Utilizing radiomics and dosiomics with AI for precision prediction of radiation dermatitis in breast cancer patients

被引:1
作者
Lee, Tsair-Fwu [1 ,2 ,3 ]
Chang, Chu-Ho [1 ]
Chi, Chih-Hsuan [1 ]
Liu, Yen-Hsien [1 ]
Shao, Jen-Chung [1 ]
Hsieh, Yang-Wei [1 ]
Yang, Pei-Ying [1 ]
Tseng, Chin-Dar [1 ]
Chiu, Chien-Liang [1 ]
Hu, Yu-Chang [4 ]
Lin, Yu-Wei [4 ]
Chao, Pei-Ju [1 ]
Lee, Shen-Hao [1 ,5 ,6 ]
Yeh, Shyh-An [1 ,7 ,8 ]
机构
[1] Natl Kaohsiung Univ Sci & Technol, Med Phys & Informat Lab Elect Engn, Jiangong RdSanmin Dist 415, Kaohsiung 80778, Taiwan
[2] Kaohsiung Med Univ, Grad Inst Clin Med, Kaohsiung 807, Taiwan
[3] Kaohsiung Med Univ, Dept Med Imaging & Radiol Sci, Kaohsiung 80708, Taiwan
[4] Kaohsiung Vet Gen Hosp, Dept Radiat Oncol, Kaohsiung, Taiwan
[5] Linkou Chang Gung Mem Hosp, Dept Radiat Oncol, Linkou, Taiwan
[6] Chang Gung Univ, Coll Med, Linkou, Taiwan
[7] I Shou Univ, Dept Med Imaging & Radiol Sci, Kaohsiung 82445, Taiwan
[8] E Da Hosp, Dept Radiat Oncol, Kaohsiung 82445, Taiwan
关键词
Artificial intelligence; Radiomics; Dosiomics; Radiation dermatitis; Breast cancer; INTENSITY-MODULATED RADIOTHERAPY; MACHINE LEARNING APPROACH; SKIN TOXICITY;
D O I
10.1186/s12885-024-12753-1
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Purpose This study explores integrating clinical features with radiomic and dosiomic characteristics into AI models to enhance the prediction accuracy of radiation dermatitis (RD) in breast cancer patients undergoing volumetric modulated arc therapy (VMAT). Materials and methods This study involved a retrospective analysis of 120 breast cancer patients treated with VMAT at Kaohsiung Veterans General Hospital from 2018 to 2023. Patient data included CT images, radiation doses, Dose-Volume Histogram (DVH) data, and clinical information. Using a Treatment Planning System (TPS), we segmented CT images into Regions of Interest (ROIs) to extract radiomic and dosiomic features, focusing on intensity, shape, texture, and dose distribution characteristics. Features significantly associated with the development of RD were identified using ANOVA and LASSO regression (p-value < 0.05). These features were then employed to train and evaluate Logistic Regression (LR) and Random Forest (RF) models, using tenfold cross-validation to ensure robust assessment of model efficacy. Results In this study, 102 out of 120 VMAT-treated breast cancer patients were included in the detailed analysis. Thirty-two percent of these patients developed Grade 2(+) RD. Age and BMI were identified as significant clinical predictors. Through feature selection, we narrowed down the vast pool of radiomic and dosiomic data to 689 features, distributed across 10 feature subsets for model construction. In the LR model, the J subset, comprising DVH, Radiomics, and Dosiomics features, demonstrated the highest predictive performance with an AUC of 0.82. The RF model showed that subset I, which includes clinical, radiomic, and dosiomic features, achieved the best predictive accuracy with an AUC of 0.83. These results emphasize that integrating radiomic and dosiomic features significantly enhances the prediction of Grade 2(+) RD. Conclusion Integrating clinical, radiomic, and dosiomic characteristics into AI models significantly improves the prediction of Grade 2(+) RD risk in breast cancer patients post-VMAT. The RF model analysis demonstrates that a comprehensive feature set maximizes predictive efficacy, marking a promising step towards utilizing AI in radiation therapy risk assessment and enhancing patient care outcomes.
