A Deep Ensemble Learning Approach to Lung CT Segmentation for Covid-19 Severity Assessment

Ben-Haim, Tal; Sofer, Ron Moshe; Ben-Arie, Gal; Shelef, Ilan; Raviv, Tammy Riklin

doi:10.1109/icip46576.2022.9897656

Cited by 3 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, using the basic U -Net as backbone [7] attained DSC 0.80. The Medseg (combination of CT-Seg and Seg-nr.2) dataset resulted in DSC 0.77 [31].…”

Section: Comparative Studymentioning

confidence: 99%

“…Well-known deep models, like U -Net [27], Residual U -Net [39], Attention U -Net [23], have been used for screening COVID-19. There exist ensemble methods for segmentation of CT images [7,11]. The Inception-V3, Xception, InceptionResNet-V2 and DenseNet-121 were ensembled [11] for a multiclass segmentation of GGO and Consolidation in COVID-19 CT data over the data CT-Seg (Table 1).…”

Section: Introductionmentioning

confidence: 99%

“…A cascade of two U -Nets, with VGG backbone, was ensembled [7] to extract the lung region, followed by the delineation of the GGO and consolidation regions. Multiclass segmentation of GGO and Consolidation was performed over CT-Seg, Seg-nr.2 and Kaggle-COVID-19 datasets (Table 1) along with some private dataset; while the training data contained parts of CT-Seg and Seg-nr.2, the remaining parts of the datasets were used for testing the model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Collective Intelligent Strategy for Improved Segmentation of COVID-19 from CT

Das

Shankar

2022

Preprint

View full text Add to dashboard Cite

The devastation caused by the coronavirus pandemic makes it imperative to design automated techniques for a fast and accurate detection. We propose a novel non-invasive tool, using deep learning and imaging, for delineating COVID-19 infection in lungs. The Ensembling Attention-based Multi-scaled Convolution network (EAMC), employing Leave-One-Patient-Out (LOPO) training, exhibits high sensitivity and precision in outlining infected regions along with assessment of severity. The Attention module combines contextual with local information, at multiple scales, for accurate segmentation. Ensemble learning integrates heterogeneity of decision through different base classifiers. The superiority of EAMC, even with severe class imbalance, is established through comparison with existing state-of-the-art learning models over four publicly-available COVID-19 datasets. The results are suggestive of the relevance of deep learning in providing assistive intelligence to medical practitioners, when they are overburdened with patients as in pandemics. Its clinical significance lies in its unprecedented scope in providing low-cost decision-making for patients lacking specialized healthcare at remote locations.

show abstract

“…On the other hand, using the basic U -Net as backbone [7] attained DSC 0.80. The Medseg (combination of CT-Seg and Seg-nr.2) dataset resulted in DSC 0.77 [31].…”

Section: Comparative Studymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Collective Intelligent Strategy for Improved Segmentation of COVID-19 from CT

Das

Shankar

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The DSC for the lungs was 0.96, whereas for COVID-19 infection, it was 0.81. Tal Ben-Haim et al [32] proposed a VGG backbone in the encoder of two UNets. The first UNet model segments the lung regions from CT images.…”

Section: Related Workmentioning

confidence: 99%

SAA-UNet: Spatial Attention and Attention Gate UNet for COVID-19 Pneumonia Segmentation from Computed Tomography

2023

View full text Add to dashboard Cite

The disaster of the COVID-19 pandemic has claimed numerous lives and wreaked havoc on the entire world due to its transmissible nature. One of the complications of COVID-19 is pneumonia. Different radiography methods, particularly computed tomography (CT), have shown outstanding performance in effectively diagnosing pneumonia. In this paper, we propose a spatial attention and attention gate UNet model (SAA-UNet) inspired by spatial attention UNet (SA-UNet) and attention UNet (Att-UNet) to deal with the problem of infection segmentation in the lungs. The proposed method was applied to the MedSeg, Radiopaedia 9P, combination of MedSeg and Radiopaedia 9P, and Zenodo 20P datasets. The proposed method showed good infection segmentation results (two classes: infection and background) with an average Dice similarity coefficient of 0.85, 0.94, 0.91, and 0.93 and a mean intersection over union (IOU) of 0.78, 0.90, 0.86, and 0.87, respectively, on the four datasets mentioned above. Moreover, it also performed well in multi-class segmentation with average Dice similarity coefficients of 0.693, 0.89, 0.87, and 0.93 and IOU scores of 0.68, 0.87, 0.78, and 0.89 on the four datasets, respectively. Classification accuracies of more than 97% were achieved for all four datasets. The F1-scores for the MedSeg, Radiopaedia P9, combination of MedSeg and Radiopaedia P9, and Zenodo 20P datasets were 0.865, 0.943, 0.917, and 0.926, respectively, for the binary classification. For multi-class classification, accuracies of more than 96% were achieved on all four datasets. The experimental results showed that the framework proposed can effectively and efficiently segment COVID-19 infection on CT images with different contrast and utilize this to aid in diagnosing and treating pneumonia caused by COVID-19.

show abstract