations 17

Authors

Jorg Sander

Bob D de Vos

Ivana Isgum

Affiliations

Soon will be listed here.

Abstract

Segmentation of cardiac anatomical structures in cardiac magnetic resonance images (CMRI) is a prerequisite for automatic diagnosis and prognosis of cardiovascular diseases. To increase robustness and performance of segmentation methods this study combines automatic segmentation and assessment of segmentation uncertainty in CMRI to detect image regions containing local segmentation failures. Three existing state-of-the-art convolutional neural networks (CNN) were trained to automatically segment cardiac anatomical structures and obtain two measures of predictive uncertainty: entropy and a measure derived by MC-dropout. Thereafter, using the uncertainties another CNN was trained to detect local segmentation failures that potentially need correction by an expert. Finally, manual correction of the detected regions was simulated in the complete set of scans of 100 patients and manually performed in a random subset of scans of 50 patients. Using publicly available CMR scans from the MICCAI 2017 ACDC challenge, the impact of CNN architecture and loss function for segmentation, and the uncertainty measure was investigated. Performance was evaluated using the Dice coefficient, 3D Hausdorff distance and clinical metrics between manual and (corrected) automatic segmentation. The experiments reveal that combining automatic segmentation with manual correction of detected segmentation failures results in improved segmentation and to 10-fold reduction of expert time compared to manual expert segmentation.

Citing Articles

Semi-supervised segmentation of cardiac chambers from LGE-CMR using feature consistency awareness.

Wang H, Huang H, Wu J, Li N, Gu K, Wu X BMC Cardiovasc Disord. 2024; 24(1):571.

PMID: 39420256 PMC: 11484209. DOI: 10.1186/s12872-024-04250-x.

Application of Mixed/Augmented Reality in Interventional Cardiology.

Annabestani M, Olyanasab A, Mosadegh B J Clin Med. 2024; 13(15).

PMID: 39124633 PMC: 11312946. DOI: 10.3390/jcm13154368.

Clinical assessment of an AI tool for measuring biventricular parameters on cardiac MR.

Salehi M, Maiter A, Strickland S, Aldabbagh Z, Karunasaagarar K, Thomas R Front Cardiovasc Med. 2024; 11:1279298.

PMID: 38374997 PMC: 10875016. DOI: 10.3389/fcvm.2024.1279298.

Temporal Uncertainty Localization to Enable Human-in-the-Loop Analysis of Dynamic Contrast-Enhanced Cardiac MRI Datasets.

Yalcinkaya D, Youssef K, Heydari B, Simonetti O, Dharmakumar R, Raman S Med Image Comput Comput Assist Interv. 2024; 14222:453-462.

PMID: 38204763 PMC: 10775176. DOI: 10.1007/978-3-031-43898-1_44.

Stochastic co-teaching for training neural networks with unknown levels of label noise.

de Vos B, Jansen G, Isgum I Sci Rep. 2023; 13(1):16875.

PMID: 37803027 PMC: 10558560. DOI: 10.1038/s41598-023-43864-7.

References

Suinesiaputra A, Bluemke D, Cowan B, Friedrich M, Kramer C, Kwong R . Quantification of LV function and mass by cardiovascular magnetic resonance: multi-center variability and consensus contours. J Cardiovasc Magn Reson. 2015; 17:63. PMC: 4517503. DOI: 10.1186/s12968-015-0170-9. View

Robinson R, Valindria V, Bai W, Oktay O, Kainz B, Suzuki H . Automated quality control in image segmentation: application to the UK Biobank cardiovascular magnetic resonance imaging study. J Cardiovasc Magn Reson. 2019; 21(1):18. PMC: 6416857. DOI: 10.1186/s12968-019-0523-x. View

Meyer H, Dawes T, Serrani M, Bai W, Tokarczuk P, Cai J . Genetic and functional insights into the fractal structure of the heart. Nature. 2020; 584(7822):589-594. PMC: 7116759. DOI: 10.1038/s41586-020-2635-8. View

Leiner T, Rueckert D, Suinesiaputra A, Baessler B, Nezafat R, Isgum I . Machine learning in cardiovascular magnetic resonance: basic concepts and applications. J Cardiovasc Magn Reson. 2019; 21(1):61. PMC: 6778980. DOI: 10.1186/s12968-019-0575-y. View

