Literature DB >> 34363582

Spectral augmentation for heart chambers segmentation on conventional contrasted and unenhanced CT scans: an in-depth study.

Pierre-Jean Lartaud1,2, David Hallé3, Arnaud Schleef3, Riham Dessouky4, Anna Sesilia Vlachomitrou5, Philippe Douek4,3, Jean-Michel Rouet5, Olivier Nempont5, Loïc Boussel4,3.   

Abstract

PURPOSE: Recently, machine learning has outperformed established tools for automated segmentation in medical imaging. However, segmentation of cardiac chambers still proves challenging due to the variety of contrast agent injection protocols used in clinical practice, inducing disparities of contrast between cavities. Hence, training a generalist network requires large training datasets representative of these protocols. Furthermore, segmentation on unenhanced CT scans is further hindered by the challenge of obtaining ground truths from these images. Newly available spectral CT scanners allow innovative image reconstructions such as virtual non-contrast (VNC) imaging, mimicking non-contrasted conventional CT studies from a contrasted scan. Recent publications have demonstrated that networks can be trained using VNC to segment contrasted and unenhanced conventional CT scans to reduce annotated data requirements and the need for annotations on unenhanced scans. We propose an extensive evaluation of this statement.
METHOD: We undertake multiple trainings of a 3D multi-label heart segmentation network with (HU-VNC) and without (HUonly) VNC as augmentation, using decreasing training dataset sizes (114, 76, 57, 38, 29, 19 patients). At each step, both networks are tested on a multi-vendor, multi-centric dataset of 122 patients, including different protocols: pulmonary embolism (PE), chest-abdomen-pelvis (CAP), heart CT angiography (CTA) and true non-contrast scans (TNC). An in-depth comparison of resulting Dice coefficients and distance metrics is performed for the networks trained on the largest dataset.
RESULTS: HU-VNC-trained on 57 patients significantly outperforms HUonly trained on 114 regarding CAP and TNC scans (mean Dice coefficients of 0.881/0.835 and 0.882/0.416, respectively). When trained on the largest dataset, significant improvements in all labels are noted for TNC and CAP scans (mean Dice coefficient of 0.882/0.416 and 0.891/0.835, respectively).
CONCLUSION: Adding VNC images as training augmentation allows the network to perform on unenhanced scans and improves segmentations on other imaging protocols, while using a reduced training dataset.
© 2021. CARS.

Entities:  

Keywords:  Data augmentation; Deep learning; Heart; Non-contrast CT; Segmentation; Spectral CT

Year:  2021        PMID: 34363582     DOI: 10.1007/s11548-021-02468-0

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  15 in total

1.  Automated aorta segmentation in low-dose chest CT images.

Authors:  Yiting Xie; Jennifer Padgett; Alberto M Biancardi; Anthony P Reeves
Journal:  Int J Comput Assist Radiol Surg       Date:  2013-07-23       Impact factor: 2.924

Review 2.  Machine learning in cardiac CT: Basic concepts and contemporary data.

Authors:  Gurpreet Singh; Subhi J Al'Aref; Marly Van Assen; Timothy Suyong Kim; Alexander van Rosendael; Kranthi K Kolli; Aeshita Dwivedi; Gabriel Maliakal; Mohit Pandey; Jing Wang; Virginie Do; Manasa Gummalla; Carlo N De Cecco; James K Min
Journal:  J Cardiovasc Comput Tomogr       Date:  2018-04-30

3.  Automatic multi-organ segmentation in dual-energy CT (DECT) with dedicated 3D fully convolutional DECT networks.

Authors:  Shuqing Chen; Xia Zhong; Shiyang Hu; Sabrina Dorn; Marc Kachelrieß; Michael Lell; Andreas Maier
Journal:  Med Phys       Date:  2020-01-01       Impact factor: 4.071

