A novel stacked generalization of models for improved TB detection in chest radiographs

Rajaraman, Sivaramakrishnan; Candemir, Sema; Xue, Zhiyun; Alderson, Philip O.; Kohli, Marc D.; Abuya, Joseph; Thoma, George R.

doi:10.1109/embc.2018.8512337

Cited by 52 publications

(44 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the component networks, which were trained on enface images from a single plexus, the shallower network of VGG19 performed better on this task than the deeper state-of-the-art networks. While there is some precedent for this, 33 it is expected that the ResNet or DenseNet architectures would perform better with more data. Although pretrained ResNet18 ImageNet weights are not currently available for use with Keras, this architecture may perform similarly or better than the VGG19 architecture.…”

Section: Discussionmentioning

confidence: 99%

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Heisler

Karst

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

To evaluate the role of ensemble learning techniques with deep learning in classifying diabetic retinopathy (DR) in optical coherence tomography angiography (OCTA) images and their corresponding co-registered structural images. Methods: A total of 463 volumes from 380 eyes were acquired using the 3 × 3-mm OCTA protocol on the Zeiss Plex Elite system. Enface images of the superficial and deep capillary plexus were exported from both the optical coherence tomography and OCTA data. Component neural networks were constructed using single data-types and fine-tuned using VGG19, ResNet50, and DenseNet architectures pretrained on ImageNet weights. These networks were then ensembled using majority soft voting and stacking techniques. Results were compared with a classifier using manually engineered features. Class activation maps (CAMs) were created using the original CAM algorithm and Grad-CAM. Results: The networks trained with the VGG19 architecture outperformed the networks trained on deeper architectures. Ensemble networks constructed using the four finetuned VGG19 architectures achieved accuracies of 0.92 and 0.90 for the majority soft voting and stacking methods respectively. Both ensemble methods outperformed the highest single data-type network and the network trained on hand-crafted features. Grad-CAM was shown to more accurately highlight areas of disease. Conclusions: Ensemble learning increases the predictive accuracy of CNNs for classifying referable DR on OCTA datasets. Translational Relevance: Because the diagnostic accuracy of OCTA images is shown to be greater than the manually extracted features currently used in the literature, the proposed methods may be beneficial toward developing clinically valuable solutions for DR diagnoses.

show abstract

Section: Discussionmentioning

confidence: 99%

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Heisler

Karst

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

show abstract

“…Previous histological examinations of biopsy samples collected from the lungs of COVID-19 patients showed diffuse alveolar damage with edema, cellular proteinaceous exudate, focal reactive pneumocytic hyperplasia with patchy inflammatory cellular infiltration, and multinucleated giant cells [14][15]. On CT, these lesions might appear as areas of ground glass opacity or consolidation [16]. Previous studies had successfully applied DL techniques to detect pneumonia in pediatric chest radiographs and chest CT [10,17].…”

Section: Discussionmentioning

confidence: 99%

Role of novel deep-learning-based CT used in management and discharge of COVID-19 patients at a “square cabin” hospital in China

Meng

Dou

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: The chest computed tomography (CT) had been used to define the diagnostic and discharge criteria for COVID-19. However, it is difficult to determine the suitability for discharge of a patient with COVID-19 based on CT features in a clinical setting. Deep learning (DL) technology has demonstrated great success in the medical imaging.Purpose: This study applied the novel deep learning (DL) on chest computed tomography (CT) of COVID-19 patients with consecutive negative respiratory pathogen nucleic acid test results at a “square cabin” hospital in Wuhan, China, with the intent to standardize criteria for discharge.Methods: The study included 270 patients (102men, 168 women; mean age, 51.9 ± 15.6[18–65] years) who had two consecutive negative respiratory pathogen tests (sampling interval: ≥1 day) and underwent low-dose CT 1 day after the first negative test, with strict adherence to epidemic prevention standards. The chest CT of COVID-19 patients with negative nucleic acid tests were evalued by DL, and the standard for discharge was a total volume ratio of lesions to lung of less than 50% determined by DL.Results: The average intersection over union is 0.7894. Fifty-seven (21.1%) and 213 (78.9%) patients exhibited normal lung findings and pneumonia, respectively. 54.0% (115/213) involved mild interstitial fibrosis. 18.8% (40/213) had total volume ratio of lesions to lung of more than and equal to 50% according to our severity scale and were monitored continuously in hospital, and three cases of which had a positive follow-up nucleic acid test during hospital observation. None of the 230 discharged cases later tested positive or exhibited pneumonia progression. Conclusions: The novel DL enables the accurate management of COVID-19 patients and can help avoid cluster transmission or exacerbation due to patients with false negitive acid test.

