Lung Infection Quantification of COVID-19 in CT Images with Deep Learning

By Fei Shan, Yaozong Gao, Jun Wang, Weiya Shi, N. Shi, Miaofei Han, Zhong Xue, Dinggang Shen, Yuxin Shi. arXiv.org, 2020

586 citations recorded by the source corpus.

CT imaging is crucial for diagnosis, assessment and staging COVID-19 infection. Follow-up scans every 3-5 days are often recommended for disease progression. It has been reported that bilateral and peripheral ground glass opacification (GGO) with or without consolidation are predominant CT findings in COVID-19 patients. However, due to lack of computerized quantification tools, only qualitative impression and rough description of infected areas are currently used in radiological reports. In this paper, a deep learning (DL)-based segmentation system is developed to automatically quantify infection regions of interest (ROIs) and their volumetric ratios w.r.t. the lung. The performance of the system was evaluated by comparing the automatically segmented infection regions with the manually-delineated ones on 300 chest CT scans of 300 COVID-19 patients. For fast manual delineation of training samples and possible manual intervention of automatic results, a human-in-the-loop (HITL) strategy has been adopted to assist radiologists for infection region segmentation, which dramatically reduced the total segmentation time to 4 minutes after 3 iterations of model updating. The average Dice simiarility coefficient showed 91.6% agreement between automatic and manual infaction segmentations, and the mean estimation error of percentage of infection (POI) was 0.3% for the whole lung. Finally, possible applications, including but not limited to analysis of follow-up CT scans and infection distributions in the lobes and segments correlated with clinical findings, were discussed.

Subfields: Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/f41870a413cfed01b83d6463ca8492d9cc655d20

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Radiology, Nuclear Medicine and Imaging

1. Ceren Kaya
2. Ali Narin
3. Ziynet Pamuk
4. Quoc-Viet Pham
5. Ling Shao
6. Dinggang Shen
7. Jianbing Shen
8. Tao Zhou

Citations in the corpus

• The Role of Imaging in the Detection and Management of COVID-19: A Review (2020, methodology): “They first used VBNet [85] to segment infected areas, bilateral lungs, 5 lung lobes, and 18 lung pulmonary areas.”
• Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19 (2020, methodology): “The popular segmentation networks for COVID-19 include classic U-Net [51]–[56], UNet++ [57], [58], VB-Net [59].”
• Mapping the Landscape of Artificial Intelligence Applications against COVID-19 (2020, background): “Studies which report operational deployment, such as [77]† , have opted for human-inthe-loop approaches to reduce the analysis time required while utilizing ML architectures.”
• Classification of COVID-19 patients from chest CT images using multi-objective differential evolution–based convolutional neural networks (2020, methodology): “[26] developed a deep learning-based system named VB-net for automatic segmentation of all the lung and infection sites using chest CT. Xu et al.”
• A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images (2020, methodology): “Second, to reduce the annotation efforts, some researchers use a humanin-the-loop strategy [9], where the annotator only provides refinements to algorithm-generated labels for annotating.”
• Weakly Supervised Deep Learning for COVID-19 Infection Detection and Classification From CT Images (2020, methodology): “Coronavirus disease 2019 (COVID-19) has been widespread worldwide since December 2019 [1], [2].”
• Dual-Sampling Attention Network for Diagnosis of COVID-19 From Community Acquired Pneumonia (2020, methodology): “To demonstrate the effectiveness in diagnosing pneumonia of different severity, we use the VB-Net toolkit [10] to get the lung mask and the pneumonia infection regions for all CT images.”
• Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images (2020, methodology): “Although plenty of AI systems have been proposed to provide assistance in diagnosing COVID-19 in clinical practice, there are only a few works related infection segmentation in CT scans [21] , [22] .”
• JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation (2020, background): “, Dice score [71] and Intersection over Union (IoU).”
• Artificial Intelligence (AI) and Big Data for Coronavirus (COVID-19) Pandemic: A Survey on the State-of-the-Arts (2020, background): “Another work leveraging DL with CT images is in [60], where two measurement metrics: volume of infection and percentage of infection are quantified.”
• Improving performance of CNN to predict likelihood of COVID-19 using chest X-ray images with preprocessing algorithms (2020, background): “In other studies, Fei et al. [7] performed a deep learning based system on chest CT scan images to automatically segment and quantify the infected area by COVID-19.”