COVID-Net CXR-2: An Enhanced Deep Convolutional Neural Network Design for Detection of COVID-19 Cases From Chest X-ray Images

Pavlova, Maya; Terhljan, Naomi; Chung, Audrey G.; Zhao, Andy; Surana, Siddharth; Aboutalebi, Hossein; Gunraj, Hayden; Sabri, Ali; Alaref, Amer; Wong, Alexander

doi:10.3389/fmed.2022.861680

Cited by 22 publications

(9 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…COVIDx CXR-2 [41] and COVID Rural [12, 47] aim to evaluate on diagnosing COVID-19. COVIDx CXR-3 contains 29,986 images from 16,648 patients with COVID-19 classification labels.…”

Section: Methodsmentioning

confidence: 99%

“…We train the model on the most widely-used medical image-report dataset MIMIC-CXR [28] and rigorously evaluate on numerous public benchmarks, e.g ., ChestXray14 [50], RSNA Pneumonia [44], SIIM-ACR Pneumothorax [1], COVIDx CXR-2 [41], COVID Rural [12, 47], and EdemaSeverity [8]. We get a state-of-the-art zero-shot classification and grounding performance on different diseases, spanning different image distributions, with further fine-tuning, our model still exceeds previous models significantly.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, we consider the problem of enhancing self-supervised visual-language pre-training (VLP) with medical-specific knowledge, by exploiting the paired image-text reports from the radiological daily practice. In particular, we make the following contributions: First, unlike existing works that directly process the raw reports, we adopt a novel report filter to extract the medical entities, avoiding unnecessary complexity from language grammar and enhancing the supervision signals; Second, we propose a novel entity embedding module by querying an external knowledge description base, to exploit the rich context of additional information that the medical domain affords, and implicitly build relationships between entities in the language embedding space; Third, we propose a novel Transformer-based fusion model for spatially aligning the entity description with visual signals at the image patch level only with self-supervised learning, thus enabling the ability for spatial grounding; Fourth, we conduct thorough experiments to validate the effectiveness of our proposed architecture, and benchmark on numerous public benchmarks e.g., ChestX-ray14, RSNA Pneumonia, SIIM-ACR Pneumothorax, COVIDx CXR-2, COVID Rural, and EdemaSeverity. In both zero-shot and fine-tuning settings, our model has demonstrated strong performance compared with the former methods on disease classification and grounding.

show abstract

“…COVIDx CXR-2 [41] and COVID Rural [12, 47] aim to evaluate on diagnosing COVID-19. COVIDx CXR-3 contains 29,986 images from 16,648 patients with COVID-19 classification labels.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…COVIDx CXR-2 [41] and COVID Rural [12,47] Edema Severity [8] contains 6,524 examples from MIMIC-CXR with pulmonary edema severity labels (0 to 3, increasing severity) extracted from the radiology reports. Of these, 141 radiologists were examined by radiologists, and consensus was reached on severity level.…”

Section: Siim-acr Pneumothoraxmentioning

confidence: 99%

“…We train the model on the most widely-used medical image-report dataset MIMIC-CXR [28] and rigorously evaluate on numerous public benchmarks, e.g., ChestX-ray14 [50], RSNA Pneumonia [44], SIIM-ACR Pneumothorax [1], COVIDx CXR-2 [41], COVID Rural [12,47], and EdemaSeverity [8]. We get a state-of-the-art zero-shot classification and grounding performance on different diseases, spanning different image distributions, with further fine-tuning, our model still exceeds previous models significantly.…”

Section: Introductionmentioning

confidence: 99%

MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training

Wu¹,

Zhang²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

In this paper, we consider the problem of enhancing self-supervised visual-language pre-training (VLP) with medical-specific knowledge, by exploiting the paired imagetext reports from the radiological daily practice. In particular, we make the following contributions: First, unlike existing works that directly process the raw reports, we adopt a novel report filter to extract the medical entities, avoiding unnecessary complexity from language grammar and enhancing the supervision signals; Second, we propose a novel entity embedding module by querying an external knowledge description base, to exploit the rich context of additional information that the medical domain affords, and implicitly build relationships between entities in the language embedding space; Third, we propose a novel Transformer-based fusion model for spatially aligning the entity description with visual signals at the image patch level only with self-supervised learning, thus enabling the ability for spatial grounding; Fourth, we conduct thorough experiments to validate the effectiveness of our proposed architecture, and benchmark on numerous public benchmarks e.g., ChestX-ray14, RSNA Pneumonia, SIIM-ACR Pneumothorax, COVIDx CXR-2, COVID Rural, and Ede-maSeverity. In both zero-shot and fine-tuning settings, our model has demonstrated strong performance compared with the former methods on disease classification and grounding.

show abstract

“…This makes the development of appropriate models difficult. In this work we publish severity labels for the 2358 COVID-19 positive images in the COVIDx8B dataset 7 , 8 , creating one of the largest collections of publicly available COVID-19 severity data. The proposed severity scores range from 1 (mild) to 5 (critical) and have been verified and labeled by a dedicated thoracic radiologist (C.K.)…”

Section: Introductionmentioning

confidence: 99%

Augmentation strategies for an imbalanced learning problem on a novel COVID-19 severity dataset

Schaudt,

von Schwerin,

Hafner

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Since the beginning of the COVID-19 pandemic, many different machine learning models have been developed to detect and verify COVID-19 pneumonia based on chest X-ray images. Although promising, binary models have only limited implications for medical treatment, whereas the prediction of disease severity suggests more suitable and specific treatment options. In this study, we publish severity scores for the 2358 COVID-19 positive images in the COVIDx8B dataset, creating one of the largest collections of publicly available COVID-19 severity data. Furthermore, we train and evaluate deep learning models on the newly created dataset to provide a first benchmark for the severity classification task. One of the main challenges of this dataset is the skewed class distribution, resulting in undesirable model performance for the most severe cases. We therefore propose and examine different augmentation strategies, specifically targeting majority and minority classes. Our augmentation strategies show significant improvements in precision and recall values for the rare and most severe cases. While the models might not yet fulfill medical requirements, they serve as an appropriate starting point for further research with the proposed dataset to optimize clinical resource allocation and treatment.

show abstract

COVID-Net CXR-2: An Enhanced Deep Convolutional Neural Network Design for Detection of COVID-19 Cases From Chest X-ray Images

Cited by 22 publications

References 61 publications

MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training

MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training

MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training

Augmentation strategies for an imbalanced learning problem on a novel COVID-19 severity dataset

Contact Info

Product

Resources

About