show abstract

“…Transfer Learning (TF) strategies are commonly adopted when limited data is available, e.g., medical images. Here, CNNs are trained on a large-scale selection of natural images and the learned knowledge is transferred and repurposed for the new task (Lopes & Valiati, 2017;Rajaraman et al, 2018a;Rajaraman et al, 2018b). However, unlike natural images, medical images exhibit different visual characteristics including color, texture, shape, appearance, and their combinations, and exhibit low intra-class variance and high inter-class similarity (Suzuki, 2017), e.g., CXRs.…”

Section: Introductionmentioning

confidence: 99%

“…The authors reported an average AUC of 0.841 and 0.871 with ResNet-50 and DenseNet-121 model backbones, respectively. Rajaraman et al (2018a) and Rajaraman et al (2018b) used model-agnostic visualization tools and generated class-specific mappings to localize ROI that is considered relevant for detecting pneumonia and further categorizing bacterial and viral pneumonia using pediatric CXRs. The performance of the customized and pretrained CNN models was statistically validated.…”

Section: Introductionmentioning

confidence: 99%

Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles

Rajaraman

Kim

Antani

2020

PeerJ

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) trained on natural images are extremely successful in image classification and localization due to superior automated feature extraction capability. In extending their use to biomedical recognition tasks, it is important to note that visual features of medical images tend to be uniquely different than natural images. There are advantages offered through training these networks on large scale medical common modality image collections pertaining to the recognition task. Further, improved generalization in transferring knowledge across similar tasks is possible when the models are trained to learn modality-specific features and then suitably repurposed for the target task. In this study, we propose modality-specific ensemble learning toward improving abnormality detection in chest X-rays (CXRs). CNN models are trained on a large-scale CXR collection to learn modality-specific features and then repurposed for detecting and localizing abnormalities. Model predictions are combined using different ensemble strategies toward reducing prediction variance and sensitivity to the training data while improving overall performance and generalization. Class-selective relevance mapping (CRM) is used to visualize the learned behavior of the individual models and their ensembles. It localizes discriminative regions of interest (ROIs) showing abnormal regions and offers an improved explanation of model predictions. It was observed that the model ensembles demonstrate superior localization performance in terms of Intersection of Union (IoU) and mean Average Precision (mAP) metrics than any individual constituent model.

show abstract

A novel stacked generalization of models for improved TB detection in chest radiographs

Cited by 52 publications

References 13 publications

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Role of novel deep-learning-based CT used in management and discharge of COVID-19 patients at a “square cabin” hospital in China

Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles

Contact Info

Product

Resources

About

A novel stacked generalization of models for improved TB detection in chest radiographs

Cited by 52 publications

References 13 publications

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Ensemble Deep Learning for Diabetic Retinopathy Detection Using Optical Coherence Tomography Angiography

Role of novel deep-learning-based CT&nbsp;used in management and discharge of COVID-19 patients at a “square cabin”&nbsp;hospital in China

Detection and visualization of abnormality in chest radiographs using modality-specific convolutional neural network ensembles

Contact Info

Product

Resources

About

Role of novel deep-learning-based CT used in management and discharge of COVID-19 patients at a “square cabin” hospital in China