Literature DB >> 35655823

Modeling long-range dependencies for weakly supervised disease classification and localization on chest X-ray.

Fangyun Li1, Lingxiao Zhou2, Yunpeng Wang1, Chuan Chen3, Shuyi Yang4,5, Fei Shan3, Lei Liu1,6.   

Abstract

Background: Computer-aided diagnosis based on chest X-ray (CXR) is an exponentially growing field of research owing to the development of deep learning, especially convolutional neural networks (CNNs). However, due to the intrinsic locality of convolution operations, CNNs cannot model long-range dependencies. Although vision transformers (ViTs) have recently been proposed to alleviate this limitation, those trained on patches cannot learn any dependencies for inter-patch pixels and thus, are insufficient for medical image detection. To address this problem, in this paper, we propose a CXR detection method which integrates CNN with a ViT for modeling patch-wise and inter-patch dependencies.
Methods: We experimented on the ChestX-ray14 dataset and followed the official training-test set split. Because the training data only had global annotations, the detection network was weakly supervised. A DenseNet with a feature pyramid structure was designed and integrated with an adaptive ViT to model inter-patch and patch-wise long-range dependencies and obtain fine-grained feature maps. We compared the performance using our method with that of other disease detection methods.
Results: For disease classification, our method achieved the best result among all the disease detection methods, with a mean area under the curve (AUC) of 0.829. For lesion localization, our method achieved significantly higher intersection of the union (IoU) scores on the test images with bounding box annotations than did the other detection methods. The visualized results showed that our predictions were more accurate and detailed. Furthermore, evaluation of our method in an external validation dataset demonstrated its generalization ability. Conclusions: Our proposed method achieves the new state of the art for thoracic disease classification and weakly supervised localization. It has potential to assist in clinical decision-making. 2022 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  Long-range dependencies; chest X-rays (CXRs); disease classification; localization; vision transformer (ViT)

Year:  2022        PMID: 35655823      PMCID: PMC9131331          DOI: 10.21037/qims-21-1117

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  12 in total

Review 1.  Advances in digital radiography: physical principles and system overview.

Authors:  Markus Körner; Christof H Weber; Stefan Wirth; Klaus-Jürgen Pfeifer; Maximilian F Reiser; Marcus Treitl
Journal:  Radiographics       Date:  2007 May-Jun       Impact factor: 5.333

Review 2.  A survey on deep learning in medical image analysis.

Authors:  Geert Litjens; Thijs Kooi; Babak Ehteshami Bejnordi; Arnaud Arindra Adiyoso Setio; Francesco Ciompi; Mohsen Ghafoorian; Jeroen A W M van der Laak; Bram van Ginneken; Clara I Sánchez
Journal:  Med Image Anal       Date:  2017-07-26       Impact factor: 8.545

3.  Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge.

Authors:  Arnaud Arindra Adiyoso Setio; Alberto Traverso; Thomas de Bel; Moira S N Berens; Cas van den Bogaard; Piergiorgio Cerello; Hao Chen; Qi Dou; Maria Evelina Fantacci; Bram Geurts; Robbert van der Gugten; Pheng Ann Heng; Bart Jansen; Michael M J de Kaste; Valentin Kotov; Jack Yu-Hung Lin; Jeroen T M C Manders; Alexander Sóñora-Mengana; Juan Carlos García-Naranjo; Evgenia Papavasileiou; Mathias Prokop; Marco Saletta; Cornelia M Schaefer-Prokop; Ernst T Scholten; Luuk Scholten; Miranda M Snoeren; Ernesto Lopez Torres; Jef Vandemeulebroucke; Nicole Walasek; Guido C A Zuidhof; Bram van Ginneken; Colin Jacobs
Journal:  Med Image Anal       Date:  2017-07-13       Impact factor: 8.545

4.  Attention-based VGG-16 model for COVID-19 chest X-ray image classification.

Authors:  Chiranjibi Sitaula; Mohammad Belayet Hossain
Journal:  Appl Intell (Dordr)       Date:  2020-11-17       Impact factor: 5.086

5.  A novel and reliable computational intelligence system for breast cancer detection.

Authors:  Amin Zadeh Shirazi; Seyyed Javad Seyyed Mahdavi Chabok; Zahra Mohammadi
Journal:  Med Biol Eng Comput       Date:  2017-09-11       Impact factor: 2.602

6.  Improvement diagnostic accuracy of sinusitis recognition in paranasal sinus X-ray using multiple deep learning models.

Authors:  Hyug-Gi Kim; Kyung Mi Lee; Eui Jong Kim; Jin San Lee
Journal:  Quant Imaging Med Surg       Date:  2019-06

Review 7.  Computer-aided detection in chest radiography based on artificial intelligence: a survey.

Authors:  Chunli Qin; Demin Yao; Yonghong Shi; Zhijian Song
Journal:  Biomed Eng Online       Date:  2018-08-22       Impact factor: 2.819

8.  New bag of deep visual words based features to classify chest x-ray images for COVID-19 diagnosis.

Authors:  Chiranjibi Sitaula; Sunil Aryal
Journal:  Health Inf Sci Syst       Date:  2021-06-18

9.  OPTICS-based Unsupervised Method for Flaking Degree Evaluation on the Murals in Mogao Grottoes.

Authors:  Pan Li; Meijun Sun; Zheng Wang; Bolong Chai
Journal:  Sci Rep       Date:  2018-10-29       Impact factor: 4.379

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.