{"title":"Automated lung tumor segmentation robust to various tumor sizes using a consistency learning-based multi-scale dual-attention network.","authors":"Jumin Lee, Min-Jin Lee, Bong-Seog Kim, Helen Hong","doi":"10.3233/XST-230003","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>It is often difficult to automatically segment lung tumors due to the large tumor size variation ranging from less than 1 cm to greater than 7 cm depending on the T-stage.</p><p><strong>Objective: </strong>This study aims to accurately segment lung tumors of various sizes using a consistency learning-based multi-scale dual-attention network (CL-MSDA-Net).</p><p><strong>Methods: </strong>To avoid under- and over-segmentation caused by different ratios of lung tumors and surrounding structures in the input patch according to the size of the lung tumor, a size-invariant patch is generated by normalizing the ratio to the average size of the lung tumors used for the training. Two input patches, a size-invariant patch and size-variant patch are trained on a consistency learning-based network consisting of dual branches that share weights to generate a similar output for each branch with consistency loss. The network of each branch has a multi-scale dual-attention module that learns image features of different scales and uses channel and spatial attention to enhance the scale-attention ability to segment lung tumors of different sizes.</p><p><strong>Results: </strong>In experiments with hospital datasets, CL-MSDA-Net showed an F1-score of 80.49%, recall of 79.06%, and precision of 86.78%. This resulted in 3.91%, 3.38%, and 2.95% higher F1-scores than the results of U-Net, U-Net with a multi-scale module, and U-Net with a multi-scale dual-attention module, respectively. In experiments with the NSCLC-Radiomics datasets, CL-MSDA-Net showed an F1-score of 71.7%, recall of 68.24%, and precision of 79.33%. This resulted in 3.66%, 3.38%, and 3.13% higher F1-scores than the results of U-Net, U-Net with a multi-scale module, and U-Net with a multi-scale dual-attention module, respectively.</p><p><strong>Conclusions: </strong>CL-MSDA-Net improves the segmentation performance on average for tumors of all sizes with significant improvements especially for small sized tumors.</p>","PeriodicalId":49948,"journal":{"name":"Journal of X-Ray Science and Technology","volume":"31 5","pages":"879-892"},"PeriodicalIF":1.7000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of X-Ray Science and Technology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3233/XST-230003","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}
引用次数: 0
Abstract
Background: It is often difficult to automatically segment lung tumors due to the large tumor size variation ranging from less than 1 cm to greater than 7 cm depending on the T-stage.
Objective: This study aims to accurately segment lung tumors of various sizes using a consistency learning-based multi-scale dual-attention network (CL-MSDA-Net).
Methods: To avoid under- and over-segmentation caused by different ratios of lung tumors and surrounding structures in the input patch according to the size of the lung tumor, a size-invariant patch is generated by normalizing the ratio to the average size of the lung tumors used for the training. Two input patches, a size-invariant patch and size-variant patch are trained on a consistency learning-based network consisting of dual branches that share weights to generate a similar output for each branch with consistency loss. The network of each branch has a multi-scale dual-attention module that learns image features of different scales and uses channel and spatial attention to enhance the scale-attention ability to segment lung tumors of different sizes.
Results: In experiments with hospital datasets, CL-MSDA-Net showed an F1-score of 80.49%, recall of 79.06%, and precision of 86.78%. This resulted in 3.91%, 3.38%, and 2.95% higher F1-scores than the results of U-Net, U-Net with a multi-scale module, and U-Net with a multi-scale dual-attention module, respectively. In experiments with the NSCLC-Radiomics datasets, CL-MSDA-Net showed an F1-score of 71.7%, recall of 68.24%, and precision of 79.33%. This resulted in 3.66%, 3.38%, and 3.13% higher F1-scores than the results of U-Net, U-Net with a multi-scale module, and U-Net with a multi-scale dual-attention module, respectively.
Conclusions: CL-MSDA-Net improves the segmentation performance on average for tumors of all sizes with significant improvements especially for small sized tumors.
期刊介绍:
Research areas within the scope of the journal include:
Interaction of x-rays with matter: x-ray phenomena, biological effects of radiation, radiation safety and optical constants
X-ray sources: x-rays from synchrotrons, x-ray lasers, plasmas, and other sources, conventional or unconventional
Optical elements: grazing incidence optics, multilayer mirrors, zone plates, gratings, other diffraction optics
Optical instruments: interferometers, spectrometers, microscopes, telescopes, microprobes