Pre-treatment 18F-choline PET/CT is prognostic for biochemical recurrence, development of bone metastasis, and cancer specific mortality following radical local therapy of high-risk prostate cancer

Artificial intelligence-based measurements of PET/CT imaging biomarkers are associated with disease-specific survival of high-risk prostate cancer patients

OBJECTIVE

Artificial intelligence (AI) offers new opportunities for objective quantitative measurements of imaging biomarkers from positron-emission tomography/computed tomography (PET/CT). Clinical image reporting relies predominantly on observer-dependent visual assessment and easily accessible measures like SUV_max, representing lesion uptake in a relatively small amount of tissue. Our hypothesis is that measurements of total volume and lesion uptake of the entire tumour would better reflect the disease`s activity with prognostic significance, compared with conventional measurements.

METHODS

An AI-based algorithm was trained to automatically measure the prostate and its tumour content in PET/CT of 145 patients. The algorithm was then tested retrospectively on 285 high-risk patients, who were examined using ¹⁸F-choline PET/CT for primary staging between April 2008 and July 2015. Prostate tumour volume, tumour fraction of the prostate gland, lesion uptake of the entire tumour, and SUV_max were obtained automatically. Associations between these measurements, age, PSA, Gleason score and prostate cancer-specific survival were studied, using a Cox proportional-hazards regression model.

RESULTS

Twenty-three patients died of prostate cancer during follow-up (median survival 3.8 years). Total tumour volume of the prostate (p = 0.008), tumour fraction of the gland (p = 0.005), total lesion uptake of the prostate (p = 0.02), and age (p = 0.01) were significantly associated with disease-specific survival, whereas SUV_max (p = 0.2), PSA (p = 0.2), and Gleason score (p = 0.8) were not.

CONCLUSION

AI-based assessments of total tumour volume and lesion uptake were significantly associated with disease-specific survival in this patient cohort, whereas SUV_max and Gleason scores were not. The AI-based approach appears well-suited for clinically relevant patient stratification and monitoring of individual therapy.

Impact of pelvic dynamic acquisition on final reading of 18 F-Fluorocholine positron emission tomography in patients with prostate adenocarcinoma: True need or unnecessary burden?

INTRODUCTION

Despite the increasing use of ¹⁸ F-fluorocholine (¹⁸ F-FCH) positron emission tomography (PET) in patients with prostate cancer, the acquisition protocol remains debated. We have evaluated the influence of the pelvic dynamic phase on the final reading of whole-body ¹⁸ F-FCH PET, to assess the need for a two-stage protocol. Reading the physician's experience and patient's previous treatment profile was also considered as potential influencing factors on final PET interpretation.

METHODS

All ¹⁸ F-FCH PET/CT performed from January 2018 to September 2019 in patients with prostate cancer and including a pelvic dynamic phase followed by a delayed whole-body acquisition were retrospectively retrieved. PET/CT were analysed by one expert nuclear medicine physician and one resident. The whole-body scan was analysed blinded (first reading) and nonblinded from the results of the dynamic phase.

RESULTS

221 consecutive PET/CT were selected from 201 patients previously treated by radical prostatectomy (n = 31), pelvic radiation therapy (n = 60), or both (n = 94). 24 patients had no previous treatments, and 12 benefited from other focal treatments. In the whole population, dynamic acquisition modified final interpretation of 32/221 scans (14.5%) for residents, 26 (11.8%) for experts and 19 (8.6%) for consensual reading. No influence of previous treatments was found. The availability of a dynamic phase would have been responsible for treatment modification in 5/221 scans (2.3%). Considering only the prostate bed, dynamic acquisition modified the final interpretation in 7/125 (5.6%) studies (consensual reading) from patients with previous prostatic surgery and 4/84 (4.8%) scans from patients without a history of prostatic surgical intervention. No significant influence of dynamic acquisition was found on the final PET interpretation on prostate lodge accordingly to previous prostatic surgery.

