Freely Available, Fully Automated AI-Based Analysis of Primary Tumour and Metastases of Prostate Cancer in Whole-Body [F-18]-PSMA-1007 PET-CT
Journal article, 2022

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 [F-18]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.

artificial intelligence

convolutional neural network

PSMA

deep learning

prostate cancer

Author

Elin Tragardh

Skåne University Hospital

Lund University

Olof Enqvist

Imaging and Image Analysis

Johannes Ulen

Eigenvision AB

Jonas Jogi

Lund University

Skåne University Hospital

Ulrika Bitzen

Skåne University Hospital

Fredrik Hedeer

Skåne University Hospital

Kristian Valind

Skåne University Hospital

Lund University

Sabine Garpered

Skåne University Hospital

Erland Hvittfeldt

Lund University

Skåne University Hospital

Pablo Borrelli

Sahlgrenska University Hospital

Lars Edenbrandt

University of Gothenburg

Diagnostics

20754418 (eISSN)

Vol. 12 9 2101

Subject Categories

Urology and Nephrology

Radiology, Nuclear Medicine and Medical Imaging

Medical Image Processing

DOI

10.3390/diagnostics12092101

PubMed

36140502

More information

Latest update

4/21/2023