Enhanced segmentation and classification for effective brain tumor diagnosis using atrous convolution based residual densenet with gated recurrent unit layer

Abstract

In the present days, one of the deadly diseases is the brain tumor, which is formed by the expansion of irregulated cells inside the skull or brain. The people's death count increases with the steadily increasing condition. Therefore early diagnosis is significant for the patient to cure the disease and it increases the chance of survival. Multiple algorithms are examined by various researchers for identifying and determining the brain tumor for accurate and fast diagnosis. As the number of patients increased, the amount of information handled also increased. Utilizing the existing technique is more costly and is ineffective for a huge number of patients. Therefore, an advanced deep learning-assisted model is developed for segmentation and also for classifying brain tumors. Initially, the input images needed for this research accumulated from benchmark sites. First, a segmentation procedure is carried out to find out the accurate region where the tumor is present. An Optimized Trans-ResUnet (OTRUnet) approach is implemented to analyze the brain tumor segmentation. In addition, the network attributes are optimized via the “Enhanced Pufferfish Optimization (EPO)” Algorithm. The resultant segmented images are passed to the stage of brain tumor classification. An Atrous Convolution-based Residual DenseNet with a Gated Recurrent Unit layer (ACRD-GRU) is designed to function in the process of categorization for brain tumors. The performance of the designed model is assessed using different statistical indicators like “accuracy, FNR, FPR, precision” to evaluate the categorization capability of the suggested model. Research finding emphasizes that the developed ACRD-GRU model improves the categorization capability by leveraging the strengths of both residual DenseNet and GRU architectures. Resultant analysis proved the effectiveness of the designed model and lowered the possibility of overfitting issues. Numerical values assessments are employed to progress the network's capability for efficient disease categorization.

Keywords

brain tumor classification adaptive segmentation optimized transformer residual Unet enhanced pufferfish optimization atrous convolution-based residual densenet with a gated recurrent unit

Get full access to this article

View all access options for this article.

References

Patil

Kirange

. Ensemble of deep learning models for brain tumor detection. Procedia Comput Sci 2023; 218: 2468–2479.

Sangui

Iqbal

Chandra

, et al. 3D MRI segmentation using U-net architecture for the detection of brain tumor. Procedia Comput Sci 2023; 218: 542–553.

Raghuram

Hanumanthu

. Brain tumor image identification and classification on the internet of medical things using deep learning. Meas: Sens 2023; 30: 100905.

Rizwan

Shabbir

Javed

, et al. Brain tumor and glioma grade classification using Gaussian convolutional neural network. IEEE Access 2022; 10: 29731–29740.

Lamba

Rani

. Deep learning-based automated detection and classification of brain tumor with VGG16-SVM in internet of healthcare. SN Comput Sci 2023; 5.

Gurunathan

Krishnan

. Detection and diagnosis of brain tumors using deep learning convolutional neural networks. Int J Imag Syst Technol 2021; 31: 1174–1184.

Sharif

Khan

Alhussein

, et al. A decision support system for multimodal brain tumor classification using deep learning. Complex Intell Syst 2021: 1–14.

Chattopadhyay

Maitra

. MRI-based brain tumour image detection using CNN based deep learning method. Neurosci Inf 2022; 2: 100060.

Maqsood

Damaševičius

Maskeliūnas

. Multi-modal brain tumor detection using deep neural network and multiclass SVM. Medicina 2022; 58: 1090.

10.

Arif

Ajesh

Shamsudheen

, et al. Brain tumor detection and classification by MRI using biologically inspired orthogonal wavelet transform and deep learning techniques. J Healthc Eng 2022.

11.

Woźniak

Siłka

Wieczorek

. Deep neural network correlation learning mechanism for CT brain tumor detection. Neural Comput Appl 2023; 35: 14611–14626.

12.

Karayegen

Aksahin

. Brain tumor prediction on MR images with semantic segmentation by using deep learning network and 3D imaging of tumor region. Biomed Signal Process Control 2021; 66: 102458.

13.

Rammurthy

Mahesh

. Whale Harris hawks optimization based deep learning classifier for brain tumor detection using MRI images. J King Saud Univ-Comput Inf Sci 2022; 34: 3259–3272.

14.

Aamir

Rahman

Dayo

, et al. A deep learning approach for brain tumor classification using MRI images. Comput Electr Eng 2022; 101: 108105.

15.

Gunasekara

Kaldera

HNTK

Dissanayake

. A systematic approach for MRI brain tumor localization and segmentation using deep learning and active contouring. J Healthc Eng 2021: 1–13.

16.

Kang

Ullah

Gwak

. Mri-based brain tumor classification using ensemble of deep features and machine learning classifiers. Sensors 2021; 21.

17.

Irmak

. Multi-classification of brain tumor MRI images using deep convolutional neural network with fully optimized framework. Iran J Sci Technol Trans Electr Eng 2021; 45: 1015–1036.

18.

Noreen

Palaniappan

Qayyum

, et al. A deep learning model based on concatenation approach for the diagnosis of brain tumor. IEEE Access 2020; 8: 55135–55144.

19.

Ahmad

Choudhury

. On the performance of deep transfer learning networks for brain tumor detection using MR images. IEEE Access 2022; 10: 59099–59114.

20.

Saeedi

Rezayi

Keshavarz

, et al. MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques. BMC Med Inf Decis Mak 2023; 23.

21.

Majib

Rahman

Sazzad

, et al. Vgg-scnet: A vgg net-based deep learning framework for brain tumor detection on MRI images. IEEE Access 2021; 9: 116942–116952.

22.

Almufareh

Imran

Khan

, et al. Automated brain tumor segmentation and classification in MRI using YOLO-based deep learning. IEEE Access 2024.

23.

Gupta

Gaurav

Arya

. Deep CNN based brain tumor detection in intelligent systems. Int J Intell Netw 2024; 5: 30–37.

24.

Turk

Ozhan

Acar

, et al. Automatic detection of brain tumors with the aid of ensemble deep learning architectures and class activation map indicators by employing magnetic resonance images. Zeitschrift für Medizinische Physik 2022.

25.

Agrawal

Katal

Hooda

. Segmentation and classification of brain tumor using 3D-UNet deep neural networks. Int J Cogn Comput Eng 2022; 3: 199–210.

26.

Al-Baik

Alomari

Alssayed

Saikat , et al. Pufferfish optimization algorithm: A new bio-inspired metaheuristic algorithm for solving optimization problems. Biomimetics 2024; 9.

27.

Young

. The technical Writer’s handbook. Mill Valley, CA: University Science, 1989.

28.

Lin

J-W

Liao

X-W

, et al. Res-UNet based optic disk segmentation in retinal image. J Comput 2020; 31.

29.

Zhang

Liu

. TransFuse: Fusing transformers and CNNs for medical image segmentation. Med Image Comput Comput Assisted Intervention 2021; 12901.

30.

Zhang

Tian

Kong

, et al. Residual dense network for image super-resolution. 2018: 2472–2481.

31.

Guiping

Raza

, et al. A gated recurrent units (GRU)-based model for early detection of soybean sudden death syndrome through time-series satellite imagery. Remote Sens (Basel) 2020; 12: 3621.

32.

Ratul

MAR

Mozaffari

Parimbelli

, et al. Atrous Convolution with Transfer Learning for Skin Lesions Classification, 2019, p.746388.

33.

Oyelade

Ezugwu

AE-S

Mohamed

TIA

, et al. Ebola optimization search algorithm: a new nature-inspired metaheuristic optimization algorithm. IEEE Access 2022; 10: 16150–16177.

34.

Azizi

Shishehgarkhaneh

Basiri

, et al. Squid Game Optimizer (SGO): a novel metaheuristic algorithm. Sci Rep 2023; 13: 5373.

35.

Dehghani

Trojovský

. Teamwork optimization algorithm: a new optimization approach for function minimization/maximization. Sensors 2021; 21: 4567.

36.

Chauhan

Ghanshala

Joshi

. Convolutional neural network (CNN) for image detection and recognition. In: 2018 first international conference on secure cyber computing and communication (ICSCCC), Jalandhar, India, 2018, pp.278–282.

37.

Shen

van den Hengel

. Wider or deeper: revisiting the ResNet model for visual recognition. Elsevier Pattern Recognit 2019; 90: 119–133.

38.

Weng

Zhou

, et al. NAS-Unet: neural architecture search for medical image segmentation. IEEE Access 2019; 7: 44247–44257.

39.

Chen

, et al. TransUNet: transformers make strong encoders for medical image segmentation. Comput Vis Pattern Recognit 2021; 13.

40.

Zhang

Jing

. PreVFs-RG: A deep hybrid model for identifying virulence factors based on residual block and gated recurrent unit. IEEE/ACM Trans Comput Biol Bioinf 2023; 20: 1926–1934.

41.

Ikuta

Zhang

. A deep convolutional gated recurrent unit for CT image reconstruction. IEEE Trans Neural Netw Learn Syst 2023; 34.

42.

Khan

Haq

Khan

, et al. Atrous convolutions and residual GRU based architecture for matching power demand with supply. Sensors 2021; 21: 7191.