The proposition of Possibilistic sigmoid features and the Shannon-Hanman transform classifier along with the pervasive learning model for the classification of brain tumor using MRI

Asthana, Pallavi; Hanmandlu, M.; Vashisth, Sharda

doi:10.1007/s11042-022-12482-2

Cited by 2 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have implemented the proposed architecture as illustrated in Table 5.1 and as per the algorithm presented in section 3.3.3 by collecting the FBID dataset. 5.1 which classifies the difference between OptimizedResNet50 and ResNet50 [18].. In OptimizedResNet50 epoch 27,28 and 30 accuracy has exceeded 100, hence we must not consider these results for the study but we are considering the validation accuracy as the measure.…”

Section: Resultsmentioning

confidence: 99%

“…Each image in the dataset has annotations describing the sort of scan used to obtain it and any pertinent clinical data [17]. This dataset is helpful for scientists researching the anatomy and pathology of the brain and for doctors who need to identify and treat neurological illnesses [18]. A total of 233 patients diagnosed with three distinct types of brain tumors, namely meningiomas (708 slices), gliomas (1426 slices), and pituitary tumors, were included in the study [19].…”

Section: Related Work Some Of the Notable Research Published In This ...mentioning

confidence: 99%

See 1 more Smart Citation

Optimised ResNet50 for Multi-Class Classification of Brain Tumors

Maloji

2024

SCPE

View full text Add to dashboard Cite

Categorizing brain cancers, including glioma, meningioma, and pituitary tumors, based on magnetic resonance imaging (MRI) images presents a significant challenge. Deep learning and machine learning techniques have shown promise in enhancing image categorization. To address this challenge, we leverage the power of the optimized ResNet50 model. Our approach involves classifying medical images using Convolutional Neural Network (CNN) features, which are then compared with the ResNet50 model. The primary goal is to detect brain tumors at an early stage using an advanced deep-learning model. We utilize an accessible dataset from Figshare, containing MRI images of the three distinct categories of brain tumors. Existing brain tumor models face limitations in handling multi-class problems and early-stage diagnosis. Therefore, we propose a fully automated approach employing Convolutional Neural Networks (CNN) to extract diverse properties from brain MRI scans. This method aims to provide accurate tumor diagnosis, even with a high number of classes and limited information in MRI data. Our proposed model involves the creation of identification blocks within a four-layered primary architecture, followed by testing and assessment of the interconnected layers. The results demonstrate that our model outperforms existing methods, achieving an impressive overall classification accuracy of 99.03%,

show abstract

Section: Resultsmentioning

confidence: 99%