PSMA-positive prostatic volume prediction with deep learning based on T2-weighted MRI

• DOI: 10.1007/s11547-024-01820-z
• Publication Date: 2024-05-03T10:02:15Z
• Authors: Riccardo Laudicella; Albert Comelli; Moritz Schwyzer; Alessandro Stefano; Ender Konukoglu; Michael Messerli; Sergio Baldari; Daniel Eberli; Irene A. Burger
• Keywords: Male; Glutamate Carboxypeptidase II; Artificial intelligence; 610 Medicine & health; Gallium Radioisotopes; 03 medical and health sciences; Deep Learning; 0302 clinical medicine; Predictive Value of Tests; 2741 Radiology, Nuclear Medicine and Imaging; Humans; Aged; Retrospective Studies; Prostate cancer; Artificial intelligence; Neural network; PET/MRI; Prediction; Prostate cancer; Prostate; Prostatic Neoplasms; 10181 Clinic for Nuclear Medicine; Organ Size; Middle Aged; Computer Application; Magnetic Resonance Imaging; Neural network; 10062 Urological Clinic; PET/MRI; Positron-Emission Tomography; Antigens, Surface; Radiopharmaceuticals; Prediction

Abstract Purpose High PSMA expression might be correlated with structural characteristics such as growth patterns on histopathology, not recognized by the human eye on MRI images. Deep structural image analysis might be able to detect such differences and therefore predict if a lesion would be PSMA positive. Therefore, we aimed to train a neural network based on PSMA PET/MRI scans to predict increased prostatic PSMA uptake based on the axial T2-weighted sequence alone.

Material and methods All patients undergoing simultaneous PSMA PET/MRI for PCa staging or biopsy guidance between April 2016 and December 2020 at our institution were selected. To increase the specificity of our model, the prostatic beds on PSMA PET scans were dichotomized in positive and negative regions using an SUV threshold greater than 4 to generate a PSMA PET map. Then, a C-ENet was trained on the T2 images of the training cohort to generate a predictive prostatic PSMA PET map.

Results One hundred and fifty-four PSMA PET/MRI scans were available (133 [68Ga]Ga-PSMA-11 and 21 [18F]PSMA-1007). Significant cancer was present in 127 of them. The whole dataset was divided into a training cohort (n = 124) and a test cohort (n = 30). The C-ENet was able to predict the PSMA PET map with a dice similarity coefficient of 69.5 ± 15.6%.

Conclusion Increased prostatic PSMA uptake on PET might be estimated based on T2 MRI alone. Further investigation with larger cohorts and external validation is needed to assess whether PSMA uptake can be predicted accurately enough to help in the interpretation of mpMRI.