PCa Commentary | Volume 181 – September 2023

Posted by Edward Weber | September 2023

PSMA PET/CT Staging of Advanced Prostate Cancer and
Artificial Intelligence Guidance in Combining ADT with Radiation

Background

The function of initial staging of prostate cancer is to accurately estimate the risk of progression in order to guide optimal therapy. The influential National Comprehensive Cancer Network (NCCN)
recommends a PSMA PET/CT as part of initial staging for men in the risk categories of intermediate- and high-risk cancer as defined by clinicopathologic features: PSA, Gleason score, clinical tumor stage and number of positive biopsy cores. For men with a life expectancy of >10 years molecular analysis (i.e., Decipher, Prolaris or OncotypeDx Prostate) is suggested by the NCCN.

PSMA PET/CT in advanced cancer identifies lesions that are missed on conventional CT and bone scans. Yaxley et al., BJU Int 2019 reported the results of primary staging by PSMA PET/CT in 1253 men, half and half with intermediate and high-risk disease in the largest published study on this subject. Metastases were identified in 12.1%; 8.2% in men with PSA values <10 ng/ml and 47% with PSA values > 20 ng/mL. Segregated by Gleason Grade, metastases were found in 6.4% with GG 2-3 (Gleason 3+3 and 3+4). Extra-pelvic lymph nodes occurred in 47%. Bone metastases were found in 5.2% in men with intermediate-risk and in 20% high-risk cancer.

Enter the Immune System — Its Influence on Cancer Behavior

The influence of immune cell infiltration within the tumor and from the surrounding microenvironment is not taken into account in assigning a Gleason score and therefore is not considered in the NCCN classifications of risk. The variety of promoter and suppressive lymphocytes and macrophages that comprise these infiltrations are not fully identified under the microscope and play no role in standard risk assessments.

The immune microenvironment of the primary tumor influences both the initiation and early progression (i.e., toward a higher Gleason score) of the developing cancer. Immune elements compete (i.e., pro-tumor and anti-tumor) to suppress malignant clones from progressing — while others promote disorganization and aggressiveness. Protective cells include immune enhancing CD8+T-cells, Killer T-cells, protective macrophages; immune suppressive cells include T-regulation cells and immune suppressive macrophages. In fact, recent studies reveal that the ratio of one particular gene in anti-tumor macrophages to a different gene in pro-tumor macrophages can by itself determine the outcome in a man’s cancer — and possibly all cancers. (Bill et al., SCIENCE, Aug 2023).

These immune cellular elements are not only found within and surrounding tumors but also can be identified in the blood to various amounts. Based on their presence in the blood, Chinese researchers have “developed and validated a machine-learning nomogram for the prediction of risk stratification of prostate cancer based on subsets of these lymphocytes in the blood.” This nomogram functioned better than the standard NCCN prognostic risk groups. (Yang et al., Journal of Translational Medicine 2023.)

The Predictive Power of Artificial Intelligence

The genomic classifier Decipher has been multiply validated to estimate prognosis based on its risk scale of 0 to 1.0. However, AI has the capability to derive a prediction — for example of an individual man’s response to a given treatment. When whole mount pathology slides, multiply stained, are digitized into a scanner, the AI process identifies standard histology but also detects the subtypes of immune cells infiltrating the tumor and the surrounding microenvironment. This comprehensive analysis presents a complete picture of a man’s cancer, its predicted behavior and supports individualized management.

Two Examples of Clinically Useful Applications of AI for Intensifying or De-intensifying
Therapy

1. Commentary #180 discusses a study assessing the relative benefits of adding ADT to
   radiation therapy in men with advanced cancer based on a derived biomarker.
2. At the 2023 annual meeting of the American Society of Clinical Oncology, Armstrong and
   colleagues from Duke University presented their abstract, “Development and validation of an
   AI-derived digital pathology-based biomarker to predict benefit of long-term androgen deprivation therapy with radiotherapy in men with localized high-risk prostate cancer across
   multiple phase III NRG/RTOG trials,” i.e., a goal “to guide ADT duration to maximize benefits
   and minimize risks.”
   “Pre-treatment prostate biopsy slides were digitized from six randomized trials evaluating the
   benefit of radiation therapy +/- ADT” in men with localized high-risk prostate cancer with end
   points of distant metastases (DM) and prostate cancer-specific mortality. The data from this
   training set was then validated in a major trial comparing radiation plus 4 vs. 28 months of ADT and determined a distinguishing biomarker. Their study found that 28 months of ADT was 13% better than 4 months in the biomarker-positive group as compared to only 2% better in the biomarker-negative group, a finding that could influence clinical decision-making.

[A spokesman for Artera AI.com said the company is working on developing a test based on this
study for commercial availability.]

BOTTOM LINE

PSMA PET/CT scans and applications of AI in prostate cancer management are aiding individualized patient management.

“We appreciate the unfailing assistance of the librarians at Providence/Swedish.”