Dataset Information

Deep learning based on 68Ga-PSMA-11 PET/CT for predicting pathological upgrading in patients with prostate cancer.

ABSTRACT:

Objectives

To explore the feasibility and importance of deep learning (DL) based on 68Ga-prostate-specific membrane antigen (PSMA)-11 PET/CT in predicting pathological upgrading from biopsy to radical prostatectomy (RP) in patients with prostate cancer (PCa).

Methods

In this retrospective study, all patients underwent 68Ga-PSMA-11 PET/CT, transrectal ultrasound (TRUS)-guided systematic biopsy, and RP for PCa sequentially between January 2017 and December 2022. Two DL models (three-dimensional [3D] ResNet-18 and 3D DenseNet-121) based on 68Ga-PSMA-11 PET and support vector machine (SVM) models integrating clinical data with DL signature were constructed. The model performance was evaluated using area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

Results

Of 109 patients, 87 (44 upgrading, 43 non-upgrading) were included in the training set and 22 (11 upgrading, 11 non-upgrading) in the test set. The combined SVM model, incorporating clinical features and signature of 3D ResNet-18 model, demonstrated satisfactory prediction in the test set with an AUC value of 0.628 (95% confidence interval [CI]: 0.365, 0.891) and accuracy of 0.727 (95% CI: 0.498, 0.893).

Conclusion

A DL method based on 68Ga-PSMA-11 PET may have a role in predicting pathological upgrading from biopsy to RP in patients with PCa.

SUBMITTER: Zang S

PROVIDER: S-EPMC10800856 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning based on 68Ga-PSMA-11 PET/CT for predicting pathological upgrading in patients with prostate cancer.

Zang Shiming S Jiang Cuiping C Zhang Lele L Fu Jingjing J Meng Qingle Q Wu Wenyu W Shao Guoqiang G Sun Hongbin H Jia Ruipeng R Wang Feng F

Frontiers in oncology 20240108

<h4>Objectives</h4>To explore the feasibility and importance of deep learning (DL) based on 68Ga-prostate-specific membrane antigen (PSMA)-11 PET/CT in predicting pathological upgrading from biopsy to radical prostatectomy (RP) in patients with prostate cancer (PCa).<h4>Methods</h4>In this retrospective study, all patients underwent 68Ga-PSMA-11 PET/CT, transrectal ultrasound (TRUS)-guided systematic biopsy, and RP for PCa sequentially between January 2017 and December 2022. Two DL models (three ...[more]

PMID: 38260839

Similar Datasets

Project description:Objective:To synthesize 68Ga-Glu-urea-Lys(Ahx)-HBED-CC (68Ga-PSMA-11) with a synthesis module and investigate PET-CT imaging to monitor PSMA expression during prostate cancer (PCa) progression and tumor growth in mice bearing subcutaneous PCa xenografts. Method:The radiochemical purity and stability of 68Ga-PSMA-11 were determined via radio-HPLC. The PCa cell lines of different PSMA expression levels (PC3, VCAP±, CWR22RV1+, and LNCaP++) were selected to mimic the PCa progression. 68Ga-PSMA-11 biodistribution was studied by dissection method and in vivo imaging with micro PET-CT. The expression levels of PSMA in tumor cells and tissues were analyzed by immunofluorescence, flow cytometry, and western blot. The correlation between PSMA expression and radio-uptake was also evaluated. 2-PMPA preadministration served as a block group. Results:The radiochemical purity of 68Ga-PSMA-11 was 99.6 ± 0.1% and stable in vitro for 2 h. The equilibrium binding constant (Kd) of 68Ga-PSMA-11 to LNCaP, CWR22Rv1, PC-3, and VCAP cells was 4.3 ± 0.8 nM, 16.4 ± 1.3 nM, 225.3 ± 20.8 nM, and 125.6 ± 13.1 nM, respectively. Results of tumor uptake (% ID and % ID/g or % ID/cm3) of 68Ga-PSMA-11 in biodistribution and micro PET imaging were LNCaP > CWR22RV1 > PC-3 and VCAP due to different PSMA expression levels. It was confirmed by flow cytometry, western blot, and immunofluorescence. Tumor uptake (% ID/cm3) of 68Ga-PSMA-11 increased with the tumor anatomical volume in quadratic polynomial fashion and reached the peak (when tumor volume was 0.5 cm3) earlier than tumor uptake (% ID). Tumor uptake (% ID/cm3) of 68Ga-PSMA-11 based on functional volume correlated well with the PSMA expression in a linear manner (y = 9.35x + 2.59, R2 = 0.8924, and p < 0.0001); however, low dose 2-PMPA causes rapid renal clearance of increased tumor/kidney uptake of 68Ga-PSMA-11. Conclusions:The 68Ga-PSMA-11 PET-CT imaging could invasively evaluate PSMA expression during PCa progression and tumor growth with % ID/cm3 (based on functional volume) as an important index. Low dose 2-PMPA preadministration might be a choice to decrease kidney uptake of 68Ga-PSMA-11.

