Towards Symmetry-Aware Pneumonia Detection on Chest X-Rays

被引:2
作者
Schneider, Helen [1 ]
Lubbering, Max [1 ,2 ]
Kador, Rebecca [1 ]
Bross, Maximilian [1 ]
Priya, Priya [1 ]
Biesner, David [1 ]
Wulff, Benjamin [1 ]
de Oliveira, Thiago Bell Felix [1 ]
Layer, Yannik C. [3 ]
Attenberger, Ulrike I. [1 ,3 ]
Sifa, Rafet [1 ]
机构
[1] Fraunhofer IAIS, Dept Media Engn, St Augustin, Germany
[2] Univ Bonn, Dept Computersci, Bonn, Germany
[3] Univ Hosp Bonn, Dept Diagnost & Intervent Radiol, Bonn, Germany
来源
2022 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI) | 2022年
关键词
Siamese Network; Lung Abnormalities; Lung Region Symmetry;
D O I
10.1109/SSCI51031.2022.10022222
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Chest X-rays show elements of bilateral symmetry of the lung field, which can be disturbed by various lung diseases. These bilateral differences are taken into account by physicians during routine radiology examinations and form the basis for diagnosing various lung diseases. While for other medical computer vision tasks such as pelvic fracture detection the bilateral symmetry of the domain is already considered, this has not yet been sufficiently explored in the evaluation of chest X-rays to aid in the diagnosis of lung diseases. To this end, we developed a symmetry-aware deep learning architecture for the classification of bacterial and viral pneumonia, demonstrating the effectiveness of symmetry-aware models on lung conditions. Our work builds upon the idea of Siamese networks, which independently process the left and right lung and fuse the two learned representations in downstream layers for classification. Two different feature map fusion methods are implemented, by integrating a difference merging layer, and by concatenating the feature maps. It is shown that the performance of the network can be improved by symmetry-motivated adaptation of the architecture in terms of AUROC and F1 score by up to 0.8% and 2.0%, respectively, without the introduction of extended loss functions. In addition, our analysis of the activation maps illustrates that the focus of the network improves compared to the baseline model. Our proposed architecture focuses on the lung lobes without a region of interest crop, pinpointing the effectiveness of symmetry incorporation. By incorporating the prior medical knowledge of the bilateral symmetry of the lung field, a more data-efficient algorithm can be developed, leading to comparable performances with fewer data samples.
引用
收藏
页码:543 / 550
页数:8
相关论文
共 31 条
  • [1] Childhood Pneumonia as a Global Health Priority and the Strategic Interest of The Bill & Melinda Gates Foundation
    Adegbola, Richard A.
    [J]. CLINICAL INFECTIOUS DISEASES, 2012, 54 : S89 - S92
  • [2] Barman A, 2019, I S BIOMED IMAGING, P1873, DOI [10.1109/ISBI.2019.8759475, 10.1109/isbi.2019.8759475]
  • [3] Bromley J., 1993, International Journal of Pattern Recognition and Artificial Intelligence, V7, P669, DOI 10.1142/S0218001493000339
  • [4] Pneumonia Detection on Chest X-Ray Using Machine Learning Paradigm
    Chandra, Tej Bahadur
    Verma, Kesari
    [J]. PROCEEDINGS OF 3RD INTERNATIONAL CONFERENCE ON COMPUTER VISION AND IMAGE PROCESSING, CVIP 2018, VOL 1, 2020, 1022 : 21 - 33
  • [5] Ewig S., 2021, Leitlinie Behandlung von erwachsenen Patienten mit ambulant erworbener Pneumonie-Update 2021
  • [6] Classification of Bacterial and Viral Childhood Pneumonia Using Deep Learning in Chest Radiography
    Gu, Xianghong
    Pan, Liyan
    Liang, Huiying
    Yang, Ran
    [J]. PROCEEDINGS OF 2018 THE 3RD INTERNATIONAL CONFERENCE ON MULTIMEDIA AND IMAGE PROCESSING (ICMIP 2018), 2018, : 88 - 93
  • [7] Haomin Chen, 2020, Computer Vision - ECCV 2020. 16th European Conference. Proceedings. Lecture Notes in Computer Science (LNCS 12368), P239, DOI 10.1007/978-3-030-58592-1_15
  • [8] Deep and machine learning techniques for medical imaging-based breast cancer: A comprehensive review
    Houssein, Essam H.
    Emam, Marwa M.
    Ali, Abdelmgeid A.
    Suganthan, Ponnuthurai Nagaratnam
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2021, 167
  • [9] Densely Connected Convolutional Networks
    Huang, Gao
    Liu, Zhuang
    van der Maaten, Laurens
    Weinberger, Kilian Q.
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 2261 - 2269
  • [10] Irvin J, 2019, AAAI CONF ARTIF INTE, P590