Dataset Information

MRI index lesion radiomics and machine learning for detection of extraprostatic extension of disease: a multicenter study.

ABSTRACT:

Objectives

To build a machine learning (ML) model to detect extraprostatic extension (EPE) of prostate cancer (PCa), based on radiomics features extracted from prostate MRI index lesions.

Methods

Consecutive MRI exams of patients undergoing radical prostatectomy for PCa were retrospectively collected from three institutions. Axial T2-weighted and apparent diffusion coefficient map images were annotated to obtain index lesion volumes of interest for radiomics feature extraction. Data from one institution was used for training, feature selection (using reproducibility, variance and pairwise correlation analyses, and a correlation-based subset evaluator), and tuning of a support vector machine (SVM) algorithm, with stratified 10-fold cross-validation. The model was tested on the two remaining institutions' data and compared with a baseline reference and expert radiologist assessment of EPE.

Results

In total, 193 patients were included. From an initial dataset of 2436 features, 2287 were excluded due to either poor stability, low variance, or high collinearity. Among the remaining, 14 features were used to train the ML model, which reached an overall accuracy of 83% in the training set. In the two external test sets, the SVM achieved an accuracy of 79% and 74% respectively, not statistically different from that of the radiologist (81-83%, p = 0.39-1) and outperforming the baseline reference (p = 0.001-0.02).

Conclusions

A ML model solely based on radiomics features demonstrated high accuracy for EPE detection and good generalizability in a multicenter setting. Paired to qualitative EPE assessment, this approach could aid radiologists in this challenging task.

Key points

• Predicting the presence of EPE in prostate cancer patients is a challenging task for radiologists. • A support vector machine algorithm achieved high diagnostic accuracy for EPE detection, with good generalizability when tested on multiple external datasets. • The performance of the algorithm was not significantly different from that of an experienced radiologist.

SUBMITTER: Cuocolo R

PROVIDER: S-EPMC8452573 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeTo validate the MRI grading system proposed by Mehralivand et al in 2019 (the "extraprostatic extension [EPE] grade") in an independent cohort and to compare the Mehralivand EPE grading system with EPE interpretation on the basis of a five-point Likert score ("EPE Likert").Materials and methodsA total of 310 consecutive patients underwent multiparametric MRI according to a standardized institutional protocol before radical prostatectomy was performed by using the same 1.5-T MRI unit at a single institution between 2010 and 2012. Two radiologists blinded to clinical information assessed EPE according to standardized criteria. On the basis of the readings performed until 2017, the diagnostic performance of EPE Likert and Mehralivand EPE score were compared using receiver operating characteristics (ROC) and decision curve methodology against histologic EPE as standard of reference. Prediction of biochemical recurrence-free survival (BRFS) was assessed by Kaplan-Meier analysis and log rank test.ResultsOf the 310 patients, 80 patients (26%) had EPE, including 33 with radial distance 1.1 mm or greater. Interrater reliability was fair (weighted κ 0.47 and 0.45) for both EPE grade and EPE Likert. Sensitivity for identifying EPE using EPE grade versus EPE Likert was 0.83 versus 0.86 and 0.86 versus 0.91 for radiologist 1 and 2, respectively. Specificity was 0.48 versus 0.58 and 0.39 versus 0.70 (P < .05 for radiologist 2). There were no significant differences in the ROC area under the curve or on decision curve analysis. Both EPE grade and EPE Likert were significant predictors of BRFS.ConclusionMehralivand EPE grade and EPE Likert have equivalent diagnostic performance for predicting EPE and BRFS with a similar degree of observer dependence.© RSNA, 2020Keywords: MR-Imaging, Neoplasms-Primary, Observer Performance, Outcomes Analysis, Prostate, StagingSupplemental material is available for this article.See also the commentary by Choyke in this issue.

Project description:ObjectiveTo assess impact of image quality on prostate cancer extraprostatic extension (EPE) detection on MRI using a deep learning-based AI algorithm.Materials and methodsThis retrospective, single institution study included patients who were imaged with mpMRI and subsequently underwent radical prostatectomy from June 2007 to August 2022. One genitourinary radiologist prospectively evaluated each patient using the NCI EPE grading system. Each T2WI was classified as low- or high-quality by a previously developed AI algorithm. Fisher's exact tests were performed to compare EPE detection metrics between low- and high-quality images. Univariable and multivariable analyses were conducted to assess the predictive value of image quality for pathological EPE.ResultsA total of 773 consecutive patients (median age 61 [IQR 56-67] years) were evaluated. At radical prostatectomy, 23% (180/773) of patients had EPE at pathology, and 41% (131/318) of positive EPE calls on mpMRI were confirmed to have EPE. The AI algorithm classified 36% (280/773) of T2WIs as low-quality and 64% (493/773) as high-quality. For EPE grade ≥ 1, high-quality T2WI significantly improved specificity for EPE detection (72% [95% CI 67-76%] vs. 63% [95% CI 56-69%], P = 0.03), but did not significantly affect sensitivity (72% [95% CI 62-80%] vs. 75% [95% CI 63-85%]), positive predictive value (44% [95% CI 39-49%] vs. 38% [95% CI 32-43%]), or negative predictive value (89% [95% CI 86-92%] vs. 89% [95% CI 85-93%]). Sensitivity, specificity, PPV, and NPV for EPE grades ≥ 2 and ≥ 3 did not show significant differences attributable to imaging quality. For NCI EPE grade 1, high-quality images (OR 3.05, 95% CI 1.54-5.86; P < 0.001) demonstrated a stronger association with pathologic EPE than low-quality images (OR 1.76, 95% CI 0.63-4.24; P = 0.24).ConclusionOur study successfully employed a deep learning-based AI algorithm to classify image quality of prostate MRI and demonstrated that better quality T2WI was associated with more accurate prediction of EPE at final pathology.

Project description:Background: To develop a radiomics model based on multiparametric MRI (mpMRI) for preoperative prediction of extraprostatic extension (EPE) in patients with prostate cancer (PCa). Methods: Ninety-five pathology-confirmed PCa patients with 115 lesions (49 positive and 66 negative) were retrospectively enrolled. A 3.0T MR scanner was used to perform T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced imaging (DCE). Radiomics features extracted from T2WI, DWI, apparent diffusion coefficient (ADC), and DCE were used to build a radiomics model. Patients' clinical and pathological variables were also obtained to build a clinical model. The radiomics model and clinical model were further integrated to build a combined nomogram. All lesions were randomly divided into the training group (82 lesions) and the validation group (33 lesions). A least absolute shrinkage and selection operator (LASSO) regression algorithm was applied to build the radiomics model. The diagnostic performance of different models was assessed by calculating the area under the curve (AUC) and compared using the Delong test. The calibration curve and decision curve analyses were used to assess the calibration and clinical usefulness of the radiomics model. Results: The AUC values for the radiomics model in the training and validation group were 0.919 and 0.865, respectively, with a good calibration performance. The decision curve analysis confirmed the clinical utility of the radiomics model. The accuracy, sensitivity, and specificity were 81.8, 71.4, and 89.5% in the validation group. In the validation group, the radiomics model outperformed the clinical model (AUC = 0.658, P = 0.020), and was comparable with the combined nomogram (AUC = 0.857, P = 0.644). Conclusion: The radiomics model based on mpMRI could different EPE and non-EPE lesions with satisfactory diagnostic performance, and this model might assist in predicting EPE before prostatectomy.