MultiTumor Analyzer (MTA-20–55): A network for efficient classification of detected brain tumors from MRI images

• Autorzy: Sahoo Akshya Kumar , Parida Priyadarsan , Panda Manoj Kumar , Muralibabu K. , Mohanty Ashima Sindhu

Identyfikatory

DOI

10.1016/j.bbe.2024.06.003

• Języki publikacji: EN

Abstrakty

EN

Brain cancer, one of the leading causes of mortality worldwide, is caused by brain tumors. Early diagnosis of tumors and predicting their progression can help doctors to save lives. In this article, we have designed an automated approach for locating and classifying tumors from MRI images. The novelties of the research work include the following two stages: Developing an encoder-decoder type 20-Layered deep neural network (DNN) named MultiTumor Analyzer (MTA-20) with 15 down-sampling layers and 4 up-sampling layers, the segmentation is performed in the initial stage. Here, we have adhered a Leaky ReLU activation function instead of ReLU which learn a parameter with negative values that may have valuable information which is essential specifically for image segmentation. Further, a 55-layered DNN using multistage feature fusion is developed in the second stage of the work for the classification of localized tumors. The classification is performed using developed MultiTumor Analyzer (MTA-55) DNN with Softmax classifier. The efficacy of the designed network is validated using highly cited quantitative measures such as accuracy, sensitivity, specificity, dice similarity coefficient (DSC), precision, and F1-measure. It is observed that the proposed MTA-20 DNN attains the average accuracy, sensitivity, specificity, DSC, and precision of 99.2 %, 94.6 %, 99.3 %, 88 %, and 82.5 % respectively against seven state-of-the-art techniques. Also, it is found that, the proposed MTA-55 DNN provides the overall accuracy, recall, specificity, F1-measure, precision, and DSC of 99.8 %, 99.633 %, 99.844 %, 99.659 %, 99.689 %, and 99.656 % respectively as compared to thirteen state-of-the-art techniques. These results corroborate the superiority of the proposed technique.

Słowa kluczowe

EN

deep learning; feature fusion; image segmentation; performance parameter

PL

uczenie maszynowe; fuzja funkcji; segmentacja obrazu

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2024
• Tom: Vol. 44, no. 3
• Strony: 617--634
• Opis fizyczny: Bibliogr. 47 poz., rys., tab., wykr.

Twórcy

autor

Sahoo Akshya Kumar

• Department of Electrical and Electronics Engineering, GIET University, Gunupur, Odisha, India

autor

Parida Priyadarsan

• Department of Electronics and Communication Engineering, GIET University, Gunupur, Odisha, India

autor

Panda Manoj Kumar

• Department of Electronics and Communication Engineering, GIET University, Gunupur, Odisha, India

autor

Muralibabu K.

• Department of Electrical and Electronics Engineering, GIET University, Gunupur, Odisha, India

autor

Mohanty Ashima Sindhu

• Department of Electronics and Communication Engineering, GIET University, Gunupur, Odisha, India

