Radiation Oncology (Apr 2022)

Applicability of a pathological complete response magnetic resonance-based radiomics model for locally advanced rectal cancer in intercontinental cohort

  • Luca Boldrini,
  • Jacopo Lenkowicz,
  • Lucia Clara Orlandini,
  • Gang Yin,
  • Davide Cusumano,
  • Giuditta Chiloiro,
  • Nicola Dinapoli,
  • Qian Peng,
  • Calogero Casà,
  • Maria Antonietta Gambacorta,
  • Vincenzo Valentini,
  • Jinyi Lang

DOI
https://doi.org/10.1186/s13014-022-02048-9
Journal volume & issue
Vol. 17, no. 1
pp. 1 – 8

Abstract

Read online

Abstract Background Predicting pathological complete response (pCR) in patients affected by locally advanced rectal cancer (LARC) who undergo neoadjuvant chemoradiotherapy (nCRT) is a challenging field of investigation, but many of the published models are burdened by a lack of reliable external validation. Aim of this study was to evaluate the applicability of a magnetic resonance imaging (MRI) radiomic-based pCR model developed and validated in Europe, to a different cohort of patients from an intercontinental cancer center. Methods The original model was based on two clinical and two radiomics features extracted from T2-weighted 1.5 T MRI of 161 LARC patients acquired before nCRT, considered as training set. Such model is here validated using the T2-w 1.5 and 3 T staging MRI of 59 LARC patients with different clinical characteristics consecutively treated in mainland Chinese cancer center from March 2017 to January 2018. Model performance were evaluated in terms of area under the receiver operator characteristics curve (AUC) and relative parameters, such as accuracy, specificity, negative and positive predictive value (NPV and PPV). Results An AUC of 0.83 (CI 95%, 0.71–0.96) was achieved for the intercontinental cohort versus a value of 0.75 (CI 95%, 0.61–0.88) at the external validation step reported in the original experience. Considering the best cut-off threshold identified in the first experience (0.26), the following predictive performance were obtained: 0.65 as accuracy, 0.64 as specificity, 0.70 as sensitivity, 0.91 as NPV and 0.28 as PPV. Conclusions Despite the introduction of significant different factors, the proposed model appeared to be replicable on a real-world data extra-European patients’ cohort, achieving a TRIPOD 4 level.

Keywords