{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T01:48:49Z","timestamp":1789523329656,"version":"build-2803163510"},"reference-count":26,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2149133"],"award-info":[{"award-number":["2149133"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["5R01CA263491-02"],"award-info":[{"award-number":["5R01CA263491-02"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>\n                    Development of artificial intelligence (AI) for medical imaging demands curation and cleaning of large-scale clinical datasets comprising hundreds of thousands of images. Some modalities, such as mammography, contain highly standardized imaging. In contrast, breast ultrasound imaging (BUS) can contain many irregularities not indicated by scan metadata, such as enhanced scan modes, sonographer annotations, or additional views. We present an open-source software solution for automatically processing clinical BUS datasets. The algorithm performs BUS scan filtering (flagging of invalid and non-B-mode scans), cleaning (dual-view scan detection, scan area cropping, and caliper detection), and knowledge extraction (BI-RADS Labeling and Measurement fields) from sonographer annotations. Its modular design enables users to adapt it to new settings. Experiments on an internal testing dataset of 430 clinical BUS images achieve &gt;95% sensitivity and &gt;98% specificity in detecting every type of text annotation, &gt;98% sensitivity and specificity in detecting scans with blood flow highlighting, alternative scan modes, or invalid scans. A case study on a completely external, public dataset of BUS scans found that BUSClean identified text annotations and scans with blood flow highlighting with 88.6% and 90.9% sensitivity and 98.3% and 99.9% specificity, respectively. Adaptation of the lesion caliper detection method to account for a type of caliper specific to the case study demonstrates the intended use of BUSClean in new data distributions and improved performance in lesion caliper detection from 43.3% and 93.3% out-of-the-box to 92.1% and 92.3% sensitivity and specificity, respectively. Source code, example notebooks, and sample data are available at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/hawaii-ai\/bus-cleaning\" xlink:type=\"simple\">https:\/\/github.com\/hawaii-ai\/bus-cleaning<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0315434","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T13:38:49Z","timestamp":1733924329000},"page":"e0315434","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["BUSClean: Open-source software for breast ultrasound image pre-processing and knowledge extraction for medical AI"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6253-8402","authenticated-orcid":true,"given":"Arianna","family":"Bunnell","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kailee","family":"Hung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John A.","family":"Shepherd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Sadowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"issue":"1","key":"pone.0315434.ref001","doi-asserted-by":"crossref","first-page":"e44310","DOI":"10.2196\/44310","article-title":"Normal Workflow and Key Strategies for Data Cleaning Toward Real-World Data.","volume":"12","author":"M Guo","year":"2023","journal-title":"Interactive Journal of Medical Research"},{"issue":"1","key":"pone.0315434.ref002","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1148\/radiol.2020192224","article-title":"Preparing medical imaging data for machine learning.","volume":"295","author":"MJ Willemink","year":"2020","journal-title":"Radiology."},{"key":"pone.0315434.ref003","unstructured":"\u0218erb\u0103nescu M-S, Rotaru-Z\u0103v\u0103leanu A-D, Istrate-Ofi\u021beru A-M, Maria BE-I-A, Enache I-A, Nagy RD, et al., editors. Medical Image Data Cleansing for Machine Learning: A Must in the Evidence-Based Medicine? International Conference on Advancements of Medicine and Health Care through Technology; 2022: Springer."},{"issue":"1","key":"pone.0315434.ref004","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-021-26023-2","article-title":"Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams","volume":"12","author":"Y Shen","year":"2021","journal-title":"Nature Communications"},{"key":"pone.0315434.ref005","article-title":"The NYU Breast Ultrasound Dataset v1.02021.","author":"FE Shamout"},{"issue":"11","key":"pone.0315434.ref006","first-page":"120","article-title":"The opencv library.","volume":"25","author":"G. Bradski","year":"2000","journal-title":"Dr Dobb\u2019s Journal: Software Tools for the Professional Programmer"},{"key":"pone.0315434.ref007","article-title":"Pillow (pil fork) documentation.","author":"A. Clark","year":"2015","journal-title":"readthedocs."