Deep learning‐based quantification of PET/CT prostate gland uptake: association with overall survival

• Published in: Clinical physiology and functional imaging Vol. 40; no. 2; pp. 106 - 113
• Main Authors: Polymeri, Eirini, Sadik, May, Kaboteh, Reza, Borrelli, Pablo, Enqvist, Olof, Ulén, Johannes, Ohlsson, Mattias, Trägårdh, Elin, Poulsen, Mads H., Simonsen, Jane A., Hoilund‐Carlsen, Poul Flemming, Johnsson, Åse A., Edenbrandt, Lars
• Format: Journal Article
• Language: English
• Published: England Wiley Subscription Services, Inc 01.03.2020; John Wiley and Sons Inc
• Subjects: Algorithms; Antigens; artificial intelligence; Automation; Biomarkers; Biopsy; Choline; Clinical Medicine; Computed tomography; convolutional neural network; Deep learning; Engineering and Technology; Image processing; Image segmentation; Klinisk medicin; Medical and Health Sciences; Medical Engineering; Medical Image Processing; Medical imaging; Medicin och hälsovetenskap; Medicinsk bildbehandling; Medicinteknik; objective quantification; Observers; Original; Positron emission; Positron emission tomography; Prostate cancer; prostatic neoplasms; Radioactive tracers; Radiologi och bildbehandling; Radiology, Nuclear Medicine and Medical Imaging; Regression analysis; Regression models; Survival; Teknik; Tomography; Tumors; Urologi och njurmedicin; Urology and Nephrology; objective quantification; convolutional neural network; artificial intelligence; prostatic neoplasms
• ISSN: 1475-0961; 1475-097X; 1475-097X
• DOI: 10.1111/cpf.12611

Summary Aim To validate a deep‐learning (DL) algorithm for automated quantification of prostate cancer on positron emission tomography/computed tomography (PET/CT) and explore the potential of PET/CT measurements as prognostic biomarkers. Material and methods Training of the DL‐algorithm regarding prostate volume was performed on manually segmented CT images in 100 patients. Validation of the DL‐algorithm was carried out in 45 patients with biopsy‐proven hormone‐naïve prostate cancer. The automated measurements of prostate volume were compared with manual measurements made independently by two observers. PET/CT measurements of tumour burden based on volume and SUV of abnormal voxels were calculated automatically. Voxels in the co‐registered 18F‐choline PET images above a standardized uptake value (SUV) of 2·65, and corresponding to the prostate as defined by the automated segmentation in the CT images, were defined as abnormal. Validation of abnormal voxels was performed by manual segmentation of radiotracer uptake. Agreement between algorithm and observers regarding prostate volume was analysed by Sørensen‐Dice index (SDI). Associations between automatically based PET/CT biomarkers and age, prostate‐specific antigen (PSA), Gleason score as well as overall survival were evaluated by a univariate Cox regression model. Results The SDI between the automated and the manual volume segmentations was 0·78 and 0·79, respectively. Automated PET/CT measures reflecting total lesion uptake and the relation between volume of abnormal voxels and total prostate volume were significantly associated with overall survival (P = 0·02), whereas age, PSA, and Gleason score were not. Conclusion Automated PET/CT biomarkers showed good agreement to manual measurements and were significantly associated with overall survival.