{"id":"W3007602809","doi":"10.1101/2020.02.24.963645","title":"Whole Slide Preview Image Segmentation and Setup for Digital Pathology Scanners","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"S2e Technologies (Canada); University of Toronto","funders":"","keywords":"Scanner; Computer vision; Artifact (error); Artificial intelligence; Computer science; Segmentation; Focus (optics); Image segmentation; Digital pathology; Identification (biology); Region of interest; Computer graphics (images); Optics","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":[0.000923269,0.0006789797,0.0006068225,0.001542105,0.0005949464,0.001070024,0.001737286,0.0008364791,0.01900651],"category_scores_gemma":[0.002298596,0.001202325,0.0005541742,0.0005682015,0.0003982372,0.0009733072,0.001469466,0.0009304287,0.006209066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008930176,"about_ca_system_score_gemma":0.0009317855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001231707,"about_ca_topic_score_gemma":0.002261018,"domain_scores_codex":[0.9994283,0.00005055397,0.00003580153,0.000184143,0.0002320376,0.0000691598],"domain_scores_gemma":[0.9986518,0.0003736908,0.0001275165,0.0004818312,0.0002378825,0.0001273015],"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":[0.0004929087,0.0000986361,0.002284595,0.0002875523,0.0000564665,0.0003766511,0.0003994246,0.008697926,0.6879643,0.004287083,0.01140573,0.2836488],"study_design_scores_gemma":[0.00004243488,0.0002342416,0.009911012,0.0000531763,0.00003336579,0.001115422,0.0001852624,0.1052274,0.8278553,0.004402874,0.05081594,0.0001236134],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02526956,0.000142038,0.9441132,0.0001670453,0.0000587381,0.0002454005,0.0006946912,0.02775227,0.001557144],"genre_scores_gemma":[0.07656863,0.0001359805,0.9148494,0.00008980172,0.00002557495,0.0002201321,0.00131734,0.003760696,0.003032474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01900651,"threshold_uncertainty_score":0.06358314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01671286705505251,"score_gpt":0.2401933857838548,"score_spread":0.2234805187288023,"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."}}