MobileNetV2 Architecture Research Articles

A divide and conquer approach to maximise deep learning mammography classification accuracies.

Breast cancer claims 11,400 lives on average every year in the UK, making it one of the deadliest diseases. Mammography is the gold standard for detecting early signs of breast cancer, which can help cure the disease during its early stages. However, incorrect mammography diagnoses are common and may harm patients through unnecessary treatments and operations (or a lack of treatment). Therefore, systems that can learn to detect breast cancer on their own could help reduce the number of incorrect interpretations and missed cases. Various deep learning techniques, which can be used to implement a system that learns how to detect instances of breast cancer in mammograms, are explored throughout this paper. Convolution Neural Networks (CNNs) are used as part of a pipeline based on deep learning techniques. A divide and conquer approach is followed to analyse the effects on performance and efficiency when utilising diverse deep learning techniques such as varying network architectures (VGG19, ResNet50, InceptionV3, DenseNet121, MobileNetV2), class weights, input sizes, image ratios, pre-processing techniques, transfer learning, dropout rates, and types of mammogram projections. This approach serves as a starting point for model development of mammography classification tasks. Practitioners can benefit from this work by using the divide and conquer results to select the most suitable deep learning techniques for their case out-of-the-box, thus reducing the need for extensive exploratory experimentation. Multiple techniques are found to provide accuracy gains relative to a general baseline (VGG19 model using uncropped 512 × 512 pixels input images with a dropout rate of 0.2 and a learning rate of 1 × 10-3) on the Curated Breast Imaging Subset of DDSM (CBIS-DDSM) dataset. These techniques involve transfer learning pre-trained ImagetNet weights to a MobileNetV2 architecture, with pre-trained weights from a binarised version of the mini Mammography Image Analysis Society (mini-MIAS) dataset applied to the fully connected layers of the model, coupled with using weights to alleviate class imbalance, and splitting CBIS-DDSM samples between images of masses and calcifications. Using these techniques, a 5.6% gain in accuracy over the baseline model was accomplished. Other deep learning techniques from the divide and conquer approach, such as larger image sizes, do not yield increased accuracies without the use of image pre-processing techniques such as Gaussian filtering, histogram equalisation and input cropping.

Using deep cnn architectures and tensorflow for bee identification on images

Problem statement. Bees are important pollinators for various plant species and are essential in maintaining our planet's biodiversity. With the decline in the number of bees worldwide, monitoring the bee hive state has become increasingly important. Pur-pose. Individual bee identification is an important task that, if performed well, will help to track the bee hive population and its health state in general. Related work. With the development of deep learning and computer vision technologies, several studies were done on their application in detecting insects like wasps, spiders, or fruit flies. Materials and methods. Photographs of bee hive frames with bees on them are being used as a da-ta source for model training. These photographs were manually annotated using Remo annotation software. This study uses five widely used deep learning architectures (Fast-er R-CNN ResNet152, CenterNet ResNet50, SSD ResNet50, Faster R-CNN Inception ResNet V2, SSD MobileNet V2) for the purpose of bee detection on test images. These models were trained on the same dataset and evaluated on the same bee image set. Re-sults and discussion. According to the confusion matrix, SSD MobileNet V2 architecture showed the best detection performance with 80% detected bees on test files, but it also had the falsest negative entries. On the other hand, Faster R-CNN ResNet152 model showed the best results in accuracy and evaluation speed, but successfully identified on-ly 61% of the bees. Conclusions. The experiment showed that state-of-the-art CNN ar-chitecture SSD MobileNet V2 is a better performer with detecting 80% and 95% accura-cy on bee images test set.

FERFM: An Enhanced Facial Emotion Recognition System Using Fine-tuned MobileNetV2 Architecture

