DECAPS: Detail-Oriented Capsule Networks

Mobiny, Aryan; Yuan, Pengyu; Cicalese, Pietro Antonio; Nguyen, Hien Van

doi:10.1007/978-3-030-59710-8_15

Cited by 47 publications

(23 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep neural networks (DNNs) have revolutionized various applied fields, including engineering and computer science (such as AI, language processing and computer vision) [1][2][3][4] , as well as the classical sciences (such as biology, physics, and medicine) [5][6][7][8] . DNNs can learn abstract concepts and extract desirable information from some high dimensional input.…”

mentioning

confidence: 99%

DropConnect is effective in modeling uncertainty of Bayesian deep networks

Mobiny

Yuan

Moulik³

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

Deep neural networks (DNNs) have achieved state-of-the-art performance in many important domains, including medical diagnosis, security, and autonomous driving. In domains where safety is highly critical, an erroneous decision can result in serious consequences. While a perfect prediction accuracy is not always achievable, recent work on Bayesian deep networks shows that it is possible to know when DNNs are more likely to make mistakes. Knowing what DNNs do not know is desirable to increase the safety of deep learning technology in sensitive applications; Bayesian neural networks attempt to address this challenge. Traditional approaches are computationally intractable and do not scale well to large, complex neural network architectures. In this paper, we develop a theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights. This method called Monte Carlo DropConnect (MC-DropConnect) gives us a tool to represent the model uncertainty with little change in the overall model structure or computational cost. We extensively validate the proposed algorithm on multiple network architectures and datasets for classification and semantic segmentation tasks. We also propose new metrics to quantify uncertainty estimates. This enables an objective comparison between MC-DropConnect and prior approaches. Our empirical results demonstrate that the proposed framework yields significant improvement in both prediction accuracy and uncertainty estimation quality compared to the state of the art.

show abstract

mentioning

confidence: 99%

DropConnect is effective in modeling uncertainty of Bayesian deep networks

Mobiny

Yuan

Moulik³

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…A novel learning architecture called Detail-Oriented Capsule Networks (DECAPS) was proposed for the automatic diagnosis of COVID-19 from CT scans. The model achieved 84.3% precision, 91.5% recall, and 96.1% AUC [ 13 ]. Another study introduced COVID-Net, a deep CNN design that was tailored to detect COVID-19 cases based on chest X-ray images [ 14 ].…”

Section: Resultsmentioning

confidence: 99%

“…Li et al [ 12 ] developed a neural network (COVNet) to extract visual features and modified a residual network with 50 layers to detect COVID-19 using CT scans. Mobiny et al [ 13 ] developed a Detail-Oriented Capsule Networks (DECAPS) learning architecture that could identify fine-grained and distinguishing image features to classify COVID-19 based on CT scans. Wang et al [ 14 ] introduced a COVID-Net for the automatic interpretation of chest radiographs from COVID patients.…”

Section: Introductionmentioning

confidence: 99%

Computed Tomography Image Processing Analysis in COVID-19 Patient Follow-Up Assessment

Tello-Mijares

Woo

2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The rapid worldwide spread of the COVID-19 pandemic has infected patients around the world in a short space of time. Chest computed tomography (CT) images of patients who are infected with COVID-19 can offer early diagnosis and efficient forecast monitoring at a low cost. The diagnosis of COVID-19 on CT in an automated way can speed up many tasks and the application of medical treatments. This can help complement reverse transcription-polymerase chain reaction (RT-PCR) diagnosis. The aim of this work is to develop a system that automatically identifies ground-glass opacity (GGO) and pulmonary infiltrates (PIs) on CT images from patients with COVID-19. The purpose is to assess the disease progression during the patient’s follow-up assessment and evaluation. We propose an efficient methodology that incorporates oversegmentation mean shift followed by superpixel-SLIC (simple linear iterative clustering) algorithm on CT images with COVID-19 for pulmonary parenchyma segmentation. To identify the pulmonary parenchyma, we described each superpixel cluster according to its position, grey intensity, second-order texture, and spatial-context-saliency features to classify by a tree random forest (TRF). Second, by applying the watershed segmentation to the mean-shift clusters, only pulmonary parenchyma segmentation-identified zones showed GGO and PI based on the description of each watershed cluster of its position, grey intensity, gradient entropy, second-order texture, Euclidean position to the border region of the PI zone, and global saliency features, after using TRF. Our classification results for pulmonary parenchyma identification on CT images with COVID-19 had a precision of over 92% and recall of over 92% on twofold cross validation. For GGO, the PI identification showed 96% precision and 96% recall on twofold cross validation.

show abstract

“…Most research is conducted on CT images, but many of them do not exploit the 3D information of CT images, such as the work by [10], [13], [14]. They only propose the DL models with 2D CNNs for COVID-19 detection.…”

Section: Related Workmentioning

confidence: 99%

Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans

Wang

Shi

et al. 2020

Preprint

View full text Add to dashboard Cite

COVID-19 pandemic has spread all over the world for months. As its transmissibility and high pathogenicity seriously threaten people's lives, the accurate and fast detection of the COVID-19 infection is crucial. Although many recent studies have shown that deep learning based solutions can help detect COVID-19 based on chest CT scans, there lacks a consistent and systematic comparison and evaluation on these techniques. In this paper, we first build a clean and segmented CT dataset called Clean-CC-CCII by fixing the errors and removing some noises in a large CT scan dataset CC-CCII with three classes: novel coronavirus pneumonia (NCP), common pneumonia (CP), and normal controls (Normal). After cleaning, our dataset consists of a total of 340,190 slices of 3,993 scans from 2,698 patients. Then we benchmark and compare the performance of a series of state-of-the-art (SOTA) 3D and 2D convolutional neural networks (CNNs). The results show that 3D CNNs outperform 2D CNNs in general. With extensive effort of hyperparameter tuning, we find that the 3D CNN model DenseNet3D121 achieves the highest accuracy of 88.63% (F1-score is 88.14% and AUC is 0.940), and another 3D CNN model ResNet3D34 achieves the best AUC of 0.959 (accuracy is 87.83% and F1-score is 86.04%). We further demonstrate that the mixup data augmentation technique can largely improve the model performance. At last, we design an automated deep learning methodology to generate a lightweight deep learning model MNas3DNet41 that achieves an accuracy of 87.14%, F1-score of 87.25%, and AUC of 0.957, which are on par with the best models made by AI experts. The automated deep learning design is a promising methodology that can help health-care professionals develop effective deep learning models using their private data sets. Our Clean-CC-CCII dataset and source code are available at: https://github.com/arthursdays/HKBU\_HPML\_COVID-19.

show abstract

DECAPS: Detail-Oriented Capsule Networks

Cited by 47 publications

References 15 publications

DropConnect is effective in modeling uncertainty of Bayesian deep networks

DropConnect is effective in modeling uncertainty of Bayesian deep networks

Computed Tomography Image Processing Analysis in COVID-19 Patient Follow-Up Assessment

Benchmarking Deep Learning Models and Automated Model Design for COVID-19 Detection with Chest CT Scans

Contact Info

Product

Resources

About