Explainable Vision Transformers and Radiomics for COVID-19 Detection in Chest X-rays

Chetoui, Mohamed; Akhloufi, Moulay A.

doi:10.3390/jcm11113013

Cited by 29 publications

(11 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As can be seen in Table 2 the accuracy of the model is 99.3%, precision is 99.0%, sensitivity is 99.5%, specificity is 99.0%, and F1-score% is 99.2%. For the chest X-ray dataset with 3 categories, we used the methods of Li (2021) [50], Shi (2021) [51], Mondal (2021) [40], Chetoui (2022) [38], and Pan (2023) [52] for comparison with our work. As can be seen in Table 2 the accuracy of the model is 96.8%, precision is 97.8%, sensitivity is 97.1%, specificity is 98.9%, and F1-score% is 97.4%.…”

Section: Results and Analysismentioning

confidence: 99%

“…For medical images, Komorowski et al ( 2023) investigated categories interpretation methods on the ViT and evaluated these methods based on loyalty, sensitivity, and complexity appropriately [37]. Chetoui et al (2022) [38] and Ukwuoma et al ( 2022) [39] are committed to using ViTs for COVID-19 detection and have made some basic interpretations for the results. XViT-COS [40] has been proposed for COVID-19 detection and offered explainability-driven with clinically interpretable visualizations.…”

Section: Vits For Covid-19 Detectionmentioning

confidence: 99%

“…Chetoui et al. (2022) [38] and Ukwuoma et al. (2022) [39] are committed to using ViTs for COVID‐19 detection and have made some basic interpretations for the results.…”

Section: Releated Workmentioning

confidence: 99%

See 2 more Smart Citations

Interpretable vision transformer based on prototype parts for COVID‐19 detection

Xu,

Meng

2024

IET Image Processing

View full text Add to dashboard Cite

Over the past few years, the COVID‐19 virus has had a significant impact on the physical and mental health of people around the world. Therefore, in order to effectively distinguish COVID‐19 patients, many deep learning efforts have used chest medical images to detect COVID‐19. As with model accuracy, interpretability is also important in the work related to human health. This work introduces an interpretable vision transformer that uses the prototype method for the detection of positive patients with COVID‐19. The model can learn the prototype features of each category based on the structural characteristics of ViT. The predictions of the model are obtained by comparing all the features of the prototype in the designed prototype block. The proposed model was applied to two chest X‐ray datasets and one chest CT dataset, achieving classification performance of 99.3%, 96.8%, and 98.5% respectively. Moreover, the prototype method can significantly improve the interpretability of the model. The decisions of the model can be interpreted based on prototype parts. In the prototype block, the entire inference process of the model can be shown and the predictions of the model can be demonstrated to be meaningful through the visualization of the prototype features.

show abstract

Section: Results and Analysismentioning

confidence: 99%

Section: Vits For Covid-19 Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Interpretable vision transformer based on prototype parts for COVID‐19 detection

Xu,

Meng

2024

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Thus, the implementation of this method in a high-volume diagnostic setting may be self-limiting; that is, the speed of validating the results depends on the availability of a radiologist and the volume of images to be reviewed [ 4 , 5 , 6 , 9 , 10 , 11 ]. Thus, the automatic detection of lung disease by AI is currently a highly valued and frequently evaluated concept in the fields of medical informatics research and radiology [ 4 , 12 ]. Several studies are already available.…”

Section: Introductionmentioning

confidence: 99%

Explainable COVID-19 Detection Based on Chest X-rays Using an End-to-End RegNet Architecture

