{"id":"W4389933919","doi":"10.1038/s41598-023-49478-3","title":"A priori prediction of breast cancer response to neoadjuvant chemotherapy using quantitative ultrasound, texture derivative and molecular subtype","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Canadian Institutes of Health Research; Terry Fox Foundation","keywords":"Breast cancer; Margin (machine learning); Computer science; Texture (cosmology); Neoadjuvant therapy; Support vector machine; Ultrasound; Oncology; Cancer; Pattern recognition (psychology); Medicine; Artificial intelligence; Internal medicine; Radiology; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002040924,0.0004106195,0.0005604717,0.0004832777,0.0001174198,0.0004694159,0.0002638336,0.0003259538,0.0005237707],"category_scores_gemma":[0.005709937,0.0001393475,0.0003826894,0.0002338694,0.0002156494,0.0003326093,0.0002509062,0.0003647048,0.0002413483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001973172,"about_ca_system_score_gemma":0.0002648952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009436566,"about_ca_topic_score_gemma":0.002075864,"domain_scores_codex":[0.9994683,0.0002748009,0.00004238493,0.00007793595,0.00009484185,0.00004171862],"domain_scores_gemma":[0.997617,0.001342279,0.000445148,0.0002736878,0.000208565,0.0001133577],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001816827,0.0002576104,0.9244712,0.00005984,0.0001793921,0.00008685578,0.00008816957,0.01221409,0.01186838,0.00008060596,0.0002343342,0.0486427],"study_design_scores_gemma":[0.00005185337,0.001202369,0.8516148,0.0000222472,0.0001802089,0.0004323279,0.0001625728,0.1386326,0.006635163,0.0004357621,0.0005905377,0.00003953448],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9943495,0.0002593758,0.004807828,0.00005153891,0.000009636328,0.00001962753,0.0001499723,0.00002858972,0.0003239197],"genre_scores_gemma":[0.9982651,0.00004390412,0.001290945,0.00001724981,0.000008235638,0.00001165205,0.0002105459,0.000004009383,0.0001485026],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002040924,"threshold_uncertainty_score":0.01079357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0156262930222796,"score_gpt":0.3217815643083377,"score_spread":0.3061552712860581,"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."}}