Improving the Diagnosis of Clinically Significant Prostate Cancer with Magnetic Resonance Imaging

Automated prostate multi-regional segmentation in magnetic resonance using fully convolutional neural networks

OBJECTIVE

Automatic MR imaging segmentation of the prostate provides relevant clinical benefits for prostate cancer evaluation such as calculation of automated PSA density and other critical imaging biomarkers. Further, automated T2-weighted image segmentation of central-transition zone (CZ-TZ), peripheral zone (PZ), and seminal vesicle (SV) can help to evaluate clinically significant cancer following the PI-RADS v2.1 guidelines. Therefore, the main objective of this work was to develop a robust and reproducible CNN-based automatic prostate multi-regional segmentation model using an intercontinental cohort of prostate MRI.

METHODS

A heterogeneous database of 243 T2-weighted prostate studies from 7 countries and 10 machines of 3 different vendors, with the CZ-TZ, PZ, and SV regions manually delineated by two experienced radiologists (ground truth), was used to train (n = 123) and test (n = 120) a U-Net-based model with deep supervision using a cyclical learning rate. The performance of the model was evaluated by means of dice similarity coefficient (DSC), among others. Segmentation results with a DSC above 0.7 were considered accurate.

RESULTS

The proposed method obtained a DSC of 0.88 ± 0.01, 0.85 ± 0.02, 0.72 ± 0.02, and 0.72 ± 0.02 for the prostate gland, CZ-TZ, PZ, and SV respectively in the 120 studies of the test set when comparing the predicted segmentations with the ground truth. No statistically significant differences were found in the results obtained between manufacturers or continents.

CONCLUSION

Prostate multi-regional T2-weighted MR images automatic segmentation can be accurately achieved by U-Net like CNN, generalizable in a highly variable clinical environment with different equipment, acquisition configurations, and population.

KEY POINTS

• Deep learning techniques allows the accurate segmentation of the prostate in three different regions on MR T2w images. • Multi-centric database proved the generalization of the CNN model on different institutions across different continents. • CNN models can be used to aid on the diagnosis and follow-up of patients with prostate cancer.

Initial phantom studies for an office-based low-field MR system for prostate biopsy

Purpose

Prostate cancer is the second most prevalent cancer in US men, with about 192,000 new cases and 33,000 deaths predicted for 2020. With only a 31% 5-year survival rate for patients with an initial diagnosis of stage-four prostate cancer, the necessity for early screening and diagnosis is clear. In this paper, we present navigation accuracy results for Promaxo’s MR system intended to be used in a physician’s office for image-guided transperineal prostate biopsy.

Methods

The office-based low-field MR system was used to acquire images of prostate phantoms with needles inserted through a transperineal template. Coordinates of the estimated sample core locations in the office-based MR system were compared to ground truth needle coordinates identified in a 1.5T external reference scan. The error was measured as the distance between the planned target and the ground truth core center and as the shortest perpendicular distance between the planned target and the ground truth trajectory of the whole core.

Results

The average error between the planned target and the ground truth core center was 2.57 ± 1.02 mm, [1.93–3.21] 95% CI. The average error between the planned target to the actual core segment was 2.05 ± 1.24 mm, [1.53–2.56] 95% CI.

Conclusion

The average navigation errors were below the clinically significant threshold of 5 mm. The initial phantom results demonstrate the feasibility of the office-based system for prostate biopsy.

Role of metabolic imaging in diagnosis of primary, metastatic, and recurrent prostate cancer

PURPOSE OF REVIEW

The present review describes the current role of metabolic imaging techniques such as multiparametric MRI (mpMRI), magnetic resonance spectroscopic imaging (MRSI), hyperpolarized MRSI, and positron emission tomography (PET) in the diagnosis of primary prostate cancer, surveillance of low-grade disease, detection of metastases, and evaluation of biochemical recurrence after therapy.

RECENT FINDINGS

The natural history of prostate cancer ranges from indolent disease that is optimally monitored by active surveillance, to highly aggressive disease that can be lethal. Current diagnostic methods remain imperfect in noninvasively distinguishing between silent versus aggressive tumors. Hence, there is a high demand for noninvasive imaging techniques that offer insight into biological behavior of prostate cancer cells. Characterization of prostate cancer metabolism is a promising area to provide such insights.

SUMMARY

Metabolic imaging may allow for greater detection and ultimately characterization of tumor based on aggressiveness and spread. Hence, it has the potential to monitor tumor activity, predict prognostic outcomes, and guide individualized therapies.

Detection and Localization of Prostate Cancer at 3-T Multiparametric MRI Using PI-RADS Segmentation

OBJECTIVE. The purpose of this study is to determine the overall and sector-based performance of 3-T multiparametric MRI for prostate cancer (PCa) detection and localization by using Prostate Imaging-Reporting and Data System version 2 (PI-RADSv2) scoring and segmentation compared with whole-mount histopathologic analysis. MATERIALS AND METHODS. Multiparametric 3-T MRI examinations of 415 consecutive men were compared with thin-section whole-mount histopathologic analysis. A genitourinary radiologist and pathologist collectively determined concordance. Two radiologists assigned PI-RADSv2 categories and sectoral location to all detected foci by consensus. Tumor detection rates were calculated for clinical and pathologic (Gleason score) variables. Both rigid and adjusted sector-matching models were used to account for fixation-related issues. RESULTS. The 415 patients had 863 PCa foci (52.7% had a Gleason score ≥ 7, 61.9% were ≥ 1 cm, and 90.4% (375/415) of index lesions were ≥ 1 cm) and 16,185 prostate sectors. Multiparametric MRI enabled greater detection of PCa lesions 1 cm or larger (all lesions vs index lesions, 61.6% vs 81.6%), lesions with Gleason score greater than or equal to 7 (all lesions vs index lesions, 71.4% vs 80.9%), and index lesions with both Gleason score greater than or equal to 7 and size 1 cm or larger (83.3%). Higher sensitivity was obtained for adjusted versus rigid tumor localization for all lesions (56.0% vs 28.5%), index lesions (55.4% vs 34.3%), lesions with Gleason score greater than or equal to 7 (55.7% vs 36.0%), and index lesions 1 cm or larger (56.1% vs 35.0%). Multiparametric 3-T MRI had similarly high specificity (96.0-97.9%) for overall and index tumor localization with adjusted and rigid sector-matching approaches. CONCLUSION. Using 3-T multiparametric MRI and PI-RADSv2, we achieved the highest sensitivity (83.3%) for the detection of lesions 1 cm or larger with Gleason score greater than or equal to 7. Sectoral localization of PCa within the prostate was moderate and was better with an adjusted model than with a rigid model.