Deep learning techniques have recently drawn a lot of attention towards automatic facial emotion recognition (FER) applications such as diagnosis of psychiatric disorders, mental health monitoring, and other human–computer interaction applications. But the models that have been developed, have still not been generalized due to the absence of substantial emotion datasets and high operational costs. To address these issues, we propose a novel technique called facial emotion recognition using fine-tuned MobileNetV2 architecture (FERFM). It uses the concept of transfer learning to improve the performance of FER systems for mobile devices. It transfers the knowledge from pre-trained ImageNet dataset to profile view RGB-KDEF dataset for diversity among learnt features. Initially, data descriptive analysis is performed on input KDEF images to automate the necessary knowledge. Then the pipeline strategy is introduced, where the pre-trained MobileNetV2 architecture is fine tuned by eliminating the last six layers and adding dropout regularization, max pooling and dense layer. To test the performance of the proposed work, we ran several tests using the KDEF-RGB dataset, FER13 dataset and real-time facial expression images to classify the results into seven discrete categories of emotions. It was also verified on VGG-16 pretrained model and demonstrated remarkable performance comparatively. Proposed FERFM achieves 85.7% accuracy and requires 1,510,599 number of trainable parameters, 43 ms running time per image that proves the enhancement of FER performance and outperforms the existing state of art methods. Also, the ability to achieve low operational costs while maintaining high accuracy demonstrates proficiency in mobile applications.

Nonlinear microscopy and deep learning classification for mammary gland microenvironment studies.

Tumors, their microenvironment, and the mechanisms by which collagen morphology changes throughout cancer progression have recently been a topic of interest. Second harmonic generation (SHG) and polarization second harmonic (P-SHG) microscopy are label-free, hallmark methods that can highlight this alteration in the extracellular matrix (ECM). This article uses automated sample scanning SHG and P-SHG microscopy to investigate ECM deposition associated with tumors residing in the mammary gland. We show two different analysis approaches using the acquired images to distinguish collagen fibrillar orientation changes in the ECM. Lastly, we apply a supervised deep-learning model to classify naïve and tumor-bearing mammary gland SHG images. We benchmark the trained model using transfer learning with the well-known MobileNetV2 architecture. By fine-tuning the different parameters of these models, we show a trained deep-learning model that suits such a small dataset with 73% accuracy.

Edge computing on TPU for brain implant signal analysis

The ever-increasing number of recording sites of silicon-based probes imposes a great challenge for detecting and evaluating single-unit activities in an accurate and efficient manner. Currently separate solutions are available for high precision offline evaluation and separate solutions for embedded systems where computational resources are more limited.We propose a deep learning-based spike sorting system, that utilizes both unsupervised and supervised paradigms to learn a general feature embedding space and detect neural activity in raw data as well as predict the feature vectors for sorting. The unsupervised component uses contrastive learning to extract features from individual waveforms, while the supervised component is based on the MobileNetV2 architecture. One of the key advantages of our system is that it can be trained on multiple, diverse datasets simultaneously, resulting in greater generalizability than previous deep learning-based models.We demonstrate that the proposed model does not only reaches the accuracy of current state-of-art offline spike sorting methods but has the unique potential to run on edge Tensor Processing Units (TPUs), specialized chips designed for artificial intelligence and edge computing. We compare our model performance with state of art solutions on paired datasets as well as on hybrid recordings as well. The herein demonstrated system paves the way to the integration of deep learning-based spike sorting algorithms into wearable electronic devices, which will be a crucial element of high-end brain–computer interfaces.

Web-based CNN Application for Arabica Coffee Leaf Disease Prediction in Smart Agriculture

In the agriculture industry, plant diseases provide difficulty, particularly for Arabica coffee production. A first step in eliminating and treating infections to avoid crop damage is recognizing ailments on Arabica coffee leaves. Convolutional neural networks (CNN) are rapidly advancing, making it possible to diagnose Arabica coffee leaf damage without a specialist's help. CNN is aimed to find features adaptively through backpropagation by adding layers including convolutional layers and pooling layers. This study aims to optimize and increase the accuracy of Arabica coffee leaf disease classification utilizing the neural network architectures: ResNet50, InceptionResNetV4, MobileNetV2, and DensNet169. Additionally, this research presents an interactive web platform integrated with the Arabica coffee leaf disease prediction system. Inside this research, 5000 image data points will be divided into five classes—Phoma, Rust, Cescospora, healthy, and Miner—to assess the efficacy of CNN architecture in classifying images of Arabica coffee leaf disease. 80:10:10 is the ratio between training data, validation, and testing. In the testing findings, the InceptionResnetV2 and DensNet169 designs had the highest accuracy, at 100%, followed by the MobileNetV2 architecture at 99% and the ResNet50 architecture at 59%. Even though MobileNetV2 is not more accurate than InceptionResnetV2 and DensNet169, MobileNetV2 is the smallest of the three models. The MobileNetV2 paradigm was chosen for web application development. The system accurately identified and advised treatment for Arabica coffee leaf diseases, as shown by the system's implementation outcomes.

Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique

Due to the rapid emergence and evolution of AI applications, the utilization of smart imaging devices has increased significantly. Researchers have started using deep learning models, such as CNN, for image classification. Unlike the traditional models, which require a lot of features to perform well, CNN does not require any handcrafted features to perform well. It uses numerous filters, which extract required features from images automatically for classification. One of the issues in the horticulture industry is fruit classification, which requires an expert with a lot of experience. To overcome this issue an automated system is required which can classify different types of fruits without the need for any human effort. In this study, a dataset of a total of 26,149 images of 40 different types of fruits was used for experimentation. The training and test set were randomly recreated and divided into the ratio of 3:1. The experiment introduces a customized head of five different layers into MobileNetV2 architecture. The classification layer of the MobileNetV2 model is replaced by the customized head, which produced the modified version of MobileNetV2 called TL-MobileNetV2. In addition, transfer learning is used to retain the pre-trained model. TL-MobileNetV2 achieves an accuracy of 99%, which is 3% higher than MobileNetV2, and the equal error rate of TL-MobileNetV2 is just 1%. Compared to AlexNet, VGG16, InceptionV3, and ResNet, the accuracy is better by 8, 11, 6, and 10%, respectively. Furthermore, the TL-MobileNetV2 model obtained 99% precision, 99% for recall, and a 99% F1-score. It can be concluded that transfer learning plays a big part in achieving better results, and the dropout technique helps to reduce the overfitting in transfer learning.

Face Mask Detection on Photo and Real-Time Video Images Using Caffe-MobileNetV2 Transfer Learning

Face detection systems have generally been used primarily for non-masked faces, which include relevant facial characteristics such as the ears, chin, lips, nose, and eyes. Masks are necessary to cover faces in many situations, such as pandemics, crime scenes, medical settings, high pollution, and laboratories. The COVID-19 epidemic has increased the requirement for people to use protective face masks in public places. Analysis of face detection technology is crucial with blocked faces, which typically have visibility only in the periocular area and above. This paper aims to implement a model on complex data, i.e., by taking tasks for the face detection of people from the photo and in real-time video images with and without a mask. This task is implemented based on the features around their eyes, ears, nose, and forehead by using the original masked and unmasked images to form a baseline for face detection. The idea of performing such a task is by using the Caffe-MobileNetV2 (CMNV2) model for feature extraction and masked image classification. The convolutional architecture for the fast feature embedding Caffe model is used as a face detector, and the MobileNetV2 is used for mask identification. In this work, five different layers are added to the pre-trained MobileNetV2 architecture for better classification accuracy with fewer training parameters for the given data for face mask detection. Experimental results revealed that the proposed methodology performed well, with an accuracy of 99.64% on photo images and good accuracy on real-time video images. Other metrics show that the model outperforms previous models with a precision of 100%, recall of 99.28%, f1-score of 99.64%, and an error rate of 0.36%. Face mask detection was originally a form of computing application, but it is now widely used in other technological areas such as smartphones and artificial intelligence. Computer-based masked-face detection belongs in the category of biometrics, since it includes using a person’s unique features to identify them with a mask on.

Intelligent surface defect detection for submersible pump impeller using MobileNet V2 architecture

Intelligent surface defect detection for submersible pump impeller using MobileNet V2 architecture

A Novel Efficient Patient Monitoring FER System Using Optimal DL-Features

Automated Facial Expression Recognition (FER) serves as the backbone of patient monitoring systems, security, and surveillance systems. Real-time FER is a challenging task, due to the uncontrolled nature of the environment and poor quality of input frames. In this paper, a novel FER framework has been proposed for patient monitoring. Preprocessing is performed using contrast-limited adaptive enhancement and the dataset is balanced using augmentation. Two lightweight efficient Convolution Neural Network (CNN) models MobileNetV2 and Neural search Architecture Network Mobile (NasNetMobile) are trained, and feature vectors are extracted. The Whale Optimization Algorithm (WOA) is utilized to remove irrelevant features from these vectors. Finally, the optimized features are serially fused to pass them to the classifier. A comprehensive set of experiments were carried out for the evaluation of real-time image datasets FER-2013, MMA, and CK+ to report performance based on various metrics. Accuracy results show that the proposed model has achieved 82.5% accuracy and performed better in comparison to the state-of-the-art classification techniques in terms of accuracy. We would like to highlight that the proposed technique has achieved better accuracy by using 2.8 times lesser number of features.

