Extraction of region of interest from brain MRI by converting images into neutrosophic domain using the modified S-function

Tufail, Zahid; Raza, Basit; Raza, Basit; Akram, Tahir; Janjua, Uzair Iqbal

doi:10.1117/1.jmi.8.1.014003

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With region of interest extraction, the identification of the region of interest (ROI), which includes the tumor and surrounding brain tissues, was a critical step in the analysis of brain cancer pictures [ 43 ]. Manual or automated segmentation techniques, such as thresholding, active contours (e.g., level sets), or deep-learning-based segmentation models, were utilized to extract the ROI accurately.…”

Section: Methodsmentioning

confidence: 99%

Enhancing Automated Brain Tumor Detection Accuracy Using Artificial Intelligence Approaches for Healthcare Environments

Abdusalomov,

Rakhimov,

Karimberdiyev

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Medical imaging and deep learning models are essential to the early identification and diagnosis of brain cancers, facilitating timely intervention and improving patient outcomes. This research paper investigates the integration of YOLOv5, a state-of-the-art object detection framework, with non-local neural networks (NLNNs) to improve brain tumor detection’s robustness and accuracy. This study begins by curating a comprehensive dataset comprising brain MRI scans from various sources. To facilitate effective fusion, the YOLOv5 and NLNNs, K-means+, and spatial pyramid pooling fast+ (SPPF+) modules are integrated within a unified framework. The brain tumor dataset is used to refine the YOLOv5 model through the application of transfer learning techniques, adapting it specifically to the task of tumor detection. The results indicate that the combination of YOLOv5 and other modules results in enhanced detection capabilities in comparison to the utilization of YOLOv5 exclusively, proving recall rates of 86% and 83% respectively. Moreover, the research explores the interpretability aspect of the combined model. By visualizing the attention maps generated by the NLNNs module, the regions of interest associated with tumor presence are highlighted, aiding in the understanding and validation of the decision-making procedure of the methodology. Additionally, the impact of hyperparameters, such as NLNNs kernel size, fusion strategy, and training data augmentation, is investigated to optimize the performance of the combined model.

show abstract

Section: Methodsmentioning

confidence: 99%

Enhancing Automated Brain Tumor Detection Accuracy Using Artificial Intelligence Approaches for Healthcare Environments

Abdusalomov,

Rakhimov,

Karimberdiyev

et al. 2024

Bioengineering

View full text Add to dashboard Cite

show abstract

“…The NS has been used by various scholars. Zavadskas et al [11] initiated the MULTIMOORA method by using interval-valued NSs; Tan [12] proposed entropy measures using redefined single-valued NSs; Ye [13] investigated entropy measures by using simplified NSs; Abdullah et al [14] developed the DEMATEL method using single-valued NSs; Tufail et al [15] proposed the investigation of brain cancer using NSs on MRI scans; Du et al [16] explored aggregation operators using neutrosophic Z-numbers; Wang et al [17] proposed aggregation operators using single-valued NSs; Wei et al [18] proposed the COPRAS method using single-valued neutrosophic 2-tuple linguistic sets; Jana et al [19] investigated Dombi power aggregation operators using single-valued NSs, and Zhao et al [20] elaborated the TODIM method by using 2-tuple linguistic NSs.…”

Section: Introductionmentioning

confidence: 99%

Dombi-Normalized Weighted Bonferroni Mean Operators with Novel Multiple-Valued Complex Neutrosophic Uncertain Linguistic Sets and Their Application in Decision Making

Mahmood¹,

Ali²,

Prangchumpol³

et al. 2022

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Although fuzzy set concepts have evolved, neutrosophic sets are attracting more attention due to the greater power of the structure of neutrosophic sets. The ability to account for components that are true, false or neither true nor false is useful in the resolution of real-life problems. However, simultaneous variations render neutrosophic sets unsuitable in specific circumstances. To enable the management of these sorts of issues, we combine the principle of multi-valued neutrosophic uncertain linguistic sets and complex fuzzy sets to develop the principle of multivalued complex neutrosophic uncertain linguistic sets. Multi-valued complex neutrosophic uncertain linguistic sets can contain grades of truth, abstinence, and falsity, and uncertain linguistic terms, which are expressed as complex numbers whose real and imaginary parts are limited to the unit interval. Some important Dombi laws are elaborated along with Bonferroni mean operators, which offer a flexible general structure with modifiable factors. Bonferroni means aggregation operators perform a significant role in conveying the magnitude level of options and characteristics. To determine relationships among any number of attributes, we develop multi-valued complex neutrosophic uncertain linguistic Dombi-normalized weighted Bonferroni mean operators and discuss their important properties with some special cases. By using these laws, we can deploy the multi-attribute decisionmaking (MADM) technique using the novel principle of multi-valued complex neutrosophic uncertain linguistic sets. To determine the power and flexibility of the elaborated approach, we resolve some numerical examples based on the proposed operator. Finally, the work is validated with the help of comparative analysis, a discussion of its advantages, and geometric expressions of the elaborated theories. KEYWORDSMulti-valued complex neutrosophic uncertain linguistic sets; Dombi normalized weighted Bonferroni mean operators; multi-attribute decision-making methods

show abstract

The multi-level classification network (MCN) with modified residual U-Net for ischemic stroke lesions segmentation from ATLAS

Alquhayz

Tufail

Raza

2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

Extraction of region of interest from brain MRI by converting images into neutrosophic domain using the modified S-function

Cited by 3 publications

References 10 publications

Enhancing Automated Brain Tumor Detection Accuracy Using Artificial Intelligence Approaches for Healthcare Environments

Enhancing Automated Brain Tumor Detection Accuracy Using Artificial Intelligence Approaches for Healthcare Environments

Dombi-Normalized Weighted Bonferroni Mean Operators with Novel Multiple-Valued Complex Neutrosophic Uncertain Linguistic Sets and Their Application in Decision Making

The multi-level classification network (MCN) with modified residual U-Net for ischemic stroke lesions segmentation from ATLAS

Contact Info

Product

Resources

About