A Convolutional Neural Network Model for Distinguishing Hemangioblastomas From Other Cerebellar‐and‐Brainstem Tumors Using Contrast‐Enhanced MRI
Journal of Magnetic Resonance Imaging · 2024
DOI: 10.1002/jmri.29230 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Magnetic Resonance Imaging, 2024. Verfasst von Yaru Sheng und 11 weiteren Autor:innen. Beteiligte Einrichtung: Radiology Department of Huashan Hospital, Fudan University, Shanghai, China. Hauptthemen laut MEDLINE: Hemangioblastoma, Neural Networks, Computer, Magnetic Resonance Imaging, Cerebellar Neoplasms. Die Arbeit nennt 34 Literaturangaben. Gefördert von: Science and Technology Innovation Plan Of Shanghai Science and Technology Commission.
Abstract (Originalsprache)
Background
Hemangioblastoma (HB) is a highly vascularized tumor most commonly occurring in the posterior cranial fossa, requiring accurate preoperative diagnosis to avoid accidental intraoperative hemorrhage and even death.
Purpose
To accurately distinguish HBs from other cerebellar‐and‐brainstem tumors using a convolutional neural network model based on a contrast‐enhanced brain MRI dataset. Study Type Retrospective. Population Four hundred five patients (182 = HBs; 223 = other cerebellar‐and brainstem tumors): 305 cases for model training, and 100 for evaluation. Field Strength/Sequence 3 T/contrast‐enhanced T1‐weighted imaging (T1WI + C). Assessment A CNN‐based 2D classification network was trained by using sliced data along the z‐axis. To improve the performance of the network, we introduced demographic information, various data‐augmentation methods and an auxiliary task to segment tumor region. Then, this method was compared with the evaluations performed by experienced and intermediate‐level neuroradiologists, and the heatmap of deep feature, which indicates the contribution of each pixel to model prediction, was visualized by Grad‐CAM for analyzing the misclassified cases. Statistical Tests The Pearson chi‐square test and an independent t ‐test were used to test for distribution difference in age and sex. And the independent t ‐test was exploited to evaluate the performance between experts and our proposed method. P value
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Radiology Department of Huashan Hospital, Fudan University, Shanghai, China.
- Research Center for Augmented Intelligence, Zhejiang Lab, Hangzhou, China.
- Neuropathology Department of Huashan Hospital, Fudan University, Shanghai, China.
- Department of Ultrasonography, Jing'an District Centre Hospital of Shanghai, Shanghai, China.
- Neurosurgery Department of Huashan Hospital, Fudan University, Shanghai, China.
- Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China.
ORCID-Profile: Yaru Sheng, Weiwei Wang, Zhenwei Yao, Xiaoyong Zhang, Yan Ren
Förderung
- Science and Technology Innovation Plan Of Shanghai Science and Technology Commission
Zitieren
APA
Sheng, Y., Zhao, B., Cheng, H., Yu, Y., Wang, W., Yang, Y., Ding, Y., Qiu, L., Qin, Z., Yao, Z., Zhang, X., & Ren, Y. (2024). A Convolutional Neural Network Model for Distinguishing Hemangioblastomas From Other Cerebellar‐and‐Brainstem Tumors Using Contrast‐Enhanced MRI. Journal of Magnetic Resonance Imaging. https://doi.org/10.1002/jmri.29230
Vancouver
Sheng Y, Zhao B, Cheng H, Yu Y, Wang W, Yang Y, et al. A Convolutional Neural Network Model for Distinguishing Hemangioblastomas From Other Cerebellar‐and‐Brainstem Tumors Using Contrast‐Enhanced MRI. Journal of Magnetic Resonance Imaging. 2024. doi:10.1002/jmri.29230
BibTeX
@article{Sheng2024,
author = {Sheng, Yaru and Zhao, Botao and Cheng, Haixia and Yu, Yang and Wang, Weiwei and Yang, Yang and Ding, Yueyue and Qiu, Longhua and Qin, Zhiyong and Yao, Zhenwei and Zhang, Xiaoyong and Ren, Yan},
title = {A Convolutional Neural Network Model for Distinguishing Hemangioblastomas From Other Cerebellar‐and‐Brainstem Tumors Using Contrast‐Enhanced MRI},
journal = {Journal of Magnetic Resonance Imaging},
year = {2024},
doi = {10.1002/jmri.29230}
}
EUVIMED