An Image Recognition Framework for Oral Cancer Cells

Zhang, Hao; Li, Wei; Zhang, Hanzhong

doi:10.1155/2021/2449128

Cited by 6 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note that one will need to adjust the range of each pixel in the input image. The program will be using the recently introduced high-resolution representation learning network (HRNet), which is pretrained on the ImageNet (Deng et al 2009;Zhang et al 2021) and then with transfer learning from the ImageNet and obtained dataset, the input is analyzed to output the probabilities of each the 5 classes. Finally, the result will be based on the class with the highest probability.…”

Section: Methodsmentioning

confidence: 99%

A low-cost Point-of-Care Diagnostic for Premature Oral Cancer Screening

Bhirud¹

2022

Preprint

View full text Add to dashboard Cite

Oral cancer is a cancerous growth in the oral cavity. More than 90% of all oral cancers are squamous cell carcinoma. Oral squamous cell carcinoma has the highest mortality ratio compared to other carcinomas. The high mortality rate is mainly due to detection of the cancer in an advanced stage on account of its initial asymptomatic nature. In addition, the methods currently in place for oral cancer detection involve expensive complex laboratory procedures and usually longer wait times for patients leading to late diagnosis. Further, the treatments for advanced staged cancers are costly and less effective in terms of the post-treatment survival rates. Thus, society needs an easy-to-use tool for assessing oral cancers at an early stage. The aim of the project is to develop an easily accessible point-of-care kit which will assist in early detection of oral cancer at a low cost. The kit will consist of a complete home-based test which could be easily operated by vulnerable individuals. The test will be based on the patient’s salivary sample and to obtain an oral cancer risk-analysis with detailed statistics on an app. Furthermore, the app will also feature a digital pathology test for an analysis of potential malignancies based on image(s) of the oral cavity. The chemical aspect of the tool will be based on a thermal reaction of formulated Thiobarbituric Acid reagent along with a spectroscopy sensor. The app will be connected to the sensor via Bluetooth and the image screening will be based on deep learning using deep convolutional neural network.

show abstract

Section: Methodsmentioning

confidence: 99%

A low-cost Point-of-Care Diagnostic for Premature Oral Cancer Screening

Bhirud¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In our study, the ROI of the images were resized to 512 X 512 pixels. The program then used recently introduced highresolution representation learning network (HRNet), which is pretrained on the ImageNet (Deng et al 2009;Zhang et al 2021). Then with transfer learning from the ImageNet and obtained dataset, the input was analyzed to output the probabilities of each the 5 classes.…”

Section: Image Testmentioning

confidence: 99%

QuickDiag: A low cost oral cancer detection kit

Bhirud¹,

Rane²

2022

Preprint

View full text Add to dashboard Cite

Significance: Oral cancer is a cancerous growth in the oral cavity. More than 90% of all oral cancers are squamous cell carcinoma. Oral squamous cell carcinoma has the highest mortality ratio compared to other carcinomas. The high mortality rate is mainly due to detection of the cancer in an advanced stage on account of its initial asymptomatic nature. In addition, the methods currently in place for oral cancer detection involve expensive complex laboratory procedures and usually longer wait times for patients leading to late diagnosis. Further, the treatments for advanced staged cancers are costly and less effective in terms of the posttreatment survival rates. Thus, society needs an easy-to-use tool for assessing oral cancers at an early stage. Aim: The aim of the project is to develop an easily accessible multi-step point of-care kit which will assist in early detection of oral cancer at a low cost in vulnerable population. Approach: The kit developed consisted of a complete and easy to operate home-based test. The test was based on the patient’s salivary and photo sample to obtain an oral cancer risk-analysis with detailed statistics on a custom developed app. These results were based on a thermal reaction of a formulated Thiobarbituric Acid reagent along with a spectroscopy sensor connected to a smartphone to determine oral cancer risk based on malondialdehyde (MDA) concentration, which is a product of the free radicals generated by smoking (leading cause of oral cancer). For the image screening, a simple yet effective centered rule image-capturing approach was proposed for collecting oral cavity images. Then, based on this method, a medium-sized oral dataset with five categories of diseases was created, and a resampling method was presented to alleviate the effect of image variability from hand-held smartphone cameras. Finally, a recent deep learning network (HRNet) was introduced to evaluate the performance of our method for oral cancer detection. Results: The image screening method achieved a sensitivity of 78.0%, specificity of 91%, and precision of 80% on 400 test images. In addition, the chemical test detected salivary MDA levels with 94% accuracy among 400 samples.

show abstract

“…Both intraoral and extraoral 3D surface imaging data can be used to enrich and expand dentistry research. For example, literature [25][26][27] indicates that certain diseases can also be diagnosed using 3D surface imaging technology. 5.…”

Section: Introductionmentioning

confidence: 99%

Application of three-dimensional reconstruction technology in dentistry: a narrative review

Cen,

Huang,

Liu

et al. 2023

BMC Oral Health

View full text Add to dashboard Cite

Background Three-dimensional(3D) reconstruction technology is a method of transforming real goals into mathematical models consistent with computer logic expressions and has been widely used in dentistry, but the lack of review and summary leads to confusion and misinterpretation of information. The purpose of this review is to provide the first comprehensive link and scientific analysis of 3D reconstruction technology and dentistry to bridge the information bias between these two disciplines. Methods The IEEE Xplore and PubMed databases were used for rigorous searches based on specific inclusion and exclusion criteria, supplemented by Google Academic as a complementary tool to retrieve all literature up to February 2023. We conducted a narrative review focusing on the empirical findings of the application of 3D reconstruction technology to dentistry. Results We classify the technologies applied to dentistry according to their principles and summarize the different characteristics of each category, as well as the different application scenarios determined by these characteristics of each technique. In addition, we indicate their development prospects and worthy research directions in the field of dentistry, from individual techniques to the overall discipline of 3D reconstruction technology, respectively. Conclusions Researchers and clinicians should make different decisions on the choice of 3D reconstruction technology based on different objectives. The main trend in the future development of 3D reconstruction technology is the joint application of technology.

show abstract

An Image Recognition Framework for Oral Cancer Cells

Cited by 6 publications

References 24 publications

A low-cost Point-of-Care Diagnostic for Premature Oral Cancer Screening

A low-cost Point-of-Care Diagnostic for Premature Oral Cancer Screening

QuickDiag: A low cost oral cancer detection kit

Application of three-dimensional reconstruction technology in dentistry: a narrative review

Contact Info

Product

Resources

About