Computer-Aided Diagnosis of Label-Free 3-D Optical Coherence Microscopy Images of Human Cervical Tissue

Objective: Ultrahigh-resolution optical coherence microscopy (OCM) has recently demonstrated its potential for accurate diagnosis of human cervical diseases. One major challenge for clinical adoption, however, is the steep learning curve clinicians need to overcome to interpret OCM images. Developing an intelligent technique for computer-aided diagnosis (CADx) to accurately interpret OCM images will facilitate clinical adoption of the technology and improve patient care. Methods: 497 high-resolution three-dimensional (3-D) OCM volumes (600 cross-sectional images each) were collected from 159 ex vivo specimens of 92 female patients. OCM image features were extracted using a convolutional neural network (CNN) model, concatenated with patient information [e.g., age and human papillomavirus (HPV) results], and classified using a support vector machine classifier. Ten-fold cross-validations were utilized to test the performance of the CADx method in a five-class classification task and a binary classification task. Results: An 88.3 ± 4.9% classification accuracy was achieved for five fine-grained classes of cervical tissue, namely normal, ectropion, low-grade and high-grade squamous intraepithelial lesions (LSIL and HSIL), and cancer. In the binary classification task [low-risk (normal, ectropion, and LSIL) versus high-risk (HSIL and cancer)], the CADx method achieved an area-under-the-curve value of 0.959 with an 86.7 ± 11.4% sensitivity and 93.5 ± 3.8% specificity. Conclusion: The proposed deep-learning-based CADx method outperformed four human experts. It was also able to identify morphological characteristics in OCM images that were consistent with histopathological interpretations. Significance: Label-free OCM imaging, combined with deep-learning-based CADx methods, holds a great promise to be used in clinical settings for the effective screening and diagnosis of cervical diseases.

[1]  J. Fujimoto,et al.  Optical biopsy and imaging using optical coherence tomography , 1995, Nature Medicine.

[2]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Eva Lankenau,et al.  Detection of cervical intraepithelial neoplasia by using optical coherence tomography in combination with microscopy , 2017, Journal of biomedical optics.

[4]  P. Sodhani,et al.  Performance of a low cost magnifying device, magnivisualizer, versus colposcope for detection of pre-cancer and cancerous lesions of uterine cervix , 2014, Journal of gynecologic oncology.

[5]  M. Schiffman,et al.  American Cancer Society, American Society for Colposcopy and Cervical Pathology, and American Society for Clinical Pathology screening guidelines for the prevention and early detection of cervical cancer , 2012, CA: a cancer journal for clinicians.

[6]  Clare Gilham,et al.  Efficacy of HPV-based screening for prevention of invasive cervical cancer: follow-up of four European randomised controlled trials , 2014, The Lancet.

[7]  Alan D. Lopez,et al.  Global, Regional, and National Cancer Incidence, Mortality, Years of Life Lost, Years Lived With Disability, and Disability-Adjusted Life-years for 32 Cancer Groups, 1990 to 2015: A Systematic Analysis for the Global Burden of Disease Study , 2017, JAMA oncology.

[8]  Karl Pearson F.R.S. LIII. On lines and planes of closest fit to systems of points in space , 1901 .

[9]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[10]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[11]  P. Escobar,et al.  Diagnostic efficacy of optical coherence tomography in the management of preinvasive and invasive cancer of uterine cervix and vulva , 2003, International Journal of Gynecologic Cancer.

[12]  J. Fujimoto,et al.  Optical coherence microscopy in scattering media. , 1994, Optics letters.

[13]  K. Friese,et al.  Optical coherence tomography as a non‐invasive imaging technique for preinvasive and invasive neoplasia of the uterine cervix , 2010, Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology.

[14]  Nima Tajbakhsh,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE Transactions on Medical Imaging.

[15]  American society for colposcopy and cervical pathology. , 1997, Journal of lower genital tract disease.

[16]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[17]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[18]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[19]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[20]  Beop-Min Kim,et al.  Optical diagnosis of cervical intraepithelial neoplasm (CIN) using polarization-sensitive optical coherence tomography. , 2008, Optics express.

[21]  Jason Jerwick,et al.  Ultrahigh-resolution optical coherence microscopy accurately classifies precancerous and cancerous human cervix free of labeling , 2018, Theranostics.

[22]  Petra M. Casey,et al.  Abnormal cervical appearance: what to do, when to worry? , 2011, Mayo Clinic proceedings.

[23]  Brett E. Bouma,et al.  In vivo cellular optical coherence tomography imaging , 1998, Nature Medicine.

[24]  G. Ripandelli,et al.  Optical coherence tomography. , 1998, Seminars in ophthalmology.

[25]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[26]  J. Fujimoto,et al.  In vivo endoscopic optical biopsy with optical coherence tomography. , 1997, Science.

[27]  Mohammad Hossein Khosravi,et al.  Global, Regional, and National Cancer Incidence, Mortality, Years of Life Lost, Years Lived With Disability, and Disability-Adjusted Life-Years for 29 Cancer Groups, 1990 to 2016 , 2018, JAMA oncology.

[28]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[29]  Mubarak Shah,et al.  Visual attention detection in video sequences using spatiotemporal cues , 2006, MM '06.

[30]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[31]  Christopher Joseph Pal,et al.  Brain tumor segmentation with Deep Neural Networks , 2015, Medical Image Anal..

[32]  D. D. de Bruin,et al.  Optical biopsy of epithelial cancers by optical coherence tomography (OCT) , 2013, Lasers in Medical Science.

[33]  Liming Wang,et al.  An artificial intelligence platform for the multihospital collaborative management of congenital cataracts , 2017, Nature Biomedical Engineering.

[34]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .

[35]  P. Escobar,et al.  Optical coherence tomography as a diagnostic aid to visual inspection and colposcopy for preinvasive and invasive cancer of the uterine cervix , 2006, International Journal of Gynecologic Cancer.

[36]  D. Sculley,et al.  Google Vizier: A Service for Black-Box Optimization , 2017, KDD.

[37]  Daniel S. Kermany,et al.  Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning , 2018, Cell.

[38]  Xin Qi,et al.  Diagnostic efficacy of computer extracted image features in optical coherence tomography of the precancerous cervix. , 2011, Medical physics.

[39]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[40]  J. Fleiss Measuring nominal scale agreement among many raters. , 1971 .

[41]  A. Jemal,et al.  Cancer statistics, 2017 , 2017, CA: a cancer journal for clinicians.

[42]  G. Gelikonov,et al.  In vivo endoscopic OCT imaging of precancer and cancer states of human mucosa. , 1997, Optics express.

[43]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

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

[45]  A. Agresti,et al.  Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions , 1998 .