Bibliografia

• [1] Miller KD, Fidler-Benaoudia M, Keegan TH, Hipp HS, Jemal A, Siegel RL. Cancer statistics for adolescents and young adults, 2020. CA: Cancer J Clin 2020;70(6): 443-59. https://doi.org/10.3322/caac.21637.
• [2] DeAngelis LM. Brain tumors. N Engl J Med 2001;344(2):114–23. https://doi.org/10.1056/NEJM200101113440207.
• [3] McNeill KA. Epidemiology of brain tumors. Neurol Clin 2016;34(4):981-98. https://doi.org/10.1016/j.ncl.2016.06.014.
• [4] Lakshmi SS. Meningiomas: a clinicopathological study. Int J Med Res Health Sci 2015;4(4):827. https://doi.org/10.5958/2319-5886.2015.00164.2.
• [5] Asa SL, Ezzat S. The pathogenesis of pituitary tumors. Annu Rev Pathol 2009;4(1): 97-126. https://doi.org/10.1146/annurev.pathol.4.110807.092259.
• [6] Kazemi A, Shiri ME, Sheikhahmadi A, Khodamoradi M. Classifying tumor brain images using parallel deep learning algorithms. Comput Biol Med 2022;148: 105775. https://doi.org/10.1016/j.compbiomed.2022.105775.
• [7] Mondal A, Shrivastava VK. A novel Parametric Flatten-p Mish activation function based deep CNN model for brain tumor classification. Comput Biol Med 2022;150: 106183. https://doi.org/10.1016/j.compbiomed.2022.106183.
• [8] Emam MM, Samee NA, Jamjoom MM, Houssein EH. Optimized deep learning architecture for brain tumor classification using improved Hunger Games Search Algorithm. Comput Biol Med 2023;160:106966. https://doi.org/10.1016/j.compbiomed.2023.106966.
• [9] Suresh Kumar R, Nagaraj B, Manimegalai P, Ajay P. Dual feature extraction based convolutional neural network classifier for magnetic resonance imaging tumor detection using U-Net and three-dimensional convolutional neural network. Comput Electr Eng 2022;101:108010. https://doi.org/10.1016/j.compeleceng.2022.108010.
• [10] Aamir M, Rahman Z, Dayo ZA, Abro WA, Uddin MI, Khan I, et al. A deep learning approach for brain tumor classification using MRI images. Comput Electr Eng 2022;101:108105. https://doi.org/10.1016/j.compeleceng.2022.108105.
• [11] Masood M, Maham R, Javed A, Tariq U, Khan MA, Kadry S. Brain MRI analysis using deep neural network for medical of internet things applications. Comput Electr Eng 2022;103:108386. https://doi.org/10.1016/j.compeleceng.2022.108386.
• [12] Jaspin K, Selvan S. Multiclass convolutional neural network based classification for the diagnosis of brain MRI images. Biomed Signal Process Control 2023;82: 104542. https://doi.org/10.1016/j.bspc.2022.104542.
• [13] Chaki J, Woźniak M. A deep learning based four-fold approach to classify brain MRI: BTSCNet. Biomed Signal Process Control 2023;85:104902. https://doi.org/10.1016/j.bspc.2023.104902.
• [14] Turk O, Ozhan D, Acar E, Akinci TC, Yilmaz M. Automatic detection of brain tumors with the aid of ensemble deep learning architectures and class activation map indicators by employing magnetic resonance images. Z Med Phys 2022. https://doi.org/10.1016/j.zemedi.2022.11.010.
• [15] Qin C, Li B, Han B. Fast brain tumor detection using adaptive stochastic gradient descent on shared-memory parallel environment. Eng Appl Artif Intel 2023;120: 105816. https://doi.org/10.1016/j.engappai.2022.105816.
• [16] Talukder MA, Islam MM, Uddin MA, Akhter A, Pramanik MAJ, Aryal S, et al. An efficient deep learning model to categorize brain tumor using reconstruction and fine-tuning. Expert Syst Appl 2023;230:120534. https://doi.org/10.1016/j.eswa.2023.120534.
• [17] Yaqub M, Jinchao F, Ahmed S, Mehmood A, Chuhan IS, Manan MA, et al. DeepLabV3, IBCO-based ALCResNet: A fully automated classification, and grading system for brain tumor. Alex Eng J 2023;76:609-27. https://doi.org/10.1016/j.aej.2023.06.062.
