Abnormal lung quantification in chest CT images of COVID‐19 patients with deep learning and its application to severity prediction

Medical Physics - Tập 48 Số 4 - Trang 1633-1645 - 2021
Fei Shan1, Yaozong Gao2, Jun Wang3, Weiya Shi1, Nannan Shi1, Meisheng Han2, Zhong Xue2, Dinggang Shen4,2,5, Yuxin Shi1
1Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, 201508, China
2Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai 200232, China
3Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication, Shanghai Institute for Advanced Communication and Data Science, School of Communication & Information Engineering, Shanghai University, Shanghai, 200444 China
4Department of Artificial Intelligence, Korea University, Seoul 02841, Republic of Korea
5School of Biomedical Engineering, ShanghaiTech University, Shanghai, China

Tóm tắt

ObjectiveComputed tomography (CT) provides rich diagnosis and severity information of COVID‐19 in clinical practice. However, there is no computerized tool to automatically delineate COVID‐19 infection regions in chest CT scans for quantitative assessment in advanced applications such as severity prediction. The aim of this study was to develop a deep learning (DL)‐based method for automatic segmentation and quantification of infection regions as well as the entire lungs from chest CT scans.MethodsThe DL‐based segmentation method employs the “VB‐Net” neural network to segment COVID‐19 infection regions in CT scans. The developed DL‐based segmentation system is trained by CT scans from 249 COVID‐19 patients, and further validated by CT scans from other 300 COVID‐19 patients. To accelerate the manual delineation of CT scans for training, a human‐involved‐model‐iterations (HIMI) strategy is also adopted to assist radiologists to refine automatic annotation of each training case. To evaluate the performance of the DL‐based segmentation system, three metrics, that is, Dice similarity coefficient, the differences of volume, and percentage of infection (POI), are calculated between automatic and manual segmentations on the validation set. Then, a clinical study on severity prediction is reported based on the quantitative infection assessment.ResultsThe proposed DL‐based segmentation system yielded Dice similarity coefficients of 91.6% ± 10.0% between automatic and manual segmentations, and a mean POI estimation error of 0.3% for the whole lung on the validation dataset. Moreover, compared with the cases with fully manual delineation that often takes hours, the proposed HIMI training strategy can dramatically reduce the delineation time to 4 min after three iterations of model updating. Besides, the best accuracy of severity prediction was 73.4% ± 1.3% when the mass of infection (MOI) of multiple lung lobes and bronchopulmonary segments were used as features for severity prediction, indicating the potential clinical application of our quantification technique on severity prediction.ConclusionsA DL‐based segmentation system has been developed to automatically segment and quantify infection regions in CT scans of COVID‐19 patients. Quantitative evaluation indicated high accuracy in automatic infection delineation and severity prediction.

Từ khóa


Tài liệu tham khảo

10.1056/NEJMoa2001017

10.46234/ccdcw2020.017

10.1056/NEJMc2001272

10.1056/NEJMoa2001191

10.1016/S0140-6736(20)30185-9

10.1016/S0140-6736(20)30493-1

Wu F, 2000, A new coronavirus associated with human respiratory disease in China, Nature, 579, 1

GorbalenyaAE.Severe acute respiratory syndrome‐related coronavirus–The species and its viruses a statement of the Coronavirus Study Group. BioRxiv;2020.

WHO.Coronavirus disease 2019 (COVID‐19)Situation Report – 158.https://www.who.int/docs/default‐source/coronaviruse/situation‐reports/20200626‐covid‐19‐sitrep‐158.pdf?sfvrsn=1d1aae8a_2(accessed June 27th 2020).

10.1148/radiol.2020200343

10.1016/S0140-6736(20)30183-5

10.1001/jama.2020.1585

Dong D, 2020, The role of imaging in the detection and management of COVID‐19: a review, IEEE Rev Biomed Eng, 1

GozesO Frid‐AdarM GreenspanH et al.Rapid AI development cycle for the coronavirus (COVID‐19) pandemic: Initial results for automated detection & patient monitoring using deep learning CT image analysis. arXiv preprint arXiv:2003.05037;2020.

