TY - JOUR
T1 - Localization of lung abnormalities on chest X-rays using self-supervised equivariant attention
AU - D’Souza, Gavin
AU - Reddy, N. V.Subba
AU - Manjunath, K. N.
N1 - Funding Information:
We want to thank Prof. Dr. Ronald Summers [1], who has made this vast chest X-Ray clinical data collection available to the research community.
Publisher Copyright:
© 2022, The Author(s).
PY - 2023/2
Y1 - 2023/2
N2 - Chest X-Ray (CXR) images provide most anatomical details and the abnormalities on a 2D plane. Therefore, a 2D view of the 3D anatomy is sometimes sufficient for the initial diagnosis. However, close to fourteen commonly occurring diseases are sometimes difficult to identify by visually inspecting the images. Therefore, there is a drift toward developing computer-aided assistive systems to help radiologists. This paper proposes a deep learning model for the classification and localization of chest diseases by using image-level annotations. The model consists of a modified Resnet50 backbone for extracting feature corpus from the images, a classifier, and a pixel correlation module (PCM). During PCM training, the network is a weight-shared siamese architecture where the first branch applies the affine transform to the image before feeding to the network, while the second applies the same transform to the network output. The method was evaluated on CXR from the clinical center in the ratio of 70:20 for training and testing. The model was developed and tested using the cloud computing platform Google Colaboratory (NVidia Tesla P100 GPU, 16 GB of RAM). A radiologist subjectively validated the results. Our model trained with the configurations mentioned in this paper outperformed benchmark results.
AB - Chest X-Ray (CXR) images provide most anatomical details and the abnormalities on a 2D plane. Therefore, a 2D view of the 3D anatomy is sometimes sufficient for the initial diagnosis. However, close to fourteen commonly occurring diseases are sometimes difficult to identify by visually inspecting the images. Therefore, there is a drift toward developing computer-aided assistive systems to help radiologists. This paper proposes a deep learning model for the classification and localization of chest diseases by using image-level annotations. The model consists of a modified Resnet50 backbone for extracting feature corpus from the images, a classifier, and a pixel correlation module (PCM). During PCM training, the network is a weight-shared siamese architecture where the first branch applies the affine transform to the image before feeding to the network, while the second applies the same transform to the network output. The method was evaluated on CXR from the clinical center in the ratio of 70:20 for training and testing. The model was developed and tested using the cloud computing platform Google Colaboratory (NVidia Tesla P100 GPU, 16 GB of RAM). A radiologist subjectively validated the results. Our model trained with the configurations mentioned in this paper outperformed benchmark results.
UR - http://www.scopus.com/inward/record.url?scp=85141175648&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85141175648&partnerID=8YFLogxK
U2 - 10.1007/s13534-022-00249-5
DO - 10.1007/s13534-022-00249-5
M3 - Article
C2 - 36711159
AN - SCOPUS:85141175648
SN - 2093-9868
VL - 13
SP - 21
EP - 30
JO - Biomedical Engineering Letters
JF - Biomedical Engineering Letters
IS - 1
ER -