SignificanceDiagnosis of cancerous and pre-cancerous oral lesions at early stages is critical for the improvement of patient care, to increase survival rates and minimize the invasiveness of tumor resection surgery. Unfortunately, oral precancerous and early-stage cancerous lesions are often difficult to distinguish from oral benign lesions with the existing diagnostic tools used during standard clinical oral examination. In consequence, early diagnosis of oral cancer can be achieved in only about 30% of patients. Therefore, clinical diagnostic technologies for fast, minimally invasive, and accurate oral cancer screening are urgently needed.AimThis study investigated the use of multispectral autofluorescence imaging endoscopy for the automated and noninvasive discrimination of cancerous and precancerous from benign oral epithelial lesions.ApproachIn vivo multispectral autofluorescence endoscopic images of clinically suspicious oral lesions were acquired from 67 patients undergoing tissue biopsy examination. The imaged lesions were classified as precancerous (n=4), cancerous (n=29), and benign (n=34) lesions based on histopathology diagnosis. Multispectral autofluorescence intensity feature maps were generated for each oral lesion and used to train and optimize support vector machine (SVM) models for automated discrimination of cancerous and precancerous from benign oral lesions.ResultsAfter a leave-one-patient-out cross-validation strategy, an optimized SVM model developed with four multispectral autofluorescence features yielded levels of sensitivity and specificity of 85% and 71%, respectively and overall accuracy of 78% in the discrimination of cancerous/precancerous versus benign oral lesions.ConclusionThis study demonstrates the potentials of a computer-assisted detection system based on multispectral autofluorescence imaging endoscopy for the early detection of cancerous and precancerous oral lesions.
Multispectral autofluorescence endoscopy is a non-invasive optical imaging modality that can provide contrast between malignant and benign oral tissue. We hypothesized that discrimination of cancerous and precancerous from benign oral lesions can be achieved through machine-learning (ML) models developed with multispectral autofluorescence intensity features. In vivo multispectral autofluorescence endoscopic images of benign, precancerous, and cancerous oral lesions were acquired from 67 patients and used to optimize ML models for discrimination between cancerous/precancerous and benign lesions. This study demonstrates the potentials of a ML-assisted system based on multispectral autofluorescence endoscopy for automated discrimination of cancerous and precancerous from benign oral lesions.
Multispectral autofluorescence lifetime imaging (maFLIM) endoscopy can be used to clinically image a plurality of metabolic and biochemical autofluorescence biomarkers of oral precancer and cancer. We tested the hypothesis that maFLIM-derived autofluorescence biomarkers can be used as features in machine-learning models to automatically discriminate precancerous and cancerous from healthy oral tissue. Clinical widefield maFLIM endoscopy images of cancerous and precancerous oral lesions from 57 patients were acquired and used to develop and validate a computer-aided detection (CAD) system. This study demonstrates the potentials of a maFLIM endoscopy-based CAD system for automated in situ clinical detection of oral precancer and cancer.
Despite the fact that the oral cavity is easily accessible, only ~30% of oral cancers are diagnosed at an early stage, which is the main factor attributed to the low 5-year survival rate (63%) of oral cancer patients. Several screening tools for oral cancer have been commercially available; however, none of them have been demonstrated to have sufficient sensitivity and specificity for early detection of oral cancer and dysplasia. We hypothesized that an array of biochemical and metabolic biomarkers for oral cancer and dysplasia can be quantified by endogenous fluorescence lifetime imaging (FLIM), thus enabling levels of sensitivity and specificity adequate for early detection of oral cancer and dysplasia. Our group has recently developed multispectral FLIM endoscopes to image the oral cavity with unprecedented imaging speed (>2fps). We have also performed an in vivo pilot study, in which endogenous multispectral FLIM images were acquired from clinically suspicious oral lesions of 52 patients undergoing tissue biopsy. The results from this pilot study indicated that mild-dysplasia and early stage oral cancer could be detected from benign lesions using a computed aided diagnosis (CAD) system developed based on biochemical and metabolic biomarkers that could be quantified from endogenous multispectral FLIM images. The diagnostic performance of this novel FLIM clinical tool was estimated using a cross-validation approach, showing levels of sensitivity and specificity >80%, and Area Under the Receiving Operating Curve (RO- AUC) >0.9. Future efforts are focused on developing cost-effective FLIM endoscopes and validating this novel clinical tool in prospective multi-center clinical studies.
Cancer development in oral epithelial tissue induces subtle changes in tissue autofluorescence that are associated with increased metabolic activity in malignant oral epithelial cells. These autofluorescence biomarkers of oral cancer progression include a decrease in the optical “redox ratio”, defined as the autofluorescence intensity of NADH divided by that of FAD, and specific changes in the fluorescence lifetime of both NADH and FAD. We therefore hypothesized that more specific biomarkers of oral cancer and dysplasia can more accurately be quantified by endogenous fluorescence lifetime imaging (FLIM). In this work, FLIM images of benign, dysplastic and early stage cancerous oral lesions from 52 patients were acquired at three emission channels (390±20nm, 452±22.5nm and >500nm) using a handheld multispectral FLIM endoscope. For each pixel, the fluorescence decays collected at the three emission bands were analyzed using a biexponential decay model, resulting on 16 FLIM-derived parameters per pixel, which generated multiparametric FLIM images of each oral lesion. Statistical analysis was performed on each of the computed FLIM parameters (Wilcoxon test: Normal vs. Benign, Normal vs. Dysplasia/Cancer; Mann-Whitney test: Benign vs. Dysplasia/Cancer). Results from this analysis revealed that FLIM-derived parameters associated with collagen lifetime, NADH lifetime, FAD autofluorescence, and the optical redox ratio were statistically different between dysplastic/cancerous vs. benign oral lesions. This study provides the first demonstration for the clinical imaging of autofluorescence biochemical and metabolic biomarkers of oral epithelial cancer and dysplasia, which could potentially enable early detection of oral cancer.
