Deep convolutional neural network algorithm for the automatic segmentation of oral potentially malignant disorders and oral cancers

Ünsal, Gürkan; Chaurasia, Akhilanand; Akkaya, Nurullah; Nadler, Chen; Abdalla‐Aslan, Ragda; Koca, Revan Birke; Orhan, Kaan; Roganović, Jelena; Reddy, Prashanti; Wahjuningrum, Dian Agustin

doi:10.1177/09544119231176116

Cited by 3 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image segmentation is one of the image processing operations that causes the separation of different parts of the image and, in fact, separates the lesion from the background [25]. Image segmentation divides the image into meaningful pixel groups for the ease of image analysis and processing and corrects distorted borders.…”

Section: Image Segmentationmentioning

confidence: 99%

An Optimal Hierarchical Approach for Oral Cancer Diagnosis Using Rough Set Theory and an Amended Version of the Competitive Search Algorithm

Song

Ren

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Oral cancer is introduced as the uncontrolled cells’ growth that causes destruction and damage to nearby tissues. This occurs when a sore or lump grows in the mouth that does not disappear. Cancers of the cheeks, lips, floor of the mouth, tongue, sinuses, hard and soft palate, and lungs (throat) are types of this cancer that will be deadly if not detected and cured in the beginning stages. The present study proposes a new pipeline procedure for providing an efficient diagnosis system for oral cancer images. In this procedure, after preprocessing and segmenting the area of interest of the inputted images, the useful characteristics are achieved. Then, some number of useful features are selected, and the others are removed to simplify the method complexity. Finally, the selected features move into a support vector machine (SVM) to classify the images by selected characteristics. The feature selection and classification steps are optimized by an amended version of the competitive search optimizer. The technique is finally implemented on the Oral Cancer (Lips and Tongue) images (OCI) dataset, and its achievements are confirmed by the comparison of it with some other latest techniques, which are weight balancing, a support vector machine, a gray-level co-occurrence matrix (GLCM), the deep method, transfer learning, mobile microscopy, and quadratic discriminant analysis. The simulation results were authenticated by four indicators and indicated the suggested method’s efficiency in relation to the others in diagnosing the oral cancer cases.

show abstract

Section: Image Segmentationmentioning

confidence: 99%

An Optimal Hierarchical Approach for Oral Cancer Diagnosis Using Rough Set Theory and an Amended Version of the Competitive Search Algorithm

Song

Ren

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

Advanced Deep Learning-Based Approach for Tooth Detection, and Dental Cavity and Restoration Segmentation in X-Ray Images

Ghahremani,

Hoseyni,

Ahmadi

et al. 2023

2023 11th RSI International Conference on Robotics and Mechatronics (ICRoM)

View full text Add to dashboard Cite

A survival prediction model based on PCA-HSIDA-LSSVM for patients with esophageal squamous cell carcinoma

Wang,

Xia,

Ling

et al. 2023

Proc Inst Mech Eng H

View full text Add to dashboard Cite

Esophageal squamous cell carcinoma (ESCC) is a type of cancer and has some of the highest rates of both incidence and mortality globally. Developing accurate models for survival prediction provides a basis clinical judgment and decision making, improving the survival status of ESCC patients. Although many predictive models have been developed, there is still lack of highly accurate survival prediction models for ESCC patients. This study proposes a novel survival prediction model for ESCC patients based on principal component analysis (PCA) and least-squares support vector machine (LSSVM) optimized by an improved dragonfly algorithm with hybrid strategy (HSIDA). The original 17 blood indicators are condensed into five new variables by PCA, reducing data dimensionality and redundancy. An improved dragonfly algorithm based on hybrid strategy is proposed, which addresses the limitations of dragonfly algorithm, such as slow convergence, low search accuracy and insufficient vitality of late search. The proposed HSIDA is used to optimize the regularization parameter and kernel parameter of LSSVM, improving the prediction accuracy of the model. The proposed model is validated on the dataset of 400 patients with ESCC in the clinical database of First Affiliated Hospital of Zhengzhou University and the State Key Laboratory of Esophageal Cancer Prevention and Control of Henan Province. The experiment results demonstrate that the proposed HSIDA-LSSVM has the best prediction performance than LSSVM, HSIDA-BP, IPSO-LSSVM, COA-LSSVM and IBA-LSSVM. The proposed model achieves the accuracy of 96.25%, sensitivity of 95.12%, specificity of 97.44%, precision of 97.50%, and F1 score of 96.30%.

show abstract

Deep convolutional neural network algorithm for the automatic segmentation of oral potentially malignant disorders and oral cancers

Cited by 3 publications

References 42 publications

An Optimal Hierarchical Approach for Oral Cancer Diagnosis Using Rough Set Theory and an Amended Version of the Competitive Search Algorithm

An Optimal Hierarchical Approach for Oral Cancer Diagnosis Using Rough Set Theory and an Amended Version of the Competitive Search Algorithm

Advanced Deep Learning-Based Approach for Tooth Detection, and Dental Cavity and Restoration Segmentation in X-Ray Images

A survival prediction model based on PCA-HSIDA-LSSVM for patients with esophageal squamous cell carcinoma

Contact Info

Product

Resources

About