Novel quantitative analysis of autofluorescence images for oral cancer screening

Huang, Tze Ta; Huang, Jow-Lay; Yy, Wang; Chen, Ken Chung; Wong, Tung Yiu; Chen, Yi Chun; Wu, Che‐Wei; Chan, Leong‐Perng; Lin, Yen-Ko; Kao, Yu Hsun; Nioka, Shoko; Yuan, Shyng‐Shiou F.; Chung, Pau Choo

doi:10.1016/j.oraloncology.2017.03.003

Cited by 42 publications

(36 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intensity-based classification alone is not good enough. Huang TT et al developed a method that VELscope autofluorescence images by QDA [27]. They calculated the intensity and heterogeneity of the ROI in the images.…”

Section: Discussionmentioning

confidence: 99%

“…They suggested that VELscope has reasonable sensitivity, but yields many false-positive results. Huang et al [27] proposed the use of quantitative analysis(quadratic discriminant analysis, QDA) to quantify the classification of VELscope images (autofluorescence images) by their intensity and heterogeneity. They used QDA as a method of discriminant analysis classification to differentiate between normal and abnormal (malignant/premalignant) lesions of oral mucosa.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis

et al. 2020

View full text Add to dashboard Cite

Background Oral cancer is one of the most common diseases globally. Conventional oral examination and histopathological examination are the two main clinical methods for diagnosing oral cancer early. VELscope is an oral cancer-screening device that exploited autofluorescence. It yields inconsistent results when used to differentiate between normal, premalignant and malignant lesions. We develop a new method to increase the accuracy of differentiation. Materials and methods Five samples (images) of each of 21 normal mucosae, as well as 31 premalignant and 16 malignant lesions of the tongue and buccal mucosa were collected under both white light and autofluorescence (VELscope, 400-460 nm wavelength). The images were developed using an iPod (Apple, Atlanta Georgia, USA). Results The normalized intensity and standard deviation of intensity were calculated to classify image pixels from the region of interest (ROI). Linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) classifiers were used. The performance of both of the classifiers was evaluated with respect to accuracy, precision, and recall. These parameters were used for multiclass classification. The accuracy rate of LDA with un-normalized data was increased by 2% and 14% and that of QDA was increased by 16% and 25% for the tongue and buccal mucosa, respectively. Conclusion The QDA algorithm outperforms the LDA classifier in the analysis of autofluorescence images with respect to all of the standard evaluation parameters.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Furthermore, coenzymes NADH and FAD are known to be involved in the catabolic reactions of amino acid and fatty acid oxidation, glycolysis, citric acid, and the electron transport chain, which ultimately results in energy generation (Pelicano et al, ; Warburg, ). Studies using new equipment such as fluorescence lifetime imaging microscopy have shown that the expression of FAD and NADH in cancer cells is decreased in comparison with normal cells (Cannon, Shah, & Skala, ; Huang et al, ; Scheer et al, ; Wallrabe et al, ; Yamamoto et al, ). Therefore, a reduction in FAD and NADH levels is considered to a factor creating the FVL in autofluorescence visualization images of tumors.…”

Section: Discussionmentioning

confidence: 99%

“…In recent years, one such possible diagnosis method involving the application of autofluorescence imaging has been increasingly used. Currently, the VELscope® (LED Dental Inc., Vancouver, Canada; Awan, Morgan, & Warnakulasuriya, ; Ganga et al, ; Hanken et al, ; Huang et al, ; Yamamoto et al, ) and DIFOTI® (Electro‐Optical Sciences Inc., Irvington, NY, USA; Bin‐Shuwaish, Yaman, Dennison, & Neiva, ) systems have been launched for general dental clinics (Lingen, Kalmar, Karrison, & Speight, ). These instruments can detect a decrease or increase in the autofluorescence of flavin adenine dinucleotide (FAD), nicotinamide adenine dinucleotide (NADH), or collagen cross linking, by irradiating the lesional tissue with blue light of a wavelength of 400 to 460 nm (Laronde et al, ; Lingen et al, ).…”

Section: Introductionmentioning

confidence: 99%

The luminance ratio of autofluorescence in a xenograft mouse model is stable through tumor growth stages

Sumi

Umemura

Adachi

et al. 2018

Clinical & Exp Dental Res

View full text Add to dashboard Cite

The aim of this research was to investigate the value of autofluorescence imaging of oral cancer across different stages of tumor growth, to assist in detecting tumors. A xenograft mouse model was created with human oral squamous cell carcinoma cell line HSC‐3 being subcutaneously inoculated into nude mice. Tumor imaging was performed with an autofluorescence imaging method (Illumiscan®) using the luminance ratio, which was defined as the luminance of the tumor site over the luminance of normal skin tissue normalized to a value of 1.0. This luminance ratio was continuously observed postinoculation. Tumor and normal skin tissues were harvested, and differences in the concentrations of flavin adenine dinucleotide and nicotinamide adenine dinucleotide were examined. The luminance ratio of the tumor sites was 0.85 ± 0.05, and there was no significant change in the ratio over time, even if the tumor proliferated and expanded. Furthermore, flavin adenine dinucleotide and nicotinamide adenine dinucleotide were significantly lower in tumor tissue than in normal skin tissue. A luminance ratio under 0.90 indicates a high possibility of tumor, irrespective of the tumor growth stage. However, this cutoff value was determined using a xenograft mouse model and therefore requires further validation before being used in clinical diagnosis.

show abstract

“…The concept has good research to show that it can detect early, moderate and advanced dysplastic cells, carcinoma in situ & squamous cell carcinomas. 3,4,5 It works on the principles of tissue fluorescence whereby healthy tissues when viewed through a narrowband green filter under blue light (dental curing light) will emit a green glow. The healthy cells literally do glow an apple green.…”

Section: Early Detection Technologymentioning

confidence: 99%

60 seconds to save a life?

2019

BDJ Team

View full text Add to dashboard Cite

Novel quantitative analysis of autofluorescence images for oral cancer screening

Cited by 42 publications

References 33 publications

Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis

Multiclass classification of autofluorescence images of oral cavity lesions based on quantitative analysis

The luminance ratio of autofluorescence in a xenograft mouse model is stable through tumor growth stages

60 seconds to save a life?

Contact Info

Product

Resources

About