Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2016 Oct;3(4):044004.
doi: 10.1117/1.JMI.3.4.044004. Epub 2016 Dec 2.

Automated algorithm for actinic cheilitis diagnosis by wide-field fluorescence imaging

Alessandro Cosci  1 , Ademar Takahama Jr  2 , Wagner Rafael Correr  3 , Rebeca Souza Azevedo  2 , Karla Bianca Fernandes da Costa Fontes  2 , Cristina Kurachi  3
Affiliations

Automated algorithm for actinic cheilitis diagnosis by wide-field fluorescence imaging

Alessandro Cosci et al. J Med Imaging (Bellingham). 2016 Oct.

Abstract

Actinic cheilitis (AC) is a disease caused by prolonged and cumulative sun exposure that mostly affects the lower lip, which can progress to a lip squamous cell carcinoma. Routine diagnosis relies on clinician experience and training. We investigated the diagnostic efficacy of wide-field fluorescence imaging coupled to an automated algorithm for AC recognition. Fluorescence images were acquired from 57 patients with confirmed AC and 46 normal volunteers. Three different algorithms were employed: two based on the emission characteristics of local heterogeneity, entropy and intensity range, and one based on the number of objects after K-mean clustering. A classification model was obtained using a fivefold cross correlation algorithm. Sensitivity and specificity rates were 86% and 89.1%, respectively.

Keywords: actinic cheilitis; cancer; fluorescence; fotonics; lips; optics; oral; wide-field imaging.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Fluorescence imaging (a) from the lower part of the lip of a healthy volunteer and (b) from a patient with AC. A high fluorescence signal from teeth is noted. Compared with normal lip, AC lip shows a more heterogeneous fluorescence characterized by a spotted pattern.
Fig. 2
Fig. 2
K-mean clustered images (a) from the lower lip of a healthy volunteer and (b) from a patient with AC.
Fig. 3
Fig. 3
Local entropy in neighborhood of 21×21  pixels image (a) from a healthy volunteer and (b) from a patient with AC. Red-shifted values show higher entropy, and blue values show lower entropy.
Fig. 4
Fig. 4
Local range in neighborhood of 21×21  pixels images (a) from a healthy volunteer and (b) from a patient with AC. Lower range values are shown with blue color; and higher values are shown with red color.
Fig. 5
Fig. 5
Scatter plot of score values: local entropy, local range, and number of objects. AC lips are represented by black dots, and normal lips as red dots.
See this image and copyright information in PMC

References

    1. Kaugars G. E., et al. , “Actinic cheilitis: a review of 152 cases,” Oral Surg. Oral Med. Oral Pathol. Oral Radiol. Endodontol. 88(2), 181–186 (1999).10.1016/S1079-2104(99)70115-0 - DOI - PubMed
    1. Markopoulos A., Albanidou-Farmaki E., Kayavis I., “Actinic cheilitis: clinical and pathologic characteristics in 65 cases,” Oral Dis. 10(4), 212–216 (2004).10.1111/odi.2004.10.issue-4 - DOI - PubMed
    1. Rodrigues Cavalcante A. S., Anbinder A. L., Carvalho Y. R., “Actinic cheilitis: clinical and histological features,” J. Oral Maxillofac. Surg. 66(3), 498–503 (2008).10.1016/j.joms.2006.09.016 - DOI - PubMed
    1. Simonsen Nico M. M., Rivitti E. A., Vanessa Lourenço S., “Actinic cheilitis: histologic study of the entire vermilion and comparison with previous biopsy,” J. Cutan. Pathol. 34(4), 309–314 (2007).10.1111/cup.2007.34.issue-4 - DOI - PubMed
    1. Jadotte Y. T., Schwartz R. A., “Solar cheilosis: an ominous precursor: part I. diagnostic insights,” J. Am. Acad. Dermatol. 66(2), 173–184 (2012).10.1016/j.jaad.2011.09.040 - DOI - PubMed