[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121502-en":3,"doc-seo-121502-105":30,"detail-sidebar-cat-0-en-105":95},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121502,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","BRAINMETDETECT - PREDICTING PRIMARY TUMOR FROM BRAIN METASTASIS MRI DATA USING RADIOMIC FEATURES AND MACHINE LEARNING ALGORITHMS - Research Summary","Brain metastases are common in cancer patients, and identifying the primary tumor site is essential for selecting effective treatment. This study predicts primary tumor origin using radiomic features extracted from post-contrast T1-weighted brain metastasis MRI and advanced machine learning classifiers. A dataset of 75 patients is analyzed with feature selection via the GINI index and normalization. Random Forest and XGBoost are trained with and without FOX hyperparameter optimization, and SHAP supports interpretability.","arXiv :2407 .0505 1v 1 [ cs .LG] 6 Jul 2024  \nBRAINMETDETECT: PREDICTING PRIMARY TUMOR FROM BRAIN METASTASIS MRI DATA USING RADIOMIC FEATURES AND MACHINE LEARNING ALGORITHMS  \nHamidreza Sadeghsalehi  \nIran University of Medical Sciences  \n[sadeghsalehi.h@iums.ac.ir](sadeghsalehi.h@iums.ac.ir)  \nABSTRACT  \nObjective: Brain metastases (BMs) are common in cancer patients and determining the primary tumor site is crucial for effective treatment. This study aims to predict the primary tumor site from BM MRI data using radiomic features and advanced machine learning algorithms.  \nMethods: We utilized a comprehensive dataset from Ocaña-Tienda et al. (2023) comprising MRI and clinical data from 75 patients with BMs. Radiomic features were extracted from post-contrast T1-weighted MRI sequences. Feature selection was performed using the GINI index, and data normalization was applied to ensure consistent scaling. We developed and evaluated Random Forest and XGBoost classifiers, both with and without hyperparameter optimization using the FOX (Fox optimizer) algorithm. Model interpretability was enhanced using SHAP (SHapley Additive exPlanations) values.  \nResults: The baseline Random Forest model achieved an accuracy of 0.85, which improved to 0.93 with FOX optimization. The XGBoost model showed an initial accuracy of 0.96, increasing to 0.99 after optimization. SHAP analysis revealed the most influential radiomic features contributing to the models’ predictions. The FOX-optimized XGBoost model exhibited the best performance with a precision, recall, and F1-score of 0.99 .  \nConclusion: This study demonstrates the effectiveness of using radiomic features and machine learning to predict primary tumor sites from BM MRI data. The FOX optimization algorithm significantly enhanced model performance, and SHAP provided valuable insights into feature importance. These findings highlight the potential of integrating radiomics and machine learning into clinical practice for improved diagnostic accuracy and personalized treatment planning.  \nKeywords Brain metastasis · MRI · Radiomics · Machine learning · FOX optimization · Random Forest · XGBoost  \n1 Introduction  \nBrain metastases (BMs) are a significant medical challenge, representing the most common type of intracranial tumor in adults, with the incidence rising due to improved systemic control of primary cancers and increased longevity of cancer patients [1] . Early and accurate identification of the primary tumor site is crucial for determining the appropriate treatment strategy and improving patient outcomes. Despite advancements in neuroimaging techniques, differentiating the primary tumor origin based solely on brain metastasis imaging remains complex and elusive [2] .  \nRadiomics, a developing discipline that produces high-dimensional, mineable data from medical images, has shown promise in enhancing diagnostic accuracy in oncology [3] . Radiomic features capture the underlying heterogeneity of tumors that may not be visually discernible, thus providing a robust quantitative basis for disease characterization [4, 5] . Integrating these features with advanced machine learning algorithms offers a compelling approach to predict the primary tumor site from brain metastasis MRI data.  \nBrainMetDetect  \nThis study leverages a comprehensive dataset of clinical information and annotated brain metastases MR images, as described by Ocaña-Tienda et al. (2023) [6] . The dataset includes imaging studies from 75 patients diagnosed with BMs, collected from five distinct medical institutions, ensuring a diverse and representative sample. The clinical data encompass various patient demographics, treatment regimens, and survival statistics, while the imaging data consist of high-resolution post-contrast T1-weighted MRI sequences, crucial for accurate feature extraction and analysis.  \nOur research aims to develop and evaluate the performance of several machine learning models for predicting the primary tumo","cbCaiobFXeu40fIZ","https://ap.wps.com/l/cbCaiobFXeu40fIZ","pdf",383583,1,10,"English","en",105,"# Abstract\n# Introduction\n## Clinical motivation\n## Radiomics and machine learning\n# BrainMetDetect\n## Dataset overview\n## Modeling approach\n## Prior work and research gap\n# Materials and Methods\n## Dataset","[{\"question\":\"What is BrainMetDetect trying to predict from MRI data?\",\"answer\":\"It predicts the primary tumor site based on brain metastasis MRI data using radiomic features and machine learning models.\"},{\"question\":\"How are radiomic features extracted and prepared for modeling?\",\"answer\":\"Radiomic features are extracted from post-contrast T1-weighted MRI sequences, with feature selection using the GINI index and normalization to standardize scaling.\"},{\"question\":\"Which models and optimization strategy are evaluated?\",\"answer\":\"Random Forest and XGBoost classifiers are evaluated both with and without hyperparameter optimization using the FOX (Fox optimizer) algorithm.\"},{\"question\":\"How is interpretability handled in the study?\",\"answer\":\"SHAP (SHapley Additive exPlanations) values are used to interpret and quantify the contribution of individual radiomic features to model predictions.\"}]","BRAINMETDETECT - PREDICTING PRIMARY TUMOR FROM BRAIN METASTASIS MRI DATA USING RADIOMIC FEATURES AND MACHINE LEARNING ALGORITHMS - Research Summary | PDF",1785735971,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":90,"head_meta":92,"extra_data":94,"updated_unix":28},"brainmetdetect-predicting-primary-tumor-from-brain-metastasis-mri-data-using-radiomic-features-and-machine-learning-algorithms-research-summary","",{"@graph":36,"@context":89},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/brainmetdetect-predicting-primary-tumor-from-brain-metastasis-mri-data-using-radiomic-features-and-machine-learning-algorithms-research-summary/121502/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81,85],{"name":72,"@type":73,"acceptedAnswer":74},"What is BrainMetDetect trying to predict from MRI data?","Question",{"text":75,"@type":76},"It predicts the primary tumor site based on brain metastasis MRI data using radiomic features and machine learning models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are radiomic features extracted and prepared for modeling?",{"text":80,"@type":76},"Radiomic features are extracted from post-contrast T1-weighted MRI sequences, with feature selection using the GINI index and normalization to standardize scaling.",{"name":82,"@type":73,"acceptedAnswer":83},"Which models and optimization strategy are evaluated?",{"text":84,"@type":76},"Random Forest and XGBoost classifiers are evaluated both with and without hyperparameter optimization using the FOX (Fox optimizer) algorithm.",{"name":86,"@type":73,"acceptedAnswer":87},"How is interpretability handled in the study?",{"text":88,"@type":76},"SHAP (SHapley Additive exPlanations) values are used to interpret and quantify the contribution of individual radiomic features to model predictions.","https://schema.org",{"og:url":52,"og:type":91,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":93,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":96},[97,101,105,109,114,119,124,127,132,135,138],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Exam",70,"exam",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},5,"Comic",60,"comic",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},6,"Technology",50,"technology",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":122,"slug":123},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":125,"slug":126},30,"research-report",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":130,"slug":131},9,"Religion & Spirituality",20,"religion-spirituality",{"id":130,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":130,"slug":134},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":21,"slug":137},"Lifestyle","lifestyle",{"id":139,"doc_module":4,"doc_module_name":46,"category_name":140,"show_sort_weight":110,"slug":141},19,"General","general"]