Deep neural network for automatic characterization of lesions on 68Ga-PSMA-11 PET/CT

Zhao, Yu; Gafita, Andrei; Vollnberg, Bernd; Tetteh, Giles; Haupt, Fabian; Afshar-Oromieh, Ali; Menze, Bjoern; Eiber, Matthias; Rominger, Axel; Shi, Kuangyu (2020). Deep neural network for automatic characterization of lesions on 68Ga-PSMA-11 PET/CT. European journal of nuclear medicine and molecular imaging, 47(3), pp. 603-613. Springer-Verlag 10.1007/s00259-019-04606-y

[img] Text
Shi_Deep neural network for automatic characterization of lesions on 68Ga-PSMA-11 PETCT.pdf - Published Version
Restricted to registered users only until 8 December 2023.
Available under License Publisher holds Copyright.

Download (5MB) | Request a copy

This study proposes an automated prostate cancer (PC) lesion characterization method based on the deep neural network to determine tumor burden on 68Ga-PSMA-11 PET/CT to potentially facilitate the optimization of PSMA-directed radionuclide therapy.
We collected 68Ga-PSMA-11 PET/CT images from 193 patients with metastatic PC at three medical centers. For proof-of-concept, we focused on the detection of pelvis bone and lymph node lesions. A deep neural network (triple-combining 2.5D U-Net) was developed for the automated characterization of these lesions. The proposed method simultaneously extracts features from axial, coronal, and sagittal planes, which mimics the workflow of physicians and reduces computational and memory requirements.
Among all the labeled lesions, the network achieved 99% precision, 99% recall, and an F1 score of 99% on bone lesion detection and 94%, precision 89% recall, and an F1 score of 92% on lymph node lesion detection. The segmentation accuracy is lower than the detection. The performance of the network was correlated with the amount of training data.
We developed a deep neural network to characterize automatically the PC lesions on 68Ga-PSMA-11 PET/CT. The preliminary test within the pelvic area confirms the potential of deep learning methods. Increasing the amount of training data should further enhance the performance of the proposed method and may ultimately allow whole-body assessments.

Item Type:

Journal Article (Original Article)


04 Faculty of Medicine > Department of Radiology, Neuroradiology and Nuclear Medicine (DRNN) > Clinic of Nuclear Medicine

UniBE Contributor:

Vollnberg, Bernd Olaf; Haupt, Fabian; Afshar Oromieh, Ali; Rominger, Axel Oliver and Shi, Kuangyu


600 Technology > 610 Medicine & health








Sabine Lanz

Date Deposited:

18 Dec 2019 10:18

Last Modified:

25 May 2022 16:50

Publisher DOI:


PubMed ID:


Uncontrolled Keywords:

Deep learning; Lesion detection; PET/CT; PSMA; Prostate cancer




Actions (login required)

Edit item Edit item
Provide Feedback