引用
收藏
页数:17
相关论文
共 34 条
[1]  
Behroozian Tara, 2021, Cancer Treat Res Commun, V28, P100403, DOI 10.1016/j.ctarc.2021.100403
[2]  
Chopra N, 2020, INT J RADIAT ONCOL, V108, pE777
[3]   Radiomics in breast cancer classification and prediction [J].
Conti, Allegra ;
Duggento, Andrea ;
Indovina, Iole ;
Guerrisi, Maria ;
Toschi, Nicola .
SEMINARS IN CANCER BIOLOGY, 2021, 72 :238-250
[4]   Non-Invasive Physical Plasma for Preventing Radiation Dermatitis in Breast Cancer: A First-In-Human Feasibility Study [J].
Dejonckheere, Cas Stefaan ;
Torres-Crigna, Adriana ;
Layer, Julian Philipp ;
Layer, Katharina ;
Wiegreffe, Shari ;
Sarria, Gustavo Renato ;
Scafa, Davide ;
Koch, David ;
Leitzen, Christina ;
Koeksal, Mumtaz Ali ;
Muedder, Thomas ;
Abramian, Alina ;
Kaiser, Christina ;
Faridi, Andree ;
Stope, Matthias Bernhard ;
Mustea, Alexander ;
Giordano, Frank Anton ;
Schmeel, Leonard Christopher .
PHARMACEUTICS, 2022, 14 (09)
[5]   Clinical factors affecting the determination of radiotherapy-induced skin toxicity in breast cancer [J].
Eugenia Cordoba, Elisa ;
Lacunza, Ezequiel ;
Mabel Guerci, Alba .
RADIATION ONCOLOGY JOURNAL, 2021, 39 (04) :315-323
[6]   Prediction of radiation-induced acute skin toxicity in breast cancer patients using data encapsulation screening and dose-gradient-based multi-region radiomics technique: A multicenter study [J].
Feng, Huichun ;
Wang, Hui ;
Xu, Lixia ;
Ren, Yao ;
Ni, Qianxi ;
Yang, Zhen ;
Ma, Shenglin ;
Deng, Qinghua ;
Chen, Xueqin ;
Xia, Bing ;
Kuang, Yu ;
Li, Xiadong .
FRONTIERS IN ONCOLOGY, 2022, 12
[7]   Systematic measurements of whole-body dose distributions for various treatment machines and delivery techniques in radiation therapy [J].
Haelg, Roger A. ;
Besserer, Juergen ;
Schneider, Uwe .
MEDICAL PHYSICS, 2012, 39 (12) :7662-7676
[8]   Skin toxicity during breast irradiation: Pathophysiology and management [J].
Harper, JL ;
Franklin, LE ;
Jenrette, JM ;
Aguero, EG .
SOUTHERN MEDICAL JOURNAL, 2004, 97 (10) :989-993
[9]   Preoperative Prediction of Perineural Invasion and Prognosis in Gastric Cancer Based on Machine Learning through a Radiomics-Clinicopathological Nomogram [J].
Jia, Heng ;
Li, Ruzhi ;
Liu, Yawei ;
Zhan, Tian ;
Li, Yuan ;
Zhang, Jianping .
CANCERS, 2024, 16 (03)
[10]   Surface dosimetry for breast radiotherapy in the presence of immobilization cast material [J].
Kelly, Andrew ;
Hardcastle, Nicholas ;
Metcalfe, Peter ;
Cutajar, Dean ;
Quinn, Alexandra ;
Foo, Kerwyn ;
Cardoso, Michael ;
Barlin, Sheree ;
Rosenfeld, Anatoly .
PHYSICS IN MEDICINE AND BIOLOGY, 2011, 56 (04) :1001-1013