BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers

Background and objectiveAccurate diagnosis of brain tumors significantly impacts patient prognosis and treatment planning. Traditional diagnostic methods primarily rely on clinicians’ subjective interpretation of medical images, which is heavily dependent on physician experience and limited by time...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng Lv, Xu-Jun Shu, Quan Liang, Jun Qiu, Zi-Cheng Xiong, Jing bo Ye, Shang bo Li, Cheng Qing Liu, Jing Zhen Niu, Sheng-Bo Chen, Hong Rao
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Oncology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fonc.2025.1585891/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850131568245342208
author Cheng Lv
Xu-Jun Shu
Xu-Jun Shu
Quan Liang
Jun Qiu
Zi-Cheng Xiong
Jing bo Ye
Shang bo Li
Cheng Qing Liu
Jing Zhen Niu
Sheng-Bo Chen
Hong Rao
author_facet Cheng Lv
Xu-Jun Shu
Xu-Jun Shu
Quan Liang
Jun Qiu
Zi-Cheng Xiong
Jing bo Ye
Shang bo Li
Cheng Qing Liu
Jing Zhen Niu
Sheng-Bo Chen
Hong Rao
author_sort Cheng Lv
collection DOAJ
description Background and objectiveAccurate diagnosis of brain tumors significantly impacts patient prognosis and treatment planning. Traditional diagnostic methods primarily rely on clinicians’ subjective interpretation of medical images, which is heavily dependent on physician experience and limited by time consumption, fatigue, and inconsistent diagnoses. Recently, deep learning technologies, particularly Convolutional Neural Networks (CNN), have achieved breakthrough advances in medical image analysis, offering a new paradigm for automated precise diagnosis. However, existing research largely focuses on single-task modeling, lacking comprehensive solutions that integrate tumor segmentation with classification diagnosis. This study aims to develop a multi-task deep learning model for precise brain tumor segmentation and type classification.MethodsThe study included 485 pathologically confirmed cases, comprising T1-enhanced MRI sequence images of high-grade gliomas, metastatic tumors, and meningiomas. The dataset was proportionally divided into training (378 cases), testing (109 cases), and external validation (51 cases) sets. We designed and implemented BrainTumNet, a deep learning-based multi-task framework featuring an improved encoder-decoder architecture, adaptive masked Transformer, and multi-scale feature fusion strategy to simultaneously perform tumor region segmentation and pathological type classification. Five-fold cross-validation was employed for result verification.ResultsIn the test set evaluation, BrainTumNet achieved an Intersection over Union (IoU) of 0.921, Hausdorff Distance (HD) of 12.13, and Dice Similarity Coefficient (DSC) of 0.91 for tumor segmentation. For tumor classification, it attained a classification accuracy of 93.4% with an Area Under the ROC Curve (AUC) of 0.96. Performance remained stable on the external validation set, confirming the model’s generalization capability.ConclusionThe proposed BrainTumNet model achieves high-precision diagnosis of brain tumor segmentation and classification through a multi-task learning strategy. Experimental results demonstrate the model’s strong potential for clinical application, providing objective and reliable auxiliary information for preoperative assessment and treatment decision-making in brain tumor cases.