An Approach to Hyperparameter Tuning in Transfer Learning for Driver Drowsiness Detection Based on Bayesian Optimization and Random Search

Driver drowsiness is a critical factor in road safety, and developing accurate models for detecting it is essential. Transfer learning has been shown to be an effective technique for driver drowsiness detection, as it enables models to leverage large, pre-existing datasets. However, the optimization of hyper-parameters in transfer learning models can be challenging, as it involves a large search space. The core purpose of this research is on presenting an approach to hyperparameter tuning in transfer learning for driving fatigue detection based on Bayesian optimization and Random search algorithms. We examine the efficiency of our approach on a publicly available dataset using transfer learning models with the MobileNetV2, Xception, and VGG19 architectures. We explore the impact of hyperparameters such as dropout rate, activation function, the number of units (the number of dense nodes), optimizer, and learning rate on the transfer learning models’ overall performance. Our experiments show that our approach improves the performance of the transfer learning models, obtaining cutting-edge results on the dataset for all three architectures. We also compare the efficiency of Bayesian optimization and Random search algorithms in terms of their ability to find optimal hyperparameters and indicate that Bayesian optimization is more efficient in finding optimal hyperparameters than Random search. The results of our study provide insights into the importance of hyperparameter tuning for transfer learning-based driver drowsiness detection using different transfer learning models and can guide the selection of hyperparameters and models for future studies in this field. Our proposed approach can be applied to other transfer learning tasks, making it a valuable contribution to the field of ML.

A Light-Weight Deep Learning-Based Architecture for Sign Language Classification

With advancements in computing powers and the overall quality of images captured on everyday cameras, a much wider range of possibilities has opened in various scenarios. This fact has several implications for deaf and dumb people as they have a chance to communicate with a greater number of people much easier. More than ever before, there is a plethora of info about sign language usage in the real world. Sign languages, and by extension the datasets available, are of two forms, isolated sign language and continuous sign language. The main difference between the two types is that in isolated sign language, the hand signs cover individual letters of the alphabet. In continuous sign language, entire words’ hand signs are used. This paper will explore a novel deep learning architecture that will use recently published large pre-trained image models to quickly and accurately recognize the alphabets in the American Sign Language (ASL). The study will focus on isolated sign language to demonstrate that it is possible to achieve a high level of classification accuracy on the data, thereby showing that interpreters can be implemented in the real world. The newly proposed MobileNetV2 architecture serves as the backbone of this study. It is designed to run on end devices like mobile phones and infer signals (what does it infer) from images in a relatively short amount of time. With the proposed architecture in this paper, the classification accuracy of 98.77% in the Indian Sign Language (ISL) and American Sign Language (ASL) is achieved, outperforming the existing state-of-the-art systems.

Mobile Based Brand and Car Type Detection Using Convolutional Neural Network

Although the parking lot is equipped with CCTV surveillance, car theft incidents still occur occasionally. These thieves exploit a loophole in the system that prevents the identification of the car's brand and model upon entering and exiting the parking lot using the same ticket. Therefore, the aim of this research is to develop a system capable of detecting the brand and model of cars. The study utilizes convolutional neural network technology and specifically focuses on the EfficientNet, MobileNet, and MobileNetV2 architectures due to their low resource requirements. Training images for the study are sourced from an online marketplace for used cars, with each of the 20 car brand and model variations consisting of 100 photographs. creates a model after being processed. For the prototype, the approach is put into practice through a mobile application. This study compares EfficientNet, MobileNetV1, and MobileNetV2 as the end result. EfficientNet scored 74%, MobileNetV1 74%, and MobileNetV2 66% on the test of accuracy. The accuracy increases to 80% after the EfficientNet has been tuned.

A Deep Transfer Learning-Based Comparative Study for Detection of Malaria Disease

Malaria is a disease caused by a parasite. The parasite is transmitted to humans through the bite of infected mosquitoes. Thousands of people die every year due to malaria. When this disease is diagnosed early, it can be fully treated with medication. Diagnosis of malaria can be made according to the presence of parasites in the blood taken from the patient. In this study, malaria detection and diagnosis study were performed using The Malaria dataset containing a total of 27,558 cell images with samples of equally parasitized and uninfected cells from thin blood smear slide images of segmented cells. It is possible to detect malaria from microscopic blood smear images via modern deep learning techniques. In this study, 5 of the popular convolutional neural network architectures for malaria detection from cell images were retrained to find the best combination of architecture and learning algorithm. AlexNet, GoogLeNet, ResNet-50, MobileNet-v2, VGG-16 architectures from pre-trained networks were used, their hyperparameters were adjusted and their performances were compared. In this study, a maximum 96.53% accuracy rate was achieved with MobileNet-v2 architecture using the adam learning algorithm

Weakly-supervised learning method for the recognition of potato leaf diseases.

