Machine-Learning Assisted Discrimination of Precancerous and Cancerous from Healthy Oral Tissue Based on Multispectral Autofluorescence Lifetime Imaging Endoscopy

Multispectral autofluorescence lifetime imaging (maFLIM) can be used to clinically image a plurality of metabolic and biochemical autofluorescence biomarkers of oral epithelial dysplasia and cancer. This study tested the hypothesis that maFLIM-derived autofluorescence biomarkers can be used in machine-learning (ML) models to discriminate dysplastic and cancerous from healthy oral tissue. Clinical widefield maFLIM endoscopy imaging of cancerous and dysplastic oral lesions was performed at two clinical centers. Endoscopic maFLIM images from 34 patients acquired at one of the clinical centers were used to optimize ML models for automated discrimination of dysplastic and cancerous from healthy oral tissue. A computer-aided detection system was developed and applied to a set of endoscopic maFLIM images from 23 patients acquired at the other clinical center, and its performance was quantified in terms of the area under the receiver operating characteristic curve (ROC-AUC). Discrimination of dysplastic and cancerous from healthy oral tissue was achieved with an ROC-AUC of 0.81. This study demonstrates the capabilities of widefield maFLIM endoscopy to clinically image autofluorescence biomarkers that can be used in ML models to discriminate dysplastic and cancerous from healthy oral tissue. Widefield maFLIM endoscopy thus holds potential for automated in situ detection of oral dysplasia and cancer.

Download Full-text

Subjectivity in evaluating oral epithelial dysplasia, carcinoma in situ and initial carcinoma

Journal of Oral Pathology and Medicine ◽

10.1111/j.1600-0714.1985.tb00549.x ◽

1985 ◽

Vol 14 (9) ◽

pp. 698-708 ◽

Cited By ~ 119

Author(s):

J. J. Pindborg ◽

J. Reibel ◽

P. Holmstrup

Keyword(s):

Carcinoma In Situ ◽

Epithelial Dysplasia ◽

Oral Epithelial Dysplasia ◽

Oral Epithelial

Download Full-text

DESIGN OF AN IN SITU DETECTION SYSTEM FOR LASER HARDENED WIDTH

Advanced Materials and Processing 2010 ◽

10.1142/9789814322799_0067 ◽

2011 ◽

Author(s):

CAIXIA YANG ◽

JICHANG LIU

Keyword(s):

Detection System ◽

In Situ Detection

Download Full-text

Real Time In-situ Detection System Research for Methane in Offshore Shallow Gas based on Thin Film Interface

MATEC Web of Conferences ◽

10.1051/matecconf/201823204053 ◽

2018 ◽

Vol 232 ◽

pp. 04053

Author(s):

Cheng-xing Miao ◽

Qing Li ◽

Sheng-yao Jia

Keyword(s):

Real Time ◽

Detection Efficiency ◽

Detection System ◽

Detection Methods ◽

Shallow Gas ◽

Micro Gas Sensor ◽

Detection Probe ◽

On Line ◽

In Situ Detection

In order to get ridded of the non real-time detection methods of artificial site sampled and laboratory instrument analyzed in the field of methane detection in the offshore shallow gas, real-time in-situ detection system for methane in offshore shallow gas was designed by the film interface.The methane in the offshore shallow gas through the gas-liquid separation membrane of polymer permeation into the system internal detection probe, analog infrared micro gas sensor sensed the methane concentration and the corresponded output value, data acquisition and communication node fitted into standard gas concentration.Based on the experimental data compared with the traditional detection method, and further analyzed the causes of error produced by the case experiment. The application results show that the system can achieve a single borehole layout, long-term on-line in-situ on-line detection, and improve the detection efficiency and the timeliness of the detection data.

