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

Abstract

BackgroundThe preoperative diagnosis of peritoneal metastasis (PM) in epithelial ovarian cancer (EOC) is challenging and can impact clinical decision‐making.PurposeTo investigate the performance of T2‐weighted (T2W) MRI‐based deep learning (DL) and radiomics methods for PM evaluation in EOC patients.Study TypeRetrospective.PopulationFour hundred seventy‐nine patients from five centers, including one training set (N = 297 [mean, 54.87 years]), one internal validation set (N = 75 [mean, 56.67 years]), and two external validation sets (N = 53 [mean, 55.58 years] and N = 54 [mean, 58.22 years]).Field Strength/Sequence1.5 or 3 T/fat‐suppression T2W fast or turbo spin‐echo sequence.AssessmentResNet‐50 was used as the architecture of DL. The largest orthogonal slices of the tumor area, radiomics features, and clinical characteristics were used to construct the DL, radiomics, and clinical models, respectively. The three models were combined using decision‐level fusion to create an ensemble model. Diagnostic performances of radiologists and radiology residents with and without model assistance were evaluated.Statistical TestsReceiver operating characteristic analysis was used to assess the performances of models. The McNemar test was used to compare sensitivity and specificity. A two‐tailed P < 0.05 was considered significant.ResultsThe ensemble model had the best AUCs, outperforming the DL model (0.844 vs. 0.743, internal validation set; 0.859 vs. 0.737, external validation set I) and clinical model (0.872 vs. 0.730, external validation set II). After model assistance, all readers had significantly improved sensitivity, especially for those with less experience (junior radiologist1, from 0.639 to 0.820; junior radiologist2, from 0.689 to 0.803; resident1, from 0.623 to 0.803; resident2, from 0.541 to 0.738). One resident also had significantly improved specificity (from 0.633 to 0.789).Data ConclusionsT2W MRI‐based DL and radiomics approaches have the potential to preoperatively predict PM in EOC patients and assist in clinical decision‐making.Evidence Level4Technical EfficacyStage 2

Deep learning in ovarian cancer diagnosis: a comprehensive review of various imaging modalities

“…Additionally, one-cycle learning rate scheduling and early stopping techniques were employed. The ensemble model had the best AUCs (0.84, 0.85, 0.87) among all validation sets, outperforming the DL model, radiomics model, and clinical model alone [ 59 ].…”

Development and validation of a deep learning radiomics model with clinical-radiological characteristics for the identification of occult peritoneal metastases in patients with pancreatic ductal adenocarcinoma

“…The proposed combined model, which merges the HCR and DLR features, can noninvasively and robustly characterize intratumoral heterogeneity from medical images at different levels 25 , 26 , which helps improve the performance of the model. Moreover, combining high-dimensional features can provide further details regarding cancer, making the model more sensitive for disease diagnosis and prediction 13 , 27 , 28 . Furthermore, the clinical and radiological features can provide a more comprehensive description of tumor characteristics.…”

“…Artificial intelligence techniques, such as radiomics and deep learning (DL) methods, are remarkable tools for predicting OPM in gastric cancer 10 , 11 , colorectal cancer 12 , and epithelial ovarian cancer 13 . Huang et al .…”

Imaging of Peritoneal Metastases in Ovarian Cancer Using MDCT, MRI, and FDG PET/CT: A Systematic Review and Meta-Analysis

“…The use of radiomics and radiogenomics may be helpful in the future in predicting OC genotype and biology and in assessing treatment response, clinical outcome, and patient survival [102][103][104][105][106]. Based on preliminary data, MRI and CT-based radiomics have been reported to predict the presence of PMs in OC [107][108][109][110].…”