{"id":"W4415534294","doi":"10.1016/j.csbj.2025.10.041","title":"SegDecon bridges histology and transcriptomics through AI-based nuclei segmentation and image-informed spatial deconvolution","year":2025,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"European Research Council; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft","keywords":"Deconvolution; Segmentation; Pattern recognition (psychology); Bayesian probability; Transcriptome; Prior probability; Spatial analysis; Image resolution","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006840879,0.0001737032,0.0001863425,0.0001199848,0.0003405756,0.00006945655,0.00008615346,0.0003147059,0.000006781937],"category_scores_gemma":[0.00003546591,0.0001608117,0.00004458028,0.00006030164,0.0005089926,0.00002613746,0.00003612891,0.0002481644,3.352446e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003671041,"about_ca_system_score_gemma":0.0001297131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003119765,"about_ca_topic_score_gemma":0.00006589208,"domain_scores_codex":[0.999146,0.00003916458,0.0002864499,0.0002727015,0.00006863378,0.0001870218],"domain_scores_gemma":[0.9996543,0.00002941452,0.00009992638,0.00006808848,0.00009575728,0.00005251306],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001167472,0.00006426725,0.03955342,0.0002073383,0.000320244,0.00001966531,0.0003332962,0.001568431,0.7760592,0.008228081,0.001099452,0.1713792],"study_design_scores_gemma":[0.01667871,0.002557446,0.3103784,0.0001862207,0.0003714663,0.003816508,0.000806976,0.1729714,0.3914486,0.08769927,0.01154488,0.001540028],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8262833,0.001269014,0.1677543,0.004235269,0.000286247,0.0001068737,0.00002171527,0.00001893385,0.00002432942],"genre_scores_gemma":[0.984571,0.0005336879,0.01362123,0.001079044,0.00006189194,0.000002855023,0.0001015394,0.000008401193,0.00002033012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3846105,"threshold_uncertainty_score":0.6557711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006726937365161322,"score_gpt":0.253912860581218,"score_spread":0.2471859232160567,"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."}}