Predicting biochemical recurrence of prostate cancer with artificial intelligence

Artificial intelligence for detection of prostate cancer in biopsies during active surveillance

OBJECTIVES

To evaluate a cancer detecting artificial intelligence (AI) algorithm on serial biopsies in patients with prostate cancer on active surveillance (AS).

PATIENTS AND METHODS

A total of 180 patients in the Prostate Cancer Research International Active Surveillance (PRIAS) cohort were prospectively monitored using pre-defined criteria. Diagnostic and re-biopsy slides from 2011 to 2020 (n = 4744) were scanned and analysed by an in-house AI-based cancer detection algorithm. The algorithm was analysed for sensitivity, specificity, and for accuracy to predict need for active treatment. Prognostic properties of cancer size, prostate-specific antigen (PSA) level and PSA density at diagnosis were evaluated.

RESULTS

The sensitivity and specificity of the AI algorithm was 0.96 and 0.73, respectively, for correct detection of cancer areas. Original pathology report diagnosis was used as the reference method. The area of cancer estimated by the pathologists correlated highly with the AI detected cancer size (r = 0.83). By using the AI algorithm, 63% of the slides would not need to be read by a pathologist as they were classed as benign, at the risk of missing 0.55% slides containing cancer. Biopsy cancer content and PSA density at diagnosis were found to be prognostic of whether the patient stayed on AS or was discontinued for active treatment.

CONCLUSION

The AI-based biopsy cancer detection algorithm could be used to reduce the pathologists' workload in an AS cohort. The detected cancer amount correlated well with the cancer length measured by the pathologist and the algorithm performed well in finding even small areas of cancer. To our knowledge, this is the first report on an AI-based algorithm in digital pathology used to detect cancer in a cohort of patients on AS.

Updates on Management of Biochemical Recurrent Prostate Cancer

OPINION STATEMENT

Patients with biochemical recurrent prostate cancer (BCR) are a heterogeneous group, whereby a personalized approach to management is critical. Patients with high-risk features such as PSA doubling time (PSADT) ≤ 9-12 months warrant earlier imaging for metastasis detection and consideration for intensified therapy (beyond intermittent androgen deprivation alone) during this phase of BCR-only disease. The BCR phase represents a unique opportunity to impact disease survival and delay metastasis progression. There is compelling evidence from the EMBARK trial that ADT monotherapy is no longer the optimal consideration for high-risk BCR patients.

Genomics and Artificial Intelligence: Prostate Cancer

Artificial intelligence (AI) is revolutionizing prostate cancer genomics research. By leveraging machine learning and deep learning algorithms, researchers can rapidly analyze vast genomic datasets to identify patterns and correlations that may be missed by traditional methods. These AI-driven insights can lead to the discovery of novel biomarkers, enhance the accuracy of diagnosis, and predict disease progression and treatment response. As such, AI is becoming an indispensable tool in the pursuit of personalized medicine for prostate cancer.

Deep Learning Methodologies Applied to Digital Pathology in Prostate Cancer: A Systematic Review

Deep learning (DL), often called artificial intelligence (AI), has been increasingly used in Pathology thanks to the use of scanners to digitize slides which allow us to visualize them on monitors and process them with AI algorithms. Many articles have focused on DL applied to prostate cancer (PCa). This systematic review explains the DL applications and their performances for PCa in digital pathology. Article research was performed using PubMed and Embase to collect relevant articles. A Risk of Bias (RoB) was assessed with an adaptation of the QUADAS-2 tool. Out of the 77 included studies, eight focused on pre-processing tasks such as quality assessment or staining normalization. Most articles (n = 53) focused on diagnosis tasks like cancer detection or Gleason grading. Fifteen articles focused on prediction tasks, such as recurrence prediction or genomic correlations. Best performances were reached for cancer detection with an Area Under the Curve (AUC) up to 0.99 with algorithms already available for routine diagnosis. A few biases outlined by the RoB analysis are often found in these articles, such as the lack of external validation. This review was registered on PROSPERO under CRD42023418661.

Recurrent Prostate Cancer Diagnostics with 18F-PSMA-1007 PET/CT: A Systematic Review of the Current State

BACKGROUND

Early diagnosis of recurrent prostate cancer is a cornerstone for further adequate therapy planning. Therefore, clinical practice and research still focuses on diagnostic tools that can detect prostate cancer in early recurrence when it is undetectable in conventional diagnostic imaging. ¹⁸F-PSMA-1007 PET/CT is a novel method to evaluate patients with biochemical recurrent PCa. The aim of this review was to evaluate the role of ¹⁸F-PSMA-1007 PET/CT in prostate cancer local recurrence, lymph node metastases and bone metastases detection.

METHODS

Original studies, reviews and five meta-analyses were included in this article. A total of 70 studies were retrieved, 31 were included in the study.

RESULTS

All patients described in the studies underwent ¹⁸F-PSMA-1007 PET/CT. The administered ¹⁸F-PSMA-1007 individual dose ranged from 159 ± 31 MBq to 363.93 ± 69.40 MBq. Results showed that ¹⁸F-PSMA-1007 PET/CT demonstrates a good detection rate in recurrent prostate cancer.

CONCLUSIONS

¹⁸F-PSMA-1007 PET/CT appears to achieve reliable performance in detecting recurrent prostate cancer. The high detection rate of ¹⁸F-PSMA-1007 PET/CT in recurrent prostate cancer was confirmed, especially in local recurrence and small lymph nodes with non-specific characteristics on conventional diagnostic imaging methods. However, several authors emphasize some limitations for this tracer-for example, non-specific uptake in bone lesions that can mimic bone metastases.

Tumor Location and a Tumor Volume over 2.8 cc Predict the Prognosis for Japanese Localized Prostate Cancer

(1) Objective: Our study investigated the prognostic value of tumor volume and location in prostate cancer patients who received radical prostatectomy (RP). (2) Methods: The prognostic significance of tumor volume and location, together with other clinical factors, was studied using 557 patients who received RP. (3) Results: The receiver operating characteristic (ROC) curve identified the optimal cutoff value of tumor volume as 2.8 cc for predicting biochemical recurrence (BCR). Cox regression analysis revealed that a tumor in the posterior area (p = 0.031), peripheral zone (p = 0.0472), and tumor volume ≥ 2.8 cc (p < 0.0001) were predictive factors in univariate analysis. After multivariate analysis, tumor volume ≥ 2.8 cc (p = 0.0225) was an independent predictive factor for BCR. Among them, a novel risk model was established using tumor volume and location in the posterior area and peripheral zone. The progression-free survival (PFS) of patients who met the three criteria (unfavorable group) was significantly worse than other groups (p ≤ 0.001). Furthermore, multivariate analysis showed that the unfavorable risk was an independent prognostic factor for BCR. The prognostic significance of our risk model was observed in low- to intermediate-risk patients, although it was not observed in high-risk patients. (4) Conclusion: Tumor volume (≥2.8 cc) and localization (posterior/peripheral zone) may be a novel prognostic factor in patients undergoing RP.