As a crucial food crop, potatoes are highly consumed worldwide, while they are also susceptible to being infected by diverse diseases. Early detection and diagnosis can prevent the epidemic of plant diseases and raise crop yields. To this end, this study proposed a weakly-supervised learning approach for the identification of potato plant diseases. The foundation network was applied with the lightweight MobileNet V2, and to enhance the learning ability for minute lesion features, we modified the existing MobileNet-V2 architecture using the fine-tuning approach conducted by transfer learning. Then, the atrous convolution along with the SPP module was embedded into the pre-trained networks, which was followed by a hybrid attention mechanism containing channel attention and spatial attention submodules to efficiently extract high-dimensional features of plant disease images. The proposed approach outperformed other compared methods and achieved a superior performance gain. It realized an average recall rate of 91.99% for recognizing potato disease types on the publicly accessible dataset. In practical field scenarios, the proposed approach separately attained an average accuracy and specificity of 97.33% and 98.39% on the locally collected image dataset. Experimental results present a competitive performance and demonstrate the validity and feasibility of the proposed approach.

Automatic Identification of banana quality with Deep Neural Network Classification (DNN)

The industrialization of agriculture has gradually taken place in Colombia, because of the need to optimize the time and effort required for the processes involved from growing fruits and vegetables to their distribution and commercialization, whether they are meant for exportation or commercialization within the country. Fruit classification is a very important process before they are being taken out as a final product, since predetermined guidelines issued by regulatory entities that define the quality of the harvested product must be followed. The authors propose a low-cost prototype for the automatic classification of bananas according to the NTC 1190 standard (Colombian normative), using a convolutional neural network (CNN) of MobileNetV2 architecture trained through transfer learning and implemented in a Raspberry Pi 3B+ with a camera to monitor the specimens and an easy interface for interaction with the user, as well as a case designed to contain the hardware and allow access to its ports in the most compact way possible. The datasets utilized in this work for training, validation, and testing, consists of images taken from two free access fruit database and others acquired by the researchers. The achieved precision is 87 %, enough to ensure reliability and low computational cost.

Enhanced mechanisms of pooling and channel attention for deep learning feature maps.

The pooling function is vital for deep neural networks (DNNs). The operation is to generalize the representation of feature maps and progressively cut down the spatial size of feature maps to optimize the computing consumption of the network. Furthermore, the function is also the basis for the computer vision attention mechanism. However, as a matter of fact, pooling is a down-sampling operation, which makes the feature-map representation approximately to small translations with the summary statistic of adjacent pixels. As a result, the function inevitably leads to information loss more or less. In this article, we propose a fused max-average pooling (FMAPooling) operation as well as an improved channel attention mechanism (FMAttn) by utilizing the two pooling functions to enhance the feature representation for DNNs. Basically, the methods are to enhance multiple-level features extracted by max pooling and average pooling respectively. The effectiveness of the proposals is verified with VGG, ResNet, and MobileNetV2 architectures on CIFAR10/100 and ImageNet100. According to the experimental results, the FMAPooling brings up to 1.63% accuracy improvement compared with the baseline model; the FMAttn achieves up to 2.21% accuracy improvement compared with the previous channel attention mechanism. Furthermore, the proposals are extensible and could be embedded into various DNN models easily, or take the place of certain structures of DNNs. The computation burden introduced by the proposals is negligible.

Artificial Intelligence based Integrated and Distributed System for Preventing Covid-19 Spread Using Deep Learning

