AI lesion tracking in PET/CT imaging: a proposal for a Siamese-based CNN pipeline applied to PSMA PET/CT scans.
Authors
Affiliations (8)
Affiliations (8)
- Department of Nuclear Medicine, School of Medicine and Health, TUM Klinikum, Technical University of Munich, Munich, 81675, Germany. [email protected].
- Chair of Biomedical Physics, Department of Physics, TUM School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany. [email protected].
- Chair of Biomedical Physics, Department of Physics, TUM School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany.
- Institute for Diagnostic and Interventional Radiology, School of Medicine and Health, TUM Klinikum, Technical University of Munich, Munich, 81675, Germany.
- Division of Nuclear Medicine and Molecular Imaging, The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, Baltimore, 21205, MD, USA.
- Department of Nuclear Medicine, School of Medicine and Health, TUM Klinikum, Technical University of Munich, Munich, 81675, Germany.
- Department of Urology, School of Medicine and Health, TUM Klinikum, Technical University of Munich, Munich, 81675, Germany.
- Munich Institute of Biomedical Engineering, Technical University of Munich, Garching, 85748, Germany.
Abstract
Assessing tumor response to systemic therapies is one of the main applications of PET/CT. Routinely, only a small subset of index lesions out of multiple lesions is analyzed. However, this operator dependent selection may bias the results due to possible significant inter-metastatic heterogeneity of response to therapy. Automated, AI-based approaches for lesion tracking hold promise in enabling the analysis of many more lesions and thus providing a better assessment of tumor response. This work introduces a Siamese CNN approach for lesion tracking between PET/CT scans. Our approach is applied on the laborious task of tracking a high number of bone lesions in full-body baseline and follow-up [<sup>68</sup>Ga]Ga- or [<sup>18</sup>F]F-PSMA PET/CT scans after two cycles of [<sup>177</sup>Lu]Lu-PSMA therapy of metastatic castration resistant prostate cancer patients. Data preparation includes lesion segmentation and affine registration. Our algorithm extracts suitable lesion patches and forwards them into a Siamese CNN trained to classify the lesion patch pairs as corresponding or non-corresponding lesions. Experiments have been performed with different input patch types and a Siamese network in 2D and 3D. The CNN model successfully learned to classify lesion assignments, reaching an accuracy of 83 % in its best configuration with an AUC = 0.91. For corresponding lesions the pipeline accomplished lesion tracking accuracy of even 89 %. We proved that a CNN may facilitate the tracking of multiple lesions in PSMA PET/CT scans. Future clinical studies are necessary if this improves the prediction of the outcome of therapies.