Three‐class classification of brain magnetic resonance images using average‐pooling convolutional neural network

Kakarla, Jagadeesh; Isunuri, Bala Venkateswarlu; Doppalapudi, Krishna Sai; Bylapudi, Karthik Satya Raghuram

doi:10.1002/ima.22554

Cited by 34 publications

(18 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study has achieved a mean accuracy of 97.08% and 97.48% with data augmentation and without data augmentation, respectively. The paper of Kakarla et al [68], an eightlayer average-pooling CNN, has proposed to address three-class brain tumour classification. This model uses three convolution blocks along with a dense layer and a softmax layer.…”

Section: Experimental Results For Figshare Datasetmentioning

confidence: 99%

A combination of feature extraction methods and deep learning for brain tumour classification

Siar

Teshnehlab

2021

IET Image Processing

View full text Add to dashboard Cite

This paper presents a method for categorizing tumour disease from magnetic resonance imaging images using a convolutional neural network. The proposed technique consists of three major phases, including feature extraction, feature selection, and combination. The authors considered the classification method using convolutional neural network without any pre-processing on input images as the original method. The original method is then improved in some sequential phases when convolutional neural network uses features generated by feature extraction methods. Many popular feature extraction methods in generating the input features of the network are examined. After examining the results, a set of feature extraction schemes with appropriate performance are selected for the next phase. Also, the authors assigned weight factors to each of the selected methods, according to their accuracy. By assigning these weight factors to the methods, the network's accuracy increased to an acceptable level compared to the first and second observations. An accuracy above 99.76% was achieved, which is a 2% improvement using these feature extraction methods compared to the original method. The authors also added a third class named 'I do not know' to increase the tumour detection problem's reliability in the last phase. The authors have successfully introduced a convolutional neural network architecture with high accuracy and reliability.

show abstract

Section: Experimental Results For Figshare Datasetmentioning

confidence: 99%

A combination of feature extraction methods and deep learning for brain tumour classification

Siar

Teshnehlab

2021

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…In contrast, average pooling uses the average of the data being observed. Average pooling has been successfully used in place of max pooling in a variety of scenarios [ 48 , 49 ]. Normalization is performed using a batch normalization layer for each Conv layer.…”

Section: Methodsmentioning

confidence: 99%

A Deep Convolutional Neural Network-XGB for Direction and Severity Aware Fall Detection and Activity Recognition

Syed

Sierra-Sosa

Kumar

et al. 2022

Sensors

View full text Add to dashboard Cite

Activity and Fall detection have been a topic of keen interest in the field of ambient assisted living system research. Such systems make use of different sensing mechanisms to monitor human motion and aim to ascertain the activity being performed for health monitoring and other purposes. Towards this end, in addition to activity recognition, fall detection is an especially important task as falls can lead to injuries and sometimes even death. This work presents a fall detection and activity recognition system that not only considers various activities of daily living but also considers detection of falls while taking into consideration the direction and severity. Inertial Measurement Unit (accelerometer and gyroscope) data from the SisFall dataset is first windowed into non-overlapping segments of duration 3 s. After suitable data augmentation, it is then passed on to a Convolutional Neural Network (CNN) for feature extraction with an eXtreme Gradient Boosting (XGB) last stage for classification into the various output classes. The experiments show that the gradient boosted CNN performs better than other comparable techniques, achieving an unweighted average recall of 88%.

show abstract

“…On the other hand, glioma tumors can be identified by the shape and size of the tumors. Thus, multi-class classification of brain tumor becomes a critical research task due to the distinct properties of tumors [10]. It motivated us to work in this direction, and hence we have proposed an ensemble model for the three-class classification of brain MR images.…”

Section: Meningioma Tumor Forms On Cells Of the Brain Andmentioning

confidence: 99%

Ensemble EfficientNet and Mixed Convolution for Three-class brain MR image classification

Kakarla

Isunuri

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The classification of brain tumor images is the prevalent task in computer-aided brain tumor diagnosis. Recently, three-class classification becomes a superlative task in brain tumor classification. The existing models are fine-tuned for a single dataset, and hence they may exhibit displeasing results on other datasets. Thus, there is a need for a generalized model that can produce superior performance on multiple datasets. In this paper, we have presented a generalized model that produces similar results on two datasets. We have proposed an ensemble EfficientNet and mixed convolution model to perform a three-class classification. We have devised a mixed convolution to enhance the feature vector extracted from pre-trained EfficientNet. The mixed convolution consists of two blocks namely separable convolution and residual convolution blocks. We have utilized a gaussian dropout layer before the softmax layer to avoid model overfitting. In our experiments, two publicly available datasets are considered for the evaluation of the proposed model. We have achieved an accuracy of 97.65% and 95.84% on BTDS and CPM datasets, respectively. The proposed model outperforms existing pre-trained models and state-of-the-art models in vital metrics.

show abstract

Three‐class classification of brain magnetic resonance images using average‐pooling convolutional neural network

Cited by 34 publications

References 21 publications

A combination of feature extraction methods and deep learning for brain tumour classification

A combination of feature extraction methods and deep learning for brain tumour classification

A Deep Convolutional Neural Network-XGB for Direction and Severity Aware Fall Detection and Activity Recognition

Ensemble EfficientNet and Mixed Convolution for Three-class brain MR image classification

Contact Info

Product

Resources

About