Histopathological Image Analysis for Oral Cancer Classification by Support Vector Machine

Bakare, Yohannes Bekuma; Kumarasamy, M.

doi:10.29284/ijasis.7.2.2021.1-10

Cited by 28 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For object based image investigation, multi label classification is used in [24] for classifying images into several classes using SVM classifier and multi class CNN performed in [25]. Brain tumour is assorted and also multi-class classification is desirable for classifying images into numerous classes such as glioma tumour, meningioma, pituitary and normal.…”

Section: Maximizementioning

confidence: 99%

Multi Class Brain Cancer Prediction System Empowered with BRISK Descriptor

Sahaai¹,

Jothilakshmi²,

Praveen³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Magnetic Resonance Imaging (MRI) is one of the important resources for identifying abnormalities in the human brain. This work proposes an effective Multi-Class Classification (MCC) system using Binary Robust Invariant Scalable Keypoints (BRISK) as texture descriptors for effective classification. At first, the potential Region Of Interests (ROIs) are detected using features from the accelerated segment test algorithm. Then, non-maxima suppression is employed in scale space based on the information in the ROIs. The discriminating power of BRISK is examined using three machine learning classifiers such as k-Nearest Neighbour (kNN), Support Vector Machine (SVM) and Random Forest (RF). An MCC system is developed which classifies the MRI images into normal, glioma, meningioma and pituitary. A total of 3264 MRI brain images are employed in this study to evaluate the proposed MCC system. Results show that the average accuracy of the proposed MCC-RF based system is 99.62% with a sensitivity of 99.16% and specificity of 99.75%. The average accuracy of the MCC-kNN system is 93.65% and 97.59% by the MCC-SVM based system.

show abstract

Section: Maximizementioning

confidence: 99%

Multi Class Brain Cancer Prediction System Empowered with BRISK Descriptor

Sahaai¹,

Jothilakshmi²,

Praveen³

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…The SVM classification [15] has emerged as a prominent technique in CAD, particularly when used in conjunction with the medical image diagnostic. SVM is a supervised machine learning method for classification, which means that it learns about the classes from the dataset.…”

Section: 3svmmentioning

confidence: 99%

Prediction of kidney disease using machine learning algorithms

Ravindra¹,

Haile²,

Haile³

et al. 2023

View full text Add to dashboard Cite

The loss of renal function occurs gradually in diabetic kidney disease (DKD), which is associated with a high death rate. India is second only to China in the number of people living with DKD and it is expected that one million new cases arise in India each year. If diagnosed at an early stage, DKD may be effectively treated. DKD is more dangerous since it often has no early warning signs in its infancy. From a healthcare provider's standpoint, it is crucial to take preventative measures by using a machine-first model to foresee the beginning of DKD. The likelihood that a patient may acquire DKD can be estimated using their health records, and there are open source machine learning methods available to do this. The amount of clinical factors and the number of datasets used to train the algorithm both affect the prediction accuracy. A machine learning method and a booster algorithm were used in this work to increase the accuracy of DKD prediction. The strategy utilized in boosting algorithm produced more reliable outcomes than models used without boosting such as random tree, KNN and support vector machine.

show abstract

“…In general, the confusion matrix, receiver operating characteristic (ROC) curves, the area under the ROC curve (AUC), classification accuracy, precision and sensitivity were used to assess the effectiveness of classifier models. In this work as well, we employed the same performance metrics listed in equations ( 8) to (10). A confusion matrix of size 2 × 2 can be used because the classification of oral cancer is a binary classification problem.…”

Section: Assessment Of Classification Schemesmentioning

confidence: 99%

“…The performance metrics such as accuracy, precision and sensitivity of the proposed algorithm is compared with six other previously reported algorithms [10] 7. Table shows that the proposed method, ResNet 50 with voting classifier outperforms the other eight algorithms in accuracy and precision for OSCC detection.…”

Section: Comparison With Existing Algorithmsmentioning

confidence: 99%

“…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]. However, as the number of layers of the network increases, the complexity also will increase.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Histopathological Image Analysis for Oral Cancer Classification by Support Vector Machine

Cited by 28 publications

References 13 publications

Multi Class Brain Cancer Prediction System Empowered with BRISK Descriptor

Multi Class Brain Cancer Prediction System Empowered with BRISK Descriptor

Prediction of kidney disease using machine learning algorithms

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

Contact Info

Product

Resources

About