For a precise characterization of time-domain fluorescence lifetime imaging microscopy (FLIM) datasets, an initial processing step is needed to identify the fluorescent impulse response (FIR) at each spatial point in the sample. Hence departing from the measured fluorescent decays, the FIRs are estimated by using the instrument response function (IRF), and this processing step is known as deconvolution. However, the deconvolution methodology requires an initial measurement of the IRF and a corresponding synchronization step with the fluorescent decays. In this context, we propose a blind deconvolution strategy that estimates jointly the FIRs and the IRF in the dataset. For this purpose, each FIR is modeled by a multi-exponential structure. In this way, the FIRs are characterized by the scaling coefficients and time constants of the exponential terms. Meanwhile, there is no explicit model or pre-defined shape for the IRF. Overall estimation process is achieved by an alternated least squares methodology between the FIRs and IRF. First, if the IRF is fixed, a nonlinear least squares framework computes the FIRs parameters at each spatial point of the sample. Meanwhile, once the FIRs are fixed, the samples of the IRF are estimated by a non-negative least squares methodology and using the whole dataset. These alternated optimization steps are performed until a convergence criterion is fulfilled. The proposed blind deconvolution strategy was validated by synthetic datasets and in vivo FLIM oral mucosa measurements. In these tests, our proposal shows good characterizations of the FIRs and the IRFs in the FLIM datasets.
Despite the fact that the oral cavity is easily accessible, only ~30% of oral cancers are diagnosed at an early stage, which is the main factor attributed to the low 5-year survival rate (63%) of oral cancer patients. Several screening tools for oral cancer have been commercially available; however, none of them have been demonstrated to have sufficient sensitivity and specificity for early detection of oral cancer and dysplasia. We hypothesized that an array of biochemical and metabolic biomarkers for oral cancer and dysplasia can be quantified by endogenous fluorescence lifetime imaging (FLIM), thus enabling levels of sensitivity and specificity adequate for early detection of oral cancer and dysplasia. Our group has recently developed multispectral FLIM endoscopes to image the oral cavity with unprecedented imaging speed (>2fps). We have also performed an in vivo pilot study, in which endogenous multispectral FLIM images were acquired from clinically suspicious oral lesions of 70 patients undergoing tissue biopsy. The results from this pilot study indicated that mild-dysplasia and early stage oral cancer could be detected from benign lesions using a computed aided diagnosis (CAD) system developed based on biochemical and metabolic biomarkers that could be quantified from endogenous multispectral FLIM images. The diagnostic performance of this novel FLIM based clinical tool was estimated using a cross-validation approach, showing levels of sensitivity >90%, specificity >80%, and Area Under the Receiving Operating Curve (RO- AUC) >0.9. Future efforts are focused on developing cost-effective FLIM endoscopes and validating this novel clinical tool in prospective multi-center clinical studies.
Increased metabolic activity, a hallmark of epithelial cell malignant transformation, induces subtle changes in the oral tissue autofluorescence. The optical “redox-ratio”, defined as the autofluorescence intensity of NADH divided by that of FAD, is sensitive to changes in the cellular metabolic rate. A decrease in the redox-ratio indicates increased cellular metabolic activity, as is typically observed in malignant cells. Specific changes in the fluorescence lifetime of both NADH and FAD have also been associated with increased metabolic activity in malignant oral epithelial cells. We therefore hypothesized that more specific biomarkers of oral cancer and dysplasia can more accurately be quantified by endogenous fluorescence lifetime imaging (FLIM). In this work, FLIM images of benign, dysplastic and early stage cancerous oral lesions from 52 patients were acquired at three emission channels (390±20nm, 452±22.5nm and >500nm) using a handheld multispectral FLIM endoscope. For each pixel, the fluorescence decays collected at the three emission bands were analyzed using a biexponential decay model, resulting on 16 FLIM-derived parameters per pixel. Statistical analysis was performed on each of the computed FLIM parameters (Wilcoxon test: Normal vs. Benign, Normal vs. Dysplasia/Cancer; Mann-Whitney test: Benign vs. Dysplasia/Cancer). Results from this analysis revealed that FLIM-derived parameters associated with collagen lifetime, NADH lifetime, FAD autofluorescence, and the optical redox ratio were statistical different between dysplastic/cancerous vs. benign oral lesions. This study provides the first demonstration for the clinical imaging of autofluorescence biochemical and metabolic biomarkers of oral epithelial cancer and dysplasia, which could potentially enable early detection of oral cancer.
The implementation of time domain fluorescence lifetime imaging (TD-FLIM) requires high cost bandwidth electronics and large storage capacity. A cross-level sampling technique for TD-FLIM is proposed. A simulation of this sampling technique was implemented using synthetic FLIM data. FLIM images were synthetically generated at different noise levels using a wide range of lifetimes. Each of the images was resampled using a cross-level approach and the lifetime maps were computed. Simulation results displayed strong correlation between the lifetime maps of the original and resampled images, suggesting that this sampling method could be adopted to reduce bandwidth and data transfer/ storage requirements.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.