An Unsupervised Learning with Feature Approach for Brain Tumor Segmentation Using Magnetic Resonance Imaging

Ejaz, Khurram; Rahim, Mohd Shafy Mohd; Bajwa, Usama Ijaz; Rana, Nadim; Rehman, Amjad

doi:10.1145/3314367.3314384

Cited by 14 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These kinds of unwanted details or artifacts decrease the quality of the images and decrease the chances of accurate skin lesion detection due to its high similarity between surrounding skin and lesion. Therefore, a preprocessing step is introduced for image quality enhancement by removing unwanted details of noise from the images such as bubbles, hairs etc., if the preprocessing steps are not performed appropriately, there are high chances of inaccurate segmentation and recognition of cancer (Ejaz, Rahim, Rehman, Chaudhry, et al, 2018;Ejaz et al, 2020;Ejaz, Rahim, Bajwa, Rana, & Rehman, 2019;.…”

Section: Preprocessingmentioning

confidence: 99%

Computer vision for microscopic skin cancer diagnosis using handcrafted and non‐handcrafted features

Saba

2021

Microscopy Res & Technique

View full text Add to dashboard Cite

Skin covers the entire body and is the largest organ. Skin cancer is one of the most dreadful cancers that is primarily triggered by sensitivity to ultraviolet rays from the sun. However, the riskiest is melanoma, although it starts in a few different ways.The patient is extremely unaware of recognizing skin malignant growth at the initial stage. Literature is evident that various handcrafted and automatic deep learning features are employed to diagnose skin cancer using the traditional machine and deep learning techniques. The current research presents a comparison of skin cancer diagnosis techniques using handcrafted and non-handcrafted features. Additionally, clinical features such as Menzies method, seven-point detection, asymmetry, border color and diameter, visual textures (GRC), local binary patterns, Gabor filters, random fields of Markov, fractal dimension, and an oriental histography are also explored in the process of skin cancer detection. Several parameters, such as jacquard index, accuracy, dice efficiency, preciseness, sensitivity, and specificity, are compared on benchmark data sets to assess reported techniques. Finally, publicly available skin cancer data sets are described and the remaining issues are highlighted.

show abstract

Section: Preprocessingmentioning

confidence: 99%

Computer vision for microscopic skin cancer diagnosis using handcrafted and non‐handcrafted features

Saba

2021

Microscopy Res & Technique

View full text Add to dashboard Cite

show abstract

“…Method is evaluated with 75 percent of Dice Index [28]. Moreover in another study With a hybrid of FCM and feature, better segmentation is attained where jaccard index is 23 and dice is 34 [29]. Segmentation through modified FCM is improved with combination of bacterial foraging organization.…”

Section: Iirelated Workmentioning

confidence: 99%

Hybrid Segmentation Method With Confidence Region Detection for Tumor Identification

et al. 2021

Self Cite

View full text Add to dashboard Cite

Segmentation methods can mutually exclude the location of the tumor. However, the challenge of complex location or incomplete identification is located in segmentation challenge dataset. Identificationof tumor location is difficult due to the variation of intensities in MRI image. Vairation of intensity extends up to to edema. Confidence Region with Contour Detection identifies the variation of intensities and level set algorithm (Region Scale Fitting) is used to delineate among the region of inner and outer of the tumor. Automatic feature selection method is required due to data complexity. An improved Self Organization Feature Map. Method is required. Weighted SOM Map selects a deterministic feature. This feature is one higher trained accuracy feature. When this specific feature is combines with cluster therefore it is known as deterministic feature clustering. This method gives confidence element.. Confidence Region with Contour detection is facing the issue due to extended variations of intensities. These intensities are segmented by hybrid SOM Pixel Labelling with Reduce Cluster Membership and Deterministic Feature Clustering. This hyhbrid method segments the complex tumor intensities. This method produces a potential cluster which is achieved through the hybrid of three unsupervised learning techniques. Hybrid cluster method segments the tumor region. Extended intensities are also segmented by this hybrid approach. Above methods are validated on MICCAI BraTs brain tumor dataset, this is a segmentation challenge dataset. Proposed hybrid algorithm is efficient and it's accuracy can be seen with testing parameters like Dice Overlap Index, Jaccard Tanimoto Coefficient Index, Mean Squared Error and Peak Signal to Noise Ratio. Dice OverlapIndex is 98%, Jaccard Index is 96 percent, Mean Squared Error is 0.06 and Peak Signal To Noise ratio is 18db. The performance of the suggested algorithm is compared to other state of the art.

show abstract

“…In clinical science, the usage of machine learning methods is a revolution, especially the usage of deep learning algorithms, which have demonstrated some encouraging outcomes. Currently, CNN has motivated experts to identify breast tumour using structural designs like VGG16 (Saba et al, 2020), GoogLeNet (Szegedy et al, 2015), CiFarNet (Roth et al, 2016), and VGG 19 (Ejaz et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Fully‐automatic identification of gynaecological abnormality using a new adaptive frequency filter and histogram of oriented gradients (HOG)

Hussein¹,

Burhanuddin

Mohammed

et al. 2021

Expert Systems

View full text Add to dashboard Cite

Ultrasound imaging (US) is one of the most common diagnostic imaging tools for producing images of the human body in clinical practice. This work is devoted to studying ultrasound images collected from gynaecological tests for medical purposes regarding ovarian and breast defects. The study revolves around (i) Enhancing the texture of the image by applying a new effective framework that can help in reducing the speckle noise from the image while preserving the most important information; (ii) Extracting the most prominent features using the histogram of oriented gradients (HOG) and; (iii) Fusing the features that are produced by the edge operators and using them as an input to the ANN classifier to generate three trained classifiers. The fusion technique has been used to get an effective decision by using the whole features. The experimental results of the proposed method for the breast cancer and ovarian tumour using the second experiment achieved 97.96% accuracy, 96.05% sensitivity, and 99.17% specificity by utilizing the breast cancer information set. Overall, 95.87% precision, 97.01% sensitivity, and 93.33% specificity have been achieved for the ovarian tumour data collection. Consequently, the proposed method has been improved to validate the output of modern computerized and automated technologies. This method analyzes the gynaecological ultrasound images to identify suspicious objects or cases with health consequences for women.

show abstract

An Unsupervised Learning with Feature Approach for Brain Tumor Segmentation Using Magnetic Resonance Imaging

Cited by 14 publications

References 15 publications

Computer vision for microscopic skin cancer diagnosis using handcrafted and non‐handcrafted features

Computer vision for microscopic skin cancer diagnosis using handcrafted and non‐handcrafted features

Hybrid Segmentation Method With Confidence Region Detection for Tumor Identification

Fully‐automatic identification of gynaecological abnormality using a new adaptive frequency filter and histogram of oriented gradients (HOG)

Contact Info

Product

Resources

About