{"id":"W3118362352","doi":"10.1016/j.compmedimag.2020.101845","title":"A deep learning approach to the screening of malaria infection: Automated and rapid cell counting, object detection and instance segmentation using Mask R-CNN","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Singapore University of Technology and Design","keywords":"Computer science; Artificial intelligence; Segmentation; Deep learning; Minimum bounding box; Object detection; Visualization; Blood smear; Bounding overwatch; Machine learning; Pattern recognition (psychology); Standardization; Cell counting; Feature (linguistics); Computer vision; Object (grammar); Malaria; Image (mathematics); Pathology; Medicine","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":[0.000736143,0.001074494,0.001097262,0.0006736404,0.0003004109,0.0007720341,0.002408946,0.001281738,0.001671583],"category_scores_gemma":[0.0008759229,0.000721085,0.00106685,0.0005602148,0.0003327508,0.0006732207,0.000979173,0.001318111,0.00101813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001154878,"about_ca_system_score_gemma":0.0014178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01468191,"about_ca_topic_score_gemma":0.0195996,"domain_scores_codex":[0.9996605,0.00005145486,0.00001508139,0.0001158744,0.00008184138,0.00007520551],"domain_scores_gemma":[0.9995772,0.0001182016,0.00004577532,0.00006335643,0.000150403,0.00004506469],"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":[0.0004217412,0.000383697,0.003575549,0.0001774562,0.0003035429,0.0002332635,0.00007178073,0.1820869,0.04920175,0.004658155,0.01231002,0.7465761],"study_design_scores_gemma":[0.000005994669,0.00006284904,0.0006710258,0.00000652011,0.0000241362,0.00005490674,0.000005364943,0.9917366,0.005545636,0.001069985,0.0008081286,0.000008850173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07079032,0.001314305,0.917329,0.0008360402,0.0001747104,0.000142221,0.0008935099,0.005659721,0.002860136],"genre_scores_gemma":[0.4238717,0.0007840231,0.5583995,0.0008563912,0.0001526455,0.0001694417,0.002078277,0.0002440307,0.01344405],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01468191,"threshold_uncertainty_score":0.02919286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01154340357787596,"score_gpt":0.2442361388011946,"score_spread":0.2326927352233186,"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."}}