Multimodal brain tumor detection and classification using deep saliency map and improved dragonfly optimization algorithm

Abstract

In the last decade, there has been a significant increase in medical cases involving brain tumors. Brain tumor is the tenth most common type of tumor, affecting millions of people. However, if it is detected early, the cure rate can increase. Computer vision researchers are working to develop sophisticated techniques for detecting and classifying brain tumors. MRI scans are primarily used for tumor analysis. We proposed an automated system for brain tumor detection and classification using a saliency map and deep learning feature optimization in this paper. The proposed framework was implemented in stages. In the initial phase of the proposed framework, a fusion‐based contrast enhancement technique is proposed. In the following phase, a tumor segmentation technique based on saliency maps is proposed, which is then mapped on original images based on active contour. Following that, a pre‐trained CNN model named EfficientNetB0 is fine‐tuned and trained in two ways: on enhanced images and on tumor localization images. Deep transfer learning is used to train both models, and features are extracted from the average pooling layer. The deep learning features are then fused using an improved fusion approach known as Entropy Serial Fusion. The best features are chosen in the final step using an improved dragonfly optimization algorithm. Finally, the best features are classified using an extreme learning machine (ELM). The experimental process is conducted on three publically available datasets and achieved an improved accuracy of 95.14, 94.89, and 95.94%, respectively. The comparison with several neural nets shows the improvement of proposed framework.

3D-shape formation of blood vessels based on computer aided design system

“…The aim is to monitor and examine the circulatory system in various parts of the human body such as the heart, brain, and kidneys. 30 In coronary angiography, a catheter is inserted into an artery in the groin, and carefully moved up into the heart and coronary arteries. The fluoroscopy machine produces X-ray images that help the cardiologist to position the catheter.…”

SkinNet‐ENDO: Multiclass skin lesion recognition using deep neural network and Entropy‐Normal distribution optimization algorithm with ELM

“…8,9 The main steps of a CAD system are preprocessing, localization of the lesion area, features extraction, and finally classification. 10,11 In the feature extraction step, the system extracts the different types of features from images such as deep CNN, shape, texture, and color, etc. 12 Then the most relevant features are utilized to classify cancer using different machine learning-based algorithms.…”

“…The CAD models utilize computer vision techniques to diagnose and analyze the disease in medical images 8,9 . The main steps of a CAD system are preprocessing, localization of the lesion area, features extraction, and finally classification 10,11 . In the feature extraction step, the system extracts the different types of features from images such as deep CNN, shape, texture, and color, etc 12 .…”

ETISTP: An Enhanced Model for Brain Tumor Identification and Survival Time Prediction

“…This dataset contains the MRIs of 369 patients represented in 5 different modalities, i.e., t1, t1ce, t2, t2flair, and segmented, as shown in Figure 3 . The integration of data from various modalities is important for achieving higher classification accuracy [ 46 , 47 ]. A t1 modality refers to a 3D-weighted image with axial 2D or sagittal native images with 1–6 millimeter (mm) slice thicknesses.…”