{"id":"W4283652538","doi":"10.1142/9789811257452_0007","title":"Peripheral Blood Smear Analysis Using Deep Learning: Current Challenges and Future Directions","year":2022,"lang":"en","type":"book-chapter","venue":"Series in computer vision","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Peripheral blood; Current (fluid); Peripheral; Medicine; Computer science; Internal medicine; Engineering; Electrical engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000287738,0.0004413028,0.0005832522,0.0008337757,0.0004454037,0.0002137671,0.0005773556,0.0002377787,0.0001482263],"category_scores_gemma":[0.000003272967,0.000480196,0.0002367348,0.0003731823,0.00009963604,0.0007106707,0.001312975,0.001123838,0.000002674694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003289345,"about_ca_system_score_gemma":0.00005809718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001813817,"about_ca_topic_score_gemma":0.0001599888,"domain_scores_codex":[0.9974636,0.0001517791,0.0004310438,0.001121494,0.0005249962,0.0003070313],"domain_scores_gemma":[0.9987499,0.00006518923,0.0002964328,0.0006985946,0.00009285231,0.00009709711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001898155,0.00003762293,0.00002687919,0.00007227062,0.0002515944,0.0000386935,0.002631268,0.005817683,0.00000366848,0.01888517,0.00001247435,0.9722037],"study_design_scores_gemma":[0.0002971156,0.0006897812,0.0006974104,0.0001177887,0.0002698642,0.0001394448,0.0000489478,0.1879946,0.000004446433,0.004121465,0.804934,0.0006851969],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.003025068,0.3283941,0.5991275,0.003004555,0.02808595,0.001604251,0.00002974556,0.001994583,0.03473425],"genre_scores_gemma":[0.02142962,0.6677545,0.2804098,0.0002765859,0.01420256,0.0001673785,0.0001821584,0.0005194379,0.01505798],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9715185,"threshold_uncertainty_score":0.999765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01988800932719548,"score_gpt":0.2631684633860333,"score_spread":0.2432804540588378,"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."}}