{"id":"W6957648385","doi":"10.60692/hz5tr-a5f86","title":"Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Radio Astronomy Observations and Technology","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre","funders":"Engineering and Physical Sciences Research Council","keywords":"Colorectal cancer; Grading (engineering); Deep learning; Random forest; Tumour heterogeneity; Transcriptome; Precision medicine; Correlation; Convolutional neural network","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":[0.00007796807,0.0001206191,0.0001959171,0.0001013565,0.00009051774,0.00004654499,0.0001055366,0.00005556419,0.00005647869],"category_scores_gemma":[0.000006356523,0.0001187911,0.00007014078,0.0002725504,0.00004870374,0.0001623639,0.00002035175,0.0001115495,0.00004187197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005108821,"about_ca_system_score_gemma":0.00007831788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004253367,"about_ca_topic_score_gemma":8.997917e-8,"domain_scores_codex":[0.9991417,0.00004232589,0.0004365481,0.0001126498,0.0001187579,0.0001480482],"domain_scores_gemma":[0.9991699,0.000006126013,0.0004468091,0.000118172,0.0002062317,0.00005273649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000532688,0.000003384075,0.9673194,0.0001342933,0.00008842019,5.727223e-7,0.004976172,0.02081548,0.002677019,0.002145125,0.000008879756,0.001777981],"study_design_scores_gemma":[0.001048382,0.00005500021,0.05159397,0.00005134181,0.00006405395,0.00000115055,0.01057754,0.9142067,0.0220296,0.000002021811,0.0001653804,0.000204835],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7357513,0.00000188345,0.2632166,0.00009348422,0.00004548326,0.0001756133,0.00004254588,0.00006824613,0.0006048308],"genre_scores_gemma":[0.9949769,8.823384e-9,0.004875044,0.00002337135,0.00003287546,0.00003796967,0.00004233403,0.000009555207,0.000001928692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9157254,"threshold_uncertainty_score":0.484416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03112781670685374,"score_gpt":0.2244332876065925,"score_spread":0.1933054708997388,"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."}}