• [18] Kesav N, Jibukumar MG. Efficient and low complex architecture for detection and classification of Brain Tumor using RCNN with Two Channel CNN. J King Saud Univ - Comput Inf Sci 2022;34(8):6229-42. https://doi.org/10.1016/j.jksuci.2021.05.008.
• [19] Mehmood M, Alshammari N, Alanazi SA, Basharat A, Ahmad F, Sajjad M, et al. Improved colorization and classification of intracranial tumor expanse in MRI images via hybrid scheme of Pix2Pix-cGANs and NASNet-large. J King Saud Univ - Comput Inf Sci 2022;34(7):4358-74. https://doi.org/10.1016/j.jksuci.2022.05.015.
• [20] Neelima G, Chigurukota DR, Maram B, Girirajan B. Optimal DeepMRSeg based tumor segmentation with GAN for brain tumor classification. Biomed Signal Process Control 2022;74:103537. https://doi.org/10.1016/j.bspc.2022.103537.
• [21] Abirami S, DrGKD PV. Deep learning and spark architecture based intelligent brain tumor MRI image severity classification. Biomed Signal Process Control 2022;76: 103644. https://doi.org/10.1016/j.bspc.2022.103644.
• [22] Nirmalapriya G, Agalya V, Regunathan R, Belsam Jeba Ananth M. Fractional Aquila spider monkey optimization based deep learning network for classification of brain tumor. Biomed Signal Process Control 2023;79:104017. https://doi.org/10.1016/j.bspc.2022.104017.
• [23] Zheng N, Zhang G, Zhang Y, Sheykhahmad FR. Brain tumor diagnosis based on Zernike moments and support vector machine optimized by chaotic arithmetic optimization algorithm. Biomed Signal Process Control 2023;82:104543. https://doi.org/10.1016/j.bspc.2022.104543.
• [24] Zulfiqar F, Ijaz Bajwa U, Mehmood Y. Multi-class classification of brain tumor types from MR images using EfficientNets. Biomed Signal Process Control 2023;84: 104777. https://doi.org/10.1016/j.bspc.2023.104777.
• [25] Sobhaninia Z, Karimi N, Khadivi P, Samavi S. Brain tumor segmentation by cascaded multiscale multitask learning framework based on feature aggregation. Biomed Signal Process Control 2023;85:104834. https://doi.org/10.1016/j.bspc.2023.104834.
• [26] Wu P, Shen J. Brain tumor diagnosis based on convolutional neural network improved by a new version of political optimizer. Biomed Signal Process Control 2023;85:104853. https://doi.org/10.1016/j.bspc.2023.104853.
• [27] Kanchanamala P, Revathi KG, Ananth MBJ. Optimization-enabled hybrid deep learning for brain tumor detection and classification from MRI. Biomed Signal Process Control 2023;84:104955. https://doi.org/10.1016/j.bspc.2023.104955.
• [28] Tabatabaei S, Rezaee K, Zhu M. Attention transformer mechanism and fusion-based deep learning architecture for MRI brain tumor classification system. Biomed Signal Process Control 2023;86:105119. https://doi.org/10.1016/j.bspc.2023.105119.
• [29] Khan MSI, Rahman A, Debnath T, Karim MR, Nasir MK, Band SS, et al. Accurate brain tumor detection using deep convolutional neural network. Comput Struct Biotechnol J 2022;20:4733-45. https://doi.org/10.1016/j.csbj.2022.08.039.
• [30] Rahman T, Islam MS. MRI brain tumor detection and classification using parallel deep convolutional neural networks. Measurement: Sensors 2023;26:100694. https://doi.org/10.1016/j.measen.2023.100694.
• [31] Kabir Anaraki A, Ayati M, Kazemi F. Magnetic resonance imaging-based brain tumor grades classification and grading via convolutional neural networks and genetic algorithms. Biocybernet Biomed Eng 2019;39(1):63-74. https://doi.org/10.1016/j.bbe.2018.10.004.
