Brain Cancer Detection and Classification Using

MRI Images
Saday Samnotra Avishkaar Chaturvedi Tanmay Sehgal Chayan Manocha
Computer Science Computer Science Computer Science Computer Science
Bharati Vidyapeeth’s College of Bharati Vidyapeeth’s College Bharati Vidyapeeth’s College Bharati Vidyapeeth’s College
Engineering of Engineering of Engineering of Engineering
Delhi, India Delhi, India Delhi, India Delhi, India
[email protected] [email protected] [email protected] [email protected]

Amrita Ticku
Asst. Proffessor,Computer Science
Bharati Vidyapeeth’s College of
Engineering
Delhi, India
[email protected]

Abstract— The study looks at the use of transfer learning, cutting-edge machine learning algorithms and modern
namely EfficientNet, to classify various forms of brain tumours imaging technology.
using a curated set of T1, contrast-enhanced T1, and T2
magnetic resonance images (MRI). With tumours ranging from Our dataset contains a comprehensive collection of T1,
astrocytoma to tuberculoma, the study intends to break down contrast enhanced T1, and T2 magnetic resonance images that
traditional diagnostic hurdles using artificial intelligence, have been rigorously categorised according to numerous brain
providing insights into subtle tumour subgroups. The study tumour forms, such as astrocytoma, carcinoma, ependymoma,
aims to improve diagnostic precision, prognostic insight, and and others. These pictures, collected without the patient's
treatment efficacy in the complex field of neuro-oncology by identify, give vital insights for neuroimaging research and
utilising cutting-edge neuroimaging and computational analyses.
approaches.
EfficientNet is a revolutionary approach to convolutional
Keywords—Efficient Net, transfer learning, neuro-oncology, neural network (CNN) architectures that emphasises efficient
Astrocytoma, tubercloma. model scaling and enhanced performance. By combining
EfficientNet V2 B0 and ViT-B16 into our classification
framework, we are able to accelerate model training while also
improving classification accuracy. Ensembling strategies
I. INTRODUCTION
improve the resilience of our models, allowing for complete
The human brain, one of the most important organs in the analysis and interpretation of brain imaging data.
body, can encounter considerable obstacles as a result of
abnormal brain cell proliferation, which can cause serious Our approach differs from prior efforts by pioneering the
harm. The frequency of brain tumours is increasing, needing integration of cutting-edge transfer learning models, such as
new diagnostic and therapeutic techniques. A brain tumour is EfficientNet, with classic image and data mining techniques.
characterised by an abnormal aggregation of cells within the This novel method has the potential to revolutionise
skull and presents a complicated medical challenge. These neuroimaging by allowing for more accurate and efficient
tumours are classified as normal, malignant, or benign, with diagnosis of brain tumours. We aim to create substantial
primary or secondary causes. Primary tumours form within advances in neuro-oncology medical research and patient
the brain from a variety of brain cells and tissues, whereas treatment by merging cutting-edge technology with advanced
secondary tumours spread throughout the body. Early machine learning techniques.Press the enter key to begin a
diagnosis of brain tumours is crucial for successful treatment new paragraph. The proper spacing and indent are
and avoiding consequences. automatically applied.
II. LITERATURE REVIEW
In response to the growing need for reliable brain tumour
identification and classification, we offer an automated The combination of several computational algorithms and
classification strategy based on image and data mining medical imaging modalities has resulted in substantial
approaches. Our goal is to investigate the efficacy of transfer advances in brain cancer detection and classification
learning models, notably EfficientNet V2 B0 and ViT-B16, research. Numerous research have contributed to improving
paired with ensembling approaches for identifying various the accuracy and efficiency of brain tumour detection
forms of brain tumours. This project intends to better the systems, using approaches ranging from standard machine
diagnosis process and improve patient outcomes by utilising learning algorithms to cutting-edge deep learning
architectures. with medical imaging holds substantial potential for
transforming the diagnosis and treatment of brain cancer.
Banerjee et al. [1] emphasised the importance of noninvasive
techniques such as MRI in brain cancer detection and III. PROPOSED METHODOLOGY
proposed an adaptive neuro-fuzzy classifier based on
linguistic hedges (ANFC-LH) for simultaneous feature
selection and tumour grade prediction, with a significantly
higher testing accuracy of 85.83%.