},{"key":"pone.0315434.ref008","doi-asserted-by":"crossref","first-page":"102368","DOI":"10.1016\/j.media.2022.102368","article-title":"Clever Hans effect found in a widely used brain tumour MRI dataset","volume":"77","author":"D Wallis","year":"2022","journal-title":"Medical image analysis"},{"issue":"1","key":"pone.0315434.ref009","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1038\/s41467-021-21895-w","article-title":"Quantitative interpretation explains machine learning models for chemical reaction prediction and uncovers bias","volume":"12","author":"DP Kov\u00e1cs","year":"2021","journal-title":"Nature communications"},{"key":"pone.0315434.ref010","doi-asserted-by":"crossref","first-page":"102903","DOI":"10.1016\/j.media.2023.102903","article-title":"Evaluation of MRI-based machine learning approaches for computer-aided diagnosis of dementia in a clinical data warehouse","volume":"89","author":"S Bottani","year":"2023","journal-title":"Medical Image Analysis"},{"issue":"4","key":"pone.0315434.ref011","first-page":"045013","article-title":"Improving breast cancer diagnosis by incorporating raw ultrasound parameters into machine learning. Machine Learning","volume":"3","author":"J Baek","year":"2022","journal-title":"Science and Technology"},{"issue":"1","key":"pone.0315434.ref012","article-title":"Deep learning based on ultrasound images assists breast lesion diagnosis in China: a multicenter diagnostic study.","volume":"13","author":"Y Gu","year":"2022","journal-title":"Insights into Imaging."},{"issue":"1","key":"pone.0315434.ref013","article-title":"Weakly-supervised deep learning for ultrasound diagnosis of breast cancer","volume":"11","author":"J Kim","year":"2021","journal-title":"Scientific Reports"},{"key":"pone.0315434.ref014","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.ultras.2016.08.004","article-title":"Deep learning based classification of breast tumors with shear-wave elastography.","volume":"72","author":"Q Zhang","year":"2016","journal-title":"Ultrasonics"},{"key":"pone.0315434.ref015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.medengphy.2018.12.005","article-title":"Dual-mode artificially-intelligent diagnosis of breast tumours in shear-wave elastography and B-mode ultrasound using deep polynomial networks","volume":"64","author":"Q Zhang","year":"2019","journal-title":"Medical engineering & physics"},{"issue":"4\u20135","key":"pone.0315434.ref016","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1177\/0161734620932609","article-title":"Classification of Breast Masses on Ultrasound Shear Wave Elastography using Convolutional Neural Networks.","volume":"42","author":"T Fujioka","year":"2020","journal-title":"Ultrasonic imaging."},{"key":"pone.0315434.ref017","doi-asserted-by":"crossref","first-page":"1621","DOI":"10.3389\/fonc.2020.01621","article-title":"Deep Learning-Based Radiomics of B-Mode Ultrasonography and Shear-Wave Elastography: Improved Performance in Breast Mass Classification.","volume":"10","author":"X Zhang","year":"2020","journal-title":"Frontiers in oncology"},{"key":"pone.0315434.ref018","article-title":"Breast imaging reporting and data system (BI-RADS).","author":"C D\u2019Orsi","year":"2018","journal-title":"Breast imaging atlas, 4th edn American College of Radiology, Reston"},{"key":"pone.0315434.ref019","unstructured":"EasyOCR: JaidedAI; 2023. Available from: https:\/\/github.com\/JaidedAI\/EasyOCR."},{"key":"pone.0315434.ref020","article-title":"Application of Artificial Intelligence Computer-Assisted Diagnosis Originally Developed for Thyroid Nodules to Breast Lesions on Ultrasound.","author":"SE Lee","year":"2022","journal-title":"Journal of Digital Imaging"},{"issue":"4","key":"pone.0315434.ref021","doi-asserted-by":"crossref","first-page":"2486","DOI":"10.21037\/qims-22-880","article-title":"Deep learning model for the diagnosis of breast cancers smaller than 1 cm with ultrasonography: integration of ultrasonography and clinical factors","volume":"13","author":"JH Bong","year":"2023","journal-title":"Quantitative Imaging in Medicine and Surgery"},{"key":"pone.0315434.ref022","doi-asserted-by":"crossref","first-page":"104863","DOI":"10.1016\/j.dib.2019.104863","article-title":"Dataset of breast ultrasound images.","volume":"28","author":"W Al-Dhabyani","year":"2020","journal-title":"Data in brief."},{"issue":"1","key":"pone.0315434.ref023","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/01617346221075769","article-title":"A Multi-Task Learning Framework for Automated Segmentation and Classification of Breast Tumors From Ultrasound Images.","volume":"44","author":"J Chowdary","year":"2022","journal-title":"Ultrasonic Imaging."},{"key":"pone.0315434.ref024","article-title":"AAU-net: An Adaptive Attention U-net for Breast Lesions Segmentation in Ultrasound Images","volume":"1","author":"G Chen","year":"2022","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0315434.ref025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/7733583","article-title":"Discrimination of Breast Cancer Based on Ultrasound Images and Convolutional Neural Network.","volume":"2022","author":"R Du","year":"2022","journal-title":"Journal of Oncology"},{"issue":"1","key":"pone.0315434.ref026","first-page":"144","article-title":"FMRNet: A fused network of multiple tumoral regions for breast tumor classification with ultrasound images.","volume":"49","author":"W Cui","year":"2022","journal-title":"Medical physics (Lancaster)."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0315434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T13:39:16Z","timestamp":1733924356000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0315434"}},"subtitle":[],"editor":[{"given":"Arka","family":"Bhowmik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,11]]},"references-count":26,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0315434","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,11]]}}}