[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-376384-105":3,"detail-sidebar-cat-0-en-105":73,"doc-detail-376384-en":123},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":66,"head_meta":68,"extra_data":70,"updated_unix":72},105,"en","utilizing-a-publicly-accessible-automated-machine-learning-platform-to-enable-diagnosis-before-tumor-surgery","Utilizing a publicly accessible automated machine learning platform to enable diagnosis before tumor surgery","","Pre-operative uncertainty in distinguishing benign tumors from malignancy can alter patient counseling and surgical planning, especially when biopsy sampling error obscures true pathology. Sinonasal inverted papilloma (IP) may transform into squamous cell carcinoma (IPSCC), for which the operative approach can differ substantially. A deep automated machine learning model was trained on CT images from 19 institutions using Google Cloud Vertex AI, then evaluated on a holdout test set with AUC, sensitivity, specificity, accuracy, and F1. Using only pre-operative CT, the model achieved 95.8% sensitivity, 99.7% specificity, and 99.1% accuracy.",{"@graph":14,"@context":65},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/utilizing-a-publicly-accessible-automated-machine-learning-platform-to-enable-diagnosis-before-tumor-surgery/376384/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/utilizing-a-publicly-accessible-automated-machine-learning-platform-to-enable-diagnosis-before-tumor-surgery/376384.png","ImageObject",300,407,{"name":42,"@type":43},"Guten tag","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-24",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59],{"name":60,"@type":61,"acceptedAnswer":62},"What clinical value does the study propose for the tool?","Question",{"text":63,"@type":64},"A deep automated machine learning model created from a publicly available AI tool could support more accurate identification of malignant transformation using pre-operative CT alone, improving surgical planning decisions.","Answer","https://schema.org",{"og:url":32,"og:type":67,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":69,"canonical":32},"index,follow",{"doc_id":71,"site_id":7},376384,1790716147,{"code":4,"msg":74,"data":75},"success",[76,80,84,88,93,98,102,107,112,115,119],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":77,"show_sort_weight":78,"slug":79},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":81,"show_sort_weight":82,"slug":83},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Exam",70,"exam",{"id":89,"doc_module":4,"doc_module_name":25,"category_name":90,"show_sort_weight":91,"slug":92},5,"Comic",60,"comic",{"id":94,"doc_module":4,"doc_module_name":25,"category_name":95,"show_sort_weight":96,"slug":97},6,"Technology",50,"technology",{"id":99,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":100,"slug":101},7,40,"healthcare",{"id":103,"doc_module":4,"doc_module_name":25,"category_name":104,"show_sort_weight":105,"slug":106},8,"Research & Report",30,"research-report",{"id":108,"doc_module":4,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},9,"Religion & Spirituality",20,"religion-spirituality",{"id":110,"doc_module":4,"doc_module_name":25,"category_name":113,"show_sort_weight":110,"slug":114},"World Cup","world-cup",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":116,"slug":118},10,"Lifestyle","lifestyle",{"id":120,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":89,"slug":122},19,"General","general",{"code":4,"msg":74,"data":124},{"doc_id":71,"user_id":125,"nickname":42,"user_avatar":126,"doc_module":4,"category_id":99,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":127,"file_id":128,"file_url":129,"file_type":130,"file_size":131,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":99,"language":132,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":133,"faqs":134,"seo_title":135,"seo_description":12,"update_tm":136,"read_time":137},687212321768,"https://ap-avatar.wpscdn.com/avatar/a0010bdbe886d2fe77?x-image-process=image/resize,m_fixed,w_180,h_180&k=1789897067658708522","| A Nature Portfolio journal |  | |  |\n| --- | --- | --- | --- |\n| [https://doi.org/10.1038/s43856-025-01134-9](https://doi.org/10.1038/s43856-025-01134-9) |  |  |  |\n| Utilizing a publicly accessible automated machine learning platform to enable diagnosis before tumor surgery\u003Cbr> Check for updates |  |  |  |\n| A list of authors and their affiliations appears at the end of the paper |  |  |  |\n| Abstract Plain Language Summary |  |  |  |\n| Background: In benign tumors with potential for malignant transformation, sampling error during pre-operative biopsy can significantly change patient counseling and surgical planning. Sinonasal inverted papilloma (IP) is the most common benign soft tissue tumor of the sinuses, yet it can undergo malignant transformation to squamous cell carcinoma (IPSCC), for which the planned surgery could be drastically different. Artificial intelligence (AI) could potentially help with this diagnostic challenge.\u003Cbr>Methods: CT images from 19 institutions were used to train the Google Cloud Vertex AI platform to distinguish between IP and IP-SCC. The model was evaluated on a holdout test dataset of images from patients whose data were not used for training or validation. Performance metrics of area under the curve(AUC), sensitivity, specificity, accuracy, and F1 were used to assess the model.\u003Cbr>Results: Here we show CT image data from 958 patients and 41099 individual images that were labeled to train and validate the deep learning image classification model. The model demonstrated a 95.8 % sensitivity in correctly identifying IP-SCC cases from IP, while specificity was robust at 99.7 % . Overall, the model achieved an accuracy of 99.1% . Conclusions: A deep automated machine learning model, created from a publicly available artificial intelligence tool, using pre-operative CT imaging alone, identified malignant transformation of inverted papilloma with excellent accuracy. |  |  | Planning for surgery to remove a tumor, and the preoperative counseling a surgeon gives to the patient, can be very different, depending on if that tumor is cancerous or non-cancerous. Unfortunately, it can be difficult to always know which it is before actually getting to the operating room. Here we show the utilization of a publicly available platform, Google Vertex AI, and pre-operative computed tomography (CT) imaging of patients from nineteen separate institutions, to identify cancerous transformation of a noncancerous tumor with excellent accuracy in aspecific tumor type. An automated machine learning (AutoML) model, created from a publicly available artificial intelligence tool, by physicians with little coding background, was able to differentiate between these types of tumors with better accuracy than previously published rates from experts. This tool could serve to better inform surgical planning for tumors. |\n| There are dozens of benign tumor types that occur throughout the body that have the potential for malignant transformation. Adenomas, meningiomas, lipomas, fibromas, endometriomas, chordomas, and more are examples. When these tumors are adjacent to critical structures, the ability to know whether the tumor is truly benign or malignant before surgical resection, which may need to remove critical structures in order to actually save a patient’s life in the setting of cancer, is paramount. Inverted papilloma (IP) is the most common benign soft tissue tumor of the sinonasal cavity. With a 15% chance of recurrence after surgical resection and a 7-10% chance of conversion to malignancy (inverted papilloma associated squamous cell carcinoma, IP-SCC), this benign tumor has been treated with the respect and care typically afforded to cancer1. Early identification of malignant transformation is crucial, influencing both treatment | strategy and patient counseling. However, accurate pre-operative diagnosis of IP-SCC presents a significant challenge. Conventional modalities such as in-office biopsies, computed tomography (CT) scans, and m","cbCaieJFdbXiU9hE","https://ap.wps.com/l/cbCaieJFdbXiU9hE","pdf",1019206,"English","# Abstract Plain Language Summary\n## Background\n## Methods\n## Results\n## Conclusions\n# Methods\n## Study approval and consent\n## Evaluation setup","[{\"question\":\"What clinical value does the study propose for the tool?\",\"answer\":\"A deep automated machine learning model created from a publicly available AI tool could support more accurate identification of malignant transformation using pre-operative CT alone, improving surgical planning decisions.\"}]","Utilizing a publicly accessible automated machine learning platform to enable diagnosis before tumor surgery | PDF",1790218531,18]