{"id":"W2963730812","doi":"10.1109/tmi.2018.2878669","title":"HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation","year":2019,"lang":"","type":"article","venue":"Espace ÉTS (ETS)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":582,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Segmentation; Abstraction; Artificial intelligence; Convolutional neural network; Representation (politics); Modal; Modality (human–computer interaction); Pattern recognition (psychology); Modalities; Deep learning; Path (computing); Pyramid (geometry); Layer (electronics); Image segmentation; Feature learning; Ranking (information retrieval); Metric (unit); Mathematics","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":[0.0006833946,0.001705616,0.0007066675,0.001135828,0.000411594,0.001029386,0.002488472,0.001832654,0.006917609],"category_scores_gemma":[0.001671792,0.0008427544,0.001049249,0.000930133,0.0006943118,0.00240708,0.002199233,0.001634715,0.002019474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001398879,"about_ca_system_score_gemma":0.001151015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01060224,"about_ca_topic_score_gemma":0.02066381,"domain_scores_codex":[0.9996578,0.00005023987,0.00001416689,0.000132092,0.00007856105,0.00006718178],"domain_scores_gemma":[0.9996876,0.0000898522,0.00003323856,0.00009346903,0.00006224135,0.00003373377],"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":[0.0005145076,0.0002393676,0.001833744,0.0003976754,0.0003899735,0.0004638639,0.0001750967,0.3437703,0.02887532,0.01663984,0.0424697,0.5642307],"study_design_scores_gemma":[0.00002345571,0.00005261324,0.0004048513,0.00002833071,0.00002629452,0.0001144369,0.00001632957,0.9760493,0.007966938,0.009877264,0.005421387,0.0000187487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04363269,0.001849516,0.9105549,0.0006741351,0.0002336705,0.0002418356,0.003112051,0.03043591,0.009265333],"genre_scores_gemma":[0.4239876,0.00107118,0.5380636,0.001061143,0.0001212843,0.0003954986,0.01502065,0.002035351,0.01824362],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01060224,"threshold_uncertainty_score":0.02314168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02677478251896863,"score_gpt":0.2958204707536173,"score_spread":0.2690456882346486,"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."}}