{"title":"两两放射组学算法-病变对关系估计(PRE)模型鉴别多发性原发性肺癌(MPLC)与肺内转移(IPM)","authors":"Ting-Fei Chen, Lei Yang, Hai-Bin Chen, Zhi-Guo Zhou, Zhen-Tian Wu, Hong-He Luo, Qiong Li, Ying Zhu","doi":"10.1093/pcmedi/pbad029","DOIUrl":null,"url":null,"abstract":"Abstract Background Distinguishing multiple primary lung cancer (MPLC) from intrapulmonary metastasis (IPM) is critical for their disparate treatment strategy and prognosis. This study aimed to establish a non-invasive model to make the differentiation pre-operatively. Methods We retrospectively studied 168 patients with multiple lung cancers (307 pairs of lesions) including 118 cases for modeling and internal validation, and 50 cases for independent external validation. Radiomic features on computed tomography (CT) were extracted to calculate the absolute deviation of paired lesions. Features were then selected by correlation coefficients and random forest classifier five-fold cross-validation, based on which the lesion pair relation estimation (PRE) model was developed. A major voting strategy was used to decide diagnosis for cases with multiple pairs of lesions. Cases from another institute were included as the external validation set for the PRE model to compete with two experienced clinicians. Results Seven radiomic features were selected for the PRE model construction. With major voting strategy, the mean area under receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the training vs. internal validation vs. external validation cohort to distinguish MPLC were 0.983 vs. 0.844 vs. 0.793, 0.942 vs. 0.846 vs. 0.760, 0.905 vs. 0.728 vs. 0.727, and 0.962 vs. 0.910 vs. 0.769, respectively. AUCs of the two clinicians were 0.619 and 0.580. Conclusions The CT radiomic feature-based lesion PRE model is potentially an accurate diagnostic tool for the differentiation of MPLC and IPM, which could help with clinical decision making.","PeriodicalId":33608,"journal":{"name":"Precision Clinical Medicine","volume":null,"pages":null},"PeriodicalIF":5.1000,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A pairwise radiomics algorithm - lesion pair relation estimation (PRE) model for distinguishing multiple primary lung cancer (MPLC) from intrapulmonary metastasis (IPM)\",\"authors\":\"Ting-Fei Chen, Lei Yang, Hai-Bin Chen, Zhi-Guo Zhou, Zhen-Tian Wu, Hong-He Luo, Qiong Li, Ying Zhu\",\"doi\":\"10.1093/pcmedi/pbad029\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Background Distinguishing multiple primary lung cancer (MPLC) from intrapulmonary metastasis (IPM) is critical for their disparate treatment strategy and prognosis. This study aimed to establish a non-invasive model to make the differentiation pre-operatively. Methods We retrospectively studied 168 patients with multiple lung cancers (307 pairs of lesions) including 118 cases for modeling and internal validation, and 50 cases for independent external validation. Radiomic features on computed tomography (CT) were extracted to calculate the absolute deviation of paired lesions. Features were then selected by correlation coefficients and random forest classifier five-fold cross-validation, based on which the lesion pair relation estimation (PRE) model was developed. A major voting strategy was used to decide diagnosis for cases with multiple pairs of lesions. Cases from another institute were included as the external validation set for the PRE model to compete with two experienced clinicians. Results Seven radiomic features were selected for the PRE model construction. With major voting strategy, the mean area under receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the training vs. internal validation vs. external validation cohort to distinguish MPLC were 0.983 vs. 0.844 vs. 0.793, 0.942 vs. 0.846 vs. 0.760, 0.905 vs. 0.728 vs. 0.727, and 0.962 vs. 0.910 vs. 0.769, respectively. AUCs of the two clinicians were 0.619 and 0.580. Conclusions The CT radiomic feature-based lesion PRE model is potentially an accurate diagnostic tool for the differentiation of MPLC and IPM, which could help with clinical decision making.\",\"PeriodicalId\":33608,\"journal\":{\"name\":\"Precision Clinical Medicine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.1000,\"publicationDate\":\"2023-10-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Precision Clinical Medicine\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/pcmedi/pbad029\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MEDICINE, RESEARCH & EXPERIMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Precision Clinical Medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/pcmedi/pbad029","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
A pairwise radiomics algorithm - lesion pair relation estimation (PRE) model for distinguishing multiple primary lung cancer (MPLC) from intrapulmonary metastasis (IPM)
Abstract Background Distinguishing multiple primary lung cancer (MPLC) from intrapulmonary metastasis (IPM) is critical for their disparate treatment strategy and prognosis. This study aimed to establish a non-invasive model to make the differentiation pre-operatively. Methods We retrospectively studied 168 patients with multiple lung cancers (307 pairs of lesions) including 118 cases for modeling and internal validation, and 50 cases for independent external validation. Radiomic features on computed tomography (CT) were extracted to calculate the absolute deviation of paired lesions. Features were then selected by correlation coefficients and random forest classifier five-fold cross-validation, based on which the lesion pair relation estimation (PRE) model was developed. A major voting strategy was used to decide diagnosis for cases with multiple pairs of lesions. Cases from another institute were included as the external validation set for the PRE model to compete with two experienced clinicians. Results Seven radiomic features were selected for the PRE model construction. With major voting strategy, the mean area under receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the training vs. internal validation vs. external validation cohort to distinguish MPLC were 0.983 vs. 0.844 vs. 0.793, 0.942 vs. 0.846 vs. 0.760, 0.905 vs. 0.728 vs. 0.727, and 0.962 vs. 0.910 vs. 0.769, respectively. AUCs of the two clinicians were 0.619 and 0.580. Conclusions The CT radiomic feature-based lesion PRE model is potentially an accurate diagnostic tool for the differentiation of MPLC and IPM, which could help with clinical decision making.
期刊介绍:
Precision Clinical Medicine (PCM) is an international, peer-reviewed, open access journal that provides timely publication of original research articles, case reports, reviews, editorials, and perspectives across the spectrum of precision medicine. The journal's mission is to deliver new theories, methods, and evidence that enhance disease diagnosis, treatment, prevention, and prognosis, thereby establishing a vital communication platform for clinicians and researchers that has the potential to transform medical practice. PCM encompasses all facets of precision medicine, which involves personalized approaches to diagnosis, treatment, and prevention, tailored to individual patients or patient subgroups based on their unique genetic, phenotypic, or psychosocial profiles. The clinical conditions addressed by the journal include a wide range of areas such as cancer, infectious diseases, inherited diseases, complex diseases, and rare diseases.