{"doi":"10.1101/2025.11.18.25340504","title":"Deep learning based ischemic lesion markers on non-contrast head CT compared to CTP and DWI","abstract":"Background: Quantification of ischemic brain tissue on non-contrast CT (NCCT) in acute ischemic stroke is challenging in the acute setting. Purpose: To compare the spatial overlap and imaging marker agreement of acute ischemic regions of interest (ROIs) using deep-learning NCCT (DLNCCT) versus manual NCCT, CTP, and DWI-based ischemic segmentations. Methods: We trained a deep learning model to segment ischemic ROIs using manual lesion annotations on admission NCCTs (DLNCCT). DLNCCT ischemic ROIs were compared with manual NCCT delineation, CTP (rCBF<30%/38%), and DWI within 5 hours after the NCCT or after recanalization in four external test sets. Spatial overlap was measured using the Dice Similarity Coefficient (DSC; mean±SD). For each ROI, we derived: average density (HU); modified net water uptake (mNWU in %); total volume (mL); and hypodense (<26HU) volume (mL), and assessed agreement via Bland-Altman (mean difference [95%CI]) and concordance correlation coefficient (CCC) analysis. Results: 218 training (n=104/89/25 male/female/unknown, mean age 68±14 years) and 762 test cases (n=243/206/313 male/female/unknown, mean age 70±15 years) were used. Spatial overlap was 0.30±0.30 between DLNCCT and manual segmentation, 0.22±0.25 between DLNCCT and DWI, 0.10±0.19/0.14±0.21 between DLNCCT and CTP (rCBF<30%/<38%), and 0.15±0.22/0.21±0.24 between CTP (rCBF<30%/<38%) and DWI. DLNCCT vs. DWI mean differences of ischemic ROI derived imaging markers were -1HU (95%CI:-7;6) for average density (CCC:0.71), 4.9% (95%CI:-7.0;16.8) for mNWU (CCC:0.35), -16mL (95%CI:-108;76) for total volume (CCC:0.57), and -4mL (95%CI:-31;23) for hypodense lesion volume (CCC: 0.75). Conclusion: Spatial overlap and agreement of imaging markers between DLNCCT and DWI ischemic ROIs were comparable to CTP and DWI. Summary Statement: Ischemic injury on NCCT is identified and quantified by a deep-learning model with accuracy similar to CTP and DWI in stroke patients with a large vessel occlusion. Key results: Deep-learning models can segment ischemic brain tissue on NCCT.Ischemic regions identified by our model demonstrate comparable overlap with ischemic core segmentation on CTP (Dice: 0.21±0.24) and DWI (Dice: 0.22±0.25).Deep learning NCCT showed high agreement with follow-up DWI in determining the hypodense (<26 HU) lesion volume (mean difference -4mL [95%CI:-31;23], CCC: 0.75).","journal":"medRxiv","year":2025,"id":581685,"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":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9242,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":192397,"name":"Bin Jiang","orcid":null,"position":1,"is_corresponding":false},{"id":1493579,"name":"Praneeta Konduri","orcid":null,"position":2,"is_corresponding":false},{"id":1234913,"name":"Adrien ter Schiphorst","orcid":"0000-0002-7354-3351","position":3,"is_corresponding":false},{"id":1258481,"name":"Aroosa Zamarud","orcid":"0000-0002-4275-5597","position":4,"is_corresponding":false},{"id":108627,"name":"Seena Dehkharghani","orcid":"0000-0002-3141-1094","position":5,"is_corresponding":false},{"id":1213539,"name":"Lieselotte Vandewalle","orcid":"0000-0002-0375-3804","position":6,"is_corresponding":false},{"id":1493580,"name":"Ewout Heylen","orcid":null,"position":7,"is_corresponding":false},{"id":298260,"name":"Yongkai Liu","orcid":"0000-0003-4478-4006","position":8,"is_corresponding":false},{"id":545437,"name":"Michael Mlynash","orcid":"0000-0001-7483-8699","position":9,"is_corresponding":false},{"id":1493581,"name":"Soren Christensen","orcid":null,"position":10,"is_corresponding":false},{"id":1235407,"name":"Nicole Yuen","orcid":null,"position":11,"is_corresponding":false},{"id":1493582,"name":"Benjamin FJ Verhaaren","orcid":null,"position":12,"is_corresponding":false},{"id":672245,"name":"Abdelkader Mahammedi","orcid":"0000-0002-8726-9269","position":13,"is_corresponding":false},{"id":620451,"name":"Patrik Michel","orcid":"0000-0003-4954-7579","position":14,"is_corresponding":false},{"id":58042,"name":"Max Wintermark","orcid":"0000-0002-6726-3951","position":15,"is_corresponding":false},{"id":1493583,"name":"Gregory W Albers","orcid":null,"position":16,"is_corresponding":false},{"id":29927,"name":"Greg Zaharchuk","orcid":"0000-0001-5781-8848","position":17,"is_corresponding":false},{"id":1493584,"name":"Maarten G Lansberg","orcid":null,"position":18,"is_corresponding":false},{"id":1222891,"name":"Jeremy J Heit","orcid":"0000-0002-1058-1393","position":19,"is_corresponding":false},{"id":1491098,"name":"Henk van Voorst","orcid":"0000-0002-2647-3557","position":0,"is_corresponding":true}],"reference_count":25,"raw_metadata":null,"created_at":"2026-07-19T02:58:51.328454Z","pmid":"41332814","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":[]}