Algorithm to quantify nuclear features and confidence intervals for classification of oral neoplasia from high-resolution optical images

Abstract. Purpose: In vivo optical imaging technologies like high-resolution microendoscopy (HRME) can image nuclei of the oral epithelium. In principle, automated algorithms can then calculate nuclear features to distinguish neoplastic from benign tissue. However, images frequently contain regions without visible nuclei, due to biological and technical factors, decreasing the data available to and accuracy of image analysis algorithms. Approach: We developed the nuclear density-confidence interval (ND-CI) algorithm to determine if an HRME image contains sufficient nuclei for classification, or if a better image is required. The algorithm uses a convolutional neural network to exclude image regions without visible nuclei. Then the remaining regions are used to estimate a confidence interval (CI) for the number of abnormal nuclei per mm2, a feature used by a previously developed algorithm (called the ND algorithm), to classify images as benign or neoplastic. The range of the CI determines whether the ND-CI algorithm can classify an image with confidence, and if so, the predicted category. The ND and ND-CI algorithm were compared by calculating their positive predictive value (PPV) and negative predictive value (NPV) on 82 oral biopsies with histopathologically confirmed diagnoses. Results: After excluding the images that could not be classified with confidence, the ND-CI algorithm had higher PPV (65% versus 59%) and NPV (78% versus 75%) than the ND algorithm. Conclusions: The ND-CI algorithm could improve the real-time classification of HRME images of the oral epithelium by informing the user if an improved image is required for diagnosis.

[1]  Peter L. Bartlett,et al.  Classification with a Reject Option using a Hinge Loss , 2008, J. Mach. Learn. Res..

[2]  E. Abt,et al.  Evidence-based clinical practice guideline for the evaluation of potentially malignant disorders in the oral cavity: A report of the American Dental Association. , 2017, Journal of the American Dental Association.

[3]  Imran S. Vohra,et al.  Prospective evaluation of oral premalignant lesions using a multimodal imaging system: a pilot study , 2019, Head & neck.

[4]  Weizhen Wang.  Exact Optimal Confidence Intervals for Hypergeometric Parameters , 2015 .

[5]  Joachim Denzler,et al.  Automated analysis of confocal laser endomicroscopy images to detect head and neck cancer , 2016, Head & neck.

[6]  Imran S. Vohra,et al.  In Vivo Multimodal Optical Imaging: Improved Detection of Oral Dysplasia in Low-Risk Oral Mucosal Lesions , 2018, Cancer Prevention Research.

[7]  P. Sandiford.  A New Binomial Approximation for Use in Sampling from Finite Populations , 1960 .

[8]  M. Poljak,et al.  Update from the 4th Edition of the World Health Organization Classification of Head and Neck Tumours: What is New in the 2017 WHO Blue Book for Tumours of the Hypopharynx, Larynx, Trachea and Parapharyngeal Space , 2017, Head and Neck Pathology.

[9]  Alonso Carrasco-Labra,et al.  Adjuncts for the evaluation of potentially malignant disorders in the oral cavity: Diagnostic test accuracy systematic review and meta-analysis-a report of the American Dental Association. , 2017, Journal of the American Dental Association.

[10]  R. Richards-Kortum,et al.  Prospective Evaluation of Multimodal Optical Imaging with Automated Image Analysis to Detect Oral Neoplasia In Vivo , 2017, Cancer Prevention Research.

[11]  J. Jeng,et al.  Factors associated with underdiagnosis from incisional biopsy of oral leukoplakic lesions. , 2007, Oral surgery, oral medicine, oral pathology, oral radiology, and endodontics.

[12]  Kristen C. Maitland,et al.  A Pulse Coupled Neural Network Segmentation Algorithm for Reflectance Confocal Images of Epithelial Tissue , 2015, PloS one.

[13]  Fabio Roli,et al.  Multi-label classification with a reject option , 2013, Pattern Recognit..

[14]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[15]  J. Fujimoto,et al.  Optical coherence tomography: advanced technology for the endoscopic imaging of Barrett's esophagus. , 2000, Endoscopy.

[16]  H. Burstein,et al.  Finite Population Correction for Binomial ConFidence Limits , 1975 .

[17]  Carmen Lopez,et al.  Hyperspectral imaging fluorescence excitation scanning for colon cancer detection , 2016, Journal of biomedical optics.

[18]  S. Dawsey,et al.  A tablet-interfaced high-resolution microendoscope with automated image interpretation for real-time evaluation of esophageal squamous cell neoplasia. , 2016, Gastrointestinal endoscopy.

[19]  Luigi Laino,et al.  The potential role of in vivo reflectance confocal microscopy for evaluating oral cavity lesions: a systematic review. , 2016, Journal of oral pathology & medicine : official publication of the International Association of Oral Pathologists and the American Academy of Oral Pathology.

[20]  Helmut Neumann,et al.  Development and validation of a classification and scoring system for the diagnosis of oral squamous cell carcinomas through confocal laser endomicroscopy , 2016, Journal of Translational Medicine.

[21]  Michele Follen,et al.  Fluorescence confocal endomicroscopy of the cervix: pilot study on the potential and limitations for clinical implementation , 2016, Journal of biomedical optics.

[22]  Yoshua Bengio,et al.  The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[23]  Susan Mallett,et al.  Systematic review of diagnostic accuracy of reflectance confocal microscopy for melanoma diagnosis in patients with clinically equivocal skin lesions , 2013, Dermatology practical & conceptual.

[24]  Thomas Brox,et al.  U-Net: deep learning for cell counting, detection, and morphometry , 2018, Nature Methods.

[25]  Richard A. Schwarz,et al.  Noninvasive diagnostic adjuncts for the evaluation of potentially premalignant oral epithelial lesions: current limitations and future directions , 2018, Oral surgery, oral medicine, oral pathology and oral radiology.

[26]  José García Rodríguez,et al.  A Review on Deep Learning Techniques Applied to Semantic Segmentation , 2017, ArXiv.

[27]  Ian D. Reid,et al.  RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[29]  Eugenio Culurciello,et al.  ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation , 2016, ArXiv.

[30]  Kristen C. Maitland,et al.  A novel multimodal optical imaging system for early detection of oral cancer. , 2016, Oral surgery, oral medicine, oral pathology and oral radiology.

[31]  Radu Herbei,et al.  Classification with reject option , 2006 .

[32]  Timothy J Muldoon,et al.  Subcellular-resolution molecular imaging within living tissue by fiber microendoscopy. , 2007, Optics express.

[33]  Rebecca R. Richards-Kortum,et al.  Development of an integrated multimodal optical imaging system with real-time image analysis for the evaluation of oral premalignant lesions , 2019, Journal of biomedical optics.

[34]  Runhua Shi,et al.  Confocal Laser Endomicroscopy in the Detection of Head and Neck Precancerous Lesions , 2014, Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery.

[35]  M. Rajadhyaksha,et al.  In vivo confocal microscopy for the oral cavity: Current state of the field and future potential. , 2016, Oral oncology.

[36]  E. S. Pearson,et al.  THE USE OF CONFIDENCE OR FIDUCIAL LIMITS ILLUSTRATED IN THE CASE OF THE BINOMIAL , 1934 .

[37]  Javier A. Jo,et al.  Handheld tunable focus confocal microscope utilizing a double-clad fiber coupler for in vivo imaging of oral epithelium , 2017, Journal of biomedical optics.

[38]  Vijayashree S. Bhattar,et al.  Accuracy of In Vivo Multimodal Optical Imaging for Detection of Oral Neoplasia , 2012, Cancer Prevention Research.