{"id":"W4415420020","doi":"10.1101/2025.10.20.683505","title":"Automatic Classification of Circulating Blood Cell Clusters based on Multi-channel Flow Cytometry Imaging","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Air Force Office of Scientific Research; Georgia Advanced Computing Resource Center, University of Georgia; U.S. Department of Energy; National Science Foundation","keywords":"Flow cytometry; Cell; Cluster of differentiation; Cell type; Convolutional neural network; Pattern recognition (psychology); Cytometry; Blood cell","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008120877,0.0006432983,0.0009860124,0.003268608,0.0003593221,0.001447771,0.00103535,0.0009850848,0.001053642],"category_scores_gemma":[0.001410152,0.0003373468,0.0008651105,0.001069403,0.0003845332,0.0006856296,0.0008723584,0.0007012399,0.0007891261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008472258,"about_ca_system_score_gemma":0.001122376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004697172,"about_ca_topic_score_gemma":0.004506944,"domain_scores_codex":[0.9994969,0.00005546631,0.00002762784,0.0001710145,0.0001509202,0.00009791613],"domain_scores_gemma":[0.9992425,0.0001628527,0.0001175842,0.00008277542,0.0003031951,0.0000911082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008609821,0.0002910153,0.04262457,0.0003132678,0.0001345011,0.0006723217,0.0004217362,0.04906626,0.4204289,0.004582584,0.009876767,0.470727],"study_design_scores_gemma":[0.00003404552,0.00007155319,0.01488871,0.00002609054,0.00005689473,0.0003294832,0.0001202757,0.9047968,0.07325462,0.003424042,0.002944111,0.00005340907],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1816967,0.0008525255,0.8089984,0.0003594879,0.0000974776,0.0002392029,0.0007986018,0.005051241,0.001906331],"genre_scores_gemma":[0.5460038,0.0007322569,0.448438,0.0002673253,0.00009723075,0.0002308795,0.001995096,0.0002706114,0.001964684],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004697172,"threshold_uncertainty_score":0.00933969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01631792056062011,"score_gpt":0.230629056754029,"score_spread":0.2143111361934089,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}