Robust Magnification Independent Colon Biopsy Grading System over Multiple Data Sources

Babu, Tina; Gupta, Deepa; Singh, Tripty; Hameed, Shahin; Zakariah, Mohammed; Alotaibi, Yousef Ajami

doi:10.32604/cmc.2021.016341

Cited by 25 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bayesian Network is known as Belief Network and is the Artificial Intelligence framework for uncertainty supervision, which is a contrast to the deterministic approach to understand phenomena [16]. Although it was published in 1763, the techniques applied in health management and medicine decision-support systems are quite recent; colon biopsy [17] was recently used in the mortality classification of COVID-19 patients [18]. Thus, the gaps discussed previously can be resolved using Bayesian theorem.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The third factor is the predictive model used by Weaver, which is based on naïve Bayes analysis method to model scanning behavior of Conficker Botnet in large Internet Service Provider (ISP) network. However, studies by [17] stated that the use of the Bayesian Network method may improve the result of prediction. Thus, this research is to extend the previous works in [8] which has established the Feature Selection Model.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Behavioral Intrusion Prediction Model on Bayesian Network over Healthcare Infrastructure

Yusof¹,

Zin²,

Satar³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Due to polymorphic nature of malware attack, a signature-based analysis is no longer sufficient to solve polymorphic and stealth nature of malware attacks. On the other hand, state-of-the-art methods like deep learning require labelled dataset as a target to train a supervised model. This is unlikely to be the case in production network as the dataset is unstructured and has no label. Hence an unsupervised learning is recommended. Behavioral study is one of the techniques to elicit traffic pattern. However, studies have shown that existing behavioral intrusion detection model had a few issues which had been parameterized into its common characteristics, namely lack of prior information (p (θ)), and reduced parameters (θ). Therefore, this study aims to utilize the previously built Feature Selection Model subsequently to design a Predictive Analytics Model based on Bayesian Network used to improve the analysis prediction. Feature Selection Model is used to learn significant label as a target and Bayesian Network is a sophisticated probabilistic approach to predict intrusion. Finally, the results are extended to evaluate detection, accuracy and false alarm rate of the model against the subject matter expert model, Support Vector Machine (SVM), k nearest neighbor (k-NN) using simulated and ground-truth dataset. The ground-truth dataset from the production traffic of one of the largest healthcare provider in Malaysia is used to promote realism on the real use case scenario. Results have shown that the proposed model consistently outperformed other models.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Behavioral Intrusion Prediction Model on Bayesian Network over Healthcare Infrastructure

Yusof¹,

Zin²,

Satar³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…The CNN prototype is frequently used for image categorization and study, especially for the study of healthcare image data, and has recently gained favour for the diagnosis of brain cancer using image data [8,9]. The CNNs technique will retrieve increasingly closely related characteristics from the data for accurate picture classification [10].…”

Section: Introductionmentioning

confidence: 99%

Brain Tumor classification using BrainNet: A Deep Learning Approach

Wagh

Bhosale

Singh

et al. 2023

Preprint

View full text Add to dashboard Cite

Cancers of any type are life-threatening diseases and totally hamper normal body functions. One of the leading causes of death in both adults and children is malignant brain tumors. Asa result, detecting brain tumors in their early stages is critical for accurate diagnosis. Magnetic resonance imaging (MRI) is commonly used to diagnose brain tumors. Brain tumors are complex due to extremely erratic shapes and locations and are challenging to fully understand the nature of the tumor. For MRI analysis, a skilled neurosurgeon is also required. Because there are frequently insufficient highly trained medical experts and a general lack of knowledge about tumors in developing countries, obtaining results from MRIs can be extremely difficult and time-consuming. To overcome this drawback of this, proposed a novel Convolution Neural Network(CNN)with BrainNet for the multiclass classification of tumors. The proposed BrianNet performs better than transfer learning models VGG13, VGG16, VGG19, Squeeznet, and InceptionResV2 which are pre-trained on the Imagenet dataset. The proposed CNN (BrainNet) architecture achieved a training accuracy of 99.96% and test accuracy of 97.71% and an average precision of 94.75%. Medical professionals can classify tumours with the aid of the proposed work.

show abstract

“…Research on image fusion of multiple medical image modalities often motivates a lot of consideration with the increased standards for the medical procedure. Owing to the development of different sensors in the medical field, numerous Multi-sensor clinical images are essential for medical interpretation and diagnostic purposes [1][2] [3]. Such images are either interactive or anatomical.…”

Section: Introductionmentioning

confidence: 99%

Multiresolution approach on Medical Image Fusion by Modified Local Energy

Nair

Babu

2022

Preprint

View full text Add to dashboard Cite

Human and machine perception data that are not redundant are very important in the medical field for diagnosis and treatment. The proposed work fuses medical images to extract valuable necessary information from dissimilar images to a single image in the Wavelet domain using a novel Modified Local Energy(MLE) fusion rule termed ModifiedLocal Energy Image Fusion(MLEIF). The image edges are essential information points that are used to display a clear visual image structure. Modified Local energy helps to provide edge characteristics more clearly in the fusion outcome than a single pixel-based fusion rule. The denoising property of the local energy is the additional advantage of the proposed fusion. The similarity of the fused image with the source images is improved by B-Spline registration in the pre-processing stage. Finally, the fused image is created with all the corresponding coefficients by transforming the inverse wavelet. SVM-based contouring of the lesion part helps observes to identify the lesion part from the fused image. Carried out experiments on real-time and standard data sets with expert radiologist subjective evaluation and quantitative analysis by well-known non-reference performance measures.

show abstract

Robust Magnification Independent Colon Biopsy Grading System over Multiple Data Sources

Cited by 25 publications

References 45 publications

Behavioral Intrusion Prediction Model on Bayesian Network over Healthcare Infrastructure

Behavioral Intrusion Prediction Model on Bayesian Network over Healthcare Infrastructure

Brain Tumor classification using BrainNet: A Deep Learning Approach

Multiresolution approach on Medical Image Fusion by Modified Local Energy

Contact Info

Product

Resources

About