Precise identification of medulloblastoma in MRI images using a convolutional neural network integrated with a self-attention mechanism

Objective Medulloblastoma (MB) is a highly malignant brain tumor. Early diagnosis and treatment are important to improve patients’ survival. However, it is difficult to distinguish MB from other brain tumors in magnetic resonance imaging (MRI) with the naked eye. This study proposed a new hybrid dee...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenhao Fang, Chao Li, Huiqing Liu, Qiang Zhou, Shuo Li, Hong Chen, Xianzhen Chen, Zhaoli Shen
Format: Article
Language:English
Published: SAGE Publishing 2025-07-01
Series:Digital Health
Online Access:https://doi.org/10.1177/20552076251351536
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060403982204928
author Chenhao Fang
Chao Li
Huiqing Liu
Qiang Zhou
Shuo Li
Hong Chen
Xianzhen Chen
Zhaoli Shen
author_facet Chenhao Fang
Chao Li
Huiqing Liu
Qiang Zhou
Shuo Li
Hong Chen
Xianzhen Chen
Zhaoli Shen
author_sort Chenhao Fang
collection DOAJ
description Objective Medulloblastoma (MB) is a highly malignant brain tumor. Early diagnosis and treatment are important to improve patients’ survival. However, it is difficult to distinguish MB from other brain tumors in magnetic resonance imaging (MRI) with the naked eye. This study proposed a new hybrid deep learning model named InceptentionNet, combining Inception and self-attention mechanisms to recognize MB with MRI images. Methods InceptentionNet integrated multiscale feature extraction and dynamic focus on relevant regions. This model was trained using a dataset with 736 MRI images, including 106 MB and 630 non-MB images. Other single convolutional neural network models, including MobileNet, Residual Network, Densely Connected Convolutional Network, Visual Geometry Group, and Inception, were also trained. All models’ performance was evaluated. In addition, we conducted external tests to verify the generalization of the model. Results The InceptentionNet model achieved an accuracy of 98.07% ± 0.77%, a precision of 91.43% ± 4.56%, a F1-score of 93.54% ± 2.44%. And the area under curve and recall were respectively 99.41% ± 0.08% and 96.03% ± 3.61%. In external tests, this model still performed best, achieving 90.94% accuracy and 92.79% AUC. These metrics indicated that our model exhibited a good performance in distinguishing MB. The accuracy of InceptentionNet was the highest among other single models, indicating our hybrid model outperform other models. Additionally, images combined with attention heatmaps exhibited high clinical interpretability. Conclusion InceptentionNet demonstrates robust predictive capabilities and has the potential as a diagnostic assistant tool. In the future, the model should be trained and validated using larger data and multiclass classification should be expanded.
format Article
id doaj-art-431b9e44bc984f66a5c3e1f4e9afa825
institution DOAJ
issn 2055-2076
language English
publishDate 2025-07-01
publisher SAGE Publishing
record_format Article
series Digital Health
spelling doaj-art-431b9e44bc984f66a5c3e1f4e9afa8252025-08-20T02:50:33ZengSAGE PublishingDigital Health2055-20762025-07-011110.1177/20552076251351536Precise identification of medulloblastoma in MRI images using a convolutional neural network integrated with a self-attention mechanismChenhao Fang0Chao Li1Huiqing Liu2Qiang Zhou3Shuo Li4Hong Chen5Xianzhen Chen6Zhaoli Shen7 Department of Neurosurgery, Shanghai Tenth People's Hospital, School of Medicine, , Shanghai, China Department of Neurosurgery, Shanghai Tenth People's Hospital, School of Medicine, , Shanghai, China Department of Neurosurgery, Shanghai Children's Medical Center, , Shanghai, China Department of Neurosurgery, Shanghai Tenth People's Hospital, School of Medicine, , Shanghai, China Department of Neurosurgery, Shanghai Tenth People's Hospital, School of Clinical Medicine, , Nanjing, Jiangsu, China Department of Pathology, The First Affiliated Hospital, Fujian Medical University, Fuzhou, China Department of Neurosurgery, Shanghai Tenth People's Hospital, School of Medicine, , Shanghai, China Department of Neurosurgery, Shanghai Tenth