T2-weighted MRI-based radiomics for discriminating between benign and borderline epithelial ovarian tumors: a multicenter study

Abstract

Background Preoperative differentiation between benign and borderline epithelial ovarian tumors (EOTs) is challenging and can significantly impact clinical decision making. The purpose was to investigate whether radiomics based on T2-weighted MRI can discriminate between benign and borderline EOTs preoperatively. Methods A total of 417 patients (309, 78, and 30 samples in the training and internal and external validation sets) with pathologically proven benign and borderline EOTs were included in this multicenter study. In total, 1130 radiomics features were extracted from manually delineated tumor volumes of interest on images. The following three different models were constructed and evaluated: radiomics features only (radiomics model); clinical and radiological characteristics only (clinic-radiological model); and a combination of them all (combined model). The diagnostic performances of models were assessed using receiver operating characteristic (ROC) analysis, and area under the ROC curves (AUCs) were compared using the DeLong test. Results The best machine learning algorithm to distinguish borderline from benign EOTs was the logistic regression. The combined model achieved the best performance in discriminating between benign and borderline EOTs, with an AUC of 0.86 ± 0.07. The radiomics model showed a moderate AUC of 0.82 ± 0.07, outperforming the clinic-radiological model (AUC of 0.79 ± 0.06). In the external validation set, the combined model performed significantly better than the clinic-radiological model (AUCs of 0.86 vs. 0.63, p = 0.021 [DeLong test]). Conclusions Radiomics, based on T2-weighted MRI, can provide critical diagnostic information for discriminating between benign and borderline EOTs, thus having the potential to aid personalized treatment options.

Editorial for “Associating Peritoneal Metastasis With T2‐Weighted MRI Images in Epithelial Ovarian Cancer Using Deep Learning and Radiomics: A Multicenter Study”

“…In conclusion, Wei et al 8 demonstrated the potential of DL and radiomics‐based models for predicting PM in EOC patients from T2‐weighted MR images. This model achieved high accuracy and showed good generalizability and robustness across different cohorts, highlighting its potential clinical utility 8 .…”

“…Artificial intelligence (AI), particularly deep learning (DL) and radiomics, has shown promise in oncology and radiology research. However, existing MRI‐based radiomics models for predicting PM in EOC patients have limitations, including small sample sizes and a lack of external validation 4–7 . Additionally, it is unclear whether AI‐assisted models can help radiologists improve their diagnostic performance.…”

“…In this issue of JMRI , Wei et al 8 describe the T2‐weighted (T2W) MRI‐based DL and radiomics approach that has the potential to preoperatively predict PM in EOC patients and assist in clinical decision‐making. In the recent multicenter retrospective study by Wei et al, 8 the authors enrolled 479 patients with EOC from five centers, including 277 with extrapelvic PM and 202 without PM. The researchers performed DL and radiomics analysis of T2W MRI images, and they compared models using DL, radiomics, and clinical factors to predict PM status.…”

Associating Peritoneal Metastasis With T2‐Weighted MRI Images in Epithelial Ovarian Cancer Using Deep Learning and Radiomics: A Multicenter Study

“…Furthermore, these aforementioned studies did not employ the DL method, which has been shown to accurately predict PM of gastric cancer 18 . T 2 ‐weighted (T2W) imaging based radiomics models have been demonstrated to identify benign, borderline, and malignant EOC, which is helpful to reduce MRI scan time and examination cost 19,20 . However, the use of AI models based on only a single MRI sequence in predicting PM remains unclear.…”

“…18 T 2 -weighted (T2W) imaging based radiomics models have been demonstrated to identify benign, borderline, and malignant EOC, which is helpful to reduce MRI scan time and examination cost. 19,20 However, the use of AI models based on only a single MRI sequence in predicting PM remains unclear. Moreover, whether an AI-assisted model can help radiologists improve performance in diagnosing the PM status of EOC patients is still vague.…”