{"doi":"10.1101/2022.02.02.22270344","title":"PSMA-Hornet: fully-automated, multi-target segmentation of healthy organs in PSMA PET/CT images","abstract":"ABSTRACT Prostate-specific membrane antigen (PSMA) PET imaging represents a valuable source of information reflecting disease stage, response rate, and treatment optimization options, particularly with PSMA radioligand therapy. Quantification of radiopharmaceutical uptake in healthy organs from PSMA images has the potential to minimize toxicity by extrapolation of the radiation dose delivery towards personalization of therapy. Furthermore, factors affecting biodistribution of PSMA radiotracers that remain mostly unknown can be investigated by analyzing PSMA PET images with segmented organs. However, segmentation and quantification of uptake in organs requires labor-intensive organ delineations that are often not feasible in the clinic nor scalable for large clinical trials. In this work we have developed and tested the PSMA Healthy organ segmentation network (PSMA-Hornet), a fully-automated deep neural net for effective and robust segmentation and labelling of 14 healthy organs representing the normal biodistribution of [ 18 F]DCFPyL on PET/CT images. Methods The study used manually-segmented [ 18 F]DCFPyL PET/CT images from 100 subjects, and 526 similar images without segmentations. The unsegmented images were used for self-supervised model pretraining. For supervised training, 3-fold cross-validation was used to evaluate the network performance, with 85 subjects reserved for model training, 5 for validation, and 10 for testing. Image segmentation and quantification metrics were evaluated on the test set with respect to manual segmentations by a nuclear medicine physician. Results With our best model, the lowest mean Dice coefficient on the test set was 0.826 for the sublingual gland, and the highest was 0.964 for liver. The highest mean error in tracer uptake quantification was 13.9% in the sublingual gland. Self-supervised pretraining improved training convergence, train-to-test generalization, and segmentation quality. In addition, we found that a multi-target network produced significantly higher segmentation accuracy than single-organ networks. Conclusion The developed network can be used to automatically obtain high-quality organ segmentations for PSMA image analysis tasks. It can be used to reproducibly extract imaging data, and holds promise for clinical applications such as personalized radiation dosimetry and improved radioligand therapy.","journal":"medRxiv","year":2022,"id":298520,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":5,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9521,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":987562,"name":"Guillaume Chaussé","orcid":"0000-0002-4083-0805","position":1,"is_corresponding":false},{"id":966413,"name":"Ingrid Bloise","orcid":null,"position":2,"is_corresponding":false},{"id":402205,"name":"Juan Lavista Ferres","orcid":"0000-0002-9654-3178","position":3,"is_corresponding":false},{"id":753473,"name":"Carlos Uribe","orcid":"0000-0003-3127-7478","position":4,"is_corresponding":false},{"id":103906,"name":"Arman Rahmim","orcid":"0000-0002-9980-2403","position":5,"is_corresponding":false},{"id":558911,"name":"Ivan S. Klyuzhin","orcid":"0000-0003-0141-7628","position":0,"is_corresponding":true}],"reference_count":20,"raw_metadata":null,"created_at":"2026-07-19T00:31:36.269611Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}