format Article
id doaj-art-a271202e1465484e8be5cdf0e9593aa0
institution OA Journals
issn 2234-943X
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Oncology
spelling doaj-art-a271202e1465484e8be5cdf0e9593aa02025-08-20T02:32:23ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2025-05-011510.3389/fonc.2025.15858911585891BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformersCheng Lv0Xu-Jun Shu1Xu-Jun Shu2Quan Liang3Jun Qiu4Zi-Cheng Xiong5Jing bo Ye6Shang bo Li7Cheng Qing Liu8Jing Zhen Niu9Sheng-Bo Chen10Hong Rao11School of Mathematics and Computer Sciences, Nanchang University, Nanchang, Jiangxi, ChinaDepartment of Neurosurgery, General Hospital of Eastern Theater Command, Nanjing, ChinaDepartment of Neurosurgery, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, ChinaDepartment of Radiology, Jinling Hospital, Nanjing, ChinaDepartment of Critical Care Medicine, The Second People’s Hospital of Yibin, Yibin, Sichuan, ChinaDepartment of Computer and Information Engineering, Henan University, Nanchang, ChinaDepartment of Computer and Information Engineering, Henan University, Nanchang, ChinaDepartment of Computer and Information Engineering, Henan University, Nanchang, ChinaSchool of Mathematics and Computer Sciences, Nanchang University, Nanchang, Jiangxi, ChinaDepartment of Critical Care Medicine, The Second People’s Hospital of Yibin, Yibin, Sichuan, ChinaSchool of Software, Nanchang University, Nanchang, Jiangxi, ChinaSchool of Software, Nanchang University, Nanchang, Jiangxi, ChinaBackground and objectiveAccurate diagnosis of brain tumors significantly impacts patient prognosis and treatment planning. Traditional diagnostic methods primarily rely on clinicians’ subjective interpretation of medical images, which is heavily dependent on physician experience and limited by time consumption, fatigue, and inconsistent diagnoses. Recently, deep learning technologies, particularly Convolutional Neural Networks (CNN), have achieved breakthrough advances in medical image analysis, offering a new paradigm for automated precise diagnosis. However, existing research largely focuses on single-task modeling, lacking comprehensive solutions that integrate tumor segmentation with classification diagnosis. This study aims to develop a multi-task deep learning model for precise brain tumor segmentation and type classification.MethodsThe study included 485 pathologically confirmed cases, comprising T1-enhanced MRI sequence images of high-grade gliomas, metastatic tumors, and meningiomas. The dataset was proportionally divided into training (378 cases), testing (109 cases), and external validation (51 cases) sets. We designed and implemented BrainTumNet, a deep learning-based multi-task framework featuring an improved encoder-decoder architecture, adaptive masked Transformer, and multi-scale feature fusion strategy to simultaneously perform tumor region segmentation and pathological type classification. Five-fold cross-validation was employed for result verification.ResultsIn the test set evaluation, BrainTumNet achieved an Intersection over Union (IoU) of 0.921, Hausdorff Distance (HD) of 12.13, and Dice Similarity Coefficient (DSC) of 0.91 for tumor segmentation. For tumor classification, it attained a classification accuracy of 93.4% with an Area Under the ROC Curve (AUC) of 0.96. Performance remained stable on the external validation set, confirming the model’s generalization capability.ConclusionThe proposed BrainTumNet model achieves high-precision diagnosis of brain tumor segmentation and classification through a multi-task learning strategy. Experimental results demonstrate the model’s strong potential for clinical application, providing objective and reliable auxiliary information for preoperative assessment and treatment decision-making in brain tumor cases.https://www.frontiersin.org/articles/10.3389/fonc.2025.1585891/fullbrain tumor diagnosisdeep learningmulti-task learningmedical image analysisConvolutional Neural Networks
spellingShingle Cheng Lv
Xu-Jun Shu
Xu-Jun Shu
Quan Liang
Jun Qiu
Zi-Cheng Xiong
Jing bo Ye
Shang bo Li
Cheng Qing Liu
Jing Zhen Niu
Sheng-Bo Chen
Hong Rao
BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers
Frontiers in Oncology
brain tumor diagnosis
deep learning
multi-task learning
medical image analysis
Convolutional Neural Networks
title BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers
title_full BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers
title_fullStr BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers
title_full_unstemmed BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers
title_short BrainTumNet: multi-task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers
title_sort braintumnet multi task deep learning framework for brain tumor segmentation and classification using adaptive masked transformers
topic brain tumor diagnosis
deep learning
multi-task learning
medical image analysis
Convolutional Neural Networks
url https://www.frontiersin.org/articles/10.3389/fonc.2025.1585891/full
work_keys_str_mv AT chenglv braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT xujunshu braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT xujunshu braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT quanliang braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT junqiu braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT zichengxiong braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT jingboye braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT shangboli braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT chengqingliu braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT jingzhenniu braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT shengbochen braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers
AT hongrao braintumnetmultitaskdeeplearningframeworkforbraintumorsegmentationandclassificationusingadaptivemaskedtransformers