Yasuhiro Fukushima, Keisuke Suzuki, Mai Kim, Wenchao Gu, Satoshi Yokoo, Yoshito Tsushima
{"title":"Evaluation of bone marrow invasion on the machine learning of 18 F-FDG PET texture analysis in lower gingival squamous cell carcinoma.","authors":"Yasuhiro Fukushima, Keisuke Suzuki, Mai Kim, Wenchao Gu, Satoshi Yokoo, Yoshito Tsushima","doi":"10.1097/MNM.0000000000001826","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Lower gingival squamous cell carcinoma (LGSCC) has the potential to invade the alveolar bone. Traditionally, the diagnosis of LGSCC relied on morphological imaging, but inconsistencies between these assessments and surgical findings have been observed. This study aimed to assess the correlation between LGSCC bone marrow invasion and PET texture features and to enhance diagnostic accuracy by using machine learning.</p><p><strong>Methods: </strong>A retrospective analysis of 159 LGSCC patients with pretreatment 18 F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) examination from 2009 to 2017 was performed. We extracted radiomic features from the PET images, focusing on pathologic bone marrow invasion detection. Extracted features underwent the least absolute shrinkage and selection operator algorithm-based selection and were then used for machine learning via the XGBoost package to distinguish bone marrow invasion presence. Receiver operating characteristic curve analysis was performed.</p><p><strong>Results: </strong>From the 159 patients, 88 qualified for further analysis (59 men; average age, 69.2 years), and pathologic bone marrow invasion was identified in 69 (78%) of these patients. Three significant radiological features were identified: Gray level co-occurrence matrix_Correlation, INTENSITY-BASED_IntensityInterquartileRange, and MORPHOLOGICAL_SurfaceToVolumeRatio. An XGBoost machine-learning model, using PET radiomic features to detect bone marrow invasion, yielded an area under the curve value of 0.83.</p><p><strong>Conclusion: </strong>Our findings highlighted the potential of 18 F-FDG PET radiomic features, combined with machine learning, as a promising avenue for improving LGSCC diagnosis and treatment. Using 18 F-FDG PET texture features may provide a robust and accurate method for determining the presence or absence of bone marrow invasion in LGSCC patients.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nuclear Medicine Communications","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/MNM.0000000000001826","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/19 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
Abstract
Objectives: Lower gingival squamous cell carcinoma (LGSCC) has the potential to invade the alveolar bone. Traditionally, the diagnosis of LGSCC relied on morphological imaging, but inconsistencies between these assessments and surgical findings have been observed. This study aimed to assess the correlation between LGSCC bone marrow invasion and PET texture features and to enhance diagnostic accuracy by using machine learning.
Methods: A retrospective analysis of 159 LGSCC patients with pretreatment 18 F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) examination from 2009 to 2017 was performed. We extracted radiomic features from the PET images, focusing on pathologic bone marrow invasion detection. Extracted features underwent the least absolute shrinkage and selection operator algorithm-based selection and were then used for machine learning via the XGBoost package to distinguish bone marrow invasion presence. Receiver operating characteristic curve analysis was performed.
Results: From the 159 patients, 88 qualified for further analysis (59 men; average age, 69.2 years), and pathologic bone marrow invasion was identified in 69 (78%) of these patients. Three significant radiological features were identified: Gray level co-occurrence matrix_Correlation, INTENSITY-BASED_IntensityInterquartileRange, and MORPHOLOGICAL_SurfaceToVolumeRatio. An XGBoost machine-learning model, using PET radiomic features to detect bone marrow invasion, yielded an area under the curve value of 0.83.
Conclusion: Our findings highlighted the potential of 18 F-FDG PET radiomic features, combined with machine learning, as a promising avenue for improving LGSCC diagnosis and treatment. Using 18 F-FDG PET texture features may provide a robust and accurate method for determining the presence or absence of bone marrow invasion in LGSCC patients.
期刊介绍:
Nuclear Medicine Communications, the official journal of the British Nuclear Medicine Society, is a rapid communications journal covering nuclear medicine and molecular imaging with radionuclides, and the basic supporting sciences. As well as clinical research and commentary, manuscripts describing research on preclinical and basic sciences (radiochemistry, radiopharmacy, radiobiology, radiopharmacology, medical physics, computing and engineering, and technical and nursing professions involved in delivering nuclear medicine services) are welcomed, as the journal is intended to be of interest internationally to all members of the many medical and non-medical disciplines involved in nuclear medicine. In addition to papers reporting original studies, frankly written editorials and topical reviews are a regular feature of the journal.