Lung Segmentation from Chest X-rays using Variational Data Imputation

Research output: Contribution to journal › Conference article › Research

Standard

Lung Segmentation from Chest X-rays using Variational Data Imputation. / Selvan, Raghavendra; Dam, Erik B.; Rischel, Sofus; Sheng, Kaining; Nielsen, Mads; Pai, Akshay.

In: OpenReview.net, 20.05.2020.

Research output: Contribution to journal › Conference article › Research

Harvard

Selvan, R, Dam, EB, Rischel, S, Sheng, K, Nielsen, M & Pai, A 2020, 'Lung Segmentation from Chest X-rays using Variational Data Imputation', OpenReview.net.

APA

Selvan, R., Dam, E. B., Rischel, S., Sheng, K., Nielsen, M., & Pai, A. (2020). Lung Segmentation from Chest X-rays using Variational Data Imputation. OpenReview.net.

Vancouver

Selvan R, Dam EB, Rischel S, Sheng K, Nielsen M, Pai A. Lung Segmentation from Chest X-rays using Variational Data Imputation. OpenReview.net. 2020 May 20.

Author

Selvan, Raghavendra ; Dam, Erik B. ; Rischel, Sofus ; Sheng, Kaining ; Nielsen, Mads ; Pai, Akshay. / Lung Segmentation from Chest X-rays using Variational Data Imputation. In: OpenReview.net. 2020.

Bibtex

@inproceedings{1259f468c8524f3b96941f2a70e23f8e,

title = "Lung Segmentation from Chest X-rays using Variational Data Imputation",

abstract = "Pulmonary opacification is the inflammation in the lungs caused by many respiratory ailments, including the novel corona virus disease 2019 (COVID-19). Chest X-rays (CXRs) with such opacifications render regions of lungs imperceptible, making it difficult to perform automated image analysis on them. In this work, we focus on segmenting lungs from such abnormal CXRs as part of a pipeline aimed at automated risk scoring of COVID-19 from CXRs. We treat the high opacity regions as missing data and present a modified CNN-based image segmentation network that utilizes a deep generative model for data imputation. We train this model on normal CXRs with extensive data augmentation and demonstrate the usefulness of this model to extend to cases with extreme abnormalities.",

keywords = "eess.IV, cs.CV, cs.LG, stat.ML",

author = "Raghavendra Selvan and Dam, {Erik B.} and Sofus Rischel and Kaining Sheng and Mads Nielsen and Akshay Pai",

note = "Source code, training data and the trained models are available here: https://github.com/raghavian/lungVAE/; ICML Workshop on Learning with Missing Values , Artemiss ; Conference date: 17-07-2020",

year = "2020",

month = may,

day = "20",

language = "English",

journal = "OpenReview.net",

url = "https://openreview.net/group?id=ICML.cc/2020/Workshop/Artemiss",

}

RIS

TY - GEN

T1 - Lung Segmentation from Chest X-rays using Variational Data Imputation

AU - Selvan, Raghavendra

AU - Dam, Erik B.

AU - Rischel, Sofus

AU - Sheng, Kaining

AU - Nielsen, Mads

AU - Pai, Akshay

N1 - Source code, training data and the trained models are available here: https://github.com/raghavian/lungVAE/

PY - 2020/5/20

Y1 - 2020/5/20

N2 - Pulmonary opacification is the inflammation in the lungs caused by many respiratory ailments, including the novel corona virus disease 2019 (COVID-19). Chest X-rays (CXRs) with such opacifications render regions of lungs imperceptible, making it difficult to perform automated image analysis on them. In this work, we focus on segmenting lungs from such abnormal CXRs as part of a pipeline aimed at automated risk scoring of COVID-19 from CXRs. We treat the high opacity regions as missing data and present a modified CNN-based image segmentation network that utilizes a deep generative model for data imputation. We train this model on normal CXRs with extensive data augmentation and demonstrate the usefulness of this model to extend to cases with extreme abnormalities.

AB - Pulmonary opacification is the inflammation in the lungs caused by many respiratory ailments, including the novel corona virus disease 2019 (COVID-19). Chest X-rays (CXRs) with such opacifications render regions of lungs imperceptible, making it difficult to perform automated image analysis on them. In this work, we focus on segmenting lungs from such abnormal CXRs as part of a pipeline aimed at automated risk scoring of COVID-19 from CXRs. We treat the high opacity regions as missing data and present a modified CNN-based image segmentation network that utilizes a deep generative model for data imputation. We train this model on normal CXRs with extensive data augmentation and demonstrate the usefulness of this model to extend to cases with extreme abnormalities.

KW - eess.IV

KW - cs.CV

KW - cs.LG

KW - stat.ML

UR - https://openreview.net/forum?id=dlzQM28tq2W&

M3 - Conference article

JO - OpenReview.net

JF - OpenReview.net

T2 - ICML Workshop on Learning with Missing Values

Y2 - 17 July 2020

ER -

ID: 255780946