Bimodal multispectral imaging system with cloud-based machine learning algorithm for real-time screening and detection of oral potentially malignant lesions and biopsy guidance

Abstract

. Significance: Screening and early detection of oral potentially malignant lesions (OPMLs) are of great significance in reducing the mortality rates associated with head and neck malignancies. Intra-oral multispectral optical imaging of tissues in conjunction with cloud-based machine learning (CBML) can be used to detect oral precancers at the point-of-care (POC) and guide the clinician to the most malignant site for biopsy. Aim: Develop a bimodal multispectral imaging system (BMIS) combining tissue autofluorescence and diffuse reflectance (DR) for mapping changes in oxygenated hemoglobin ( ) absorption in the oral mucosa, quantifying tissue abnormalities, and guiding biopsies. Approach: The hand-held widefield BMIS consisting of LEDs emitting at 405, 545, 575, and 610 nm, 5MPx monochrome camera, and proprietary Windows-based software was developed for image capture, processing, and analytics. The DR image ratio (R610/R545) was compared with pathologic classification to develop a CBML algorithm for real-time assessment of tissue status at the POC. Results: Sensitivity of 97.5% and specificity of 92.5% were achieved for discrimination of OPML from patient normal in 40 sites, whereas 82% sensitivity and 96.6% specificity were obtained for discrimination of abnormal (OPML + SCC) in 89 sites. Site-specific algorithms derived for buccal mucosa (27 sites) showed improved sensitivity and specificity of 96.3% for discrimination of OPML from normal. Conclusions: Assessment of oral cancer risk is possible by mapping of absorption in tissues, and the BMIS system developed appears to be suitable for biopsy guidance and early detection of oral cancers.

Machine learning for detection and classification of oral potentially malignant disorders: A conceptual review

“…For this purpose, it was used a hand‐held widefield BMIS of LEDs emitting at 405, 545, 575, and 610 nm and a 5 MPx monochrome camera. Results indicated a sensitivity of 97.5% and specificity of 92.5% to differentiate OPMDs from normal samples and concluded that their system is suitable for biopsy guidance and early detection of oral cancers 35 …”

“…The use of multispectral images has also been employed as a diagnostic method to assist the oral medicine specialists 35 . Subhash and collaborators developed a bimodal imaging system which combines tissue, autofluorescence, and diffuse reflectance.…”

“…The use of multispectral images has also been employed as a diagnostic method to assist the oral medicine specialists. 35 Subhash and collaborators developed a bimodal imaging system which combines tissue, autofluorescence, and diffuse reflectance. This method was used for mapping changes in oxygenated hemoglobin absorption in the oral mucosa, quantifying tissue abnormalities, and guiding biopsies.…”

“…Results indicated a sensitivity of 97.5% and specificity of 92.5% to differentiate OPMDs from normal samples and concluded that their system is suitable for biopsy guidance and early detection of oral cancers. 35 Optical instruments have been shown to enhance the detection of OPMDs. For instance, Morikawa et al determined the usefulness of optical instruments in oral screening by fluorescence visualization images.…”

Distinguishing tumor from healthy tissue in human liver ex vivo using machine learning and multivariate analysis of diffuse reflectance spectra

“…Many research groups are attempting to establish diagnostic criteria, or a form of "optical biopsy", based on the correlation between the histology and optical signatures of tissues, for a variety of human tissues, such as colon [9][10][11], skin [12][13][14], breast [15][16][17][18][19][20], cervical [21][22][23], oral [23][24][25][26][27], prostate [28][29][30][31], nasopharynx [32,33] and lung tissues [34][35][36][37]. Studies have also showed the potential of probe-based DRS to discriminate between human liver tumors and tumor-free surrounding tissue [7,8,[38][39][40][41][42][43].…”