People's Hospital, School of Medicine, , Shanghai, ChinaObjective Medulloblastoma (MB) is a highly malignant brain tumor. Early diagnosis and treatment are important to improve patients’ survival. However, it is difficult to distinguish MB from other brain tumors in magnetic resonance imaging (MRI) with the naked eye. This study proposed a new hybrid deep learning model named InceptentionNet, combining Inception and self-attention mechanisms to recognize MB with MRI images. Methods InceptentionNet integrated multiscale feature extraction and dynamic focus on relevant regions. This model was trained using a dataset with 736 MRI images, including 106 MB and 630 non-MB images. Other single convolutional neural network models, including MobileNet, Residual Network, Densely Connected Convolutional Network, Visual Geometry Group, and Inception, were also trained. All models’ performance was evaluated. In addition, we conducted external tests to verify the generalization of the model. Results The InceptentionNet model achieved an accuracy of 98.07% ± 0.77%, a precision of 91.43% ± 4.56%, a F1-score of 93.54% ± 2.44%. And the area under curve and recall were respectively 99.41% ± 0.08% and 96.03% ± 3.61%. In external tests, this model still performed best, achieving 90.94% accuracy and 92.79% AUC. These metrics indicated that our model exhibited a good performance in distinguishing MB. The accuracy of InceptentionNet was the highest among other single models, indicating our hybrid model outperform other models. Additionally, images combined with attention heatmaps exhibited high clinical interpretability. Conclusion InceptentionNet demonstrates robust predictive capabilities and has the potential as a diagnostic assistant tool. In the future, the model should be trained and validated using larger data and multiclass classification should be expanded.https://doi.org/10.1177/20552076251351536
spellingShingle Chenhao Fang
Chao Li
Huiqing Liu
Qiang Zhou
Shuo Li
Hong Chen
Xianzhen Chen
Zhaoli Shen
Precise identification of medulloblastoma in MRI images using a convolutional neural network integrated with a self-attention mechanism
Digital Health
title Precise identification of medulloblastoma in MRI images using a convolutional neural network integrated with a self-attention mechanism
title_full Precise identification of medulloblastoma in MRI images using a convolutional neural network integrated with a self-attention mechanism
title_fullStr Precise identification of medulloblastoma in MRI images using a convolutional neural network integrated with a self-attention mechanism
title_full_unstemmed Precise identification of medulloblastoma in MRI images using a convolutional neural network integrated with a self-attention mechanism
title_short Precise identification of medulloblastoma in MRI images using a convolutional neural network integrated with a self-attention mechanism
title_sort precise identification of medulloblastoma in mri images using a convolutional neural network integrated with a self attention mechanism
url https://doi.org/10.1177/20552076251351536
work_keys_str_mv AT chenhaofang preciseidentificationofmedulloblastomainmriimagesusingaconvolutionalneuralnetworkintegratedwithaselfattentionmechanism
AT chaoli preciseidentificationofmedulloblastomainmriimagesusingaconvolutionalneuralnetworkintegratedwithaselfattentionmechanism
AT huiqingliu preciseidentificationofmedulloblastomainmriimagesusingaconvolutionalneuralnetworkintegratedwithaselfattentionmechanism
AT qiangzhou preciseidentificationofmedulloblastomainmriimagesusingaconvolutionalneuralnetworkintegratedwithaselfattentionmechanism
AT shuoli preciseidentificationofmedulloblastomainmriimagesusingaconvolutionalneuralnetworkintegratedwithaselfattentionmechanism
AT hongchen preciseidentificationofmedulloblastomainmriimagesusingaconvolutionalneuralnetworkintegratedwithaselfattentionmechanism
AT xianzhenchen preciseidentificationofmedulloblastomainmriimagesusingaconvolutionalneuralnetworkintegratedwithaselfattentionmechanism
AT zhaolishen preciseidentificationofmedulloblastomainmriimagesusingaconvolutionalneuralnetworkintegratedwithaselfattentionmechanism