GAUSSIAN WEIGHTED DEEP CNN WITH LSTM FOR BRAIN TUMOR DETECTION

Brain tumors are recognized as severe illnesses wherein the precision of images plays a crucial role. Accurately identifying tumors is essential for precisely pinpointing the affected area and thereby reducing the mortality rate. Consequently, understanding the hidden patterns becomes imperative for an improved diagnosis and image quality. However, achieving accurate diagnoses across various lesion cases poses a significant challenge. To address the limitations of existing methods, we introduce the Gaussian Weighted Deep Convolutional Neural Network with LSTM (GWDeepCNN-LSTM) for the automatic detection of brain tumor patients from their tumor images. The GWDeepCNN-LSTM technique comprises multiple layers. Initially, brain MR images are retrieved from the designated database, and image preprocessing is carried out using a Gaussian weighted non-local mean filter to eliminate noisy pixels. Subsequently, segmentation is implemented using Hartigan's segmentation method to partition the image into similar regions. Following segmentation, feature extraction is conducted to extract more informative features, including texture, color, and intensity, from the segmented image. Finally, the classification of brain MR images is accomplished through Long Short-Term Memory (LSTM). This classification process enables the identification of the input image as normal or tumor with higher accuracy. Notably, GWDeepCNN-LSTM demonstrates superior performance in disease detection accuracy while minimizing the time and error rate. Keywords: Brain tumor, Convolutional Neural Network (CNN), LSTM, RNN.