Ansari and colleagues [3] introduced a framework for the

identification of brain tumors utilizing MRI imagery,
achieving a precision of 98.91% by employing feature
extraction coupled with SVM classification. Hebli and Gupta
[4] proposed a system integrating image processing
techniques and machine learning to achieve precise detection
and categorization of brain tumors, achieving a notable 100%
accuracy utilizing the RBF kernel. A comprehensive
examination conducted by Amin et al. [5] offered insights
into diverse methodologies and hurdles in brain tumor
identification via MRI, underscoring the significance of deep
learning approaches.

Sadad et al. [6] underscored the exigency of early and

accurate diagnosis of brain tumors, presenting a segmentation
methodology employing the UNet architecture with
ResNet50 as its foundation. Bhanothu et al. [7] effectively
employed the Faster R-CNN algorithm leveraging VGG-16
architecture for the detection and categorization of brain
tumors. Joshi et al. [8] devised an efficient system for the
Detection and Classification of Brain Cancer utilizing image
processing methodologies and Artificial Neural Network
with MRI images.
Tun Hein et al. [9] aspired to precisely detect brain tissues
afflicted by cancer, notably Glioblastoma multiforme (GBM)
of grade-4, utilizing Naïve Bayes classification.
Thirumurugan and Shanthakumar [10] introduced a
methodology for brain tumor detection and diagnosis
employing an ANFIS classifier, resulting in the segmentation
of brain tumor regions into mild, moderate, and severe cases.
Figure 1: Flowchart of the proposed methodology.
Chauhan et al. [11] leveraged image and data mining
principles for automation in brain tumor classification, The proposed methodology initiates with the preprocessing
achieving a classification accuracy of 86.6% utilizing the of image data derived from an extensive dataset containing
IBkLG classifier. Rehman et al. [12] introduced a deep brain tumor images. This initial phase encompasses multiple
learning-oriented approach for microscopic brain tumor essential steps: reading image files, standardizing their
detection and classification utilizing a 3D CNN architecture, dimensions to 224x224 pixels, and converting pixel values to
demonstrating high accuracy through experiments and floating-point format while normalizing them within the 0 to
validation with BraTS datasets. Hu and Razmjooy [13] 1 range. Such meticulous preprocessing ensures consistency
introduced a novel system for early detection of brain tumors in image sizes and pixel values, thereby facilitating seamless
utilizing metaheuristics and deep learning, showcasing processing during subsequent stages of the methodology.
superior performance in comparison to extant methodologies.
Following preprocessing, optional data augmentation
In synthesis, the corpus of literature reflects the dynamic techniques are employed to enhance the dataset's diversity
milieu of research efforts dedicated to advancing and reinforce the model's ability to generalize to novel data
methodologies for the detection and classification of brain instances. Techniques like random flipping and zooming are
tumors. From conventional machine learning algorithms to judiciously applied to generate augmented versions of the
state-of-the-art deep learning techniques, scholars persist in original images, thereby enriching the reservoir of training
exploring innovative approaches aimed at enhancing data and mitigating the risk of overfitting. Data augmentation
diagnostic precision and ameliorating patient outcomes in emerges as a crucial strategy in bolstering the robustness and
neuro-oncology. As technology progresses and datasets efficacy of the deep learning model by exposing it to a wider
expand, the amalgamation of computational methodologies spectrum of image variations.
Upon completion of preprocessing and augmentation, the training efficiency. Additionally, prefetching batches of data
dataset is partitioned into distinct subsets comprising optimizes resource utilization by concurrently loading data
training, validation, and test sets to facilitate model training and executing model operations, effectively minimizing
and evaluation. This stratified partitioning ensures that the latency and maximizing hardware utilization.
model undergoes training on a designated subset, validation
on another segment for hyperparameter optimization and In our pursuit of augmenting model generalization and
overfitting mitigation, and subsequent testing on an fortifying robustness, we judiciously deploy data
independent subset to gauge its performance on previously augmentation methodologies, encompassing stochastic
unseen data instances. Such partitioning strategies enable transformations such as random flipping and zooming. These
rigorous assessment of the model's generalization capacity transformative operations inject variability into the dataset,
and detection of potential issues such as underfitting or thereby exposing the model to an expansive spectrum of
overfitting. image variations and fostering superior performance on novel
data instances. Concurrently, we institute label encoding
Central to the proposed methodology lies the construction of techniques to seamlessly translate categorical class labels into
a deep learning model utilizing the EfficientNet V2 numerical representations conducive to model training. This
architecture, renowned for its efficiency and efficacy in encoding paradigm facilitates streamlined computation and
image classification tasks. The EfficientNet V2 architecture interpretation throughout the training regimen, empowering
employs a compound scaling technique that uniformly scales the model to discern and assimilate underlying patterns
depth, width, and resolution dimensions, yielding a highly within the dataset with heightened efficacy.
parameter-efficient and computationally lightweight model
compared to conventional CNN architectures. Comprising Moreover, meticulous partitioning of the dataset into discrete
multiple blocks of convolutional layers, each complemented subsets tailored for training, validation, and testing endeavors
by batch normalization and activation functions such as underscores our commitment to fostering equitable model
ReLU, this architecture facilitates feature extraction and assessment and performance evaluation. This methodical
nonlinear transformations crucial for discerning intricate partitioning schema ensures that the model undergoes
patterns within the data. rigorous training on one subset, whilst concurrently
undergoing validation on another subset to optimize
During the model training phase, the EfficientNet V2 model hyperparameters and preempt overfitting tendencies.
undergoes fine-tuning utilizing the training dataset to tailor Subsequently, the model's generalization prowess is
its parameters to the unique characteristics of brain tumor meticulously scrutinized through evaluation on an
images. This iterative training process entails parameter independent subset, culminating in a comprehensive
adjustments using optimization algorithms like Adam, aimed assessment of its efficacy across varied data distributions.
at minimizing categorical cross-entropy loss between Such meticulous partitioning methodologies serve as
predicted and actual labels. Model performance is bulwarks against biases and variances, thereby fostering
meticulously monitored through evaluation metrics impartial evaluation and fostering dependable insights into
encompassing accuracy, precision, recall, and F1-score model performance.
computed on the validation dataset, with early stopping and
learning rate reduction techniques deployed to forestall
overfitting and enhance convergence. B) DATA AUGMENTATION AND SPLITTING
Data augmentation serves as a crucial facet in the
Upon completion of model training, rigorous evaluation preprocessing pipeline of brain tumor images, aimed at
ensues on the test dataset to ascertain the model's enriching the dataset's diversity and complexity,
performance and generalization prowess. Evaluation metrics consequently fostering more resilient and adaptable model
including accuracy, precision, recall, and F1-score are training. By integrating data augmentation techniques, we
computed to quantify the model's efficacy in classifying brain deliberately introduce variations and transformations to the
tumor images across diverse categories. Furthermore, a original images, thereby broadening the spectrum of visual
confusion matrix is constructed to visualize the model's representations accessible to the model and cultivating a more
predictions and pinpoint potential areas of misclassification comprehensive understanding of the dataset's intricacies.
across distinct tumor types, furnishing valuable insights into
the model's strengths and limitations.