• [32] Kaur T, Saini BS, Gupta S. An optimal spectroscopic feature fusion strategy for MR brain tumor classification using Fisher Criteria and Parameter-Free BAT optimization algorithm. Biocybernet Biomed Eng 2018;38(2):409-24. https://doi.org/10.1016/j.bbe.2018.02.008.
• [33] Raju AR, Suresh P, Rao RR. Bayesian HCS-based multi-SVNN: A classification approach for brain tumor segmentation and classification using Bayesian fuzzy clustering. Biocybernet Biomed Eng 2018;38(3):646-60. https://doi.org/10.1016/j.bbe.2018.05.001.
• [34] Sumathi R, Venkatesulu M, Arjunan SP. Extracting tumor in MR brain and breast image with Kapur’s entropy based Cuckoo Search Optimization and morphological reconstruction filters. Biocybernet Biomed Eng 2018;38(4):918-30. https://doi. org/10.1016/j.bbe.2018.07.005.
• [35] Yang T, Song J, Li L. A deep learning model integrating SK-TPCNN and random forests for brain tumor segmentation in MRI. Biocybernet Biomed Eng 2019;39(3): 613-23. https://doi.org/10.1016/j.bbe.2019.06.003.
• [36] Dey N, Rajinikanth V, Shi F, Tavares JMRS, Moraru L, Arvind Karthik K, et al. Social-Group-Optimization based tumor evaluation tool for clinical brain MRI of Flair/diffusion-weighted modality. Biocybernet Biomed Eng 2019;39(3):843-56. https://doi.org/10.1016/j.bbe.2019.07.005.
• [37] Siva Raja PM, Rani AV. Brain tumor classification using a hybrid deep autoencoder with Bayesian fuzzy clustering-based segmentation approach. Biocybernet Biomed Eng 2020;40(1):440-53. https://doi.org/10.1016/j.bbe.2020.01.006.
• [38] Devi S, Sahoo MN, Bakshi S. A novel privacy-supporting 2-class classification technique for brain MRI images. Biocybernet Biomed Eng 2020;40(3):1022-35. https://doi.org/10.1016/j.bbe.2020.05.005.
• [39] Kumar S, Mankame DP. Optimization driven Deep Convolution Neural Network for brain tumor classification. Biocybernet Biomed Eng 2020;40(3):1190-11104. https://doi.org/10.1016/j.bbe.2020.05.009.
• [40] Dandıl E, Karaca S. Detection of pseudo brain tumors via stacked LSTM neural networks using MR spectroscopy signals. Biocybernet Biomed Eng 2021;41(1): 173-95. https://doi.org/10.1016/j.bbe.2020.12.003.
• [41] Lu SL, Liao HC, Hsu FM, Liao CC, Lai F, Xiao F. The intracranial tumor segmentation challenge: contour tumors on brain MRI for radiosurgery. Neuroimage 2021;244:118585. https://doi.org/10.1016/j.neuroimage.2021.118585.
• [42] Kumar Sahoo A, Parida P, Muralibabu K, Dash S. Efficient simultaneous segmentation and classification of brain tumors from MRI scans using deep learning. Biocybernet Biomed Eng 2023;43(3):616-33. https://doi.org/10.1016/j.bbe.2023.08.003.
• [43] Cheng J. https://doi.org/10.6084/m9.figshare.1512427.v5 2017. Doi: 10.6084/m9.figshare.1512427.v5.
• [44] Sahoo AK, Parida P, Muralibabu K, Dash S. An improved DNN with FFCM method for multimodal brain tumor segmentation. Intell Syst Appl 2023;18:200245. https://doi.org/10.1016/j.iswa.2023.200245.
• [45] Li X, Jiang H, Liu Y, Wang T, Li Z. An integrated deep multiscale feature fusion network for aeroengine remaining useful life prediction with multisensor data. Knowl-Based Syst 2022;235:107652. https://doi.org/10.1016/j.knosys.2021.107652.
• [46] Mayala S, Herdlevær I, Haugsřen JB, Anandan S, Gavasso S, Brun M. Brain tumor segmentation based on minimum spanning tree. Front Signal Process 2022:2. https://doi.org/10.3389/frsip.2022.816186.
• [47] El-Shafai W, Mahmoud AA, El-Rabaie ESM, Taha TE, Zahran OF, El-Fishawy AS, et al. Hybrid segmentation approach for different medical image modalities. Comput Mater Continua 2022;73(2):3455-72. https://doi.org/10.32604/cmc.2022.028722.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).