Farideh Hosseinzadeh, George Liu, Esmond Tsai, Ahmad Mahmoudi, Angela Yang, Dayoung Kim, Maxime Fieux, Lirit Levi, Soraya Abdul-Hadi, Nithin D Adappa, Jeremiah A Alt, Khaled A Altartoor, Norbert Banyi, Megana Challa, Rakesh Chandra, Michael T Chang, Philip G Chen, Do-Yeon Cho, Camila Rios de Choudens, Naweed Chowdhury, Clariliz Munet Colon, John M DelGaudio, Anthony Del Signore, Christina Dorismond, Daniel Dutra, Shaun Edalati, Thomas S Edwards, Jose Busquets Ferriol, Mathew Geltzeiler, Christos Georgalas, Satish Govindaraj, Jessica W Grayson, David A Gudis, Richard J Harvey, Austin Heffernan, Peter H Hwang, Alfred Marc Iloreta, Nicolaus D Knight, Michael A Kohanski, David K Lerner, Argyro Leventi, Lik Hang Lee, Rory Lubner, Chengetai Mahomva, Conner Massey, Edward D McCoul, Jayakar V Nayak, Ezra Pak-Harvey, James N Palmer, Vivek C Pandrangi, Alkis J Psaltis, Joseph Raviv, Peta Sacks, Ray Sacks, Madeleine Schaberg, Ethan Soudry, Auddie Sweis, Andrew Thamboo, Justin H Turner, Steve X Wang, Sarah K Wise, Bradford A Woodworth, Peter-John Wormald, Zara M Patel
{"title":"Utilizing a publicly accessible automated machine learning platform to enable diagnosis before tumor surgery.","authors":"Farideh Hosseinzadeh, George Liu, Esmond Tsai, Ahmad Mahmoudi, Angela Yang, Dayoung Kim, Maxime Fieux, Lirit Levi, Soraya Abdul-Hadi, Nithin D Adappa, Jeremiah A Alt, Khaled A Altartoor, Norbert Banyi, Megana Challa, Rakesh Chandra, Michael T Chang, Philip G Chen, Do-Yeon Cho, Camila Rios de Choudens, Naweed Chowdhury, Clariliz Munet Colon, John M DelGaudio, Anthony Del Signore, Christina Dorismond, Daniel Dutra, Shaun Edalati, Thomas S Edwards, Jose Busquets Ferriol, Mathew Geltzeiler, Christos Georgalas, Satish Govindaraj, Jessica W Grayson, David A Gudis, Richard J Harvey, Austin Heffernan, Peter H Hwang, Alfred Marc Iloreta, Nicolaus D Knight, Michael A Kohanski, David K Lerner, Argyro Leventi, Lik Hang Lee, Rory Lubner, Chengetai Mahomva, Conner Massey, Edward D McCoul, Jayakar V Nayak, Ezra Pak-Harvey, James N Palmer, Vivek C Pandrangi, Alkis J Psaltis, Joseph Raviv, Peta Sacks, Ray Sacks, Madeleine Schaberg, Ethan Soudry, Auddie Sweis, Andrew Thamboo, Justin H Turner, Steve X Wang, Sarah K Wise, Bradford A Woodworth, Peter-John Wormald, Zara M Patel","doi":"10.1038/s43856-025-01134-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>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 (IP-SCC), for which the planned surgery could be drastically different. Artificial intelligence (AI) could potentially help with this diagnostic challenge.</p><p><strong>Methods: </strong>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.</p><p><strong>Results: </strong>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%.</p><p><strong>Conclusions: </strong>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.</p>","PeriodicalId":72646,"journal":{"name":"Communications medicine","volume":"5 1","pages":"419"},"PeriodicalIF":5.4000,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Communications medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1038/s43856-025-01134-9","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0
Abstract
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 (IP-SCC), for which the planned surgery could be drastically different. Artificial intelligence (AI) could potentially help with this diagnostic challenge.
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.
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.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
