Brain tumor detection and classification using machine learning: a comprehensive survey

Amin, Javeria; Sharif, Muhammad; Haldorai, Anandakumar; Yasmin, Mussarat; Nayak, Ramesh Sundar

doi:10.1007/s40747-021-00563-y

Cited by 131 publications

(48 citation statements)

References 235 publications

(126 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accelerated Particle Swarm Optimization. Segmentation is a significant process in the tumor detection process that segregates the input image into several regions overlapping each other [29]. It is used to define the object boundaries effectively and the segmented parts are combined to get the full image.…”

Section: 2mentioning

confidence: 99%

Improved Machine Learning Method for Intracranial Tumor Detection with Accelerated Particle Swarm Optimization

Pradeep¹,

Gangadharan

Hatamleh

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The field of image processing is distinguished by the variety of functions it offers and the wide range of applications it has in biomedical imaging. It becomes a difficult and time-consuming process for radiologists to do the manual identification and categorization of the tumour. It is a complex and time-consuming procedure conducted by radiologists or clinical professionals to remove the contaminated tumour region from magnetic resonance (MR) pictures. It is the goal of this study to improve the performance and reduce the complexity of the image segmentation process by investigating FCM predicted image segmentation procedures in order to reduce the intricacy of the process. Furthermore, relevant characteristics are collected from each segmented tissue and aligned as input to the classifiers for autonomous identification and relegation of encephalon cancers in order to increase the accuracy and quality rate of the neural network classifier. An evaluation, validation, and presentation of the experimental performance of the suggested approach have been completed. A unique APSO (accelerated particle swarm optimization) based artificial neural network model (ANNM) for the relegation of benign and malignant tumours is presented in this study effort, which allows for the automated identification and categorization of brain tumours. Using APSO training to improve the suggested ANNM model parameters would give a unique method to alleviate the stressful work of radiologists performing manual identification of encephalon cancers from MR images. The use of an APSO-based ANNM (artificial neural network model) model for automated brain tumour classification has been presented in order to demonstrate the resilience of the classification model. It has been suggested to utilise the improved enhanced fuzzy c means (IEnFCM) method for image segmentation, while the GLCM (gray level co-occurrence matrix) feature extraction approach has been employed for feature extraction from magnetic resonance imaging (MR pictures).

show abstract

Section: 2mentioning

confidence: 99%

Improved Machine Learning Method for Intracranial Tumor Detection with Accelerated Particle Swarm Optimization

Pradeep¹,

Gangadharan

Hatamleh

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…The algorithm then converges to false detection when the background and target have a color attribute that is similar to one another. These flaws are the consequences of using a simpler color histogram model to define the goal in the first place [ 16 ]. The tracking of the mean shift is based on the measure of similarity between two locations (Rubner et al 2001) [ 17 ].…”

Section: Literature Surveymentioning

confidence: 99%

Intelligent Wearable Devices Enabled Automatic Vehicle Detection and Tracking System with Video-Enabled UAV Networks Using Deep Convolutional Neural Network and IoT Surveillance

Jayasudha

Dadheech

Prasad³

et al. 2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The discipline of computer vision is becoming more popular as a research subject. In a surveillance-based computer vision application, item identification and tracking are the core procedures. They consist of segmenting and tracking an object of interest from a sequence of video frames, and they are both performed using computer vision algorithms. In situations when the camera is fixed and the backdrop remains constant, it is possible to detect items in the background using more straightforward methods. Aerial surveillance, on the other hand, is characterized by the fact that the target, as well as the background and video camera, are all constantly moving. It is feasible to recognize targets in the video data captured by an unmanned aerial vehicle (UAV) using the mean shift tracking technique in combination with a deep convolutional neural network (DCNN). It is critical that the target detection algorithm maintains its accuracy even in the presence of changing lighting conditions, dynamic clutter, and changes in the scene environment. Even though there are several approaches for identifying moving objects in the video, background reduction is the one that is most often used. An adaptive background model is used to create a mean shift tracking technique, which is shown and implemented in this work. In this situation, the background model is provided and updated frame-by-frame, and therefore, the problem of occlusion is fully eliminated from the equation. The target tracking algorithm is fed the same video stream that was used for the target identification algorithm to work with. In MATLAB, the works are simulated, and their performance is evaluated using image-based and video-based metrics to establish how well they operate in the real world.

show abstract

“…The phrase “number of dead nodes per unit time,” in this context, refers to b . the prompt largeness [ 21 ] of the count of protuberances that have depleted their battery resources and are thus no longer capable of communication with the base station.…”

Section: Proposed Energy Protocol With Blockchainmentioning

confidence: 99%

Smart Healthcare System with Light-Weighted Blockchain System and Deep Learning Techniques

Singh

Mir

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

A radio communication sensor system is a collection of sensor modules that are connected to one another through wireless communication. It is common for them to be battery-powered and responsive to a nearby controller, referred to as the base station. They are capable of doing basic computations and transferring information to the base station in most scenarios. They are also in charge of transporting data from distant nodes, putting a burden on nodes with limited resources, and contributing to the quick depletion of energy in these nodes in the process. Nodes in close proximity to the base station are responsible for more than only detecting and sending data to the base station; they are also responsible for transmitting data from faraway nodes. To reward nodes that perform well, a protocol known as the Improved Fuzzy Inspired Energy Effective Protocol (IFIEEP) employs three separate sorts of nodes in order to provide more energy to those who do not. It takes into account the remaining node energy, the node's proximity to the base station, the node's neighbor concentration, and the node's centrality in a cluster when determining node viability. All of these assumptions are founded on a shaky understanding of the situation. Adaptive clustering must be applied to the most viable nodes in order to identify cluster leaders and transmit data to the base station, in addition to disseminating data across the rest of the network, in order to achieve success. In addition, the research provides proper heterogeneity parameters, which describe, among other things, the number of nodes as well as the starting energy of each node. The percentage gain in-network lifetime when compared to current approaches is minor for smaller numbers of supernodes; however, the percentage gain in the area covered 12.89 percent and 100% when more significant numbers of super nodes are used. These improvements in stability, residual energy, and throughput are accomplished by combining these improvements while also taking into consideration the previously neglected energy-intensive sensing energy aspect. The protocol that has been presented is meant to be used in conjunction with applications that make use of blockchain technology.

show abstract

Brain tumor detection and classification using machine learning: a comprehensive survey

Cited by 131 publications

References 235 publications

Improved Machine Learning Method for Intracranial Tumor Detection with Accelerated Particle Swarm Optimization

Improved Machine Learning Method for Intracranial Tumor Detection with Accelerated Particle Swarm Optimization

Intelligent Wearable Devices Enabled Automatic Vehicle Detection and Tracking System with Video-Enabled UAV Networks Using Deep Convolutional Neural Network and IoT Surveillance

Smart Healthcare System with Light-Weighted Blockchain System and Deep Learning Techniques

Contact Info

Product

Resources

About