New research suggests that an emerging deep learning-based algorithm based on biparametric magnetic resonance imaging (bpMRI) may provide a viable alternative for detecting prostate cancer recurrence in patients with large gland volumes and those previously treated with external beam radiation treatment (EBRT).
For the study, recently published in the European Journal of Radiology, researchers compared a bpMRI-based deep learning model versus prospective radiologist assessment of multiparametric MRI (mpMRI) for prostate cancer (PCa) recurrence in 62 patients (median age of 70) who had prior radiotherapy treatment for the disease. All patients in the cohort had mpMRI and subsequent MRI/ultrasound fusion-guided and/or systematic biopsy, according to the study.
Out of 46 patients who had a total of 56 recurrent PCa foci, the researchers found the deep learning model detected a total of 40 lesions in 35 patients. In comparison to prospective interpretation by radiology with mpMRI, the deep learning model had a 15.2 percent lower sensitivity at the patient level (76.1 percent vs. 91.3 percent) and a 16.1 percent lower sensitivity at the lesion level (71.4 percent vs. 87.5 percent).
Here one can see imaging, including T2-weighted MRI (A), diffusion-weighted MRI (C) and dynamic contrast-enhanced MRI (D), for an 82-year-old male who had a serum PSA level of 9.33 ng/ml and previous external beam radiation therapy (EBRT) for prostate cancer. The lesions in the right mid-base anterior transition zone (see arrows) and the right mid-periurethral transition zone (see arrowhead) were also detected with AI prediction and probability maps (see E and F) and were confirmed as prostate cancer recurrence with targeted biopsies. (Images courtesy of the European Journal of Radiology.)
The study authors also noted that in patients with prior external beam radiation treatment (EBRT), the deep learning model had an 81.5 percent sensitivity rate at the patient level and a 79.4 percent sensitivity rate at the lesion level for PCa recurrence. For patients with gland volumes greater than 34 ml, the researchers found that the deep learning model had a 100 percent sensitivity rate at the patient level and a 94.1 percent sensitivity rate at the lesion level.
“Although our findings are preliminary, they suggest that an end-to-end, bpMRI-based AI may detect and localize most of the local recurrences following an initial course of radiotherapy without requiring one of the essential components of mpMRI: DCE,” wrote Baris Turkbey, M.D., a senior clinician and radiologist at the National Cancer Institute and the National Institutes of Health in Rockville, Md., and colleagues.
“Moreover, avoiding contrast injection with the application of this bpMRI-based AI-detection algorithm could render more frequent, routine imaging a viable strategy in the post-radiotherapy surveillance. This may serve as a companion to PSA monitoring to possibly allow for early detection and intervention for the subgroup of patients with locally recurrent prostate cancer.”
Three Key Takeaways
1. Enhanced detection in large gland volumes. The study suggests that a deep learning algorithm based on biparametric MRI (bpMRI) shows promise in detecting prostate cancer recurrence, particularly in patients with larger gland volumes. The algorithm achieved 100 percent sensitivity in patients with gland volumes greater than 34 ml, indicating its potential as a valuable tool for detecting recurrence in this subgroup.
2. Sensitivity rates in previous EBRT patients. For patients who had undergone external beam radiation treatment (EBRT) in the past, the deep learning model demonstrated an 81.5 percent sensitivity rate at the patient level and a 79.4 percent sensitivity rate at the lesion level for prostate cancer recurrence. This finding suggests that the algorithm may be particularly effective in identifying recurrence in EBRT-treated patients.
3. Potential for routine post-radiotherapy surveillance. The study suggests that the bpMRI-based AI detection algorithm could reduce the need for contrast injections and make routine imaging a viable strategy for post-radiotherapy surveillance of prostate cancer. This approach, combined with PSA monitoring, may facilitate early detection and intervention for patients with locally recurrent prostate cancer.
The study authors pointed out that the mean prostate volume in the study cohort (27.55 ml) was less than half of that in the in the training set for the deep learning model (60 ml), and that prior treatments of EBRT and brachytherapy both contribute to significantly reduced gland volume. Turkbey and colleagues also suggested the lesions may be more apparent on MRI for patients with a higher gland volume.
“It is worth noting that we have observed better detection performance of AI in EBRT patients, and their median gland volume (30.35 ml) was higher than patients who received brachytherapy (25.5 ml). Thus, rather than a direct association between the prostate size and AI detection rate, the technique of treatment could be the primary factor impacting both the AI model performance and the gland size,” added Turkbey and colleagues.
(Editor’s note: For related content, see "Emerging Nomogram May Predict Outcomes After PSMA PET-Guided Salvage Radiotherapy in Patients with Prostate Cancer," “Utilizing AI for Quantitative Assessment of Prostate Cancer Recurrence” and “Can an Emerging PET Radiotracer be a Viable Alternative to Multiparametric MRI for Detecting Prostate Cancer Recurrence?”)
In regard to study limitations, the authors acknowledged the relatively small sample size drawn from a single institution. Noting that the AI model in the study prohibited predictions outside of prostate segmentation, the study authors explained that the model could not detect tumors in the seminal vesicles. The researchers also acknowledged that reported false positive rates with the AI model may have been inflated as a result of the authors identifying AI predictions outside of the targeted biopsy region as false positives in patients who did not have a systematic biopsy.