Fully Automated Segmentation of [ 18 F]FDG and [ 68 Ga]/[ 18 F]PSMA PET/CT Images via Data-Centric Deep Learning

The purpose of this study was to develop and validate lesion identification in oncologic nuclear imaging (LION), an open-source PET-only tumor segmentation pipeline for [18F]FDG and prostate-specific membrane antigen (PSMA)–targeted PET/CT, and to investigate how training data characteristics influence segmentation performance. Methods: In this retrospective multicenter study, 5209 [18F]FDG PET/CT scans spanning 19 disease types and 2046 PSMA-targeted PET/CT scans were used to train PET-only segmentation models. Tumor segmentation incorporated organs with physiologic uptake as auxiliary classes to enable PET-only inference. Tumor occurrence maps (TOMs) quantified tumor spatial diversity across the training data. For [18F]FDG, disease-specific and mixed-disease models trained on progressively larger subsets were compared to test whether increasing spatial diversity improves generalization. Scanner-related domain shift was analyzed using DINOv2 embeddings. Models were evaluated on multicenter holdout cohorts (616 [18F]FDG scans across 4 diseases; 443 PSMA-targeted prostate cancer scans) and compared with 3 open-source tools. Results: Organ context improved median Dice from 0.62 to 0.71 for [18F]FDG and from 0.75 to 0.83 for PSMA, on the complete holdout cohorts. Spatial diversity measured by TOMs was strongly associated with Dice (Spearman ρ = 0.80, P = 0.003). A mixed-disease model trained on 500 patients matched the performance of a lymphoma specialist model trained on 3031 cases. DINOv2 embeddings revealed scanner-induced domain shift between same-disease cohorts. LION achieved median Dice scores of 0.71 for [18F]FDG and 0.85 for PSMA and outperformed other open-source approaches on the model-comparison test set, which excluded the AutoPET test cases. Conclusion: LION enables PET-only automated segmentation for [18F]FDG and PSMA-targeted PET. Training data composition, particularly spatial diversity quantified by TOMs, was strongly associated with segmentation performance.

Authors

Institutions

Publication Details

Journal
Journal of Nuclear Medicine
Published
2026-09-30
DOI
https://doi.org/10.2967/jnumed.126.272852
Primary Topic
Prostate Cancer Treatment and Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Fully Automated Segmentation of [ 18 F]FDG and [ 68 Ga]/[ 18 F]PSMA PET/CT Images via Data-Centric Deep Learning

Michael Ingrisch, Elisabetta Abenavoli, Lorenzo Nardo, Jukka Kemppainen et al.
Journal of Nuclear Medicine
Prostate Cancer Treatment and Research
article

Fully Automated Segmentation of [ 18 F]FDG and [ 68 Ga]/[ 18 F]PSMA PET/CT Images via Data-Centric Deep Learning

Michael Ingrisch, Elisabetta Abenavoli, Lorenzo Nardo, Jukka Kemppainen, Lalith Kumar Shiyam Sundar, Fanny Orlhac, Hande Nalbant, Sebastian Gutschmayer, Rodney Hicks, Eduardo Calderón, Ramsey Derek Badawi, Roberto Sciagrà, Riku Klén, Irene Johanna Virgolini, Jakob Dexl, Giulia Santo, Liam Widjaja, Miju Cheon, Mej Kazazi, Dominik Amereller, Clemens C. Cyran, Enrica Bergalla, Iustin Tibu, Anting Li, Ariane Kronthaler, Julie Auriac, David Kersting, Manuel Pires, Sophie C. Siegmund, Fabian Schmidt, Irene Buvat, Moon-Sung Kim, Aleksa Lazarević, Thomas Beyer, Ahti Vehmanen, Natalia Wegrzyn, Philip Richter, Ken Miller, Maurice Heimer, Romain-David Seban, Jason Callahan, Rudolf A. Werner, Jonas Benecke, Stephane Chauvie, Yasser Gaber Abdelhafez
article en

Abstract

The purpose of this study was to develop and validate lesion identification in oncologic nuclear imaging (LION), an open-source PET-only tumor segmentation pipeline for [18F]FDG and prostate-specific membrane antigen (PSMA)–targeted PET/CT, and to investigate how training data characteristics influence segmentation performance. Methods: In this retrospective multicenter study, 5209 [18F]FDG PET/CT scans spanning 19 disease types and 2046 PSMA-targeted PET/CT scans were used to train PET-only segmentation models. Tumor segmentation incorporated organs with physiologic uptake as auxiliary classes to enable PET-only inference. Tumor occurrence maps (TOMs) quantified tumor spatial diversity across the training data. For [18F]FDG, disease-specific and mixed-disease models trained on progressively larger subsets were compared to test whether increasing spatial diversity improves generalization. Scanner-related domain shift was analyzed using DINOv2 embeddings. Models were evaluated on multicenter holdout cohorts (616 [18F]FDG scans across 4 diseases; 443 PSMA-targeted prostate cancer scans) and compared with 3 open-source tools. Results: Organ context improved median Dice from 0.62 to 0.71 for [18F]FDG and from 0.75 to 0.83 for PSMA, on the complete holdout cohorts. Spatial diversity measured by TOMs was strongly associated with Dice (Spearman ρ = 0.80, P = 0.003). A mixed-disease model trained on 500 patients matched the performance of a lymphoma specialist model trained on 3031 cases. DINOv2 embeddings revealed scanner-induced domain shift between same-disease cohorts. LION achieved median Dice scores of 0.71 for [18F]FDG and 0.85 for PSMA and outperformed other open-source approaches on the model-comparison test set, which excluded the AutoPET test cases. Conclusion: LION enables PET-only automated segmentation for [18F]FDG and PSMA-targeted PET. Training data composition, particularly spatial diversity quantified by TOMs, was strongly associated with segmentation performance.

Journal of Nuclear Medicine
Centre National de la Recherche Scientifique (FR), Innsbruck Medical University (AT), Inserm (FR), Universität Innsbruck (AT), Université de Versailles Saint-Quentin-en-Yvelines (FR), Université Paris Sciences et Lettres (FR), Turku University Hospital (FI), LMU Klinikum (DE), St Vincent's Hospital Melbourne (AU), Veterans Health Service Medical Center (KR), Turku PET Centre (FI), Azienda Ospedaliero-Universitaria Careggi (IT), Essen University Hospital (DE), Azienda Sanitaria Ospedaliera S.Croce e Carle Cuneo (IT), University of Duisburg-Essen (DE), Medical University of Vienna (AT), Institut Curie (FR), University of Tübingen (DE), Ludwig-Maximilians-Universität München (DE), University of California, Davis (US), Assiut University (EG)
Openalex Percentile: Top 12%
Prostate Cancer Treatment and Research
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.