{"doi":"10.1101/2022.02.28.22271565","title":"AI based pre-screening of large bowel cancer via weakly supervised learning of colorectal biopsy histology images","abstract":"<jats:title>Abstract</jats:title>\n                <jats:p>Histopathological examination is a pivotal step in the diagnosis and treatment planning of many major diseases. To facilitate the diagnostic decision-making and reduce the workload of pathologists, we present an AI-based pre-screening tool capable of identifying normal and neoplastic colon biopsies. To learn the differential histological patterns from whole slides images (WSIs) stained with hematoxylin and eosin (H&amp;E), our proposed weakly supervised deep learning method requires only slide-level labels and no detailed cell or region-level annotations. The proposed method was developed and validated on an internal cohort of biopsy slides (n=4 292) from two hospitals labeled with corresponding diagnostic categories assigned by pathologists after reviewing case reports. Performance of the proposed colon cancer pre-screening tool was evaluated in a cross-validation setting using the internal cohort (n=4 292) and also by an external validation on The Cancer Genome Atlas (TCGA) cohort (n=731). With overall cross-validated classification accuracy (AUROC = 0.9895) and external validation accuracy (AUROC = 0.9746), the proposed tool promises high accuracy to assist with the pre-screening of colorectal biopsies in clinical practice. Analysis of saliency maps confirms the representation of disease heterogeneity in model predictions and their association with relevant pathological features. The proposed AI tool correctly reported some slides as neoplastic while clinical reports suggested they were normal. Additionally, we analyzed genetic mutations and gene enrichment analysis of AI-generated neoplastic scores to gain further insight into the model predictions and explore the association between neoplastic histology and genetic heterogeneity through representative genes and signaling pathways.</jats:p>","journal":null,"year":null,"id":634884,"datarank":0.4493598410330987,"base_score":2.995732273553991,"endowment":2.995732273553991,"self_citation_contribution":0.4493598410330987,"citation_network_contribution":0.0,"self_endowment_contribution":0.4493598410330987,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":19,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1646854,"name":"Yee Wah Tsang","orcid":null,"position":1,"is_corresponding":false},{"id":1646855,"name":"Mahmoud Ali","orcid":null,"position":2,"is_corresponding":false},{"id":1193874,"name":"Simon Graham","orcid":"0000-0001-6602-4046","position":3,"is_corresponding":false},{"id":1646858,"name":"Emily Hero","orcid":null,"position":4,"is_corresponding":false},{"id":1646860,"name":"Noorul Wahab","orcid":null,"position":5,"is_corresponding":false},{"id":768744,"name":"Katherine Dodd","orcid":null,"position":6,"is_corresponding":false},{"id":1646862,"name":"Harvir Sahota","orcid":null,"position":7,"is_corresponding":false},{"id":1213468,"name":"Wenqi Lu","orcid":"0000-0003-1076-6985","position":8,"is_corresponding":false},{"id":1165150,"name":"Mostafa Jahanifar","orcid":"0000-0001-5842-0460","position":9,"is_corresponding":false},{"id":614848,"name":"Andrew Robinson","orcid":"0000-0003-2208-7728","position":10,"is_corresponding":false},{"id":1646864,"name":"Ayesha Azam","orcid":null,"position":11,"is_corresponding":false},{"id":1646866,"name":"Ksenija Benes","orcid":null,"position":12,"is_corresponding":false},{"id":1646868,"name":"Mohammed Nimir","orcid":null,"position":13,"is_corresponding":false},{"id":1646869,"name":"Abhir Bhalerao","orcid":null,"position":14,"is_corresponding":false},{"id":1646871,"name":"Hesham Eldaly","orcid":null,"position":15,"is_corresponding":false},{"id":235931,"name":"Shan E Ahmed Raza","orcid":"0000-0002-1097-1738","position":16,"is_corresponding":false},{"id":1042064,"name":"Kishore Gopalakrishnan","orcid":null,"position":17,"is_corresponding":false},{"id":271842,"name":"Fayyaz Minhas","orcid":"0000-0001-9129-1189","position":18,"is_corresponding":false},{"id":239981,"name":"David Snead","orcid":"0000-0001-7839-452X","position":19,"is_corresponding":false},{"id":1198899,"name":"Nasir Rajpoot","orcid":"0000-0001-6760-1271","position":20,"is_corresponding":false},{"id":1646852,"name":"Mohsin Bilal","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"AI based pre-screening of large bowel cancer via weakly supervised learning of colorectal biopsy histology images","abstract":"<jats:title>Abstract</jats:title>\n                <jats:p>Histopathological examination is a pivotal step in the diagnosis and treatment planning of many major diseases. To facilitate the diagnostic decision-making and reduce the workload of pathologists, we present an AI-based pre-screening tool capable of identifying normal and neoplastic colon biopsies. To learn the differential histological patterns from whole slides images (WSIs) stained with hematoxylin and eosin (H&amp;E), our proposed weakly supervised deep learning method requires only slide-level labels and no detailed cell or region-level annotations. The proposed method was developed and validated on an internal cohort of biopsy slides (n=4 292) from two hospitals labeled with corresponding diagnostic categories assigned by pathologists after reviewing case reports. Performance of the proposed colon cancer pre-screening tool was evaluated in a cross-validation setting using the internal cohort (n=4 292) and also by an external validation on The Cancer Genome Atlas (TCGA) cohort (n=731). With overall cross-validated classification accuracy (AUROC = 0.9895) and external validation accuracy (AUROC = 0.9746), the proposed tool promises high accuracy to assist with the pre-screening of colorectal biopsies in clinical practice. Analysis of saliency maps confirms the representation of disease heterogeneity in model predictions and their association with relevant pathological features. The proposed AI tool correctly reported some slides as neoplastic while clinical reports suggested they were normal. Additionally, we analyzed genetic mutations and gene enrichment analysis of AI-generated neoplastic scores to gain further insight into the model predictions and explore the association between neoplastic histology and genetic heterogeneity through representative genes and signaling pathways.</jats:p>","is_dataset_classified":null,"base_score":2.995732273553991,"endowment":2.995732273553991,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"19767382","pmcid":null,"openalex_id":"https://openalex.org/W4214596669","authors":[],"funders":[],"total_grants":0,"fwci":null,"citation_percentile":null,"influential_citations":0,"citation_trend":[{"year":2022,"count":1},{"year":2023,"count":10},{"year":2024,"count":5},{"year":2025,"count":2},{"year":2026,"count":1}],"oa_status":"green","license":"cc-by-nc-nd","oa_locations":[{"url":"https://www.medrxiv.org/content/medrxiv/early/2022/02/28/2022.02.28.22271565.full.pdf","host_type":"repository"},{"url":"https://www.medrxiv.org/content/medrxiv/early/2022/02/28/2022.02.28.22271565.full.pdf","host_type":"repository"},{"url":"https://syndication.highwire.org/content/doi/10.1101/2022.02.28.22271565","host_type":"publisher"},{"url":"https://doi.org/10.1101/2022.02.28.22271565","host_type":"repository"}],"fields_of_study":["AI in cancer detection","Colorectal Cancer Screening and Detection","Radiomics and Machine Learning in Medical Imaging"],"mesh_terms":[],"keywords":["Medicine","Biopsy","Colorectal cancer","Cohort","Histology","Artificial intelligence","Cancer","Pathology","Radiology","Computer science","Internal medicine"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Peace, Justice and strong institutions"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-06T14:19:20.097984Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}