Automated Prediction of Neoadjuvant Chemoradiotherapy Response in Locally Advanced Cervical Cancer Using Hybrid Model-Based MRI Radiomics

被引:2
|
作者
Yang, Hua [1 ,2 ]
Xu, Yinan [3 ]
Dong, Mohan [4 ]
Zhang, Ying [1 ]
Gong, Jie [1 ]
Huang, Dong [5 ]
He, Junhua [6 ]
Wei, Lichun [1 ]
Huang, Shigao [1 ]
Zhao, Lina [1 ]
机构
[1] Air Force Med Univ, Xijing Hosp, Dept Radiat Oncol, Xian 710032, Peoples R China
[2] Xi An Jiao Tong Univ, Affiliated Hosp 1, Dept Radiat Oncol, Xian 710061, Peoples R China
[3] Xidian Univ, Key Lab Intelligent Percept & Image Understanding, Minist Educ, Xian 710071, Peoples R China
[4] Air Force Med Univ, Xijing Hosp, Dept Med Educ, Xian 710032, Peoples R China
[5] Air Force Med Univ, Dept Mil Biomed Engn, Xian 710012, Peoples R China
[6] Air Force Med Univ, Hosp 986, Dept Radiat Oncol, Xian 710054, Peoples R China
关键词
automated prediction; MRI radiomics; radiotherapy response; cervical cancer;
D O I
10.3390/diagnostics14010005
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: This study aimed to develop a model that automatically predicts the neoadjuvant chemoradiotherapy (nCRT) response for patients with locally advanced cervical cancer (LACC) based on T2-weighted MR images and clinical parameters. Methods: A total of 138 patients were enrolled, and T2-weighted MR images and clinical information of the patients before treatment were collected. Clinical information included age, stage, pathological type, squamous cell carcinoma (SCC) level, and lymph node status. A hybrid model extracted the domain-specific features from the computational radiomics system, the abstract features from the deep learning network, and the clinical parameters. Then, it employed an ensemble learning classifier weighted by logistic regression (LR) classifier, support vector machine (SVM) classifier, K-Nearest Neighbor (KNN) classifier, and Bayesian classifier to predict the pathologic complete response (pCR). The area under the receiver operating characteristics curve (AUC), accuracy (ACC), true positive rate (TPR), true negative rate (TNR), and precision were used as evaluation metrics. Results: Among the 138 LACC patients, 74 were in the pCR group, and 64 were in the non-pCR group. There was no significant difference between the two cohorts in terms of tumor diameter (p = 0.787), lymph node (p = 0.068), and stage before radiotherapy (p = 0.846), respectively. The 109-dimension domain features and 1472-dimension abstract features from MRI images were used to form a hybrid model. The average AUC, ACC, TPR, TNR, and precision of the proposed hybrid model were about 0.80, 0.71, 0.75, 0.66, and 0.71, while the AUC values of using clinical parameters, domain-specific features, and abstract features alone were 0.61, 0.67 and 0.76, respectively. The AUC value of the model without an ensemble learning classifier was 0.76. Conclusions: The proposed hybrid model can predict the radiotherapy response of patients with LACC, which might help radiation oncologists create personalized treatment plans for patients.
引用
收藏
页数:12
相关论文
共 50 条
  • [31] MRI volumetry for prediction of tumour response to neoadjuvant chemotherapy followed by chemoradiotherapy in locally advanced rectal cancer
    Seierstad, T.
    Hole, K. H.
    Groholt, K. K.
    Dueland, S.
    Ree, A. H.
    Flatmark, K.
    Redalen, K. R.
    BRITISH JOURNAL OF RADIOLOGY, 2015, 88 (1051):
  • [32] Significance of MRI-based radiomics in predicting pathological complete response to neoadjuvant chemoradiotherapy of locally advanced rectal cancer: A narrative review
    Li, Y.
    Liu, X.
    Gu, M.
    Xu, T.
