{"title":"A Multi-Scale Self-Attention Network to Discriminate Pulmonary Nodules","authors":"A. Moreno, A. Rueda, F. Martínez","doi":"10.1109/ISBI52829.2022.9761574","DOIUrl":null,"url":null,"abstract":"Lung cancer is the main cause of cancer-related deaths. Pulmonary nodules are the principal disease indicator, whose malignancy is mainly related with textural and geometrical patterns. Different computational alternatives have been proposed so far in the literature to support lung nodule characterization, however, they remain limited to properly capture the geometrical signatures that discriminate between each malignant class. This work introduces a multi-scale self-attention (MSA) network that accurately recovers geometrical and textural nodule maps. At each hierarchical level is recovered a set of saliency nodule maps that find non-local nodule correlations, properly representing radiological finding patterns. Validation was performed on the LICD-IDRI dataset, obtaining classification percentages that outperform the state of the art: 95.56% in accuracy, and 98.67% in AUC.","PeriodicalId":6827,"journal":{"name":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","volume":"31 1","pages":"1-4"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISBI52829.2022.9761574","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Lung cancer is the main cause of cancer-related deaths. Pulmonary nodules are the principal disease indicator, whose malignancy is mainly related with textural and geometrical patterns. Different computational alternatives have been proposed so far in the literature to support lung nodule characterization, however, they remain limited to properly capture the geometrical signatures that discriminate between each malignant class. This work introduces a multi-scale self-attention (MSA) network that accurately recovers geometrical and textural nodule maps. At each hierarchical level is recovered a set of saliency nodule maps that find non-local nodule correlations, properly representing radiological finding patterns. Validation was performed on the LICD-IDRI dataset, obtaining classification percentages that outperform the state of the art: 95.56% in accuracy, and 98.67% in AUC.