The COVID-19 pandemic is causing a worldwide emergency in healthcare. This virus mainly spreads through droplets which emerge from a person infected with coronavirus and poses a risk to others. The risk of transmission is highest in public places. Many measures have been suggested, such as maintaining a social distance, and wearing a face mask to avoid the spread of this virus. There are three modules in this work, in the first module a mask detection system which detects whether a person wears a mask or not using deep learning techniques such as MobileNet V2 architecture along with Facenet and Masknet. Accuracy of 98.6% is achieved in this module with one or two people in the frame. Barricade has been set which does not allow people who does not wear mask and allows people who wears a mask. LED light indicators and LCD displays are used as alerts, and they are programmed to provide information that is both worn and not worn, depending on the output. In the second module, a system has been designed which detects the temperature of the person and detects whose temperature is above normal body temperature and alerts accordingly. In the third module a social distancing system has been designed which detects people who does not follow social distancing protocol and alerts them using deep learning techniques. The YOLOv3 algorithm is used which creates a square box around people that displays green or red color box according to the measurement output. The transfer learning methodology is also implemented to increase the accuracy of this module. The accuracy of 98.2% is achieved for social distance detection module using YOLOv3 detection model with transfer learning. All three modules are integrated so it automatically monitors human body temperature, detects mask and social distancing at the barricade system.

A NOVEL COMPARATIVE STUDY FOR AUTOMATIC THREE-CLASS AND FOUR-CLASS COVID-19 CLASSIFICATION ON X-RAY IMAGES USING DEEP LEARNING

The contagiousness rate of the COVID-19 virus, which was evaluated to have been transmitted from an animal to a human during the last months of 2019, is higher than the MERS-Cov and SARS-Cov viruses originating from the same family. The high rate of contagion has caused the COVID-19 virus to spread rapidly to all countries of the world. It is of great importance to be able to detect cases quickly in order to control the spread of the COVID-19 virus. Therefore, the development of systems that make automatic COVID-19 diagnoses using artificial intelligence approaches based on Xray, CT scans, and ultrasound images are an urgent and indispensable requirement. In order to increase the number of X-ray images used within the study, a mixed data set was created by combining eight different data sets, thus maximizing the scope of the study. In the study, a total of 9,667 X ray images were used, including 3,405 of COVID-19 samples, 2,780 of bacterial pneumonia samples, 1,493 of viral pneumonia samples and 1,989 of healthy samples. In this study, which aims to diagnose COVID-19 disease using X-ray images, automatic classification has been performed using two different classification structures: COVID-19 Pneumonia/Other Pneumonia/Healthy and COVID-19 Pneumonia/Bacterial Pneumonia/Viral Pneumonia/Healthy. Convolutional Neural Networks (CNNs), a successful deep learning method, were used as a classifier within the study. A total of seven CNN architectures were used: Mobilenetv2, Resnet101, Googlenet, Xception, Densenet201, Efficientnetb0, and Inceptionv3 architectures. The classification results were obtained from the original X-ray images, and the images were obtained by using Local Binary Pattern and Local Entropy. Then, new classification results were calculated from the obtained results using a pipeline algorithm. Detailed results were obtained to meet the scope of the study. According to the results of the experiments carried out, the three most successful CNN architectures for both three-class and four class automatic classification were Densenet201, Xception, and Inceptionv3, respectively. In addition, it is understood that the pipeline algorithm used in the study is very useful for improving the results. The study results show that up to an improvement of 1.57% were achieved in some comparison parameters.

Detection of Alzheimer’s Disease with Deep Learning Method

Alzheimer hastalığı yaygın olarak görülen bir demans türü olup, ilerleyen ve tedavisi bulunmayan nörodejeneratif bir hastalıktır. Hastalığı teşhis edebilmek için birçok görüntüleme tekniği kullanılmaktadır. Bu tekniklerden biri Manyetik Rezonans Görüntüleme (MRG) tekniğidir. Erken teşhis edilmesi hastalığın ilerlemesini yavaşlatmak ve gerekli önlemleri alma konusunda hasta ve ailesi için büyük önem taşımaktadır. Erken ve doğru teşhis için derin öğrenme yöntemleriyle bu konuda destekleyici çalışmalar gerçekleştirilmiştir. Aynı zamanda hastalığın seyrini takip etmek için de derin öğrenme yöntemleri kullanılmaktadır. Bu çalışmada hastalığın teşhisi için AlexNet, MobileNetV2 mimarileri ve ESA (Evrişimsel Sinir Ağları) modeli kullanılarak gerçekleştirilmiştir. Toplamda 6400 adet MR görüntüsü kullanılarak her iki mimariden özellik çıkarma işlemi yapılarak bu özellikler birleştirilmiştir. KBA (Komşuluk Bileşen Analizi) algoritması kullanılarak özellik seçimi yapılmış ve DVM (Destek Vektör Makineleri) ile sınıflandırma işlemi gerçekleştirilmiştir. Çalışılan modelde %100 doğruluk değeri hesaplanmıştır.