Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification

Pooch, Eduardo; Ballester, Pedro; Barros, Rodrigo C.

doi:10.48550/arxiv.1909.01940

Cited by 11 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We hypothesized a distributional difference in noise and texture characteristics between the data sources due to diverse conditions in X-ray equipment and their configurations for generating the images. We based our hypothesis on the recent findings (Pooch et al, 2019;Yao et al, 2019), which implicitly showed the existence of some characteristic differences between these data sources. This work has developed an explicit method to show the characteristic differences between the data sources.…”

Section: Discussionmentioning

confidence: 99%

Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation

Dubey¹,

Young²,

Stanley³

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep learning (DL) models are being deployed at medical centers to aid radiologists for diagnosis of lung conditions from chest radiographs. Such models are often trained on a large volume of publicly available labeled radiographs. These pre-trained DL models' ability to generalize in clinical settings is poor because of the changes in data distributions between publicly available and privately held radiographs. In chest radiographs, the heterogeneity in distributions arises from the diverse conditions in X-ray equipment and their configurations used for generating the images. In the machine learning community, the challenges posed by the heterogeneity in the data generation source is known as domain shift, which is a mode shift in the generative model. In this work, we introduce a domain-shift detection and removal method to overcome this problem. Our experimental results show the proposed method's effectiveness in deploying a pre-trained DL model for abnormality detection in chest radiographs in a clinical setting.

show abstract

Section: Discussionmentioning

confidence: 99%

Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation

Dubey¹,

Young²,

Stanley³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…1-2, one can observe that there are clear distribution shifts in these medical imaging data. However, many conventional machine learning methods ignore this problem, which would lead to performance degradation [26], [30]. Recently, domain adaptation has attracted increasing interests and attention of researchers, and become an important research topic in machine learning based medical image analysis [22], [31]- [33].…”

Section: A Domain Shift In Medical Image Analysismentioning

confidence: 99%

Domain Adaptation for Medical Image Analysis: A Survey

Guan,

Liu

2021

Preprint

View full text Add to dashboard Cite

Machine learning techniques used in computeraided medical image analysis usually suffer from the domain shift problem caused by different distributions between source/reference data and target data. As a promising solution, domain adaptation has attracted considerable attention in recent years. The aim of this paper is to survey the recent advances of domain adaptation methods in medical image analysis. We first present the motivation of introducing domain adaptation techniques to tackle domain heterogeneity issues for medical image analysis. Then we provide a review of recent domain adaptation models in various medical image analysis tasks. We categorize the existing methods into shallow and deep models, and each of them is further divided into supervised, semi-supervised and unsupervised methods. We also provide a brief summary of the benchmark medical image datasets that support current domain adaptation research. This survey will enable researchers to gain a better understanding of the current status, challenges and future directions of this energetic research field.

show abstract

“…The domain shift across different hospital settings is the main obstacle in transferring deep learning models into clinical practice [11]. It can result in poor generalization and decreased accuracy [4].…”

Section: Model Performance On External Test Setmentioning

confidence: 99%

DICOM Imaging Router: An Open Deep Learning Framework for Classification of Body Parts from DICOM X-ray Scans

Pham¹,

Do²,

Nguyen³

2021

Preprint

View full text Add to dashboard Cite

X-ray imaging in Digital Imaging and Communications in Medicine (DICOM) format is the most commonly used imaging modality in clinical practice, resulting in vast, nonnormalized databases. This leads to an obstacle in deploying artificial intelligence (AI) solutions for analyzing medical images, which often requires identifying the right body part before feeding the image into a specified AI model. This challenge raises the need for an automated and efficient approach to classifying body parts from X-ray scans. Unfortunately, to the best of our knowledge, there is no open tool or framework for this task to date. To fill this lack, we introduce a DICOM Imaging Router that deploys deep convolutional neural networks (CNNs) for categorizing unknown DICOM X-ray images into five anatomical groups: abdominal, adult chest, pediatric chest, spine, and others. To this end, a large-scale X-ray dataset consisting of 16,093 images has been collected and manually classified. We then trained a set of state-of-the-art deep CNNs using a training set of 11,263 images. These networks were then evaluated on an independent test set of 2,419 images and showed superior performance in classifying the body parts. Specifically, our best performing model (i.e., MobileNet-V1) achieved a recall of 0.982 (95% CI, 0.977-0.988), a precision of 0.985 (95% CI, 0.975-0.989) and a F1-score of 0.981 (95% CI, 0.976-0.987), whilst requiring less computation for inference (0.0295 second per image). Our external validity on 1,000 X-ray images shows the robustness of the proposed approach across hospitals. These remarkable performances indicate that deep CNNs can accurately and effectively differentiate human body parts from X-ray scans, thereby providing potential benefits for a wide range of applications in clinical settings. The dataset, codes, and trained deep learning models from this study will be made publicly available on our project website at https://vindr.ai/datasets/bodypartxr.

show abstract

Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification

Cited by 11 publications

References 13 publications

Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation

Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation

Domain Adaptation for Medical Image Analysis: A Survey

DICOM Imaging Router: An Open Deep Learning Framework for Classification of Body Parts from DICOM X-ray Scans

Contact Info

Product

Resources

About