(UroToday.com) The 2024 GU ASCO annual meeting featured a prostate cancer session and a presentation by Dr. Francisco Osvaldo Garcia-Perez discussing the prognostic value of artificial intelligence–driven tumor estimation of PSMA PET total tumor burden in newly diagnosed high-volume metastatic hormone-sensitive prostate cancer (mHSPC). Prostate cancer represents a significant economic burden for health systems.
The identification of risk factors that allow the identification of subgroups of patients that require closer follow-up or more intense therapeutic regimens has a direct impact on the prognosis and expenses for the patient. There is currently great interest in patients with high-volume mHSPC, which is defined according to the number of lesions and their location. Identifying these patients could represent a challenge in decision making due to the variety of presentations regarding tumor burden. Currently, with the development of artificial intelligence algorithms, it is possible to estimate the PSMA total tumor burden by identifying patients who are candidates for specific therapies without exposing them to side effects associated with aggressive regimens. The following are examples of patients with high volume mHSPC segmented with artificial intelligence:
Baseline PSMA PET scans of patients with histopathological corroborated diagnosis of prostate cancer and considered as high volume according to 68Ga PSMA PET/CT imaging in the period from October 2017 to June 2020 were retrospectively analyzed using an automated algorithm to estimate PSMA total tumor burden. These patients were divided into two groups according to the optimal cutoff values of PSMA total tumor burden (45 cm3). Progression-free survival after initial therapy was estimated with Kaplan-Meier curves and correlation index between tumor burden and PSA.
There were 53 patients with a mean age of 71 years (+/- 5.1) that were included in this study, with 17 patients having Gleason 7 (4+3/3+4) prostate cancer, 18 with Gleason 8 (4+4) prostate cancer, 15 with Gleason 9 (5+4/4+5), and 3 with Gleason 10 (5+5). Sites of visceral disease were lung (n = 11), pleura (n = 9), liver (n = 9), adrenal, (n = 5) brain, (n = 2), and sites of extra spinal and pelvic disease were ribs (n = 24), femur (n = 16), skull (n = 8), scapula (n = 7), and humerus (n = 7). For ISUP group 3 (n = 17), group 4 (n = 18) group 5 (n = 18), the mean PSA value at diagnosis was 62.1 ng/dL (range 25.2- 201.5). The median follow-up was of 44 +/- 9.7 months, and mean PSMA total tumor burden was 100.1cm3 (range: 21cm3- 518.8 cm3). Log-rank test revealed that PSMA total tumor burden lower than 45 cm3 (n = 21) was associated with shorter progression-free survival in comparison with patients with PSMA total tumor burden higher than 45 cm3 (n = 32) (31.1 months vs 47.8 months, HR 0.56, 95% CI 0.63-0.95; p <0.003):
Total tumor burden and PSA also demonstrated a significant correlation (Pearson r= 0.526, p< 0.0001):
There was no difference between groups of low and high PSMA total tumor burden and ISUP groups (p = 0.78) or Gleason score (p = 0.81).
Dr. Garcia-Perez concluded his presentation discussing the prognostic value of artificial intelligence–driven tumor estimation of PSMA PET total tumor burden in newly diagnosed high-volume mHSPC with the following take-home points:
- PSMA total tumor burden has value in predicting progression-free survival of patients with newly diagnosed high-volume mHSPC
- There is a strong correlation with PSA, strengthening the role of next-generation molecular imaging with PSMA PET as a tool in initial diagnosis and potentially in follow-up by providing information on the biological behavior of the disease
Presented by: Francisco Osvaldo Garcia-Perez, MD, Instituto Nacional de Cancerologia. Mexico City, Mexico
Written by: Zachary Klaassen, MD, MSc – Urologic Oncologist, Associate Professor of Urology, Georgia Cancer Center, Wellstar MCG Health, @zklaassen_md on Twitter during the Genitourinary (GU) American Society of Clinical Oncology (ASCO) Annual Meeting, San Francisco, CA, Thurs, Jan 25 – Sat, Jan 27, 2024.