Freely Available, Fully Automated AI-Based Analysis of Primary Tumour and Metastases of Prostate Cancer in Whole-Body [18F]-PSMA-1007 PET-CT
Authors:
- Elin TrägårdhETElin Trägårdh
- Olof EnqvistOEOlof Enqvist
- Johannes UlénJUJohannes Ulén
- Jonas JögiJJJonas Jögi
- Ulrika BitzénUBUlrika Bitzén
- Fredrik HedeerFHFredrik Hedeer
- Kristian ValindKVKristian Valind
- Sabine GarperedSGSabine Garpered
- Erland HvittfeldtEHErland Hvittfeldt
- Pablo BorrelliPBPablo Borrelli
- Lars EdenbrandtLELars Edenbrandt
Open Access
- 30 August 2022
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 12 (9) , 2101
Abstract
Here, we aimed to develop and validate a fully automated artificial intelligence (AI)-based method for the detection and quantification of suspected prostate tumour/local recurrence, lymph node metastases, and bone metastases from [18F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) images. Images from 660 patients were included. Segmentations by one expert reader were ground truth. A convolutional neural network (CNN) was developed and trained on a training set, and the performance was tested on a separate test set of 120 patients. The AI method was compared with manual segmentations performed by several nuclear medicine physicians. Assessment of tumour burden (total lesion volume (TLV) and total lesion uptake (TLU)) was performed. The sensitivity of the AI method was, on average, 79% for detecting prostate tumour/recurrence, 79% for lymph node metastases, and 62% for bone metastases. On average, nuclear medicine physicians’ corresponding sensitivities were 78%, 78%, and 59%, respectively. The correlations of TLV and TLU between AI and nuclear medicine physicians were all statistically significant and ranged from R = 0.53 to R = 0.83. In conclusion, the development of an AI-based method for prostate cancer detection with sensitivity on par with nuclear medicine physicians was possible. The developed AI tool is freely available for researchers.Keywords
Funding Information
- Swedish Prostate Cancer Federation
- Knut and Alice Wallenberg Foundation
- Region Skåne
- Lund University
This publication has 31 references indexed in Scilit:
- Deep learning for segmentation of 49 selected bones in CT scans: First step in automated PET/CT-based 3D quantification of skeletal metastasesEuropean Journal of Radiology, 2019
- Impact of penalizing factor in a block-sequential regularized expectation maximization reconstruction algorithm for 18F-fluorocholine PET-CT regarding image quality and interpretationEJNMMI Physics, 2019
- Review of Gallium-68 PSMA PET/CT Imaging in the Management of Prostate CancerDiagnostics, 2018
- 3D skeletal uptake of 18F sodium fluoride in PET/CT images is associated with overall survival in patients with prostate cancerEJNMMI Research, 2017
- 68Ga-PSMA Positron Emission Tomography/Computed Tomography Provides Accurate Staging of Lymph Node Regions Prior to Lymph Node Dissection in Patients with Prostate CancerEuropean Urology, 2016
- Diagnostic Efficacy of 68 Gallium-PSMA Positron Emission Tomography Compared to Conventional Imaging for Lymph Node Staging of 130 Consecutive Patients with Intermediate to High Risk Prostate CancerJournal of Urology, 2016
- PSMA-Based [18F]DCFPyL PET/CT Is Superior to Conventional Imaging for Lesion Detection in Patients with Metastatic Prostate CancerMolecular Imaging and Biology, 2016
- Assessment of the bone scan index in a randomized placebo-controlled trial of tasquinimod in men with metastatic castration-resistant prostate cancer (mCRPC)Urologic Oncology: Seminars and Original Investigations, 2014
- Improved Classifications of Planar Whole-Body Bone Scans Using a Computer-Assisted Diagnosis System: A Multicenter, Multiple-Reader, Multiple-Case StudyJournal of Nuclear Medicine, 2009
- Detection and characterization of the prostate‐specific membrane antigen (PSMA) in tissue extracts and body fluidsInternational Journal of Cancer, 1995