Utilizing a publicly accessible automated machine learning platform to enable diagnosis before tumor surgery.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Hosseinzadeh Farideh, Liu George, Tsai Esmond, Mahmoudi Ahmad, Yang Angela, Kim Dayoung, Fieux Maxime, Levi Lirit, Abdul-Hadi Soraya, Adappa Nithin D, Alt Jeremiah A, Altartoor Khaled A, Banyi Norbert, Challa Megana, Chandra Rakesh, Chang Michael T, Chen Philip G, Cho Do-Yeon, de Choudens Camila Rios, Chowdhury Naweed, Colon Clariliz Munet, DelGaudio John M, Del Signore Anthony, Dorismond Christina, Dutra Daniel, Edalati Shaun, Edwards Thomas S, Ferriol Jose Busquets, Geltzeiler Mathew, Georgalas Christos, Govindaraj Satish, Grayson Jessica W, Gudis David A, Harvey Richard J, Heffernan Austin, Hwang Peter H, Iloreta Alfred Marc, Knight Nicolaus D, Kohanski Michael A, Lerner David K, Leventi Argyro, Lee Lik Hang, Lubner Rory, Mahomva Chengetai, Massey Conner, McCoul Edward D, Nayak Jayakar V, Pak-Harvey Ezra, Palmer James N, Pandrangi Vivek C, Psaltis Alkis J, Raviv Joseph, Sacks Peta, Sacks Ray, Schaberg Madeleine, Soudry Ethan, Sweis Auddie, Thamboo Andrew, Turner Justin H, Wang Steve X, Wise Sarah K, Woodworth Bradford A, Wormald Peter-John, Patel Zara M
Аннотация
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.