Project description:Combined positron emission tomography (PET) and magnetic resonance imaging (MRI) targeting the prostate-specific membrane antigen (PSMA) with a 68Ga-labelled PSMA-analog (68Ga-PSMA-11) is discussed as a promising diagnostic method for patients with suspicion or history of prostate cancer. One potential drawback of this method are severe photopenic (halo-) artifacts surrounding the bladder and the kidneys in the scatter-corrected PET images, which have been reported to occur frequently in clinical practice. The goal of this work was to investigate the occurrence and impact of these artifacts and, secondly, to evaluate variants of the standard scatter correction method with regard to halo-artifact suppression.Experiments using a dedicated pelvis phantom were conducted to investigate whether the halo-artifact is modality-, tracer-, and/or concentration-dependent. Furthermore, 31 patients with history of prostate cancer were selected from an ongoing 68Ga-PSMA-11-PET/MRI study. For each patient, PET raw data were reconstructed employing six different variants of PET scatter correction: absolute scatter scaling, relative scatter scaling, and relative scatter scaling combined with prompt gamma correction, each of which was combined with a maximum scatter fraction (MaxSF) of MaxSF = 75% or MaxSF = 40%. Evaluation of the reconstructed images with regard to halo-artifact suppression was performed both quantitatively using statistical analysis and qualitatively by two independent readers.The phantom experiments did not reveal any modality-dependency (PET/MRI vs. PET/CT) or tracer-dependency (68Ga vs. 18F-FDG). Patient- and phantom-based data indicated that halo-artifacts derive from high organ-to-background activity ratios (OBR) between bladder/kidneys and surrounding soft tissue, with a positive correlation between OBR and halo size. Comparing different variants of scatter correction, reducing the maximum scatter fraction from the default value MaxSF = 75% to MaxSF = 40% was found to efficiently suppress halo-artifacts in both phantom and patient data. In 1 of 31 patients, reducing the maximum scatter fraction provided new PET-based information changing the patient's diagnosis.Halo-artifacts are particularly observed for 68Ga-PSMA-11-PET/MRI due to 1) the biodistribution of the PSMA-11-tracer resulting in large OBRs for bladder and kidneys and 2) inaccurate scatter correction methods currently used in clinical routine, which tend to overestimate the scatter contribution. If not compensated for, 68Ga-PSMA-11 uptake pathologies may be masked by halo-artifacts leading to false-negative diagnoses. Reducing the maximum scatter fraction was found to efficiently suppress halo-artifacts.

