Hyperparameter Tuning Bidirectional Gated Recurrent Unit Model for Oral Cancer Classification

Shankar, K.; Lydia, E. Laxmi; Kumar, Sachin; Abosinne, Ali S.; Alkhayyat, Ahmed; Abbas, A. H.; Mahmood, Sarmad Nozad

doi:10.32604/cmc.2022.031247

Cited by 3 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Textural characteristics were extracted from the images as well by converting them to the Gray Level Co-Occurrence Matrix (GLCM) [13] and the Local Binary Pattern (LBP) [14] because the GLCM determines an image's texture by determining how frequently pairs of pixels with specific values and spatial relationships appear in the image [15] and the local spatial patterns and the contrast in the grey scale in an image are effectively captured by LBP descriptors [16]. With the most recent advancements in machine learning, numerous deep learning-based techniques, including convolutional neural network (CNN), pre-trained deep CNN networks [17], like Alexnet, VGG 16, VGG 19, ResNet 50 [18], MobileNet [19], multimodal fusion with CoaT (coat-lite-small), PiT (pooling based vision transformer pits-distilled-224), ViT (vision transformer small-patch16-384), ResNetV2 and ResNetY [20], and concatenated models of VGG 16, Inception V3 [21], have been proposed for the automated extraction of morphological features. After the feature extraction, the images were classified into normal and OSCC categories using different classifiers such as random forest [22], support vector machine (SVM) [10], extreme gradient boosting (XGBoost) with binary particle swarm optimization (BPSO) feature selection [23], K nearest neighbor (KNN) [10], duck patch optimization based deep learning method [24] and two pretrained models, ResNet 50 and DenseNet 201 [11].…”

Section: Introductionmentioning

confidence: 99%

An image patch selection algorithm for the detection of Oral Squamous Cell Carcinoma using textural and morphological features

Subhija

Reju

2023

Preprint

View full text Add to dashboard Cite

A significant proportion of cancer-related deaths are caused by oral cancer, and oral squamous cell carcinoma is prevalent. Systems for computer-aided diagnosis can lower subjective errors and assist the pathologist in making a more accurate diagnosis. Feature extraction from the whole histopathology images is difficult due to the structural variation of the oral tissue images. A new patch selection algorithm can be used to create and select image patches containing nuclei-specific information and extract their textural and morphological characteristics, improving cancer diagnosis. We extract the morphological characteristics of the nucleus from the selected patches using five pretrained networks. The texture from the regions of the selected patches is also extracted from the Haar wavelet decomposed components using the gray-level co-occurrence matrix. Then, we combine the textural and morphological features to create the final feature vector, followed by feature selection using an extra trees classifier. In order to detect oral squamous cell carcinoma, we examined the feasibility of using six classifiers, including voting classifier, logistic regression, random forest, Naive Bayes, K nearest neighbor, and support vector machine. The performance of the algorithm is evaluated using accuracy, precision, sensitivity, confusion matrix, ROC curves, and AUC values of characteristic curves. Together, ResNet 50 and the voting classifier produce results with a high accuracy of 97.66 % and a precision of 98.00 %. The suggested patch-based method outperforms the image based method and is accurate and efficient for identifying oral squamous cell carcinoma and will be a reliable and precise support tool for oral pathologists.

show abstract

Section: Introductionmentioning

confidence: 99%

An image patch selection algorithm for the detection of Oral Squamous Cell Carcinoma using textural and morphological features

Subhija

Reju

2023

Preprint

View full text Add to dashboard Cite

show abstract

Deep Learning‐Based Image Classification and Segmentation on Digital Histopathology for Oral Squamous Cell Carcinoma: A Systematic Review and Meta‐Analysis

Pirayesh,

Mohammad‐Rahimi,

Ghasemi

et al. 2024

J Oral Pathology Medicine

View full text Add to dashboard Cite

BackgroundArtificial intelligence (AI)‐based tools have shown promise in histopathology image analysis in improving the accuracy of oral squamous cell carcinoma (OSCC) detection with intent to reduce human error.ObjectivesThis systematic review and meta‐analysis evaluated deep learning (DL) models for OSCC detection on histopathology images by assessing common diagnostic performance evaluation metrics for AI‐based medical image analysis studies.MethodsDiagnostic accuracy studies that used DL models for the analysis of histopathological images of OSCC compared to the reference standard were analyzed. Six databases (PubMed, Google Scholar, Scopus, Embase, ArXiv, and IEEE) were screened for publications without any time limitation. The QUADAS‐2 tool was utilized to assess quality. The meta‐analyses included only studies that reported true positives (TP), true negatives (TN), false positives (FP), and false negatives (FN) in their test sets.ResultsOf 1267 screened studies, 17 studies met the final inclusion criteria. DL methods such as image classification (n = 11) and segmentation (n = 3) were used, and some studies used combined methods (n = 3). On QUADAS‐2 assessment, only three studies had a low risk of bias across all applicability domains. For segmentation studies, 0.97 was reported for accuracy, 0.97 for sensitivity, 0.98 for specificity, and 0.92 for Dice. For classification studies, accuracy was reported as 0.99, sensitivity 0.99, specificity 1.0, Dice 0.95, F1 score 0.98, and AUC 0.99. Meta‐analysis showed pooled estimates of 0.98 sensitivity and 0.93 specificity.ConclusionApplication of AI‐based classification and segmentation methods on image analysis represents a fundamental shift in digital pathology. DL approaches demonstrated significantly high accuracy for OSCC detection on histopathology, comparable to that of human experts in some studies. Although AI‐based models cannot replace a well‐trained pathologist, they can assist through improving the objectivity and repeatability of the diagnosis while reducing variability and human error as a consequence of pathologist burnout.

show abstract

Efficient, Lightweight Cyber Intrusion Detection System for IoT Ecosystems Using MI2G Algorithm

Kaushik¹,

Bhardwaj

Alomari

et al. 2022

Computers

View full text Add to dashboard Cite

The increase in internet connectivity has led to an increased usage of the Internet of Things (IoT) and devices on the internet. These IoT devices are becoming the backbone of Industry 4.0. The dependence on IoT devices has made them vulnerable to cyber-attacks. IoT devices are often deployed in harsh conditions, challenged with less computational costs, and starved with energy. All these limitations make it tough to deploy accurate intrusion detection systems (IDSs) in IoT devices and make the critical IoT ecosystem more susceptible to cyber-attacks. A new lightweight IDS and a novel feature selection algorithm are introduced in this paper to overcome the challenges of computational cost and accuracy. The proposed algorithm is based on the Information Theory models to select the feature with high statistical dependence and entropy reduction in the dataset. This feature selection algorithm also showed an increase in performance parameters and a reduction in training time of 27–63% with different classifiers. The proposed IDS with the algorithm showed accuracy, Precision, Recall, and F1-Score of more than 99% when tested with the CICIDS2018 dataset. The proposed IDS is competitive in accuracy, Precision, Recall, and training time compared to the latest published research. The proposed IDS showed consistent performance on the UNSWNB15 dataset.

show abstract

Hyperparameter Tuning Bidirectional Gated Recurrent Unit Model for Oral Cancer Classification

Cited by 3 publications

References 20 publications

An image patch selection algorithm for the detection of Oral Squamous Cell Carcinoma using textural and morphological features

An image patch selection algorithm for the detection of Oral Squamous Cell Carcinoma using textural and morphological features

Deep Learning‐Based Image Classification and Segmentation on Digital Histopathology for Oral Squamous Cell Carcinoma: A Systematic Review and Meta‐Analysis

Efficient, Lightweight Cyber Intrusion Detection System for IoT Ecosystems Using MI2G Algorithm

Contact Info

Product

Resources

About