Learning to detect chest radiographs containing pulmonary lesions using visual attention networks

Pesce, Emanuele; Withey, Samuel; Ypsilantis, Petros-Pavlos; Bakewell, Robert; Goh, Vicky; Montana, Giovanni

doi:10.1016/j.media.2018.12.007

Cited by 107 publications

(76 citation statements)

References 39 publications

(51 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The dataset used in this study was collected from the historical archives of the PACS (Picture Archiving and Communication System) at Guy's and St. Thomas' NHS Foundation Trust, in London, during the period from January 2005 to March 2016. The dataset has been previously used for the detection of lung nodules [14] and for multi-label metric learning [1]. It consists of 745 480 chest radiographs representative of an adult population and acquired using 40 different x-ray systems.…”

Section: Motivating Dataset and Problem Formulationmentioning

confidence: 99%

See 1 more Smart Citation

Longitudinal Detection of Radiological Abnormalities with Time-Modulated LSTM

Santeramo

Withey

Montana

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have been successfully employed in recent years for the detection of radiological abnormalities in medical images such as plain x-rays. To date, most studies use CNNs on individual examinations in isolation and discard previously available clinical information. In this study we set out to explore whether Long-Short-Term-Memory networks (LSTMs) can be used to improve classification performance when modelling the entire sequence of radiographs that may be available for a given patient, including their reports. A limitation of traditional LSTMs, though, is that they implicitly assume equally-spaced observations, whereas the radiological exams are event-based, and therefore irregularly sampled. Using both a simulated dataset and a large-scale chest x-ray dataset, we demonstrate that a simple modification of the LSTM architecture, which explicitly takes into account the time lag between consecutive observations, can boost classification performance. Our empirical results demonstrate improved detection of commonly reported abnormalities on chest x-rays such as cardiomegaly, consolidation, pleural effusion and hiatus hernia.

show abstract

Section: Motivating Dataset and Problem Formulationmentioning

confidence: 99%

“…Example of longitudinal x-rays for a given patient. [14,5]. For this study, we extracted a subset of 80 737 patients having a history of at least two exams, which resulted in 337 575 images (with 232 610 used for training and 104 965 for testing).…”

Section: Motivating Dataset and Problem Formulationmentioning

confidence: 99%

Longitudinal Detection of Radiological Abnormalities with Time-Modulated LSTM

Santeramo

Withey

Montana

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…They hold the view that the occurrence of disease is related to the age and gender of patient, so the identification accuracy can be improved by introducing these non-image features. Pesce et al 22 proposed a convolutional neural network with attention feedback to screen chest radiographs containing pulmonary nodules. The architecture has a localization capability, which improves the classification performance.…”

Section: Introductionmentioning

confidence: 99%

Dense networks with relative location awareness for thorax disease identification

et al. 2019

View full text Add to dashboard Cite

Purpose Chest X‐ray is one of the most common examinations for diagnosing heart and lung diseases. Due to the existing of a large number of clinical cases, many automated diagnosis algorithms based on chest X‐ray images have been proposed. To our knowledge, almost none of the previous auto‐diagnosis algorithms consider the effect of relative location information on disease incidence. In this study, we propose to use relative location information to assist the identification of thorax diseases. Method In this work, U‐Net is used to segment lung and heart from chest image. The relative location maps are computed through Euclidean distance transformation from segmented masks. By introducing the relative location information into the network, the usual location of disease is combined with the incidence. The proposed network is the fusion of two branches: mask branch and image branch. A mask branch is designed to be a bottom‐up and top‐down structure to extract relative location information. The structure has a large receptive field, which can extract more information for large lesion and contextual information for small lesion. The features learned from mask branch are fused with image branch, which is a 121‐layers DenseNet. Results We compare our proposed method with four state‐of‐the‐art methods on the largest public chest X‐ray dataset: ChestX‐ray14. The proposed method achieves the area under a curve of 0.820, which outperforms all the existing models and algorithms. Conclusion This paper proposed a dense network with relative location information to identify thorax disease. The method combines the usual location of disease with the incidence for the first time and performs good.

show abstract

“…Automatic analysis of chest X-rays is critical for diagnosis and treatment planning of thoracic diseases. Recently, several methods applying deep learning for automatic chest X-ray analysis [8,5,11,14,7] have been proposed. In particular, much work has focused on the ChestX-ray14 dataset [11], which is an unprecedentedly large-scale and rich dataset but only provides image-level labels for the far majority of the samples.…”

Section: Introductionmentioning

confidence: 99%

Iterative Attention Mining for Weakly Supervised Thoracic Disease Pattern Localization in Chest X-Rays

Cai

Lü

Harrison

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Given image labels as the only supervisory signal, we focus on harvesting, or mining, thoracic disease localizations from chest X-ray images. Harvesting such localizations from existing datasets allows for the creation of improved data sources for computer-aided diagnosis and retrospective analyses. We train a convolutional neural network (CNN) for image classification and propose an attention mining (AM) strategy to improve the model's sensitivity or saliency to disease patterns. The intuition of AM is that once the most salient disease area is blocked or hidden from the CNN model, it will pay attention to alternative image regions, while still attempting to make correct predictions. However, the model requires to be properly constrained during AM, otherwise, it may overfit to uncorrelated image parts and forget the valuable knowledge that it has learned from the original image classification task. To alleviate such side effects, we then design a knowledge preservation (KP) loss, which minimizes the discrepancy between responses for X-ray images from the original and the updated networks. Furthermore, we modify the CNN model to include multi-scale aggregation (MSA), improving its localization ability on small-scale disease findings, e.g., lung nodules. We experimentally validate our method on the publicly-available ChestX-ray14 dataset, outperforming a class activation map (CAM)-based approach, and demonstrating the value of our novel framework for mining disease locations.

show abstract

Learning to detect chest radiographs containing pulmonary lesions using visual attention networks

Cited by 107 publications

References 39 publications

Longitudinal Detection of Radiological Abnormalities with Time-Modulated LSTM

Longitudinal Detection of Radiological Abnormalities with Time-Modulated LSTM

Dense networks with relative location awareness for thorax disease identification

Iterative Attention Mining for Weakly Supervised Thoracic Disease Pattern Localization in Chest X-Rays

Contact Info

Product

Resources

About