Project description:BackgroundAndrogen deprivation therapy (ADT) remains the standard therapy for patients with oligometastatic prostate cancer (OMPC). Prostate-specific membrane antigen positron emission tomography/computed tomography (PSMA-PET/CT)-based stereotactic body radiotherapy (SBRT) is emerging as an alternative option to postpone starting ADT and its associated side effects including the development of drug resistance. The aim of this study was to determine progression free-survival (PFS) and treatment failure free-survival (TFFS) after PSMA-PET/CT-based SBRT in OMPC patients. The efficacy and safety of single fraction radiosurgery (SFRS) and ADT delay were investigated.MethodsPatients with ≤5 metastases from OMPC, with/without ADT treated with PSMA-PET/CT-based SBRT were retrospectively analyzed. PFS and TFFS were primary endpoints. Secondary endpoints were local control (LC), overall survival (OS) and ADT-free survival (ADTFS).ResultsFifty patients with a total of 75 metastases detected by PSMA-PET/CT were analyzed. At the time of SBRT, 70% of patients were castration-sensitive. Overall, 80% of metastases were treated with SFRS (median dose 20 Gy, range: 16-25). After median follow-up of 34 months (range: 5-70) median PFS and TFFS were 12 months (range: 2-63) and 14 months (range: 2-70), respectively. Thirty-two (64%) patients had repeat oligometastatic disease. Twenty-four (48%) patients with progression underwent second SBRT course. Two-year LC after SFRS was 96%. Grade 1 and 2 toxicity occurred in 3 (6%) and 1 (2%) patients, respectively. ADTFS and OS rates at 2-years were 60.5% and 100%, respectively. In multivariate analysis, TFFS significantly improved in patients with time to first metastasis (TTM) >36 months (p = 0.01) and PSA before SBRT ≤1 ng/ml (p = 0.03).ConclusionFor patients with OMPC, SBRT might be used as an alternative to ADT. This way, the start/escalation of palliative ADT and its side effects can be deferred. Metastases treated with PSMA-PET/CT-based SFRS reached excellent LC with minimal toxicity. Low PSA levels and longer TTM predict elongated TFFS.

Project description:ObjectiveThis study aimed to evaluate predictors for upgrading of newly diagnosed prostate cancer from systematic biopsy (SB) to radical prostatectomy (RP) using fluorine-18 prostate-specific membrane antigen 1007 (18F-PSMA-1007) positron emission tomography/computed tomography (PET/CT) and association with clinical parameters.Materials and methodsWe retrospectively collected data from biopsy-confirmed prostate cancer (PCa) patients who underwent 18F-PSMA-1007 PET/CT prior to RP from July 2019 and October 2022. Imaging characteristics derived from 18F-PSMA-1007 PET/CT and clinical parameters were compared in patients of pathological upgrading and concordance subgroups. Univariable and multivariable logistic regressions were performed to analyze factors predicting histopathological upgrading from SB to RP specimens. Discrimination ability of independent predictors was further evaluated by receiver operating characteristic (ROC) analysis with corresponding area under the curve (AUC).ResultsPathological upgrading occurred in 26.97% (41/152) PCa patients, and 23.03% (35/152) of all patients experienced pathological downgrading. Concordance rate reached 50% (76/152). International Society of Urological Pathology grade group (ISUP GG) 1(77.78%) and ISUP GG 2 (65.22%) biopsies were related with the highest rate of upgrading. Multivariable logistic regression analyses showed that prostate volume (OR= 0.933; 95% CI, 0.887-0.982; p = 0.008), ISUP GG 1 vs. 4 (OR= 13.856; 95% CI: 2.467-77.831; p = 0.003), and total uptake of PSMA-avid lesions (PSMA-TL) (OR = 1.003; 95% CI, 1.000-1.006; p = 0.029) were found to be independent risk factors of pathological upgrading after RP. The AUCs and corresponding sensitivity and specificity of the independent predictors of synthesis for upgrading were 0.839, 78.00%, and 83.30% respectively, which showed good discrimination capacity.Conclusion18F-PSMA-1007 PET/CT may help to predict pathological upgrading between biopsy and RP specimens, particularly for ISUP GG 1 and ISUP GG 2 patients with higher PSMA-TL and smaller prostate volume.

Dataset Information

Deep learning based on 68Ga-PSMA-11 PET/CT for predicting pathological upgrading in patients with prostate cancer.

Objectives

Methods

Results

Conclusion

Publications

Deep learning based on 68Ga-PSMA-11 PET/CT for predicting pathological upgrading in patients with prostate cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets