An Efficient Approach for Tumor Grade Classification from MRI Image using Hybrid ResNet-101 with Enhanced GoogLeNet Algorithm

Abstract

A brain tumor is defined by the abnormal growth of brain cells, some of which may become cancerous. Early detection and treatment of the disease are critical for improving the patients’ quality of life and increasing their lifespan. Artificial intelligence and medical imaging technologies have made significant advances in disease analysis and prediction, particularly in the detection of brain tumors. Extracting relevant features from Magnetic Resonance Imaging (MRI) scans is an important step in the diagnostic process, and several methods have been proposed. Traditional approaches frequently result in treatment delays, which can negatively affect patient outcomes. To address these issues, this study aimed to develop a precise brain tumor detection and classification system using advanced deep learning techniques. Initially, a homomorphic wavelet filter is used during the preprocessing stage to enhance MRI images by minimizing noise and improving image clarity. Subsequently, segmentation is performed using the Fuzzy C-Means (FCM) clustering algorithm combined with the Salp Swarm Algorithm (SSA). SSA’s optimization capabilities of SSA refine the clustering process, resulting in a more accurate delineation of tumor regions. For feature extraction, the ResNet-101 model was employed owing to its deep residual learning framework, which captures complex patterns and features from the segmented images. The classification was carried out using an enhanced GoogLeNet model, which leverages its advanced convolutional architecture to improve tumor detection accuracy by effectively managing extracted features and differentiating between tumor types. Comparative analysis demonstrates that the proposed model outperforms other classifiers, such as SqueezeNet, MobileNetv2, VGG-16, and AlexNet, achieving an accuracy of 98.17%, specificity of 91.34%, and sensitivity of 98.79%.

Keywords

Brain tumor / deep learning / Fuzzy C-Means clustering (FCM) / Salp Swarm Algorithm (SSA) / enhanced GoogLeNet

References

[1] Abrams-PompeRS, FantiS, SchootsI G, MooreC M, TurkbeyB, VickersA J, EasthamJ A. The role of magnetic resonance imaging and positron emission tomography/computed tomography in the primary staging of newly diagnosed prostate cancer: A systematic review of the literature. EuropeanUrology Oncology, 2021, 4(3): 370-395

[2] AgarwalM, RaniG, KumarA, KumarP, ManikandanR, GandomiAH. Deep learning for enhanced brain tumor detection and classification. Results in Engineering, 2024, 22: 102117

[3] Al-GalalS A, AlshaikhliI F T, AbdulrazzaqM M. MRI brain tumor medical images analysis using deep learning techniques: A systematic review. Health and Technology, 2021, 11(2): 267-282

[4] AlamM S, RahmanM M, HossainM A, IslamM K, AhmedK M, AhmedK T, MiahM S. Automatic human brain tumor detection in MRI image using templatebased K means and improved fuzzy C means clustering algorithm. Big Data and Cognitive Computing, 2019, 3(2): 27

[5] AliR, ManikandanA, LeiR, et al.. A novel SpaSA based hyper-parameter optimized FCEDN with adaptive CNN classification for skin cancer detection. Scientific Reports, 2024, 14: 9336

[6] AliR, ManikandanA, XuJ. A novel framework of adaptive fuzzy-GLCM segmentation and fuzzy with capsules network (F-CapsNet) classification. Neural Computing & Applications, 2023, 35: 22133-22149

[7] American Cancer Society Key statistics for brain and spinal cord tumors, 2021

[8] AnantharajanS, GunasekaranS, SubramanianT, VenkateshR. MRI brain tumor detection using deep learning and machine learning approaches. Measurement: Sensors, 2024, 31: 101026

[9] AnnamalaiM, MuthiahP. An early prediction of tumor in heart by cardiac masses classification in echocardiogram images using robust back propagation neural network classifier. Brazilian Archives of Biology and Technology, 2022, 65: e22210316

[10] AnilkumarB, KumarP R. Tumor classification using block wise fine tuning and transfer learning of deep neural network andKNNclassifier onMRbrain images. International, 2020, JournalofEmergingTrendsinEngineeringResearch8(2): 574-583

[11] AsadR, RehmanS U, ImranA, LiJ, AlmuhaimeedA, AlzahraniA. Computer-aided early melanoma brain-tumor detection using deep-learning approach. Biomedicines, 2023, 11(1): 184

[12] AyadiW, ElhamziW, CharfiI, AtriM. Deep CNN for brain tumor classification. Neural Processing Letters, 2021, 53: 671-700

[13] BalamuruganD, SeshadriSA, AravinthP, ReddyP, RupaniA, ManikandanA. Multiview objects recognition using deep learning-based wrap-CNN with voting scheme. Neural Processing Letters, 2022, 54: 1-27

[14] ChengJ, HuangW, CaoS, YangR, YangW, YunZ, FengQ. Enhanced performance of brain tumor classification via tumor region augmentation and partition. PloS One, 2015, 10(10): e0140381

[15] El-KenawyE S M, AlbalawiF, WardSA, GhoneimSS, EidMM, AbdelhamidAA, IbrahimA, et al.. Feature selection and classification of transformer faults based on novel meta-heuristic algorithm. Mathematics, 2022, 10(17): 3144

[16] El-KenawyE S M, MirjaliliS, AbdelhamidA A, IbrahimA, KhodadadiN, EidMM. Meta-heuristic optimization and keystroke dynamics for authentication of smartphone users. Mathematics, 2022, 10(16): 2912

[17] FonsecaN A, GregorioA C, MendesV M, LopesR, AbreuT, GoncalvesN, et al.. GMP-grade nanoparticle targeted to nucleolin downregulates tumor molecular signature, blocking growth and invasion, at low systemic exposure. Nano Today, 2021, 37: 101095

[18] GadekalluT R, AlazabM, KaluriR, MaddikuntaP K R, BhattacharyaS, LakshmannaK. Hand gesture classification using a novel CNN-crowsearch algorithm. Complex & Intelligent Systems, 2021, 7: 1855-1868

[19] HaoS, HuangC, HeidariAA, ChenH, LiL, AlgarniA D, XuS. Salp swarm algorithm with iterative mapping and local escaping for multi-level threshold image segmentation: A skin cancer dermoscopic case study. Journal, 2023, ofComputationalDesignandEngineering10(2): 655-693

[20] HashemzehiR, MahdaviS J S, KheirabadiM, KamelS R. Detection of brain tumors from MRI images base on deep learning using hybrid model CNN and NADE. Biocybernetics and Biomedical Engineering, 2020, 40(3): 1225-1232

[21] IqbalS, SiddiquiG F, RehmanA, HussainL, SabaT, TariqU, AbbasiA A. Prostate cancer detection using deep learning and traditional techniques. IEEE Access, 2021, 9: 27085-27100

[22] IslamMNA M, IslamMS, KanchanMH, ParvezAS, IslamMM. An improved deep learning-based hybrid model with ensemble techniques for brain tumor detection from MRI image. Informatics in Medicine Unlocked, 2024, 47: 101483

[23] JayamohanM, YuvarajS. Video-based action recognition of spatial and temporal deep learning models. International Conference on Advances in Data-driven Computing and Intelligent Systems, 2023 379-391

[24] JayamohanM, YuvarajS. Iv3-MGRUA: A novel human action recognition features extraction using Inception v3 and video behaviour prediction using modified gated recurrent units with attention mechanism model. Signal, Image and Video Processing, 2025, 19(1): 1-12

[25] JenaKK, BhoiSK, NaikKD, MallickC, NayakRP. SqueezeNet deep neural network embedderbased brain tumor classification using supervised machine intelligent approach. Data Intelligence and Cognitive Informatics, Algorithms for Intelligent Systems, 2023 337-348

[26] KesavN, JibukumarMG. Efficient and low complex architecture for detection and classification of brain tumor using RCNN with Two Channel CNN. Journal of King Saud University-Computer and Information Sciences, 2022, 34(8): 6229-6242

[27] KhairandishMOS M, JainV, ChatterjeeJ M, JhanjhiN Z. A hybrid CNN-SVM threshold segmentation approach for tumor detection and classification of MRI brain images. IRBM, 2022, 43(4): 290-299

[28] KhanMA, KhanA, AlhaisoniM, AlqahtaniA, AlsubaiS, AlharbiM, MalikNA, DamaševičiusR. Multimodal brain tumor detection and classification using deep saliency map and improved dragonfly optimization algorithm. Int. J. Imaging Syst. Technol., 2023, 33(2): 572-587

[29] KokkallaS, KakarlaJ, VenkateswarluI B, SinghM. Three-class brain tumor classification using deep dense inception residual network. Soft Computing, 2021, 25(13): 8721-8729

[30] KolliS, PraveenV. Internet of things for pervasive and personalized healthcare: Architecture, technologies, components, applications, and prototype development. Advances in Internet of Things for Healthcare, 2023 188-214

[31] KonarD, BhattacharyyaS, PanigrahiB K, BehrmanE C. Qutrit-inspired fully self-supervised shallow quantum learning network for brain tumor segmentation. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(11): 6331-6345

[32] MahmudMI, MamunM, AbdelgawadA. A deep analysis of brain tumor detection from MR images using deep learning networks. Algorithms, 2023, 16(4): 176

[33] MaqsoodS, DamaševičiusR, MaskeliūnasR. Multimodal brain tumor detection using deep neural network and multiclass SVM. Medicina, 2022, 58(8): 1090

[34] MukherjeeD, SahaP, KaplunD, SinitcaA, SarkarR. Brain tumor image generation using an aggregation of GAN models with style transfer. Scientific Reports, 2022, 12(1): 9141

[35] NazirM, ShakilS, KhurshidK. Role of deep learning in brain tumor detection and classification (2015 to 2020): A review. Computerized Medical Imaging and Graphics, 2021, 91: 101940

[36] ÖzyurtF, SertE, AvcıD. An expert system for brain tumor detection: Fuzzy C-means with super resolution and convolutional neural network with extreme learning machine. Medical Hypotheses, 2020, 134: 109433

[37] PalaniappanM, AnnamalaiM. Advances in signal and image processing in biomedical applications. Coding Theory, 2019 131-141

[38] PatilS C, KasulaB Y, MohammedV A, GuptaK, ThamaraimanalanT. Utilizing genetic algorithms for detecting congenital heart defects. 2024 International Conference on E-mobility, Power Control and Smart Systems (ICEMPS). Thiruvananthapuram, India, April 18–20, 2024, 2024

[39] PatilS, KirangeD. Ensemble of deep learning models for brain tumor detection. Procedia Computer Science, 2023, 218: 2468-2479

[40] PriyaA, VasudevanV. Brain tumor classification and detection via hybrid AlexNet-Gru based on deep learning. Biomedical Signal Processing and Control, 2024, 89: 105716

[41] RahmanM L, RezaA W, ShabujS I. An internet of things-based automatic brain tumor detection system. Indonesian Journal of Electrical Engineering and Computer Science, 2022, 25(1): 214-222

[42] RammurthyD, MaheshP K. Whale Harris hawks optimization based deep learning classifier for brain tumor detection using MRI images. Journal of King Saud University-Computer and Information Sciences, 2022, 34(6): 3259-3272

[43] RehmanA, KhanM A, SabaT, MehmoodZ, TariqU, AyeshaN. Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture. Microscopy Research and Technique, 2021, 84(1): 133-149

[44] SaeediS, RezayiS, KeshavarzH, Niakan KalhoriSR. MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques. BMC, 2023, MedicalInformaticsandDecisionMaking23(1): 16

[45] Sartaj Brain tumor classification MRI [dataset], 2020

[46] SharifMI, LiJP, AminJ, SharifA. An improved framework for brain tumor analysis using MRI based on YOLOv2 and convolutional neural network. Complex & Intelligent Systems, 2021, 7: 2023-2036

[47] SharmaAK, NandalA, DhakaA, PolatK, AlwadieR, AleneziF, AlhudhaifA. HOG transformation based feature extraction framework in modified Resnet50 model for brain tumor detection. Biomedical Signal Processing and Control, 2023, 84: 104737

[48] SheikdavoodK, SurendarP, ManikandanA. Certain investigation on latent fingerprint improvement through multi-scale patch based sparse representation. Indian Journal of Engineering, 2016, 13(31): 59-64

[49] SrinivasC, KSN P, ZakariahM, AlothaibiY A, ShaukatK, PartibaneB, AwalH 2022, et al.. Deep transfer learning approaches in performance analysis of brain tumor classification using MRI images. Journal of Healthcare Engineering, 2022 3264367

[50] TummalaS, KadryS, BukhariS A C, RaufH T. Classification of brain tumor from magnetic resonance imaging using vision transformers ensembling. Current Oncology, 2022, 29(10): 7498-7511

[51] VenkatesanC, BalamuruganD, ThamaraimanalanT, RamkumarM. Efficient machine learning technique for tumor classification based on gene expression data. 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS). March 25–26, 2022, Coimbatore, India, 2022

[52] VenmathiA R, DavidS, GovindaE, GanapriyaK, DhanapalR, ManikandanA. An automatic brain tumors detection and classification using deep convolutional neural network with VGG-19. 2023 2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA). Coimbatore, India, June 16–17, 2023, 2023

[53] VijhS, SharmaS, GauravP. Brain tumor segmentation using OTSU embedded adaptive particle swarm optimization method and convolutional neural network. Data Visualization and Knowledge Engineering: Spotting Data Points with Artificial Intelligence, 2020 171-194

[54] YilmazE, TrocanM. A modified version of GoogLeNet for melanoma diagnosis. Journal of Information and Telecommunication, 2021, 5(3): 395-405

[55] YounisA, QiangL, NyategaC O, AdamuM J, KawuwaH B. Brain tumor analysis using deep learning and VGG-16 ensembling learning approaches. Applied Sciences, 2022, 12(14): 7282

[56] ZaineldinH, GamelS A, El-KenawyE S M, AlharbiA H, KhafagaD S, IbrahimA, TalaatF M. Brain tumor detection and classification using deep learning and sine-cosine fitness grey wolf optimization. Bioengineering, 2022, 10(1): 18

[57] ZeineldinR A, KararM E, CoburgerJ, WirtzC R, BurgertO. DeepSeg: Deep neural network framework for automatic brain tumor segmentation using magnetic resonance FLAIR images. International, 2020, JournalofComputerAssistedRadiologyandSurgery15(6): 909-920

RIGHTS & PERMISSIONS

Systems Engineering Society of China and Springer-Verlag GmbH Germany