Cancerous brain tumor detection using hybrid deep learning framework

Tidke, Sonali Kothari; Chiwhane, Shwetambari; Jain, Shruti; Baghel, Malti

doi:10.11591/ijeecs.v26.i3.pp1651-1661

Cited by 8 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluation metrics include the mean intersection over union (IoU) and the accuracy of the pneumothorax segmentation. The mean IoU measures the overlap between the predicted and ground-truth pneumothorax masks, while the accuracy measures the percentage of correctly predicted pixels in the pneumothorax region [12] , [13] , [14] , [15] .…”

Section: Methodsmentioning

confidence: 99%

Data mining approaches to pneumothorax detection: Integrating mask-RCNN and medical transfer learning techniques

Chiwhane,

Shrotriya,

Dhumane

et al. 2024

MethodsX

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Data mining approaches to pneumothorax detection: Integrating mask-RCNN and medical transfer learning techniques

Chiwhane,

Shrotriya,

Dhumane

et al. 2024

MethodsX

Self Cite

View full text Add to dashboard Cite

“…Greater rates of misclassification might be the result of the extraction of duplicate features. The deep features from CNN classifiers [11] are therefore extracted in this work. By utilizing backpropagation to obtain the essential characteristics, deep learning models simplify the laborious process of using hand-crafted features.…”

Section: Deep Feature Extractionmentioning

confidence: 99%

“…The pack's grey wolves of the, are more knowledgeable about the location of potential prey. The first three top solutions are therefore preserved, which places stress on the remaining search agents to change their rankings to match the top three as per the equations given from ( 5) to (11):…”

Section: Optimal Feature Selectionmentioning

confidence: 99%

An optimal model for classification of lung cancer using grey wolf optimizer and deep hybrid learning

Mothkur

Nagendrappa

2023

IJEECS

View full text Add to dashboard Cite

In recent years, metaheuristic methods have shown major advantages in the field of feature selection due to its comprehensibility and possible extensive search competence. However, the majority of evolutionary computation-based feature selection algorithms in use today are wrapper approaches, which are expensive to compute, particularly for extensive biomedical data. Developing an effective evaluation strategy is crucial for significant reduction of computational cost. The proposed framework extracts deep feature from ResNet-50 and VGG-16 based convolutional neural models with initial segmentation process based on marker-controlled watershed method. Next the feature reduction is a two-fold approach with principal component analysis applied to reduce the dimensionality of large feature space from convolutional neural network (CNN) models as first step. The second step is optimal feature subset selection using a swarm intelligence method referred as modified grey wolf optimization. Finally, the selected feature subset is fed to various machine learning classifiers. The experimental result reveals that the proposed algorithm outperforms the other state-of-the-art methods with classification accuracy of 96.56%, thus upholding the dependability of the approach.

show abstract

“…This method has been an active research area due to the reliability of its performance in a wide range of applications [1], [2]. HSI has aided researchers in the detection of cancer [3], agricultural [4], [5], and military equipment [6]. Researchers have looked towards HSI as a potential tool to solve the environmental problem due to the exponential growth of plastic waste around the world.…”

Section: Introductionmentioning

confidence: 99%

A review of hyperspectral imaging-based plastic waste detection state-of-the-arts

Tamin

Moung

Dargham

et al. 2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Plastic waste issues emerged from the build-up of plastics that negatively impacts the environment. As a result, plastic waste detection is proposed in many research studies to tackle the problems. Therefore, this paper aims to review hyperspectral imaging techniques and machine learning in plastic waste detection. Hyperspectral imaging techniques are found to be effective in detecting plastic waste and microplastics as they were able to capture plastic reflectance spectral by using the near-infrared sensor. However, the review also shows that hyperspectral imaging techniques were less efficient in capturing the electromagnetic spectrum of black plastics due to carbon-black absorption properties. Carbon-black strongly absorbs light in the ultraviolet and infrared spectral range of the electromagnetic spectrum, therefore not detected by the near-infrared sensor. This paper also reviews how machine learning can alternatively detect and sort all types of waste, including plastics. Multiple studies show that the machine learning model achieved good accuracy in detecting all types of plastics based on the waste dataset. Finally, it can be seen that the spectral information of plastic can be used as feature extraction for machine learning models for better plastic detection. It is hoped that this study will contribute to more systematic research on the same topic.</span>

show abstract

Cancerous brain tumor detection using hybrid deep learning framework

Cited by 8 publications

References 23 publications

Data mining approaches to pneumothorax detection: Integrating mask-RCNN and medical transfer learning techniques

Data mining approaches to pneumothorax detection: Integrating mask-RCNN and medical transfer learning techniques

An optimal model for classification of lung cancer using grey wolf optimizer and deep hybrid learning

A review of hyperspectral imaging-based plastic waste detection state-of-the-arts

Contact Info

Product

Resources

About