Pretreatment MRI Radiomics Based Response Prediction Model in Locally Advanced Cervical Cancer

Abstract

The aim of this study was to create a radiomics model for Locally Advanced Cervical Cancer (LACC) patients to predict pathological complete response (pCR) after neoadjuvant chemoradiotherapy (NACRT) analysing T2-weighted 1.5 T magnetic resonance imaging (MRI) acquired before treatment start. Patients with LACC and an International Federation of Gynecology and Obstetrics stage from IB2 to IVA at diagnosis were retrospectively enrolled for this study. All patients underwent NACRT, followed by radical surgery; pCR―assessed on surgical specimen―was defined as absence of any residual tumour. Finally, 1889 features were extracted from MR images; features showing statistical significance in predicting pCR at the univariate analysis were selected following an iterative method, which was ad-hoc developed for this study. Based on this method, 15 different classifiers were trained considering the most significant features selected. Model selection was carried out using the area under the receiver operating characteristic curve (AUC) as target metrics. One hundred eighty-three patients from two institutions were analysed. The model, showing the highest performance with an AUC of 0.80, was the random forest method initialised with default parameters. Radiomics appeared to be a reliable tool in pCR prediction for LACC patients undergoing NACRT, supporting the identification of patient risk groups, which paves treatment pathways tailored according to the predicted outcome.

Laparoscopic Radical Hysterectomy Combined with Neoadjuvant Chemotherapy for Cervical Cancer Patients Effectively Improves Immune Function

“…In addition, neoadjuvant chemotherapy has a strong tumor-killing effect, which reduces tumor load and thus tumor-induced immunosuppression. The denaturation of tumor proteins after chemotherapy treatment induces the formation of other antigens of the same type, which in turn increases the immune function of the body [ 26 , 27 ].…”

Radiomic Score as a Potential Imaging Biomarker for Predicting Survival in Patients With Cervical Cancer

“…Radiomics has been involved in many aspects of cervical cancer, including prediction of tumor staging (21,22), histological grading (23,24), lymphovascular space invasion (LVI) (25), LNM (26)(27)(28)(29)(30)(31)(32)(33)(34)(35)(36), treatment response (37)(38)(39)(40)(41)(42), and outcome (43)(44)(45)(46)(47)(48) based on multimodal imaging tools (e.g., CT, MRI, and PET/CT). In clinical practice, the issues of most concern may be the evaluation of LNM, treatment response, and survival prediction.…”

“…Treatment response to neoadjuvant or concurrent chemotherapy may have a significant impact on patient management by identifying tailored approaches for patient subgroups to achieve a better clinical outcome. All relevant studies showed the additional value of radiomics to clinical factors and its potential to screen patients who are sensitive to chemotherapy (37)(38)(39)(40)(41)(42). Survival evaluation is an eternal proposition for the field of oncology, which may benefit treatment strategies and follow-up plans.…”

Neoadjuvant Chemoradiotherapy With Simultaneous Integrated Boost in Locally Advanced Cervical Cancer: Long Term Results of a Single-Center Experience

“…Taken into consideration that our study showed a 46% pathological complete response, these response prediction models could play a fundamental role in the management of patients with LACC by identifying patients who could benefit from lower doses, resulting in less toxicity. Based on this assumption, new dose delivery and targeting paradigms could be proposed and better treatment outcomes may be achieved, as already demonstrated in rectal and cervical cancer ( 36 – 38 ).…”

“…These results underscore the need to stratify patients into risk classes in order to pave treatment pathways tailored according to the predicted outcome. Recently, a radiomics model for LACC patients undergoing neoadjuvant CRT was developed analyzing T2-weighted 1.5 T MRI acquired before treatment start, appearing to be a reliable tool in pCR prediction after neoadjuvant CRT ( 36 ). Taken into consideration that our study showed a 46% pathological complete response, these response prediction models could play a fundamental role in the management of patients with LACC by identifying patients who could benefit from lower doses, resulting in less toxicity.…”