A) IMAGE PRE-PROCESSING
The preprocessing phase of brain tumor images stands as a
pivotal component within our methodology, strategically
engineered to refine data representation and expedite model
training and evaluation processes. Through harnessing the
versatile capabilities of TensorFlow's tf.data API, we
proficiently load and manage the dataset, fostering seamless
handling of extensive image data. Employing batching Figure 2: Image of MRI after augmentation and preprocessing
techniques enables concurrent processing of multiple images,
thereby harnessing parallel processing capabilities to bolster
Within our methodology, data augmentation techniques, We endeavor to assess the efficacy of our scaling
notably random flipping and zooming, are strategically methodology by juxtaposing it against established
applied to augment images. Random flipping entails both Convolutional Neural Networks (ConvNets). However, to
horizontal and vertical mirroring of images with a defined underscore the potency of our scaling methodology, we have
probability, fostering the model's acquisition of invariant devised a novel baseline tailored to mobile-size constraints,
features and orientations, thereby enhancing its adaptability christened EfficientNet V2.
to images with diverse orientations or viewpoints.
EfficientNet V2 epitomizes a highly efficient convolutional
Likewise, random zooming introduces fluctuations in the neural network (CNN) architecture lauded for its exceptional
scale and perspective of images through zooming in or out performance and scalability across an array of computer
with a designated factor. This augmentation modality vision tasks. Pre-trained on expansive image datasets, the
simulates fluctuations in image resolution and scale, architecture engenders a rich repository of hierarchical visual
equipping the model with improved capabilities to address representations, ripe for fine-tuning to our specific objective
images of disparate sizes and resolutions encountered within of brain tumor classification.
real-world contexts.
Our overarching aim converges on maximizing model
Through the integration of data augmentation into the accuracy within defined resource constraints, thereby
preprocessing pipeline, our objective is to immerse the model constituting an optimization conundrum warranting
in a multifaceted array of image variations and scenarios, meticulous scrutiny and strategic resolution.:
mirroring the complexity inherent in real-world data. This
strategic maneuver serves as a bulwark against overfitting by
infusing noise and variability into the training data, thereby
thwarting the model's inclination towards memorizing

