Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation

Rajamani, Kumar; Siebert, Hanna; Heinrich, Mattias P.

doi:10.1016/j.jbi.2021.103816

Cited by 21 publications

(14 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, a number of attempts of using semantic segmentation in medical imaging have been made. We have seen its application from the microscopic scale of segmenting red blood cells for sickle cell disease ( 16 ) to segmenting the COVID-19 infection area from chest CT ( 19 ) or lesions from endoscope images ( 22 ). However, the above-mentioned applications are mostly single-labeled tasks, using a large training set to achieve an organ or lesion recognition task.…”

Section: Discussionmentioning

confidence: 99%

“…According to literatures, semantic segmentation algorithms are capable of detecting red blood cells for sickle cell disease in microscopic images ( 16 ); deciding the tumor border in pathological images ( 17 , 18 ); recognizing the infection area of coronavirus disease of 2019 (COVID-19) lesions on chest CTs ( 19 ); distinguishing the brachia plexus, fetal head, and lymph node from ultrasound images ( 20 ); segmenting the thalamus, caudate nucleus, and lenticular nucleus in brain MRI ( 21 ); and diagnosing gastrointestinal cancer margins during endoscopy ( 22 ). Aiming to optimize the surgical planning process, we have previously developed a fully automated 3-D reconstruction algorithm ( 23 ) to classify and reconstruct the pulmonary artery and vein.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels

Chen

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

BackgroundThe recognition of anatomical variants is essential in preoperative planning for lung cancer surgery. Although three-dimensional (3-D) reconstruction provided an intuitive demonstration of the anatomical structure, the recognition process remains fully manual. To render a semiautomated approach for surgery planning, we developed an artificial intelligence (AI)–based chest CT semantic segmentation algorithm that recognizes pulmonary vessels on lobular or segmental levels. Hereby, we present a retrospective validation of the algorithm comparing surgeons’ performance.MethodsThe semantic segmentation algorithm to be validated was trained on non-contrast CT scans from a single center. A retrospective pilot study was performed. An independent validation dataset was constituted by an arbitrary selection from patients who underwent lobectomy or segmentectomy in three institutions during Apr. 2020 to Jun. 2021. The golden standard of anatomical variants of each enrolled case was obtained via expert surgeons’ judgments based on chest CT, 3-D reconstruction, and surgical observation. The performance of the algorithm is compared against the performance of two junior thoracic surgery attendings based on chest CT.ResultsA total of 27 cases were included in this study. The overall case-wise accuracy of the AI model was 82.8% in pulmonary vessels compared to 78.8% and 77.0% for the two surgeons, respectively. Segmental artery accuracy was 79.7%, 73.6%, and 72.7%; lobular vein accuracy was 96.3%, 96.3%, and 92.6% by the AI model and two surgeons, respectively. No statistical significance was found. In subgroup analysis, the anatomic structure-wise analysis of the AI algorithm showed a significant difference in accuracies between different lobes (p = 0.012). Higher AI accuracy in the right-upper lobe (RUL) and left-lower lobe (LLL) arteries was shown. A trend of better performance in non-contrast CT was also detected. Most recognition errors by the algorithm were the misclassification of LA1+2 and LA3. Radiological parameters did not exhibit a significant impact on the performance of both AI and surgeons.ConclusionThe semantic segmentation algorithm achieves the recognition of the segmental pulmonary artery and the lobular pulmonary vein. The performance of the model approximates that of junior thoracic surgery attendings. Our work provides a novel semiautomated surgery planning approach that is potentially beneficial to lung cancer patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels

Chen

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…(a) Imaging data analysis . Rajamani et al [41] proposed a new deep learning model called the Dynamic Deformable Attention Network (DDANet) to accurately segment the lesion regions from the lung CT scans of COVID-19 patients.…”

Section: Other Topicsmentioning

confidence: 99%

“… Special Communication [40] Reservoir hosts prediction for COVID-19 by hybrid transfer learning model Yang, Y. Original Research Others (7) [41] Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation Rajamani, K. T. Original Research [42] An aberration detection-based approach for sentinel syndromic surveillance of COVID-19 and other novel influenza-like illnesses Wen, A. Original Research [43] IoT-based GPS assisted surveillance system with inter-WBAN geographic routing for pandemic situations Savasci Sen, S. Special Communication [44] Face mask detection using deep learning: An approach to reduce risk of Coronavirus spread Sethi, S. Original Research [45] Visual analytics of COVID-19 dissemination in Sao Paulo state, Brazil Marcilio-Jr, W. E. Original Research [46] COnVIDa: COVID-19 multidisciplinary data collection and dashboard Martinez Beltran, E. T. Special Communication [47] Factors influencing mHealth adoption and its impact on mental well-being during COVID-19 pandemic: A SEM-ANN approach Alam, M. M. D. Special Communication …”

Section: Introductionmentioning

confidence: 99%

Novel informatics approaches to COVID-19 Research: From methods to applications

Buckeridge

Wang

et al. 2022

Journal of Biomedical Informatics

View full text Add to dashboard Cite

“…Rajamani et al. ( 2021 ) proposed a dynamic deformable attention network (DDANet) for COVID-19 lesion semantic segmentation. The model is based on a deformable criss-cross attention block, which continuously learn sparse attention filter offsets to capture sufficient context information and improve segmentation performance.…”

Section: Related Workmentioning

confidence: 99%

DBF-Net: a semi-supervised dual-task balanced fusion network for segmenting infected regions from lung CT images

Zhang

Yuan

2022

Evolving Systems

View full text Add to dashboard Cite

Accurate segmentation of infected regions in lung computed tomography (CT) images is essential to improve the timeliness and effectiveness of treatment for coronavirus disease 2019 (COVID-19). However, the main difficulties in developing of lung lesion segmentation in COVID-19 are still the fuzzy boundary of the lung-infected region, the low contrast between the infected region and the normal trend region, and the difficulty in obtaining labeled data. To this end, we propose a novel dual-task consistent network framework that uses multiple inputs to continuously learn and extract lung infection region features, which is used to generate reliable label images (pseudo-labels) and expand the dataset. Specifically, we periodically feed multiple sets of raw and data-enhanced images into two trunk branches of the network; the characteristics of the lung infection region are extracted by a lightweight double convolution (LDC) module and fusiform equilibrium fusion pyramid (FEFP) convolution in the backbone. According to the learned features, the infected regions are segmented, and pseudo-labels are made based on the semi-supervised learning strategy, which effectively alleviates the semi-supervised problem of unlabeled data. Our proposed semi-supervised dual-task balanced fusion network (DBF-Net) creates pseudo-labels on the COVID-SemiSeg dataset and the COVID-19 CT segmentation dataset. Furthermore, we perform lung infection segmentation on the DBF-Net model, with a segmentation sensitivity of 70.6% and specificity of 92.8%. The results of the investigation indicate that the proposed network greatly enhances the segmentation ability of COVID-19 infection.

show abstract

Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation

Cited by 21 publications

References 29 publications

AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels

AI-based chest CT semantic segmentation algorithm enables semi-automated lung cancer surgery planning by recognizing anatomical variants of pulmonary vessels

Novel informatics approaches to COVID-19 Research: From methods to applications

DBF-Net: a semi-supervised dual-task balanced fusion network for segmenting infected regions from lung CT images

Contact Info

Product

Resources

About