Skip to main content

ORIGINAL RESEARCH article

Front. Physiol.
Sec. Computational Physiology and Medicine
Volume 15 - 2024 | doi: 10.3389/fphys.2024.1426468
This article is part of the Research Topic Medical Knowledge-Assisted Machine Learning Technologies in Individualized Medicine Volume II View all articles

A deep learning radiomics model based on CT images for predicting the biological activity of hepatic cystic echinococcosis

Provisionally accepted
Mayidili Nijiati Mayidili Nijiati 1Mihray Turdi Mihray Turdi 2Maihemitijiang ，. Damola Maihemitijiang ，. Damola 2Yasen Yimit Yasen Yimit 2Yang Jing Yang Jing 3Adilijiang Abulaiti Adilijiang Abulaiti 2Aibibulajiang Mutailifu Aibibulajiang Mutailifu 2Diliaremu Aihaiti Diliaremu Aihaiti 2Yunling Wang Yunling Wang 4Xiaoguang Zou Xiaoguang Zou 2*
  • 1 Fourth Affiliated Hospital, Xinjiang Medical University, Urumqi, China
  • 2 First People's Hospital of Kashi, Kashi, China
  • 3 Huiying Medical Technology Co.,Ltd., Beijing, China
  • 4 First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang Uyghur Region, China

The final, formatted version of the article will be published soon.

    This work aims to explore the potential applications of a deep learning radiomics (DLR) model, based on CT images, in predicting the biological activity grading of hepatic cystic echinococcosis. A retrospective analysis of 160 patients with hepatic echinococcosis was performed (127 and 33 in training and validation sets). Volume of interests (VOIs) were drawn, and radiomics features and deep neural network features were extracted. Feature selection was performed on the training set, and radiomics score (Rad Score) and deep learning score (Deep Score) were calculated. Seven diagnostics models (based on logistic regression algorithm) for the biological activity grading were constructed using the selected radiomics features and two deep model features respectively. All models were evaluated using the receiver operating characteristic curve, and the area under the curve (AUC) was calculated. A nomogram was constructed using the combined model, and its calibration, discriminatory ability, and clinical utility were assessed.12,6 and 10 optimal radiomics features, deep learning features were selected from two deep learning network (DLN) features, respectively. For biological activity grading of hepatic cystic echinococcosis, the combined model demonstrated strong diagnostic performance, with an AUC value of 0.888 (95%CI:0.837-0.936) in the training set and 0.876 (0.761-0.964) in the validation set. The clinical decision analysis curve indicated promising results, while the calibration curve revealed that the nomogram's prediction result was highly compatible with the actual result. The DLR model can be used for predicting the biological activity grading of hepatic echinococcosis.

    Keywords: Hepatic cystic echinococcosis, biological activity grading, Radiomics, deep learning, 3D-Resnet

    Received: 18 May 2024; Accepted: 15 Jul 2024.

    Copyright: © 2024 Nijiati, Turdi, Damola, Yimit, Jing, Abulaiti, Mutailifu, Aihaiti, Wang and Zou. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Xiaoguang Zou, First People's Hospital of Kashi, Kashi, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.