Figure 3: Distribution of total images inro their respective criteria. Table 1Efficient Net Baseline Data

specific patterns or features prevalent within the training

set.. Following is our efficient net structure for our intended
purpose of finding brain tumour and classification:
In essence, data augmentation emerges as a potent instrument
for amplifying dataset richness and refining the model's
generalization prowess. Through methodical application of
transformations to images, we equip the model with the
capacity to glean resilient and invariant representations,
thereby bolstering its proficiency in precisely classifying and
scrutinizing brain tumor images across a spectrum of clinical
scenarios.
C) MODEL BUILDING(EFFICIENT NET)
The model construction phase within our methodology stands
as a pivotal juncture where we meticulously craft the neural
network architecture tasked with analyzing brain tumor
images and rendering precise predictions. Our approach
entails harnessing cutting-edge deep learning methodologies
and frameworks to engender a resilient and efficient model
adept at adeptly capturing the nuanced patterns and features Figure 4: Efficient Net Architecture used for our model.
intrinsic to the image data.
 D) MODEL TRAINING AND EVALUATION set, fostering ongoing performance assessment on unseen
The model training process entailed the employment of a data and pre-empting overfitting phenomena. The validation
convolutional neural network (CNN) architecture, split parameter, integral within the val_ds dataset, facilitates
specifically EfficientNet, tailored for the classification of automatic partitioning of the training data, earmarking a
brain tumor images. EfficientNet stands distinguished for its specified fraction for validation purposes.
adeptness in image classification tasks, distinguished by its
ability to achieve elevated accuracy with fewer parameters By finetuning these hyperparameters and vigilantly
vis-à-vis other architectures. In the provided code, the monitoring the model's performance via the validation set, the
instantiation of the model involved the delineation of the training regimen aspires to strike a delicate balance between
EfficientNet architecture and the calibration of its model complexity, training duration, and generalization
hyperparameters. capacity, culminating in an optimized neural network model
tailored for brain tumor classification.
1) EfficientNet Architecture: TensorFlow's Keras API
IV. RESULTS AND DISCUSSION
facilitated the instantiation of the EfficientNet architecture,
drawing upon pre-existing implementations to seamlessly The outcomes derived from our brain tumor classification
integrate the model into the training regimen. The model unveil encouraging performance across a spectrum of
architecture's depth, width, and resolution were guided by evaluation metrics. Precision, recall, and F1-score metrics
scaling coefficients, meticulously chosen in alignment with furnish valuable insights into the model's efficacy in precise
the exigencies of the brain tumor classification task. classification of diverse brain tumor types predicated upon
input images.
2) Data Augmentation Techniques: Augmentation layers,
constructed via TensorFlow's Sequential API, were In totality, our model attained a commendable accuracy rate
instrumental in infusing variations into the training dataset, of 91.46%, underscoring its adeptness in accurately
thereby enriching model generalization and mitigating delineating class labels across a substantial segment of the
overfitting risks. test dataset. This elevated accuracy underscores the efficacy
of our model in discerning nuanced differences among varied
3) Hyperparameter Configuration: Crucial hyperparameters, tumor types, leveraging feature extraction from MRI images.
including batch size, learning rate, optimizer selection, and
loss function, were meticulously configured during the model
compilation phase. The Adam optimizer, esteemed for its
adeptness in parameter updates, was harnessed, with
categorical cross-entropy serving as the loss function for
multi-class classification tasks. The initial learning rate was
set to 0.001, governing the model's convergence rate.