Chetoui

Akhloufi

Bouattane

et al. 2023

Viruses

Self Cite

View full text Add to dashboard Cite

COVID-19,which is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is one of the worst pandemics in recent history. The identification of patients suspected to be infected with COVID-19 is becoming crucial to reduce its spread. We aimed to validate and test a deep learning model to detect COVID-19 based on chest X-rays. The recent deep convolutional neural network (CNN) RegNetX032 was adapted for detecting COVID-19 from chest X-ray (CXR) images using polymerase chain reaction (RT-PCR) as a reference. The model was customized and trained on five datasets containing more than 15,000 CXR images (including 4148COVID-19-positive cases) and then tested on 321 images (150 COVID-19-positive) from Montfort Hospital. Twenty percent of the data from the five datasets were used as validation data for hyperparameter optimization. Each CXR image was processed by the model to detect COVID-19. Multi-binary classifications were proposed, such as: COVID-19 vs. normal, COVID-19 + pneumonia vs. normal, and pneumonia vs. normal. The performance results were based on the area under the curve (AUC), sensitivity, and specificity. In addition, an explainability model was developed that demonstrated the high performance and high generalization degree of the proposed model in detecting and highlighting the signs of the disease. The fine-tuned RegNetX032 model achieved an overall accuracy score of 96.0%, with an AUC score of 99.1%. The model showed a superior sensitivity of 98.0% in detecting signs from CXR images of COVID-19 patients, and a specificity of 93.0% in detecting healthy CXR images. A second scenario compared COVID-19 + pneumonia vs. normal (healthy X-ray) patients. The model achieved an overall score of 99.1% (AUC) with a sensitivity of 96.0% and specificity of 93.0% on the Montfort dataset. For the validation set, the model achieved an average accuracy of 98.6%, an AUC score of 98.0%, a sensitivity of 98.0%, and a specificity of 96.0% for detection (COVID-19 patients vs. healthy patients). The second scenario compared COVID-19 + pneumonia vs. normal patients. The model achieved an overall score of 98.8% (AUC) with a sensitivity of 97.0% and a specificity of 96.0%. This robust deep learning model demonstrated excellent performance in detecting COVID-19 from chest X-rays. This model could be used to automate the detection of COVID-19 and improve decision making for patient triage and isolation in hospital settings. This could also be used as a complementary aid for radiologists or clinicians when differentiating to make smart decisions.

show abstract

“…In this work, we propose to perform the PCa aggressiveness classification task from T2w images by exploiting an ensemble of vision transformers(ViTs) [ 24 ]. ViTs are becoming increasingly popular in the medical imaging domain [ 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ], usually outperforming classical CNNs [ 35 , 36 ], which are one of the most significant networks in the deep learning field [ 37 ]. The existing literature typically employs ViTs in transfer learning scenarios by pre-training them on large datasets of natural images and fine-tuning them on specific datasets [ 27 , 28 , 38 ].…”

Section: Introductionmentioning

confidence: 99%

3D-Vision-Transformer Stacking Ensemble for Assessing Prostate Cancer Aggressiveness from T2w Images

Pachetti,

Colantonio

2023

Bioengineering

View full text Add to dashboard Cite

Vision transformers represent the cutting-edge topic in computer vision and are usually employed on two-dimensional data following a transfer learning approach. In this work, we propose a trained-from-scratch stacking ensemble of 3D-vision transformers to assess prostate cancer aggressiveness from T2-weighted images to help radiologists diagnose this disease without performing a biopsy. We trained 18 3D-vision transformers on T2-weighted axial acquisitions and combined them into two- and three-model stacking ensembles. We defined two metrics for measuring model prediction confidence, and we trained all the ensemble combinations according to a five-fold cross-validation, evaluating their accuracy, confidence in predictions, and calibration. In addition, we optimized the 18 base ViTs and compared the best-performing base and ensemble models by re-training them on a 100-sample bootstrapped training set and evaluating each model on the hold-out test set. We compared the two distributions by calculating the median and the 95% confidence interval and performing a Wilcoxon signed-rank test. The best-performing 3D-vision-transformer stacking ensemble provided state-of-the-art results in terms of area under the receiving operating curve (0.89 [0.61–1]) and exceeded the area under the precision–recall curve of the base model of 22% (p < 0.001). However, it resulted to be less confident in classifying the positive class.

show abstract

Explainable Vision Transformers and Radiomics for COVID-19 Detection in Chest X-rays

Cited by 29 publications

References 40 publications

Interpretable vision transformer based on prototype parts for COVID‐19 detection

Interpretable vision transformer based on prototype parts for COVID‐19 detection

Explainable COVID-19 Detection Based on Chest X-rays Using an End-to-End RegNet Architecture

3D-Vision-Transformer Stacking Ensemble for Assessing Prostate Cancer Aggressiveness from T2w Images

Contact Info

Product

Resources

About