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

Abstract

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.

PDC-Net: parallel dilated convolutional network with channel attention mechanism for pituitary adenoma segmentation

“…To evaluate the performance of the PDC-Net on the dataset, Sensitivity ( Shen et al, 2022 ; Siar and Teshnehlab, 2022 ), Specificity ( Rai and Chatterjee, 2021 ; Ramachandran et al, 2021 ), Dice value ( Yang Y et al, 2020 ; You et al, 2021 ), and Intersection over Union ( Ahmed et al, 2021 ; Zou et al, 2021 ) are utilized as evaluation metrics, which can be defined as: where TP represents the number of adenoma pixels judged to be adenoma, TN represents the number of non-adenoma pixels judged to be non-adenoma, FP represents the number of non-adenoma pixels judged to be adenoma, and FN represents the number of adenoma pixels judged to be non-adenoma.…”

Global Self-Attention Module Based Convolutional Neural Network for Brain Tumor Classification

“…The feature selection plays a main part in the classification, because it reduces the estimation time and enhance the classification performance [13]. The DL application produces an ideal solution because it extracts prominent features from the image, better than manually extracted features [14]. The newly implemented techniques for classification based on DL necessitate masked images for the predictable result [15].…”

“…Next, multiplication among 𝑄 𝑠𝑝 𝑎𝑛𝑑 𝐾 𝑠𝑝 is managed through softmax activation for acquiring spatial attention weights 𝐹 𝑠𝑝 ′ ∈ 𝑅 𝐻𝑊×𝐻𝑊 , as expressed in Eq. (14).…”

Brain tumour segmentation of MR images based on custom attention mechanism with transfer‐learning

“…Therefore, the development of an automatic or semi-automatic computeraided diagnostic (CAD) system in real medical therapies is needed to reduce the workload of physicians and improve accuracy. CAD system for brain tumours consists of tumour detection [4][5][6], segmentation [7][8][9], and classification [10][11][12][13] processes from MR images.…”