4) Epochs and Validation Split: The model underwent

training over a stipulated number of epochs, with the training
data bifurcated into training and validation subsets. The fit()
function facilitated model training, with the validation split
parameter enabling real-time performance monitoring and
overfitting mitigation.
Figure 5Accuracy and Loss graph for our model
5) Optimizer Selection: The choice of optimizer dictates the
way the model's parameters are updated to minimize the loss
The precision score, quantifying the ratio of true positive
function. In this instance, the Adam optimizer, lauded for its
predictions to all positive predictions rendered by the model,
adaptive learning rate and parameter update efficiency, was
stands at an impressive 93.22%. This metric elucidates the
embraced, manifesting accelerated convergence and
model's proficiency in averting erroneous classification of
enhanced performance, especially within high-dimensional
images into specific tumor types when such categorization is
parameter spaces.

6) Loss Function: The selection of an appropriate loss

function is paramount, as it quantifies the discrepancy
between predicted and actual class labels, guiding the model
towards superior classification accuracy. Categorical cross-
entropy emerges as a prevalent choice for multi-class
classification tasks, computing the cross-entropy loss
between predicted probabilities and ground truth labels for
each class.

7) Validation Split: Integral to the training process is the

allocation of a portion of the training dataset as a validation
unwarranted. Meningioma T2 0.89 1.00 0.94 31
Neurocitoma T1 1.00 1.00 1.00 8
Neurocitoma 1.00 1.00 1.00 17
T1C+
Neurocitoma T2 1.00 1.00 0.76 9
Papiloma T1 0.89 0.89 0.89 9
Papiloma T1C+ 0.96 1.00 0.98 23
Papiloma T2 1.00 0.83 0.91 6
Schwannoma T1 0.60 1.00 0.75 3
Schwannoma 1.00 0.92 0.96 13
T1C+
Schwannoma T2 1.00 1.00 1.00 3
_NORMAL T1 1.00 1.00 1.00 18
NORMAL T2 1.00 1.00 1.00 5
Accuracy 0.96 282
Macro Avg 0.95 0.96 0.96 282
Weighted Avg 0.97 0.96 0.96 282

In summary, the outcomes underscore the efficacy of our

Figure 6: Confusion matrix for the labels model in precisely classifying brain tumor images, boasting
elevated precision, recall, and F1-scores across various tumor
types. These results underscore the transformative potential
The recall score, synonymous with sensitivity or true positive of deep learning methodologies in augmenting medical
rate, gauges the proportion of true positive predictions professionals' diagnostic and therapeutic capabilities
accurately identified by the model. Our model achieved an pertaining to brain tumors. Ultimately, these advancements
impressive recall score of 91.46%, signifying its proficiency hold promise for enhancing patient outcomes and refining
in correctly identifying a significant majority of positive healthcare practices in the domain of neuro-oncology.
instances within the dataset.