Download Full-text

Oral Cancer Discrimination and Novel Oral Epithelial Dysplasia Stratification Using FTIR Imaging and Machine Learning

Diagnostics ◽

10.3390/diagnostics11112133 ◽

2021 ◽

Vol 11 (11) ◽

pp. 2133

Author(s):

Rong Wang ◽

Aparna Naidu ◽

Yong Wang

Keyword(s):

Machine Learning ◽

Cluster Analysis ◽

Discriminant Analysis ◽

Oral Cancer ◽

Epithelial Dysplasia ◽

Support Vector ◽

Epithelial Tissue ◽

Ftir Imaging ◽

Oral Epithelial Dysplasia ◽

Oral Epithelial

The Fourier transform infrared (FTIR) imaging technique was used in a transmission model for the evaluation of twelve oral hyperkeratosis (HK), eleven oral epithelial dysplasia (OED), and eleven oral squamous cell carcinoma (OSCC) biopsy samples in the fingerprint region of 1800–950 cm−1. A series of 100 µm × 100 µm FTIR imaging areas were defined in each sample section in reference to the hematoxylin and eosin staining image of an adjacent section of the same sample. After outlier removal, signal preprocessing, and cluster analysis, a representative spectrum was generated for only the epithelial tissue in each area. Two representative spectra were selected from each sample to reflect intra-sample heterogeneity, which resulted in a total of 68 representative spectra from 34 samples for further analysis. Exploratory analyses using Principal component analysis and hierarchical cluster analysis showed good separation between the HK and OSCC spectra and overlaps of OED spectra with either HK or OSCC spectra. Three machine learning discriminant models based on partial least squares discriminant analysis (PLSDA), support vector machines discriminant analysis (SVMDA), and extreme gradient boosting discriminant analysis (XGBDA) were trained using 46 representative spectra from 12 HK and 11 OSCC samples. The PLSDA model achieved 100% sensitivity and 100% specificity, while both SVM and XGBDA models generated 95% sensitivity and 96% specificity, respectively. The PLSDA discriminant model was further used to classify the 11 OED samples into HK-grade (6), OSCC-grade (4), or borderline case (1) based on their FTIR spectral similarity to either HK or OSCC cases, providing a potential risk stratification strategy for the precancerous OED samples. The results of the current study support the application of the FTIR-machine learning technique in early oral cancer detection.

Download Full-text

Implementation of seafloor heat-flux in-situ detection system based on MEMS

Advances in Electrical and Electronics Engineering ◽

10.2495/iceee140711 ◽

2014 ◽

Author(s):

Tao Wang ◽

Qian Zhao ◽

Cungen Liu

Keyword(s):

Heat Flux ◽

Detection System ◽

In Situ Detection

Download Full-text

Multiple Phage-Based Magnetoelastic Biosensors System for the Detection of Salmonella typhimurium and Bacillus anthracis Spores

MRS Proceedings ◽

10.1557/proc-1129-v04-16 ◽

2008 ◽

Vol 1129 ◽

Author(s):

S. Huang ◽

S. Li ◽

H. Yang ◽

M. L. Johnson ◽

Ramji S Lakshmanan ◽

...

Keyword(s):

Resonance Frequency ◽

Rapid Detection ◽

Detection System ◽

Additional Mass ◽

Response Curves ◽

Biosensor System ◽

Bacillus Anthracis Spores ◽

In Situ Detection ◽

Multiple Pathogens

AbstractThis paper presents a multiple magnetoelastic (ME) biosensor system for in-situ detection of S. typhimurium and B. anthracis spores in a flowing bacterial/spore suspension (5 x 101 - 5 x 108 cfu/ml). The ME biosensor was formed by immobilizing filamentous phage (specific to each detection target) on the ME platforms. An alternating magnetic field was used to resonate the ME biosensor to determine its resonance frequency. When cells/spores are bound to a ME biosensor surface, the additional mass of the cells/spores causes a decrease in the resonance frequency of the biosensor. The detection system was composed of a control sensor, an E2 phage-based biosensor (specific to S. typhimurium) and a JRB7 phage-based biosensor (specific to B. anthracis spores). The frequency response curves of the ME biosensors as a function of exposure time were then measured and the detection limit of the ME biosensor was observed to be 5 x 103 cfu/ml. The results show that phage-based ME biosensors can detect multiple pathogens simultaneously and offer good performance, including good sensitivity and rapid detection.

Download Full-text