Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge

Roth, Holger R.; Xu, Ziyue; Díez, Carlos Tor; Jacob, Ramon Sanchez; Zember, Jonathan; Moltó, José; Li, Wenqi; Xu, Sheng; Türkbey, Barış; Türkbey, Evrim; Yang, Dong; Harouni, Ahmed; Rieke, Nicola; Hu, Shishuai; Isensee, Fabian; Tang, Claire; Yu, Qinji; Sölter, Jan; Zheng, Tong; Liauchuk, Vitali; Zhou, Ziqi; Moltz, Jan Hendrik; Oliveira, Bruno; Xia, Yong; Maier‐Hein, Klaus H.; Li, Qikai; Husch, Andreas; Kovalev, Vassili; Li, Kang; Hering, Alessa; Vilaça, João L.; Flores, Mona G.; Xu, Daguang; Wood, Bradford J.; Linguraru, Marius George

doi:10.21203/rs.3.rs-571332/v1

Cited by 29 publications

(24 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The literature has seen a wide number of CNN-based methodologies for automatic segmentation of lung abnormality on CT scan. Works may be divided in three categories: those that base the training on CT scans fully annotated by experts [ 21 , 27 ], those that make use of weak/noisy labels to lower the annotation load [ 20 , 28 , 29 ]) and those using transfer learning to transfer knowledge from non-COVID19 lesions [30] ). Regarding the network architectures, 2D CNNs [ 20 , 21 , 27 ] and 3D CNNs [ 27 , 28 , 30 ] are both represented.…”

Section: Discussionmentioning

confidence: 99%

Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT

Bartoli

Fournel

Maurin

et al. 2022

Research in Diagnostic and Interventional Imaging

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT

Bartoli

Fournel

Maurin

et al. 2022

Research in Diagnostic and Interventional Imaging

View full text Add to dashboard Cite

“…In addition to the lung tumor and pleural effusion datasets introduced before, we use LiTS dataset [9] with liver tumor annotations in abdominal CT volumes as non-COVID lesions in our method for comparison. Besides, to make comparison between intra-disease and interdisease relations, we use another multi-national CT dataset with labeled ground glass opacities [51] as an out-of-domain dataset for the learning of general branch, which is more relevant with similar appearance to the target dataset in our framework. In our experiments, we follow the settings of our 2D experiments with the same network backbone and implementation details.…”

Section: G Comparison On Different Datasets For Shared Knowledge Learningmentioning

confidence: 99%

Exploiting Shared Knowledge From Non-COVID Lesions for Annotation-Efficient COVID-19 CT Lung Infection Segmentation

Zhang

Liao

Yuan

et al. 2021

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

The novel Coronavirus disease (COVID-19) is a highly contagious virus and has spread all over the world, posing an extremely serious threat to all countries. Automatic lung infection segmentation from computed tomography (CT) plays an important role in the quantitative analysis of COVID-19. However, the major challenge lies in the inadequacy of annotated COVID-19 datasets. Currently, there are several public non-COVID lung lesion segmentation datasets, providing the potential for generalizing useful information to the related COVID-19 segmentation task. In this paper, we propose a novel relation-driven collaborative learning model to exploit shared knowledge from non-COVID lesions for annotation-efficient COVID-19 CT lung infection segmentation. The model consists of a general encoder to capture general lung lesion features based on multiple non-COVID lesions, and a target encoder to focus on task-specific features based on COVID-19 infections. We develop a collaborative learning scheme to regularize feature-level relation consistency of given input and encourage the model to learn more general and discriminative representation of COVID-19 infections. Extensive experiments demonstrate that trained with limited COVID-19 data, exploiting shared knowledge from non-COVID lesions can further improve state-of-the-art performance with up to 3.0% in dice similarity coefficient and 4.2% in normalized surface dice. In addition, experimental results on large scale 2D dataset with CT slices show that Manuscript

show abstract

“…The two datasets used in the experiments come from the Italian Society of Medical and Interventional Radiology obtaining a DSC~83%. To overcome the issue of proprietary data or single-site data, Roth et al [ 17 ] organized an international challenge and competition for the development and comparison of AI algorithms using public data. Consequently, this study aims to propose a customized Efficient Neural Network (ENET) to segment Covid-19 infections using the dataset provided by [ 17 ] for the experiments.…”

Section: Introductionmentioning

confidence: 99%

“…To overcome the issue of proprietary data or single-site data, Roth et al [ 17 ] organized an international challenge and competition for the development and comparison of AI algorithms using public data. Consequently, this study aims to propose a customized Efficient Neural Network (ENET) to segment Covid-19 infections using the dataset provided by [ 17 ] for the experiments. Specifically, ENET was originally proposed for real-time image delineation on low-power mobile devices [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

“…Consequently, this study aims to investigate how a DL network used for the parenchyma segmentation task in patients with IPF can be applied, with appropriate adjustments, to detect and segment COVID-19 infected lung regions. We explore the effectiveness of the customized ENET model, namely C-ENET, compared to other state-of-the-art models, namely UNET [ 24 ] and ERFNET [ 25 ], using the online COVID-19 Lung CT Lesion Segmentation Challenge—2020 (COVID-19-20) dataset [ 17 , 26 ]. The results show the great potential of the proposed network in automatically identifying and segmenting COVID-19 infected subregions for the subsequent extraction of quantitative features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Customized Efficient Neural Network for COVID-19 Infected Region Identification in CT Images

Stefano

Comelli

2021

J. Imaging

View full text Add to dashboard Cite

Background: In the field of biomedical imaging, radiomics is a promising approach that aims to provide quantitative features from images. It is highly dependent on accurate identification and delineation of the volume of interest to avoid mistakes in the implementation of the texture-based prediction model. In this context, we present a customized deep learning approach aimed at addressing the real-time, and fully automated identification and segmentation of COVID-19 infected regions in computed tomography images. Methods: In a previous study, we adopted ENET, originally used for image segmentation tasks in self-driving cars, for whole parenchyma segmentation in patients with idiopathic pulmonary fibrosis which has several similarities to COVID-19 disease. To automatically identify and segment COVID-19 infected areas, a customized ENET, namely C-ENET, was implemented and its performance compared to the original ENET and some state-of-the-art deep learning architectures. Results: The experimental results demonstrate the effectiveness of our approach. Considering the performance obtained in terms of similarity of the result of the segmentation to the gold standard (dice similarity coefficient ~75%), our proposed methodology can be used for the identification and delineation of COVID-19 infected areas without any supervision of a radiologist, in order to obtain a volume of interest independent from the user. Conclusions: We demonstrated that the proposed customized deep learning model can be applied to rapidly identify, and segment COVID-19 infected regions to subsequently extract useful information for assessing disease severity through radiomics analyses.

show abstract

Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge

Cited by 29 publications

References 48 publications

Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT

Value and prognostic impact of a deep learning segmentation model of COVID-19 lung lesions on low-dose chest CT

Exploiting Shared Knowledge From Non-COVID Lesions for Annotation-Efficient COVID-19 CT Lung Infection Segmentation

Customized Efficient Neural Network for COVID-19 Infected Region Identification in CT Images

Contact Info

Product

Resources

About