Petitjean C, Dacher J . A review of segmentation methods in short axis cardiac MR images. Med Image Anal. 2011; 15(2):169-84. DOI: 10.1016/j.media.2010.12.004. View

Litjens G, Kooi T, Bejnordi B, Setio A, Ciompi F, Ghafoorian M . A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42:60-88. DOI: 10.1016/j.media.2017.07.005. View

Peng P, Lekadir K, Gooya A, Shao L, Petersen S, Frangi A . A review of heart chamber segmentation for structural and functional analysis using cardiac magnetic resonance imaging. MAGMA. 2016; 29(2):155-95. PMC: 4830888. DOI: 10.1007/s10334-015-0521-4. View

Kohlberger T, Singh V, Alvino C, Bahlmann C, Grady L . Evaluating segmentation error without ground truth. Med Image Comput Comput Assist Interv. 2013; 15(Pt 1):528-36. DOI: 10.1007/978-3-642-33415-3_65. View

Bernard O, Lalande A, Zotti C, Cervenansky F, Yang X, Heng P . Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?. IEEE Trans Med Imaging. 2018; 37(11):2514-2525. DOI: 10.1109/TMI.2018.2837502. View

10.

Bai W, Sinclair M, Tarroni G, Oktay O, Rajchl M, Vaillant G . Automated cardiovascular magnetic resonance image analysis with fully convolutional networks. J Cardiovasc Magn Reson. 2018; 20(1):65. PMC: 6138894. DOI: 10.1186/s12968-018-0471-x. View

11.

Alba X, Lekadir K, Pereanez M, Medrano-Gracia P, Young A, Frangi A . Automatic initialization and quality control of large-scale cardiac MRI segmentations. Med Image Anal. 2017; 43:129-141. DOI: 10.1016/j.media.2017.10.001. View

12.

Duan J, Bello G, Schlemper J, Bai W, Dawes T, Biffi C . Automatic 3D Bi-Ventricular Segmentation of Cardiac Images by a Shape-Refined Multi- Task Deep Learning Approach. IEEE Trans Med Imaging. 2019; 38(9):2151-2164. PMC: 6728160. DOI: 10.1109/TMI.2019.2894322. View

13.

White H, Norris R, Brown M, Brandt P, Whitlock R, Wild C . Left ventricular end-systolic volume as the major determinant of survival after recovery from myocardial infarction. Circulation. 1987; 76(1):44-51. DOI: 10.1161/01.cir.76.1.44. View

14.

Tan L, McLaughlin R, Lim E, Abdul Aziz Y, Liew Y . Fully automated segmentation of the left ventricle in cine cardiac MRI using neural network regression. J Magn Reson Imaging. 2018; 48(1):140-152. DOI: 10.1002/jmri.25932. View

15.

Valindria V, Lavdas I, Bai W, Kamnitsas K, Aboagye E, Rockall A . Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth. IEEE Trans Med Imaging. 2017; 36(8):1597-1606. DOI: 10.1109/TMI.2017.2665165. View

16.

Roy A, Conjeti S, Navab N, Wachinger C . Bayesian QuickNAT: Model uncertainty in deep whole-brain segmentation for structure-wise quality control. Neuroimage. 2019; 195:11-22. DOI: 10.1016/j.neuroimage.2019.03.042. View

17.

Oktay O, Ferrante E, Kamnitsas K, Heinrich M, Bai W, Caballero J . Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation. IEEE Trans Med Imaging. 2017; 37(2):384-395. DOI: 10.1109/TMI.2017.2743464. View

18.

Bello G, Dawes T, Duan J, Biffi C, de Marvao A, Howard L . Deep learning cardiac motion analysis for human survival prediction. Nat Mach Intell. 2019; 1:95-104. PMC: 6382062. DOI: 10.1038/s42256-019-0019-2. View

19.

Zheng Q, Delingette H, Duchateau N, Ayache N . 3-D Consistent and Robust Segmentation of Cardiac Images by Deep Learning With Spatial Propagation. IEEE Trans Med Imaging. 2018; 37(9):2137-2148. DOI: 10.1109/TMI.2018.2820742. View

20.

Grothues F, Smith G, Moon J, Bellenger N, Collins P, Klein H . Comparison of interstudy reproducibility of cardiovascular magnetic resonance with two-dimensional echocardiography in normal subjects and in patients with heart failure or left ventricular hypertrophy. Am J Cardiol. 2002; 90(1):29-34. DOI: 10.1016/s0002-9149(02)02381-0. View