Search

Purpose: The present study assessed the predictive value of peritumoral regions on three tumor tasks, and further explored the influence of peritumors with different sizes. Methods: We retrospectively collected 333 samples of gastrointestinal stromal tumors from the Second Affiliated Hospital of Zhejiang University School of Medicine, and 183 samples of gastrointestinal stromal tumors from Tianjin Medical University Cancer Hospital. We also collected 211 samples of laryngeal carcinoma and 233 samples of nasopharyngeal carcinoma from the First Affiliated Hospital of Jinan University. The tasks of three tumor datasets were risk assessment (gastrointestinal stromal tumor), T3/T4 staging prediction (laryngeal carcinoma), and distant metastasis prediction (nasopharyngeal carcinoma), respectively. First, deep learning and radiomics were respectively used to construct peritumoral models, to study whether the peritumor had predictive value on three tumor datasets. Furthermore, we defined different sizes peritumors including fixed size (not considering tumor size) and adaptive size (according to average tumor radius) to explore the influence of peritumor of different sizes and types of tumors. Finally, we visualized the deep learning and radiomic models to observe the influence of the peritumor in three datasets. Results: The performance of intra‐peritumors are better than intratumors alone in three datasets. Specifically, the comparisons of area under receiver operating characteristic curve in the testing set between intra‐peritumoral and intratumoral models are: 0.908 vs 0.873 (P value: 0.037) in gastrointestinal stromal tumor datasets, 0.796 vs 0.756 (P value: 0.188) in laryngeal carcinoma datasets and 0.660 vs 0.579 (P value: 0.431) in nasopharyngeal carcinoma datasets. Furthermore, for gastrointestinal stromal tumor datasets, deep learning is more stable to learn peritumors with both fixed and adaptive size than radiomics. For laryngeal carcinoma datasets, the intra‐peritumoral radiomic model could make model performance more balanced. For nasopharyngeal carcinoma datasets, radiomics is also more suitable for modeling peritumors than deep learning. The size of the peritumor is critical in this task, and only the performance of 1.5 mm–4.5 mm peritumors is stable. Conclusions: Our results indicate that peritumors have additional predictive value in three tumor datasets through deep learning or radiomics. The definitions of the peritumoral region and artificial intelligence method also have great influence on the performance of the peritumor. [ABSTRACT FROM AUTHOR]

Background: Gleason score (GS) is a histologic prognostic factor and the basis of treatment decision-making for prostate cancer (PCa). Treatment regimens between lower-grade (GS ≤7) and high-grade (GS >7) PCa differ largely and have great effects on cancer progression.Purpose: To investigate the use of different sequences in biparametric MRI (bpMRI) of the prostate gland for noninvasively distinguishing high-grade PCa.Study Type: Retrospective.Population: In all, 489 patients (training cohort: N = 326; test cohort: N = 163) with PCa between June 2008 and January 2018.Field Strength/sequence: 3.0T, pelvic phased-array coils, bpMRI including T2 -weighted imaging (T2 WI) and diffusion-weighted imaging (DWI); apparent diffusion coefficient map extracted from DWI.Assessment: The whole prostate gland was delineated. Radiomic features were extracted and selected using the Kruskal-Wallis test, the minimum redundancy-maximum relevance, and the sequential backward elimination algorithm. Two single-sequence radiomic (T2 WI, DWI) and two combined (T2 WI-DWI, T2 WI-DWI-Clinic) models were respectively constructed and validated via logistic regression.Statistical Tests: The Kruskal-Wallis test and chi-squared test were utilized to evaluate the differences among variable groups. P < 0.05 determined statistical significance. The area under the receiver operating characteristic curve (AUC), specificity, sensitivity, and accuracy were used to evaluate model performance. The Delong test was conducted to compare the differences between the AUCs of all models.Result: All radiomic models showed significant (P < 0.001) predictive performances. Between the single-sequence radiomic models, the DWI model achieved the most encouraging results, with AUCs of 0.801 and 0.787 in the training and test cohorts, respectively. For the combined models, the T2 WI-DWI models acquired an AUC of 0.788, which was almost the same with DWI in the test cohort, and no significant difference was found between them (training cohort: P = 0.199; test cohort: P = 0.924).Data Conclusion: Radiomics based on bpMRI can noninvasively identify high-grade PCa before the operation, which is helpful for individualized diagnosis of PCa.Level Of Evidence: 4 TECHNICAL EFFICACY STAGE: 2 J. Magn. Reson. Imaging 2020;52:1102-1109. [ABSTRACT FROM AUTHOR]