{"id":"W4413049571","doi":"10.1016/j.jpi.2025.100465","title":"Neighborhood clustering analysis to define epithelial–stromal interface for tumor infiltrating lymphocyte evaluation","year":2025,"lang":"en","type":"article","venue":"Journal of Pathology Informatics","topic":"Cancer Immunotherapy and Biomarkers","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs","funders":"Medical Center, University of Rochester","keywords":"Stromal cell; Computer science; Cluster analysis; Lymphocyte; Interface (matter); Information retrieval; Computational biology; Pathology; Medicine; Artificial intelligence; Immunology; Biology","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":[0.001658962,0.0001240796,0.0004678375,0.0006752897,0.00007015881,0.00003039099,0.0001237281,0.00007517813,0.00003652176],"category_scores_gemma":[0.0005109264,0.00009964436,0.0002820457,0.0005824784,0.00003490262,0.0001633269,0.00003607306,0.0001431961,0.000002717615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002948662,"about_ca_system_score_gemma":0.0003889597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003407444,"about_ca_topic_score_gemma":0.00001232737,"domain_scores_codex":[0.9983168,0.00004741789,0.001153365,0.00005990122,0.0002345436,0.0001880046],"domain_scores_gemma":[0.998473,0.0001257903,0.0006372757,0.0001712891,0.0005266736,0.00006594942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0247364,0.0005832688,0.06124499,0.00150615,0.01384659,0.0001536515,0.02559024,0.05691439,0.2350176,0.0002788964,0.003975762,0.576152],"study_design_scores_gemma":[0.05848366,0.01243343,0.1394701,0.00217319,0.02517488,0.008324544,0.01746061,0.6392422,0.07891975,0.0008378484,0.0163652,0.001114593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7488565,0.0003352431,0.2483904,0.000822311,0.0004390461,0.0003550672,0.00001492193,0.000009553272,0.0007769232],"genre_scores_gemma":[0.9562137,0.00004136481,0.04108579,0.002482765,0.00009458086,0.00001602042,0.000008725071,0.000007313395,0.00004977792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5823278,"threshold_uncertainty_score":0.4063379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0189739855435667,"score_gpt":0.337929179648516,"score_spread":0.3189551941049493,"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."}}