Guanfeng Chen , Wenxi Liu , Yingmin Lin , Jie Zhang , Risheng Huang , Deqiu Ye , Jing Huang , Jieyun Chen
{"title":"Predicting bone metastasis risk of colorectal tumors using radiomics and deep learning ViT model","authors":"Guanfeng Chen , Wenxi Liu , Yingmin Lin , Jie Zhang , Risheng Huang , Deqiu Ye , Jing Huang , Jieyun Chen","doi":"10.1016/j.jbo.2024.100659","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Colorectal cancer is a prevalent malignancy with a significant risk of metastasis, including to bones, which severely impacts patient outcomes. Accurate prediction of bone metastasis risk is crucial for optimizing treatment strategies and improving prognosis.</div></div><div><h3>Purpose</h3><div>This study aims to develop a predictive model combining radiomics and Vision Transformer (ViT) deep learning techniques to assess the risk of bone metastasis in colorectal cancer patients using both plain and contrast-enhanced CT images.</div></div><div><h3>Materials and methods</h3><div>We conducted a retrospective analysis of 155 colorectal cancer patients, including 81 with bone metastasis and 74 without. Radiomic features were extracted from segmented tumors on both plain and contrast-enhanced CT images. LASSO regression was applied to select key features, which were then used to build traditional machine learning models, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest, LightGBM, and XGBoost. Additionally, a dual-modality ViT model was trained on the same CT images, with a late fusion strategy employed to combine outputs from the different modalities. Model performance was evaluated using AUC-ROC, accuracy, sensitivity, and specificity, and differences were statistically assessed using DeLong’s test.</div></div><div><h3>Results</h3><div>The ViT model demonstrated superior predictive performance, achieving an AUC of 0.918 on the test set, significantly outperforming all traditional radiomics-based models. The SVM model, while the best among traditional models, still underperformed compared to the ViT model. The ViT model’s strength lies in its ability to capture complex spatial relationships and long-range dependencies within the imaging data, which are often missed by traditional models. DeLong’s test confirmed the statistical significance of the ViT model’s enhanced performance, highlighting its potential as a powerful tool for predicting bone metastasis risk in colorectal cancer patients.</div></div><div><h3>Conclusion</h3><div>The integration of radiomics with ViT-based deep learning offers a robust and accurate method for predicting bone metastasis risk in colorectal cancer patients. The ViT model’s ability to analyze dual-modality CT imaging data provides greater precision in risk assessment, which can improve clinical decision-making and personalized treatment strategies. These findings underscore the promise of advanced deep learning models in enhancing the accuracy of metastasis prediction. Further validation in larger, multicenter studies is recommended to confirm the generalizability of these results.</div></div>","PeriodicalId":48806,"journal":{"name":"Journal of Bone Oncology","volume":"51 ","pages":"Article 100659"},"PeriodicalIF":3.4000,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Bone Oncology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2212137424001398","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Colorectal cancer is a prevalent malignancy with a significant risk of metastasis, including to bones, which severely impacts patient outcomes. Accurate prediction of bone metastasis risk is crucial for optimizing treatment strategies and improving prognosis.
Purpose
This study aims to develop a predictive model combining radiomics and Vision Transformer (ViT) deep learning techniques to assess the risk of bone metastasis in colorectal cancer patients using both plain and contrast-enhanced CT images.
Materials and methods
We conducted a retrospective analysis of 155 colorectal cancer patients, including 81 with bone metastasis and 74 without. Radiomic features were extracted from segmented tumors on both plain and contrast-enhanced CT images. LASSO regression was applied to select key features, which were then used to build traditional machine learning models, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest, LightGBM, and XGBoost. Additionally, a dual-modality ViT model was trained on the same CT images, with a late fusion strategy employed to combine outputs from the different modalities. Model performance was evaluated using AUC-ROC, accuracy, sensitivity, and specificity, and differences were statistically assessed using DeLong’s test.
Results
The ViT model demonstrated superior predictive performance, achieving an AUC of 0.918 on the test set, significantly outperforming all traditional radiomics-based models. The SVM model, while the best among traditional models, still underperformed compared to the ViT model. The ViT model’s strength lies in its ability to capture complex spatial relationships and long-range dependencies within the imaging data, which are often missed by traditional models. DeLong’s test confirmed the statistical significance of the ViT model’s enhanced performance, highlighting its potential as a powerful tool for predicting bone metastasis risk in colorectal cancer patients.
Conclusion
The integration of radiomics with ViT-based deep learning offers a robust and accurate method for predicting bone metastasis risk in colorectal cancer patients. The ViT model’s ability to analyze dual-modality CT imaging data provides greater precision in risk assessment, which can improve clinical decision-making and personalized treatment strategies. These findings underscore the promise of advanced deep learning models in enhancing the accuracy of metastasis prediction. Further validation in larger, multicenter studies is recommended to confirm the generalizability of these results.
期刊介绍:
The Journal of Bone Oncology is a peer-reviewed international journal aimed at presenting basic, translational and clinical high-quality research related to bone and cancer.
As the first journal dedicated to cancer induced bone diseases, JBO welcomes original research articles, review articles, editorials and opinion pieces. Case reports will only be considered in exceptional circumstances and only when accompanied by a comprehensive review of the subject.
The areas covered by the journal include:
Bone metastases (pathophysiology, epidemiology, diagnostics, clinical features, prevention, treatment)
Preclinical models of metastasis
Bone microenvironment in cancer (stem cell, bone cell and cancer interactions)
Bone targeted therapy (pharmacology, therapeutic targets, drug development, clinical trials, side-effects, outcome research, health economics)
Cancer treatment induced bone loss (epidemiology, pathophysiology, prevention and management)
Bone imaging (clinical and animal, skeletal interventional radiology)
Bone biomarkers (clinical and translational applications)
Radiotherapy and radio-isotopes
Skeletal complications
Bone pain (mechanisms and management)
Orthopaedic cancer surgery
Primary bone tumours
Clinical guidelines
Multidisciplinary care
Keywords: bisphosphonate, bone, breast cancer, cancer, CTIBL, denosumab, metastasis, myeloma, osteoblast, osteoclast, osteooncology, osteo-oncology, prostate cancer, skeleton, tumour.