CONCLUSION

The dynamic phase changes the interpretation of ¹⁸ F-FCH PET in about 9% of cases and the therapeutic strategy in <3% of patients. The influence of the early phase reduces with physician experience. Patient's treatment profile does not appear to have a significant influence on the variability of interpretation, also including the prostate bed.

Predicting early outcomes in patients with intermediate- and high-risk prostate cancer using prostate-specific membrane antigen positron emission tomography and magnetic resonance imaging

Objectives

To identify predictors of early oncological outcomes in patients who opt for robot‐assisted laparoscopic radical prostatectomy (RARP) for localized prostate cancer (PCa), including conventional prognostic variables as well as multiparametric magnetic resonance imaging (mpMRI) and prostate‐specific membrane antigen (PSMA) positron emission tomography (PET).

Patients and Methods

This observational study included 493 patients who underwent RARP and extended pelvic lymph node dissection (ePLND) for unfavourable intermediate‐ or high‐risk PCa. Outcome measurement was biochemical progression of disease, defined as any postoperative prostate‐specific antigen (PSA) value ≥0.2 ng/mL, or the start of additional treatment. Cox regression analysis was performed to assess predictors for biochemical progression, including initial PSA value, biopsy Grade Group (GG), T‐stage on mpMRI, and lymph node status on PSMA PET imaging (miN0 vs miN1).

Results

The median (interquartile range) total follow‐up of all included patients without biochemical progression was 12.6 (7.5–22.7) months. When assessing biochemical progression after surgery, initial PSA value (per doubling; odds ratio [OR] 1.22, 95% confidence interval [CI] 1.07–1.40; P = 0.004), biopsy GG ≥4 vs GG 1–2 (OR 1.83, 95% CI 1.18–2.85; P = 0.007), T‐stage on mpMRI (rT3a vs rT2: OR 2.13, 95% CI 1.39–3.27; P = 0.001; ≥rT3b vs rT2: OR 4.78, 95% CI 3.20–7.16; P < 0.001) and miN1 on PSMA PET imaging (OR 2.94, 95% CI 2.02–4.27; P < 0.001) were independent predictors of early biochemical progression of disease.

Conclusion

Initial PSA value, biopsy GG ≥4, ≥rT3 disease on mpMRI and miN1 disease on PSMA PET were predictors of early biochemical progression after RARP. Identifying these patients with an increased risk of early biochemical progression after surgery may have major implications for patient counselling in radical treatment decisions and on patient selection for modern (neo‐)adjuvant and systematic treatments.

Artificial intelligence-based detection of lymph node metastases by PET/CT predicts prostate cancer-specific survival

INTRODUCTION

Lymph node metastases are a key prognostic factor in prostate cancer (PCa), but detecting lymph node lesions from PET/CT images is a subjective process resulting in inter-reader variability. Artificial intelligence (AI)-based methods can provide an objective image analysis. We aimed at developing and validating an AI-based tool for detection of lymph node lesions.

METHODS

A group of 399 patients with biopsy-proven PCa who had undergone ¹⁸ F-choline PET/CT for staging prior to treatment were used to train (n = 319) and test (n = 80) the AI-based tool. The tool consisted of convolutional neural networks using complete PET/CT scans as inputs. In the test set, the AI-based lymph node detections were compared to those of two independent readers. The association with PCa-specific survival was investigated.

RESULTS

The AI-based tool detected more lymph node lesions than Reader B (98 vs. 87/117; p = .045) using Reader A as reference. AI-based tool and Reader A showed similar performance (90 vs. 87/111; p = .63) using Reader B as reference. The number of lymph node lesions detected by the AI-based tool, PSA, and curative treatment was significantly associated with PCa-specific survival.

CONCLUSION

This study shows the feasibility of using an AI-based tool for automated and objective interpretation of PET/CT images that can provide assessments of lymph node lesions comparable with that of experienced readers and prognostic information in PCa patients.