MRI radiomics predicts progression-free survival in prostate cancer

Can we predict pathology without surgery? Weighing the added value of multiparametric MRI and whole prostate radiomics in integrative machine learning models

OBJECTIVE

To test the ability of high-performance machine learning (ML) models employing clinical, radiological, and radiomic variables to improve non-invasive prediction of the pathological status of prostate cancer (PCa) in a large, single-institution cohort.

METHODS

Patients who underwent multiparametric MRI and prostatectomy in our institution in 2015-2018 were considered; a total of 949 patients were included. Gradient-boosted decision tree models were separately trained using clinical features alone and in combination with radiological reporting and/or prostate radiomic features to predict pathological T, pathological N, ISUP score, and their change from preclinical assessment. Model behavior was analyzed in terms of performance, feature importance, Shapley additive explanation (SHAP) values, and mean absolute error (MAE). The best model was compared against a naïve model mimicking clinical workflow.

RESULTS

The model including all variables was the best performing (AUC values ranging from 0.73 to 0.96 for the six endpoints). Radiomic features brought a small yet measurable boost in performance, with the SHAP values indicating that their contribution can be critical to successful prediction of endpoints for individual patients. MAEs were lower for low-risk patients, suggesting that the models find them easier to classify. The best model outperformed (p ≤ 0.0001) clinical baseline, resulting in significantly fewer false negative predictions and overall was less prone to under-staging.

CONCLUSIONS

Our results highlight the potential benefit of integrative ML models for pathological status prediction in PCa. Additional studies regarding clinical integration of such models can provide valuable information for personalizing therapy offering a tool to improve non-invasive prediction of pathological status.

CLINICAL RELEVANCE STATEMENT

The best machine learning model was less prone to under-staging of the disease. The improved accuracy of our pathological prediction models could constitute an asset to the clinical workflow by providing clinicians with accurate pathological predictions prior to treatment.

KEY POINTS

• Currently, the most common strategies for pre-surgical stratification of prostate cancer (PCa) patients have shown to have suboptimal performances. • The addition of radiological features to the clinical features gave a considerable boost in model performance. Our best model outperforms the naïve model, avoiding under-staging and resulting in a critical advantage in the clinic. •Machine learning models incorporating clinical, radiological, and radiomics features significantly improved accuracy of pathological prediction in prostate cancer, possibly constituting an asset to the clinical workflow.

Amide Proton Transfer-Weighted Magnetic Resonance Imaging for Application in Renal Fibrosis: A Radiological-Pathological-Based Analysis

INTRODUCTION

Renal fibrosis (RF), being the most important pathological change in the progression of CKD, is currently assessed by the evaluation of a biopsy. This present study aimed to apply a novel functional MRI (fMRI) protocol named amide proton transfer (APT) weighting to evaluate RF noninvasively.

METHODS

Male Sprague-Dawley (SD) rats were initially subjected to bilateral kidney ischemia/reperfusion injury (IRI), unilateral ureteral obstruction, and sham operation, respectively. All rats underwent APT mapping on the 7th and 14th days after operation. Besides, 26 patients underwent renal biopsy at the Nephrology Department of Shanghai Tongji Hospital between July 2022 and May 2023. Patients underwent APT and apparent diffusion coefficient (ADC) mappings within 1 week before biopsy. MRI results of both patients and rats were calculated by comparing with gold standard histology for fibrosis assessment.

RESULTS

In animal models, the cortical APT (cAPT) and medullary APT (mAPT) values were positively correlated with the degree of RF. Compared to the sham group, IRI group showed significantly increased cAPT and mAPT values on the 7th and 14th days after surgery, but no group differences were found in ADC values. Similar results were found in human patients. Cortical/medullary APT values were significantly increased in patients with moderate-to-severe fibrosis than in patients with mild fibrosis. ROC curve analysis indicated that APT value displayed a better diagnostic value for RF. Furthermore, combination of cADC and cAPT improved fibrosis detection by imaging variables alone (p < 0.1).

CONCLUSION

APT values had better diagnostic capability at early stage of RF compared to ADC values, and the addition of APT imaging to conventional ADC will significantly improve the diagnostic performance for predicting kidney fibrosis.

Robustness of magnetic resonance imaging and positron emission tomography radiomic features in prostate cancer: Impact on recurrence prediction after radiation therapy

Background and purpose

Radiomic features from MRI and PET are an emerging tool with potential to improve prostate cancer outcomes. However, feature robustness due to image segmentation variations is currently unknown. Therefore, this study aimed to evaluate the robustness of radiomic features with segmentation variations and their impact on predicting biochemical recurrence (BCR).

Materials and methods

Multi-scanner, pre-radiation therapy imaging from 142 patients with localised prostate cancer was used. Imaging included T2-weighted (T2), apparent diffusion coefficient (ADC) MRI, and prostate-specific membrane antigen (PSMA)-PET. The prostate gland and intraprostatic tumours were manually and automatically segmented, and differences were quantified using Dice Coefficient (DC). Radiomic features including shape, first-order, and texture features were extracted for each segmentation from original and filtered images. Intraclass Correlation Coefficient (ICC) and Mean Absolute Percentage Difference (MAPD) were used to assess feature robustness. Random forest (RF) models were developed for each segmentation using robust features to predict BCR.

Results

Prostate gland segmentations were more consistent (mean DC = 0.78) than tumour segmentations (mean DC = 0.46). 112 (3.6 %) radiomic features demonstrated 'excellent' robustness (ICC > 0.9 and MAPD < 1 %), and 480 features (15.4 %) demonstrated 'good' robustness (ICC > 0.75 and MAPD < 5 %). PET imaging provided more features with excellent robustness than T2 and ADC. RF models showed strong predictive power for BCR with a mean area under the receiver-operator-characteristics curve (AUC) of 0.89 (range 0.85-0.93).

Conclusion

When using radiomic features for predictive modelling, segmentation variability should be considered. To develop BCR predictive models, radiomic features from the entire prostate gland are preferable over tumour segmentation-based features.

Research on texture images and radiomics in urology: a review of urological MR imaging applications

PURPOSE OF REVIEW

Tumor volume and heterogenicity are associated with diagnosis and prognosis of urological cancers, and assessed by conventional imaging. Quantitative imaging, Radiomics, using advanced mathematical analysis may contain information imperceptible to the human eye, and may identify imaging-based biomarkers, a new field of research for individualized medicine. This review summarizes the recent literature on radiomics in kidney and prostate cancers and the future perspectives.

RECENT FINDINGS

Radiomics studies have been developed and showed promising results in diagnosis, in characterization, prognosis, treatment planning and recurrence prediction in kidney tumors and prostate cancer, but its use in guiding clinical decision-making remains limited at present due to several limitations including lack of external validations in most studies, lack of prospective studies and technical standardization.

SUMMARY

Future challenges, besides developing prospective and validated studies, include automated segmentation using artificial intelligence deep learning networks and hybrid radiomics integrating clinical data, combining imaging modalities and genomic features. It is anticipated that these improvements may allow identify these noninvasive, imaging-based biomarkers, to enhance precise diagnosis, improve decision-making and guide tailored treatment.