TY - GEN
T1 - A DEEP ENSEMBLE LEARNING APPROACH TO LUNG CT SEGMENTATION FOR COVID-19 SEVERITY ASSESSMENT
AU - Ben-Haim, Tal
AU - Sofer, Ron Moshe
AU - Ben-Arie, Gal
AU - Shelef, Ilan
AU - Raviv, Tammy Riklin
N1 - Funding Information:
This study was partially supported by the Israel Ministry of Science, Technology and Space (MOST 3-16902 T.R.R.).
Publisher Copyright:
© 2022 IEEE.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - We present a novel deep learning approach to categorical segmentation of lung CTs of COVID-19 patients. Specifically, we partition the scans into healthy lung tissues, non-lung regions, and two different, yet visually similar, pathological lung tissues, namely, ground-glass opacity and consolidation. This is accomplished via a unique, end-to-end hierarchical network architecture and ensemble learning, which contribute to the segmentation and provide a measure for segmentation uncertainty. The proposed framework achieves competitive results and outstanding generalization capabilities for three COVID-19 datasets. Our method is ranked second in a public Kaggle competition for COVID-19 CT images segmentation. Moreover, segmentation uncertainty regions are shown to correspond to the disagreements between the manual annotations of two different radiologists. Finally, preliminary promising correspondence results are shown for our private dataset when comparing the patients' COVID-19 severity scores (based on clinical measures), and the segmented lung pathologies. Code and data are available at our repository.
AB - We present a novel deep learning approach to categorical segmentation of lung CTs of COVID-19 patients. Specifically, we partition the scans into healthy lung tissues, non-lung regions, and two different, yet visually similar, pathological lung tissues, namely, ground-glass opacity and consolidation. This is accomplished via a unique, end-to-end hierarchical network architecture and ensemble learning, which contribute to the segmentation and provide a measure for segmentation uncertainty. The proposed framework achieves competitive results and outstanding generalization capabilities for three COVID-19 datasets. Our method is ranked second in a public Kaggle competition for COVID-19 CT images segmentation. Moreover, segmentation uncertainty regions are shown to correspond to the disagreements between the manual annotations of two different radiologists. Finally, preliminary promising correspondence results are shown for our private dataset when comparing the patients' COVID-19 severity scores (based on clinical measures), and the segmented lung pathologies. Code and data are available at our repository.
KW - Categorical Segmentation
KW - COVID-19
KW - Deep Learning
KW - Lung CT
KW - Severity Assessment
UR - http://www.scopus.com/inward/record.url?scp=85145471473&partnerID=8YFLogxK
U2 - 10.1109/ICIP46576.2022.9897656
DO - 10.1109/ICIP46576.2022.9897656
M3 - Conference contribution
AN - SCOPUS:85145471473
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 151
EP - 155
BT - 2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers
T2 - 29th IEEE International Conference on Image Processing, ICIP 2022
Y2 - 16 October 2022 through 19 October 2022
ER -