{"id":"https://openalex.org/W7151656955","doi":"https://doi.org/10.1109/icmla66185.2025.00031","title":"Accurate Polyp Sizing via Attention-Guided Parallel CNN-ViT Depth and Learned Scale","display_name":"Accurate Polyp Sizing via Attention-Guided Parallel CNN-ViT Depth and Learned Scale","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151656955","doi":"https://doi.org/10.1109/icmla66185.2025.00031"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120346619","display_name":"Alimire Nabijiang","orcid":"https://orcid.org/0009-0009-6081-7016"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alimire Nabijiang","raw_affiliation_strings":["University of Massachusetts Lowell,Miner School of Computer & Information Sciences,USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell,Miner School of Computer & Information Sciences,USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133115282","display_name":"Feng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132741","display_name":"Shanghai Tenth People's Hospital","ror":"https://ror.org/03vjkf643","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210132741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["Tongji University School of Medicine,Shanghai Tenth People’s Hospital,China"],"affiliations":[{"raw_affiliation_string":"Tongji University School of Medicine,Shanghai Tenth People’s Hospital,China","institution_ids":["https://openalex.org/I4210132741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133147570","display_name":"Jiao Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210132741","display_name":"Shanghai Tenth People's Hospital","ror":"https://ror.org/03vjkf643","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210132741"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Feng","raw_affiliation_strings":["Tongji University School of Medicine,Shanghai Tenth People’s Hospital,China"],"affiliations":[{"raw_affiliation_string":"Tongji University School of Medicine,Shanghai Tenth People’s Hospital,China","institution_ids":["https://openalex.org/I4210132741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013490400","display_name":"Qilei Chen","orcid":"https://orcid.org/0000-0001-5506-8094"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"QiLei Chen","raw_affiliation_strings":["University of Massachusetts Lowell,Miner School of Computer & Information Sciences,USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell,Miner School of Computer & Information Sciences,USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133131820","display_name":"Yu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Cao","raw_affiliation_strings":["University of Massachusetts Lowell,Miner School of Computer & Information Sciences,USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell,Miner School of Computer & Information Sciences,USA","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058709752","display_name":"B Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"BenYuan Liu","raw_affiliation_strings":["University of Massachusetts Lowell,Miner School of Computer & Information Sciences,USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell,Miner School of Computer & Information Sciences,USA","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5120346619"],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7494545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"192","last_page":"199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15309999883174896,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.15309999883174896,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.10580000281333923,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.09640000015497208,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5540000200271606},{"id":"https://openalex.org/keywords/sizing","display_name":"Sizing","score":0.5450000166893005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27149999141693115},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2694999873638153}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C2777767291","wikidata":"https://www.wikidata.org/wiki/Q1080291","display_name":"Sizing","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5271999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49880000948905945},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4535999894142151},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24709999561309814}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1994287255","https://openalex.org/W2007610503","https://openalex.org/W2020637151","https://openalex.org/W2155195757","https://openalex.org/W2162262467","https://openalex.org/W2194775991","https://openalex.org/W2197178725","https://openalex.org/W2609883120","https://openalex.org/W2752782242","https://openalex.org/W2890803520","https://openalex.org/W2916798096","https://openalex.org/W2922504529","https://openalex.org/W2939157633","https://openalex.org/W2955639361","https://openalex.org/W3005078169","https://openalex.org/W3008070655","https://openalex.org/W3032893211","https://openalex.org/W3178692652","https://openalex.org/W3197714691","https://openalex.org/W4206545998","https://openalex.org/W4210340989","https://openalex.org/W4210430456","https://openalex.org/W4214520160","https://openalex.org/W4225874030","https://openalex.org/W4247541259","https://openalex.org/W4280647564","https://openalex.org/W4295096627","https://openalex.org/W4312977443","https://openalex.org/W4321512633","https://openalex.org/W4366550188","https://openalex.org/W4379660300","https://openalex.org/W4382877880","https://openalex.org/W4386527936","https://openalex.org/W4387568103","https://openalex.org/W4389080219","https://openalex.org/W4389675532","https://openalex.org/W4390693694","https://openalex.org/W4390873769","https://openalex.org/W4390874218","https://openalex.org/W4399021842","https://openalex.org/W4401749956","https://openalex.org/W4402727115","https://openalex.org/W4402727359","https://openalex.org/W4403049212","https://openalex.org/W4403062944","https://openalex.org/W4404624926","https://openalex.org/W4406240018","https://openalex.org/W4410924065","https://openalex.org/W4415798746","https://openalex.org/W4415821356"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"sizing":[1],"of":[2,137],"colorectal":[3],"polyps":[4,125],"is":[5],"essential":[6],"for":[7,143],"malignancy":[8],"risk":[9],"assessment":[10],"and":[11,18,57,69,86,98,114],"surveillance":[12],"planning.":[13],"However,":[14],"both":[15],"visual":[16],"estimation":[17],"current":[19],"instrument-based":[20],"aids":[21],"often":[22],"suffer":[23],"from":[24,126],"variability":[25],"or":[26,39,105],"workflow":[27],"disruption.":[28],"Recent":[29],"AI-based":[30],"approaches":[31],"typically":[32],"rely":[33],"on":[34,109,119],"reference":[35,99],"objects,":[36],"camera":[37,96],"calibration,":[38],"depth":[40,87,117],"networks":[41,108],"with":[42,75],"suboptimal":[43],"accuracy":[44],"in":[45],"endoscopic":[46],"imagery.":[47],"We":[48],"present":[49],"a":[50,61,79,92,133],"calibration-free":[51],"pipeline":[52],"that":[53,65,82],"segments":[54],"the":[55,110,130],"polyp":[56],"then":[58],"couples":[59],"ViTCAN-Depth,":[60],"monocular":[62],"metric-depth":[63,107],"model":[64],"fuses":[66],"parallel":[67],"CNN":[68],"Vision-Transformer":[70],"encoders":[71],"via":[72],"channel-attention":[73],"gating,":[74],"Depth\u2013Pixel":[76],"Linear":[77],"(DPL),":[78],"lightweight":[80],"module":[81],"converts":[83],"pixel":[84],"diameter":[85,90],"into":[88,145],"real-world":[89],"using":[91],"learned":[93],"scalar,":[94],"eliminating":[95],"calibration":[97],"objects.":[100],"ViTCAN-Depth":[101],"outperforms":[102],"state-of-the-art":[103],"CNN-":[104],"ViT-based":[106],"C3VD":[111],"synthetic":[112],"benchmark,":[113],"yields":[115],"higher-fidelity":[116],"maps":[118],"real":[120],"colonoscopy":[121],"images.":[122],"Across":[123],"78":[124],"five":[127],"independent":[128],"cohorts,":[129],"system":[131],"achieves":[132],"mean":[134],"absolute":[135],"error":[136],"0.67mm":[138],"(RMSE=0.88mm),":[139],"suggesting":[140],"its":[141],"potential":[142],"integration":[144],"clinical":[146],"workflows.":[147]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}