    Ge, C.
    Chang, P.
    CANCER RADIOTHERAPIE, 2024, 28 (04): : 390 - 401
  • [33] MRI-based delta-radiomics are predictive of pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer
    Wan, Lijuan
    Peng, Wenjing
    Zou, Shuangmei
    Ye, Feng
    Geng, Yayuan
    Ouyang, Han
    Zhao, Xinming
    Zhang, Hongmei
    ACADEMIC RADIOLOGY, 2021, 28 : S95 - S104
  • [34] Development of a Joint Prediction Model Based on Both the Radiomics and Clinical Factors for Predicting the Tumor Response to Neoadjuvant Chemoradiotherapy in Patients with Locally Advanced Rectal Cancer
    Liu, Yang
    Zhang, Feng-Jiao
    Zhao, Xi-Xi
    Yang, Yuan
    Liang, Chun-Yi
    Feng, Li-Li
    Wan, Xiang-Bo
    Ding, Yi
    Zhang, Yao-Wei
    CANCER MANAGEMENT AND RESEARCH, 2021, 13 : 3235 - 3246
  • [35] MRI-Based Multi-Region Delta-Radiomics for Prediction of Recurrence After Chemoradiotherapy in Locally Advanced Cervical Cancer
    Kawamura, M.
    Kawahara, D.
    Nishibuchi, I.
    Saito, A.
    Yoshida, T.
    Nagata, Y.
    MEDICAL PHYSICS, 2021, 48 (06)
  • [36] MRI-Based Radiomics Model Improves Prognosis Prediction in Advanced Rectal Cancer Undergoing Neoadjuvant Chemoradiotherapy and Surgical Resection
    Zhao, Q.
    MEDICAL PHYSICS, 2022, 49 (06) : E643 - E643
  • [37] Prediction of treatment response in patients with locally advanced cervical cancer using midtreatment PET/MRI during concurrent chemoradiotherapy
    Radovan Vojtíšek
    Jan Baxa
    Petra Kovářová
    Amira Almortaza
    Petr Hošek
    Emília Sukovská
    Radek Tupý
    Jiří Ferda
    Jindřich Fínek
    Strahlentherapie und Onkologie, 2021, 197 : 494 - 504
  • [38] Prediction of treatment response in patients with locally advanced cervical cancer using midtreatment PET/MRI during concurrent chemoradiotherapy
    Vojtisek, Radovan
    Baxa, Jan
    Kovarova, Petra
    Almortaza, Amira
    Hosek, Petr
    Sukovska, Emilia
    Tupy, Radek
    Ferda, Jiri
    Finek, Jindrich
    STRAHLENTHERAPIE UND ONKOLOGIE, 2021, 197 (06) : 494 - 504
  • [39] Radiomics of locally advanced rectal cancer: machine learning-based prediction of response to neoadjuvant chemoradiotherapy using pre-treatment sagittal T2-weighted MRI
    Yardimci, Aytul Hande
    Kocak, Burak
    Sel, Ipek
    Bulut, Hasan
    Bektas, Ceyda Turan
    Cin, Merve
    Dursun, Nevra
    Bektas, Hasan
    Mermut, Ozlem
    Yardimci, Veysi Hakan
    Kilickesmez, Ozgur
    JAPANESE JOURNAL OF RADIOLOGY, 2023, 41 (01) : 71 - 82
  • [40] Radiomics of locally advanced rectal cancer: machine learning-based prediction of response to neoadjuvant chemoradiotherapy using pre-treatment sagittal T2-weighted MRI
    Aytul Hande Yardimci
    Burak Kocak
    Ipek Sel
    Hasan Bulut
    Ceyda Turan Bektas
    Merve Cin
    Nevra Dursun
    Hasan Bektas
    Ozlem Mermut
    Veysi Hakan Yardimci
    Ozgur Kilickesmez
    Japanese Journal of Radiology, 2023, 41 : 71 - 82