4.  Segmentation of bones in medical dual-energy computed tomography volumes using the 3D U-Net.

Authors:  José Carlos González Sánchez; Maria Magnusson; Michael Sandborg; Åsa Carlsson Tedgren; Alexandr Malusek
Journal:  Phys Med       Date:  2020-01-06       Impact factor: 2.685

5.  Automatic segmentation and quantification of the cardiac structures from non-contrast-enhanced cardiac CT scans.

Authors:  Rahil Shahzad; Daniel Bos; Ricardo P J Budde; Karlijn Pellikaan; Wiro J Niessen; Aad van der Lugt; Theo van Walsum
Journal:  Phys Med Biol       Date:  2017-03-01       Impact factor: 3.609

Review 6.  Machine learning in cardiovascular medicine: are we there yet?

Authors:  Khader Shameer; Kipp W Johnson; Benjamin S Glicksberg; Joel T Dudley; Partho P Sengupta
Journal:  Heart       Date:  2018-01-19       Impact factor: 5.994

7.  Deep learning from dual-energy information for whole-heart segmentation in dual-energy and single-energy non-contrast-enhanced cardiac CT.

Authors:  Steffen Bruns; Jelmer M Wolterink; Richard A P Takx; Robbert W van Hamersvelt; Dominika Suchá; Max A Viergever; Tim Leiner; Ivana Išgum
Journal:  Med Phys       Date:  2020-08-27       Impact factor: 4.071

8.  Automated 3D segmentation and diameter measurement of the thoracic aorta on non-contrast enhanced CT.

Authors:  Zahra Sedghi Gamechi; Lidia R Bons; Marco Giordano; Daniel Bos; Ricardo P J Budde; Klaus F Kofoed; Jesper Holst Pedersen; Jolien W Roos-Hesselink; Marleen de Bruijne
Journal:  Eur Radiol       Date:  2019-01-23       Impact factor: 5.315

Review 9.  Deep Learning for Cardiac Image Segmentation: A Review.

Authors:  Chen Chen; Chen Qin; Huaqi Qiu; Giacomo Tarroni; Jinming Duan; Wenjia Bai; Daniel Rueckert
Journal:  Front Cardiovasc Med       Date:  2020-03-05

10.  Evaluation of algorithms for Multi-Modality Whole Heart Segmentation: An open-access grand challenge.

Authors:  Xiahai Zhuang; Lei Li; Christian Payer; Darko Štern; Martin Urschler; Mattias P Heinrich; Julien Oster; Chunliang Wang; Örjan Smedby; Cheng Bian; Xin Yang; Pheng-Ann Heng; Aliasghar Mortazi; Ulas Bagci; Guanyu Yang; Chenchen Sun; Gaetan Galisot; Jean-Yves Ramel; Thierry Brouard; Qianqian Tong; Weixin Si; Xiangyun Liao; Guodong Zeng; Zenglin Shi; Guoyan Zheng; Chengjia Wang; Tom MacGillivray; David Newby; Kawal Rhode; Sebastien Ourselin; Raad Mohiaddin; Jennifer Keegan; David Firmin; Guang Yang
Journal:  Med Image Anal       Date:  2019-08-01       Impact factor: 8.545

View more
  2 in total

1.  Assessment of fully automatic segmentation of pulmonary artery and aorta on noncontrast CT with optimal surface graph cuts.

Authors:  Zahra Sedghi Gamechi; Andres M Arias-Lorza; Zaigham Saghir; Daniel Bos; Marleen de Bruijne
Journal:  Med Phys       Date:  2021-10-29       Impact factor: 4.506

2.  Automated 3D Segmentation of the Aorta and Pulmonary Artery on Non-Contrast-Enhanced Chest Computed Tomography Images in Lung Cancer Patients.

Authors:  Hao-Jen Wang; Li-Wei Chen; Hsin-Ying Lee; Yu-Jung Chung; Yan-Ting Lin; Yi-Chieh Lee; Yi-Chang Chen; Chung-Ming Chen; Mong-Wei Lin
Journal:  Diagnostics (Basel)       Date:  2022-04-12
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.