Furthermore, the F1-score, representing the harmonic mean V) CONCLUSION AND FUTURE SCOPE
of precision and recall, offers a balanced assessment of the In conclusion, the application of deep learning
model's performance. With an F1-score of 91.63%, our model methodologies, particularly convolutional neural networks
showcases a robust equilibrium between precision and recall, (CNNs), has exhibited considerable promise within the realm
underscoring its capacity to sustain elevated levels of both of brain tumor classification utilizing MRI images. Through
metrics concurrently. the implementation of an efficient net architecture and
diligent training methodologies, we have showcased the
In tandem with individual metrics, the macro and weighted capacity of deep learning models to effectively discern brain
averages furnish a comprehensive overview of the model's tumor subtypes, yielding commendable precision and recall
performance across all classes. The macro average, scores. The holistic evaluation metrics, encompassing
computing the average of metrics for each class sans precision, recall, F1-score, and accuracy, underscore the
consideration of class imbalance, yields an average F1-score efficacy of our model in delineating between distinct tumor
of 84%, while the weighted average, accounting for class classes, thereby furnishing invaluable insights for clinical
imbalance, yields an average F1-score of 92%. diagnosis and treatment strategizing.
Class Precision Recall F1- Support
Score
Astrocitoma T1 1.00 0.92 0.96 13 The successful integration of data preprocessing techniques,
Astrocitoma 0.92 1.00 0.96 11 inclusive of image augmentation and input data pipeline
T1C+ construction, has emerged as a pivotal factor in fortifying the
Astrocitoma T2 1.00 1.00 1.00 9 resilience and generalization prowess of the model. By
Ependimoma 1.00 1.00 1.00 4 incorporating these preprocessing paradigms, we have
T1C+ adeptly mitigated challenges associated with data scarcity,
Ependimoma T2 1.00 1.00 1.00 4 class imbalance, and overfitting, thereby fortifying the
Ganglioglioma 1.00 1.00 1.00 2 model's adaptability to variances in input data and
T1 augmenting its overall efficacy.
Ganglioglioma 0.50 1.00 0.67 1
T1C+ Looking forward to a plethora of avenues for future research
Ganglioglioma 1.00 1.00 1.00 3
and refinement within the domain of brain tumor
T2
classification using deep learning beckon. Primarily, the
Germinoma T2 1.00 1.00 1.00 4
Meduloblastoma 1.00 1.00 1.00 2 exploration of advanced neural network architectures and
T2 ensemble methodologies could further amplify the model's
Meningioma T1 1.00 1.00 1.00 28 predictive aptitude and resilience to noise and variations in
Meningioma 1.00 0.96 0.98 56 MRI images. Furthermore, the incorporation of multimodal
T1C+ imaging data, encompassing functional MRI (fMRI) and
diffusion tensor imaging (DTI), harbors potential for [https://www.semanticscholar.org/paper/Brain-tumor-detection-and-
classification-using-a-Amin-
capturing complementary insights into tumor attributes and Sharif/f630ee33272b8505668b70975c3c9df015b21105].
spatial interrelationships, thereby fostering more nuanced and
precise tumor classification frameworks.
[7] Y. Bhanothu, A. Kamalakannan and G. Rajamanickam, "Detection and
Classification of Brain Tumor in MRI Images using Deep
Additionally, the deployment of transfer learning strategies, Convolutional Network," 2020 6th International Conference on
whereby pre-trained models are fine-tuned on bespoke brain Advanced Computing and Communication Systems (ICACCS),
tumor datasets, stands poised to expedite model development Coimbatore, India, 2020, pp. 248-252, doi:
10.1109/ICACCS48705.2020.9074375. keywords:
and facilitate knowledge transfer across diverse medical {Tumors;Classification algorithms;Proposals;Image
imaging endeavors. Moreover, the integration of segmentation;Training;Magnetic resonance imaging;Testing;Brain
interpretability techniques, such as attention mechanisms and tumor detection;glioma;meningioma;pituitary;Faster R-CNN;VGG-
saliency map, has the potential to furnish clinicians with 16;mean average precision;MRI},
invaluable insights into the decision-making mechanisms of
the deep learning model, fostering trust and confidence in its [8] D. M. Joshi, N. K. Rana and V. M. Misra, "Classification of Brain
Cancer using Artificial Neural Network," 2010 2nd International
diagnostic acumen. Conference on Electronic Computer Technology, Kuala Lumpur,
Malaysia, 2010, pp. 112-116, doi: 10.1109/ICECTECH.2010.5479975.
In summation, the convergence of deep learning keywords: {Artificial neural networks;Neoplasms;Magnetic resonance
methodologies and medical imaging evinces substantial imaging;System testing;Cancer detection;Feature extraction;Computer
networks;Lesions;Image processing;Histograms;Brain
potential for revolutionizing the landscape of brain tumor cancer;MRI;Co-occurrence Matrix;ANN},
diagnosis and treatment. Through the adept utilization of
cutting-edge techniques and the cultivation of [9] H. T. Zaw, N. Maneerat and K. Y. Win, "Brain tumor detection based
interdisciplinary collaborations, we stand poised to usher in on Naïve Bayes Classification," 2019 5th International Conference on
an era marked by more precise, efficient, and accessible Engineering, Applied Sciences and Technology (ICEAST), Luang
healthcare solutions for patients worldwide.. Prabang, Laos, 2019, pp. 1-4, doi: 10.1109/ICEAST.2019.8802562.
keywords: {Tumors;Magnetic resonance imaging;Image
segmentation;Feature extraction;Cancer;Classification
algorithms;Databases;Glioblastoma Multiforme (GBM);Magnetic
VI) REFERENCES resonance imaging (MRI);Naïve Bayes classification;maximum
[1] S. Banerjee, S. Mitra and B. U. Shankar, "Synergetic neuro-fuzzy entropy threshold;statistical features extraction},
feature selection and classification of brain tumors," 2017 IEEE
International Conference on Fuzzy Systems (FUZZ-IEEE), Naples, [10] P. Thirumurugan and P. Shanthakumar, "Brain tumor detection and
Italy, 2017, pp. 1-6, doi: 10.1109/FUZZ-IEEE.2017.8015514. diagnosis using ANFIS classifier," International Journal of Imaging
keywords: {Feature extraction;Tumors;Pragmatics;Magnetic Systems and Technology, vol. 26, 2016. [Online]. Available:
resonance imaging;Cancer;Shape}, https://api.semanticscholar.org/CorpusID:40434958
[11] S. Chauhan, A. More, R. Uikey, P. Malviya and A. Moghe, "Brain
[2] M. Gurbină, M. Lascu and D. Lascu, "Tumor Detection and tumor detection and classification in MRI images using image and data
Classification of MRI Brain Image using Different Wavelet mining," 2017 International Conference on Recent Innovations in
Transforms and Support Vector Machines," 2019 42nd International Signal processing and Embedded Systems (RISE), Bhopal, India,
Conference on Telecommunications and Signal Processing (TSP), 2017, pp. 223-231, doi: 10.1109/RISE.2017.8378158. keywords:
Budapest, Hungary, 2019, pp. 505-508, doi: {Feature extraction;Tumors;Image segmentation;Image color
10.1109/TSP.2019.8769040. keywords: {Tumors;Support vector analysis;Image edge detection;Data mining;Clustering
machines;Magnetic resonance imaging;Noise reduction;Discrete algorithms;MRI image;L∗a∗b colour space;K-means
wavelet transforms;brain;classification;denoising;detection;support clustering;segmentation;Classification},
vector machines;tumor;wavelet transforms},

