{"id":"W3176224216","doi":"10.1016/j.asoc.2021.107656","title":"AFLN-DGCL: Adaptive Feature Learning Network with Difficulty-Guided Curriculum Learning for skin lesion segmentation","year":2021,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Overfitting; Segmentation; Computer science; Artificial intelligence; Feature (linguistics); Convolutional neural network; Pattern recognition (psychology); Machine learning; Deep learning; Feature learning; Task (project management); Artificial 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001068488,0.00133949,0.0009472619,0.001214175,0.0004820302,0.000696753,0.001908275,0.001563943,0.001842444],"category_scores_gemma":[0.00284062,0.0003152048,0.0009209969,0.0009710958,0.0004001523,0.001416424,0.00108655,0.001597074,0.0007205643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00109934,"about_ca_system_score_gemma":0.00105498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01152053,"about_ca_topic_score_gemma":0.009537037,"domain_scores_codex":[0.9993906,0.0001146464,0.00002904927,0.0002342288,0.0001321558,0.00009929019],"domain_scores_gemma":[0.9993122,0.0002036342,0.00007732039,0.00009996732,0.0002425318,0.00006433709],"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":[0.0002844065,0.0004160997,0.005510684,0.0001479454,0.0001734746,0.0002028077,0.0001256361,0.2254324,0.0112475,0.001486673,0.01433767,0.7406348],"study_design_scores_gemma":[0.00001800687,0.0001006863,0.0007856566,0.00001491092,0.00003269311,0.00007588294,0.00001759669,0.9928919,0.00320072,0.001461143,0.001384979,0.00001583752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1483516,0.002957275,0.831223,0.000888763,0.000339033,0.0002857709,0.000939659,0.01056089,0.004454],"genre_scores_gemma":[0.7439598,0.0008113455,0.2413732,0.0008931732,0.0002072792,0.0003032377,0.00400235,0.0003683902,0.008081196],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01152053,"threshold_uncertainty_score":0.02290696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0143410365380731,"score_gpt":0.2572232696820712,"score_spread":0.2428822331439981,"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."}}