10.1016/S0140-6736(20)30211-7

ChassagnonG VakalopoulouM BattistellE et al.AI‐Driven CT‐based quantification staging and short‐term outcome prediction of COVID‐19 pneumonia. arXiv preprint arXiv:2004.12852;2020.

LiangT.The First Affiliated Hospital. In: Z. U. S. o. M Ed.Handbook of COVID‐19 Prevention and Treatment;2020.

10.1016/j.neuroimage.2010.02.025

10.1016/j.neuroimage.2011.07.036

MilletariF NavabN AhmadiS‐A.V‐net: Fully convolutional neural networks for volumetric medical image segmentation. In:2016 Fourth International Conference on 3D Vision (3DV);2016. IEEE: 565–571.

HeK ZhangX RenS SunJ.Deep residual learning for image recognition. In:Proceedings of the IEEE conference on computer vision and pattern recognition;2016:770–778.

HanM GaoY ZhangY et al.Large‐scale evaluation of V‐Net for organ segmentation in image guided radiation therapy. In:Medical Imaging 2019: Image‐Guided Procedures Robotic Interventions and Modeling 2019 vol. 10951: International Society for Optics and Photonics p. 109510O.

MuG MaY HanM et al.Automatic MR kidney segmentation for autosomal dominant polycystic kidney disease. In:Medical Imaging 2019: Computer‐Aided Diagnosis 2019 vol. 10950: International Society for Optics and Photonics p. 109500X.

Slicer Wiki.https://www.slicer.org/w/index.php?title=Main_Page&oldid=62645(accessed 2020).

10.1016/j.media.2013.12.001

10.1007/978-3-319-24574-4_28

10.1148/ryct.2020200082

10.1148/ryct.2020200075

10.1148/radiol.14132324

10.1056/NEJM199701233360402

Shah BA, 2010, Validity of pneumonia severity index and CURB‐65 severity scoring systems in community acquired pneumonia in an Indian setting, Indian J Chest Dis All Sci, 52, 9

10.1148/radiol.2020200370

10.1148/radiol.2020200274

10.1148/radiol.2020200463

Pang T, 2019, Automatic lung segmentation based on texture and deep features of HRCT images with interstitial lung disease, Biomed Res Int, 2019, 1, 10.1155/2019/2045432

10.1007/s10278-019-00254-8

Shi W, Deep learning‐based quantitative computed tomography model in predicting the severity of COVID‐19: A retrospective study in 196 patients, SSRN Elec J

ShiF WangJ ShiJ et al.Review of artificial intelligence techniques in imaging data acquisition segmentation and diagnosis for covid‐19. IEEE reviews in biomedical engineering;2020.

10.1109/TMI.2020.2995508

10.1109/TMI.2020.2992546

RaptisC HammerMM ShortRG et al.Chest CT and Coronavirus disease (COVID‐19): A critical review of the literature to date. AJR. American journal of roentgenology pp. 1‐4 04/16 2020.https://doi.org/10.2214/AJR.20.23202

A. C. o. R. (ACR).ACR recommendations for the use of chest radiography and computed tomography (CT) for suspected COVID‐19 infection.www.acr.org/Advocacy‐and‐Economics/ACR‐Position‐Statements/Recommendations‐for‐Chest‐Radiography‐and‐CT‐for‐Suspected‐COVID19‐Infection(accessed June 20th 2020).

LUNA16 ‐ Grand Challenge.https://luna16.grand‐challenge.org(accessed September 5th 2020).

10.1016/j.media.2017.01.008

Thông tin
Thông tin xuất bản

Medical Physics

Tập 48 Số 4

1633-1645

Thông tin tác giả