[3] M A Ansari, Rajeev Agrawal, and Rajat Mehrotra, “Detection and [12] A. Rehman, M. A. Khan, T. Saba, Z. Mehmood, U. Tariq, and N.
classification of brain tumor in MRI images using wavelet transform Ayesha, “Microscopic brain tumor detection and classification using
and support vector machine,” 2002. 3D CNN and feature selection architecture,” Microscopy Research and
Technique, vol. 84, no. 1, pp. 133–149, Sep. 2020, doi:
[4] A. Hebli and S. Gupta, "Brain tumor prediction and classification using https://doi.org/10.1002/jemt.23597.
support vector machine," 2017 International Conference on Advances
in Computing, Communication and Control (ICAC3), Mumbai, India, [13] [13]A. Hu and N. Razmjooy, "Brain tumor diagnosis based on
2017, pp. 1-6, doi: 10.1109/ICAC3.2017.8318767. keywords: metaheuristics and deep learning," International Journal of Imaging
{Tumors;Feature extraction;Support vector machines;Discrete wavelet Systems and Technology, vol. 31, pp. 657-669, 2020. [Online].
transforms;Training;Magnetic resonance imaging;Principal Available: https://api.semanticscholar.org/CorpusID:224879353
component analysis;Brain Tumor;MRI (magnetic resonance
imaging);DWT (Discrete wavelet transform);PCA (Principal
[14] M. Thachayani and S. Kurian, “AI Based Classification Framework
component analysis);SVM (Support vector machine)},
For Cancer Detection Using Brain MRI Images,” 2021 International
Conference on System, Computation, Automation and Networking
[5] J. Amin, M. Sharif, A. Haldorai, M. Yasmin, and R. S. Nayak, "Brain (ICSCAN), Jul. 2021, doi:
tumor detection and classification using machine learning: a https://doi.org/10.1109/icscan53069.2021.9526456.
comprehensive survey," Complex & Intelligent Systems, vol. 8, pp.
3161-3183, 2021. [15] Pritanjli and Amit Doegar, “Brain Tumor Detection and Classification
Using Machine Learning,” Algorithms for intelligent systems, pp. 227–
[6] T. Sadad, A. Rehman, A. Munir, Tanzila, U. Tariq, Noor, and R. A. 234, Jan. 2020, doi: https://doi.org/10.1007/978-981-15-0426-6_24.
Rehman, "Brain tumor detection and multi-classification using
advanced deep learning techniques,". Available: