Share：
Share this content in WeChat
X
[Chinese][PDF]981
• Review •
Advances in deep residual networks for MRI classification of brain tumors
LI Guangyu  YANG Feng  ZHANG Zhiyue  CHEN Lei 

Cite this article as: LI G Y, YANG F, ZHANG Z Y, et al. Advances in deep residual networks for MRI classification of brain tumors[J]. Chin J Magn Reson Imaging, 2025, 16(3): 143-149, 161 DOI:10.12015/issn.1674-8034.2025.03.024.


[Abstract] Brain tumors, as a group of tissues that proliferate abnormally in or around the human brain, may grow in ways that lead to severe neurological dysfunction, posing a significant threat to patients' quality of life and life safety. Therefore, accurately classifying brain tumors is of crucial importance for formulating targeted treatment plans and evaluating the prognosis of patients. In recent years, the rapid development of deep learning technology has opened up new avenues in the field of medical image analysis, and the deep residual network (ResNet) and its derived variants have demonstrated excellent performance in image classification tasks, bringing new breakthroughs in brain tumor MRI classification. In this paper, the optimization strategy of the network model based on deep residual networks in brain tumor MRI classification is discussed in depth, firstly, the development of deep residual networks is introduced, followed by a detailed analysis of the current applications of deep residual networks and their derived variants on brain tumor MRI images. Finally, the current challenges faced in this field are pointed out, and the future research directions are prospected, aiming to provide comprehensive references and ideas for related research, and to promote the further development and application of deep residual networks in brain tumor MRI classification, so as to improve the accuracy and efficiency of brain tumor diagnosis, and to provide more powerful support for clinical treatment.
[Keywords] deep residual network；brain tumor；magnetic resonance imaging；image classification；attentional mechanisms；transfer learning

LI Guangyu1   YANG Feng2   ZHANG Zhiyue1   CHEN Lei2*  

1 School of Medical Information Engineering, Shandong University of Chinese Medicine, Jinan 250355, China

2 Assets and Equipment Department, the Affiliated Hospital of Shandong University of Chinese Medicine, Jinan 250014, China

Corresponding author: CHEN L, E-mail: szysbc@163.com

Conflicts of interest   None.

Received  2025-01-09
Accepted  2025-03-10
DOI: 10.12015/issn.1674-8034.2025.03.024
Cite this article as: LI G Y, YANG F, ZHANG Z Y, et al. Advances in deep residual networks for MRI classification of brain tumors[J]. Chin J Magn Reson Imaging, 2025, 16(3): 143-149, 161 DOI:10.12015/issn.1674-8034.2025.03.024.

[1]
TANDEL G S, BISWAS M, KAKDE O G, et al. A review on a deep learning perspective in brain cancer classification[J/OL]. Cancers, 2019, 11(1): 111 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/30669406/. DOI: 10.3390/cancers11010111.
[2]
GBD 2016 Brain and Other CNS Cancer Collaborators. Global, regional, and national burden of brain and other CNS cancer, 1990-2016: a systematic analysis for the Global Burden of Disease Study 2016[J]. Lancet Neurol, 2019, 18(4): 376-393. DOI: 10.1016/S1474-4422(18)30468-X.
[3]
LI C, ZHANG F X, DU Y J, et al. Classification of brain tumor types through MRIs using parallel CNNs and firefly optimization[J/OL]. Sci Rep, 2024, 14: 15057 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/38956224/. DOI: 10.1038/s41598-024-65714-w.
[4]
XIA Q L, ZHENG H, ZOU H N, et al. A comprehensive review of deep learning for medical image segmentation[J/OL]. Neurocomputing, 2025, 613: 128740 [2025-01-08]. https://www.sciencedirect.com/science/article/abs/pii/S092523122401511X. DOI: 10.1016/j.neucom.2024.128740.
[5]
HOSAIN M T, JIM J R, MRIDHA M F, et al. Explainable AI approaches in deep learning: Advancements, applications and challenges[J/OL]. Comput Electr Eng, 2024, 117: 109246 [2025-01-08]. https://www.sciencedirect.com/science/article/abs/pii/S0045790624001745. DOI: 10.1016/j.compeleceng.2024.109246.
[6]
HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA. IEEE, 2016: 770-778. DOI: 10.1109/CVPR.2016.90.
[7]
XIE S N, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017: 5987-5995. DOI: 10.1109/CVPR.2017.634.
[8]
TAN M X, LE Q V. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks[C]//International Conference on Machine Learning, 2019. DOI: 10.48550/arXiv.1905.11946.
[9]
ZHANG H, WU C R, ZHANG Z Y, et al. ResNeSt: Split-Attention Networks[J/OL]. arXiv preprint arXiv, 2020 [2025-01-08]. https://arxiv.org/abs/2004.08955. DOI: 10.48550/arXiv.2004.08955.
[10]
RAGAB M, KATIB I, SHARAF S A, et al. Automated brain tumor recognition using equilibrium optimizer with deep learning approach on MRI images[J/OL]. Sci Rep, 2024, 14: 29448 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/39604452/. DOI: 10.1038/s41598-024-80888-z.
[11]
DUAN J W, XIONG J Q, LI Y H, et al. Deep learning based multimodal biomedical data fusion: an overview and comparative review[J/OL]. Inf Fusion, 2024, 112: 102536 [2025-01-08]. https://www.sciencedirect.com/science/article/abs/pii/S1566253524003142. DOI: 10.1016/j.inffus.2024.102536.
[12]
DESHPANDE A, ESTRELA V V, PATAVARDHAN P. The DCT-CNN-ResNet50 architecture to classify brain tumors with super-resolution, convolutional neural network, and the ResNet50[J/OL]. Neurosci Inform, 2021, 1(4): 100013 [2025-01-08]. https://www.sciencedirect.com/science/article/pii/S2772528621000133. DOI: 10.1016/j.neuri.2021.100013.
[13]
JIANG M W, ZENG P Y, WANG K, et al. FECAM: Frequency enhanced channel attention mechanism for time series forecasting[J/OL]. Adv Eng Inform, 2023, 58: 102158 [2025-01-08]. https://www.sciencedirect.com/science/article/abs/pii/S1474034623002860. DOI: 10.1016/j.aei.2023.102158.
[14]
ZHU Z Q, ATTIQUE KHAN M, WANG S H, et al. RBEBT: a ResNet-based BA-ELM for brain tumor classification[J]. Comput Mater Continua, 2023, 74(1): 101-111. DOI: 10.32604/cmc.2023.030790.
[15]
HUANG S J, CHEN W Q, LU B X, et al. An improved BAT algorithm for collaborative dynamic target tracking and path planning of multiple UAV[J/OL]. Comput Electr Eng, 2024, 118: 109340 [2025-01-08]. https://www.sciencedirect.com/science/article/abs/pii/S0045790624002684. DOI: 10.1016/j.compeleceng.2024.109340.
[16]
ASIRI A A, SHAF A, ALI T, et al. Brain tumor detection and classification using fine-tuned CNN with ResNet50 and U-Net model: a study on TCGA-LGG and TCIA dataset for MRI applications[J/OL]. Life, 2023, 13(7): 1449 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/37511824/. DOI: 10.3390/life13071449.
[17]
EL-FESHAWY S A, SAAD W, SHOKAIR M, et al. IoT framework for brain tumor detection based on optimized modified ResNet 18 (OMRES)[J]. J Supercomput, 2023, 79(1): 1081-1110. DOI: 10.1007/s11227-022-04678-y.
[18]
ZOU Q, CAI K Y, CHEN Z X, et al. Comment on Prognostic Factors for Lymph Node Metastases in pT1 Colorectal Cancer Differ According to Tumor Morphology: A Nationwide Cohort Study[J/OL]. Ann Surg Open, 2023, 4(2): e289 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/37601461/. DOI: 10.1097/as9.0000000000000289.
[19]
BHAGYALAXMI K, DWARAKANATH B, REDDY P V P. Deep learning for multi-gradebrain tumor detection and classification: a prospectivesurvey[J]. Multimed Tools Appl, 2024, 83(25): 65889-65911. DOI: 10.1007/s11042-024-18129-8.
[20]
PEI L M, JONES K A, SHBOUL Z A, et al. Deep neural network analysis of pathology images with integrated molecular data for enhanced glioma classification and grading[J/OL]. Front Oncol, 2021, 11: 668694 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/34277415/. DOI: 10.3389/fonc.2021.668694.
[21]
ELAZAB N, GAB-ALLAH W A, ELMOGY M. A multi-class brain tumor grading system based on histopathological images using a hybrid YOLO and RESNET networks[J/OL]. Sci Rep, 2024, 14(1): 4584 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/38403597/. DOI: 10.1038/s41598-024-54864-6.
[22]
BUTEREZ D, JANET J P, KIDDLE S J, et al. Transfer learning with graph neural networks for improved molecular property prediction in the multi-fidelity setting[J/OL]. Nat Commun, 2024, 15(1): 1517 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/38409255/. DOI: 10.1038/s41467-024-45566-8.
[23]
JOCHER G, STOKEN A, BOROVEC J, et al. ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements[J/OL]. Zenodo, 2020 [2025-01-08]. https://ui.adsabs.harvard.edu/abs/2020zndo...4154370J/abstract. DOI: 10.5281/ZENODO.4154370.
[24]
ZENG Y H, LIU N B, YANG X, et al. Enhanced multimodal brain tumor classification in MR images using 2D ResNet as backbone with explicit tumor size information[J]. J Cancer, 2024, 15(13): 4275-4286. DOI: 10.7150/jca.95987.
[25]
XIA J M, XING L P, TAN L, et al. Brain tumors classification based on MDM-ResNet[J]. J Nanjing Univ Inf Sci Technol Nat Sci Ed, 2022, 14(2): 212-219. DOI: 10.13878/j.cnki.jnuist.2022.02.009.
[26]
LIU Y B, HUANG H Y, ZENG Y H. DC-net: a dual-channel and cross-scale feature fusion infrared small target detection network[J/OL]. IEEE Trans Geosci Remote Sens, 2024, 62: 4708809 [2025-01-08]. https://ieeexplore.ieee.org/abstract/document/10706880. DOI: 10.1109/TGRS.2024.3475742.
[27]
KOKKALLA S, KAKARLA J, VENKATESWARLU I B, et al. Three-class brain tumor classification using deep dense inception residual network[J]. Soft comput, 2021, 25(13): 8721-8729. DOI: 10.1007/s00500-021-05748-8.
[28]
WANG T T, HU Z H, GUAN Y R. Author Correction: an efficient lightweight network for image denoising using progressive residual and convolutional attention feature fusion[J/OL]. Sci Rep, 2024, 14: 15834 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/38982102/. DOI: 10.1038/s41598-024-66739-x.
[29]
ASHWINI B, KAUR M, SINGH D, et al. Efficient skip connections-based residual network (ESRNet) for brain tumor classification[J/OL]. Diagnostics, 2023, 13(20): 3234 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/37892055/. DOI: 10.3390/diagnostics13203234.
[30]
HUANG M, XIONG Z Y, ZHU J L. MRI brain tumor classification based on multi-scale residual network[J]. Chin J Magn Reson Imag, 2023, 14(1): 124-129. DOI: 10.12015/issn.1674-8034.2023.01.022.
[31]
ZHANG X Q, LUO J, YANG M, et al. Classification method of brain tumor based on improved SE-net network and multi-attention[J]. J China West Norm Univ Nat Sci, 2024, 45(1): 93-101. DOI: 10.16246/j.issn.1673-5072.2024.01.013.
[32]
WU B, SHI D H, LYU D L, et al. Brain tumor classification based on federated learning and improved CBAM-ResNet18[J]. Comput Syst Appl, 2024, 33(4): 39-49. DOI: 10.15888/j.cnki.csa.009469.
[33]
LIU B Y, LV N Y, GUO Y C, et al. Recent advances on federated learning: a systematic survey[J/OL]. Neurocomputing, 2024, 597: 128019 [2025-01-08]. https://www.sciencedirect.com/science/article/pii/S0925231224007902. DOI: 10.1016/j.neucom.2024.128019.
[34]
LIU W S, HAN S, RONG N. A novel ensemble method based on residual convolutional neural network with attention module for transient stability assessment considering operational variability[J/OL]. Eng Appl Artif Intell, 2025, 139: 109519 [2025-01-08]. https://www.sciencedirect.com/science/article/abs/pii/S0952197624016774. DOI: 10.1016/j.engappai.2024.109519.
[35]
SCHMAINDA K M, PRAH M A, RAND S D, et al. Multisite concordance of DSC-MRI analysis for brain tumors: results of a national cancer institute quantitative imaging network collaborative project[J]. AJNR Am J Neuroradiol, 2018, 39(6): 1008-1016. DOI: 10.3174/ajnr.A5675.
[36]
HAO Z C, AGHAKOUCHAK A, NAKHJIRI N, et al. Global integrated drought monitoring and prediction system[J/OL]. Sci Data, 2014, 1: 140001 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/25977759/. DOI: 10.1038/sdata.2014.1.
[37]
CHENG J, YANG W, HUANG M Y, et al. Retrieval of brain tumors by adaptive spatial pooling and fisher vector representation[J/OL]. PLoS One, 2016, 11(6): e0157112 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/27273091/. DOI: 10.1371/journal.pone.0157112.
[38]
JIANG L Q, NING C Y, LI J Y. Glioma classification framework based on SE-ResNeXt network and its optimization[J]. IET Image Process, 2022, 16(2): 596-605. DOI: 10.1049/ipr2.12374.
[39]
LIN Z Y, CUI Y P, LIU J, et al. Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network[J]. Eur Radiol, 2021, 31(7): 5021-5031. DOI: 10.1007/s00330-020-07608-9.
[40]
QUON J L, BALA W, CHEN L C, et al. Deep learning for pediatric posterior Fossa tumor detection and classification: a multi-institutional study[J]. AJNR Am J Neuroradiol, 2020, 41(9): 1718-1725. DOI: 10.3174/ajnr.A6704.
[41]
WEN J, ZHENG L Y. Brain tumor classification based on attention guided deep learning model[J/OL]. Int J Comput Intell Syst, 2022, 15(1): 35 [2025-01-08]. https://link.springer.com/article/10.1007/s44196-022-00090-9. DOI: 10.1007/s44196-022-00090-9.
[42]
GAYATHRI T, SUNDEEP KUMAR K. A deep learning based effective model for brain tumor segmentation and classification using MRI images[J]. J Adv Inf Technol, 2023, 14(6): 1280-1288. DOI: 10.12720/jait.14.6.1280-1288.
[43]
LIU G Q, YANG Y P, LI X S, et al. Gca-pvt-net: group convolutional attention and PVT dual-branch network for oracle bone drill chisel segmentation[J/OL]. Herit Sci, 2024, 12(1): 260 [2025-01-08]. https://www.nature.com/articles/s40494-024-01378-z. DOI: 10.1186/s40494-024-01378-z.
[44]
KAZEROONI A, KHALILI N, LIU X, et al. The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)[J/OL]. ArXiv, 2023 [2025-01-08]. https://pubmed.ncbi.nlm.nih.gov/37292481/. DOI: 10.48550/arXiv.2305.17033.
[45]
ISUNURI B V, KAKARLA J. EfficientNet and multi-path convolution with multi-head attention network for brain tumor grade classification[J/OL]. Comput Electr Eng, 2023, 108: 108700 [2025-01-08]. https://www.sciencedirect.com/science/article/abs/pii/S0045790623001246. DOI: 10.1016/j.compeleceng.2023.108700.
[46]
ISUNURI B V, KAKARLA J. EfficientNet and mixed convolution network for three-class brain tumor magnetic resonance image classification[J]. Soft Comput, 2024, 28(17): 10741-10750. DOI: 10.1007/s00500-024-09830-9.
[47]
CUI B, JIA Z N, JI P, et al. Brain tumor classification method based on improved EfficientNetV2 network[J]. J Jilin Univ Sci Ed, 2023, 61(5): 1169-1177. DOI: 10.13413/j.cnki.jdxblxb.2022383.
[48]
GHOSH A, SONI B, BARUAH U. Transfer learning-based deep feature extraction framework using fine-tuned EfficientNet B7 for multiclass brain tumor classification[J]. Arab J Sci Eng, 2024, 49(9): 12027-12048. DOI: 10.1007/s13369-023-08607-w.
[49]
WANG Y, YANG Y L, FAN X H, et al. Brain tumor classification algorithm based on transfer learning and improved EfficientNet-B0[J/OL]. China Ind Econ, 2024: 1-7. DOI: 10.16180/j.cnki.issn1007-7820.2025.04.007.
[50]
HUA X Y, QI Y S. IC+IEffxNet: a hybrid brain tumor classfication study based on CBAM and EfficientNet with improved channel attention[J]. Comput Mod, 2023(5): 1-7. DOI: 10.3969/j.issn.1006-2475.2023.05.001.
[51]
ZHANG Y H, WANG S H, WU H X, et al. Brain tumors classification for MR images based on attention guided deep learning model[C]//2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). November 1-5, 2021, Mexico. IEEE, 2021: 3233-3236. DOI: 10.1109/EMBC46164.2021.9630571.

PREV Progress of multimodal MRI research on central abnormalities induced by chemotherapy-induced peripheral neuropathy in breast cancer
NEXT Research progress in the application of cardiac magnetic resonance imaging in dilated cardiomyopathy
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn