Deep metric learning for otitis media classification

In this study, we propose an automatic diagnostic algorithm for detecting otitis media based on otoscopy images of the tympanic membrane. A total of 1336 images were assessed by a medical specialist into three diagnostic groups: acute otitis media, otitis media with effusion, and no effusion. To provide proper treatment and care and limit the use of unnecessary antibiotics, it is crucial to correctly detect tympanic membrane abnormalities, and to distinguish between acute otitis media and otitis media with effusion. The proposed approach for this classification task is based on deep metric learning, and this study compares the performance of different distance-based metric loss functions. Contrastive loss, triplet loss and multi-class N-pair loss are employed, and compared with the performance of standard cross-entropy and class-weighted cross-entropy classification networks. Triplet loss achieves high precision on a highly imbalanced data set, and the deep metric methods provide useful insight into the decision making of a neural network. The results are comparable to the best clinical experts and paves the way for more accurate and operator-independent diagnosis of otitis media.

[1]  J. Kittler,et al.  Comparative study of Hough Transform methods for circle finding , 1990, Image Vis. Comput..

[2]  Yann LeCun,et al.  Dimensionality Reduction by Learning an Invariant Mapping , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[3]  M. Pichichero,et al.  Assessing diagnostic accuracy and tympanocentesis skills in the management of otitis media. , 2001, Archives of pediatrics & adolescent medicine.

[4]  Yann LeCun,et al.  Learning a similarity metric discriminatively, with application to face verification , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  O. Hjalmarson,et al.  Adherence to treatment guidelines for acute otitis media in children. The necessity of an effective strategy of guideline implementation. , 2014, International journal of pediatric otorhinolaryngology.

[6]  Jelena Kovacevic,et al.  Automated Diagnosis of Otitis Media: Vocabulary and Grammar , 2013, Int. J. Biomed. Imaging.

[7]  I. Williamson,et al.  Otitis media with effusion in children: current management , 2012 .

[8]  H. Bauchner,et al.  Pediatricians' Attitudes, Beliefs, and Practices Regarding Clinical Practice Guidelines: A National Survey , 2000, Pediatrics.

[9]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Constantin Vertan,et al.  Automatic pediatric otitis detection by classification of global image features , 2011, 2011 E-Health and Bioengineering Conference (EHB).

[11]  Kihyuk Sohn,et al.  Improved Deep Metric Learning with Multi-class N-pair Loss Objective , 2016, NIPS.

[12]  Maria Francisca Colella-Santos,et al.  Wideband Tympanometry Wideband Tympanometry , 2017 .

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

[14]  Josef Kittler,et al.  A Comparative Study of Hough Transform Methods for Circle Finding , 1989, Alvey Vision Conference.

[15]  E. Çiftçi,et al.  Evaluation of clinical approaches and physician adherence to guidelines for otitis media with effusion. , 2018, International journal of pediatric otorhinolaryngology.

[16]  Hermanus Carel Myburgh,et al.  Towards low cost automated smartphone- and cloud-based otitis media diagnosis , 2018, Biomed. Signal Process. Control..

[17]  J. Lous,et al.  Criteria, performance and diagnostic problems in diagnosing acute otitis media. , 1999, Family practice.

[18]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[19]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Metin Nafi Gürcan,et al.  Detection of eardrum abnormalities using ensemble deep learning approaches , 2018, Medical Imaging.

[21]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[22]  Federico Marchetti,et al.  Burden of Disease Caused by Otitis Media: Systematic Review and Global Estimates , 2012, PloS one.

[23]  Edward Y. Chang,et al.  Transfer representation learning for medical image analysis , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[24]  Zhifeng Liu,et al.  Fine-Grained Classification of Endoscopic Tympanic Membrane Images , 2019, 2019 IEEE International Conference on Image Processing (ICIP).

[25]  M. Pichichero.  Acute otitis media: part II. Treatment in an era of increasing antibiotic resistance. , 2000, American family physician.

[26]  M. Lo,et al.  Development of an Automatic Diagnostic Algorithm for Pediatric Otitis Media. , 2018, Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology.

[27]  Chongwon Pae,et al.  Automated diagnosis of ear disease using ensemble deep learning with a big otoendoscopy image database , 2019, EBioMedicine.

[28]  Anne Pitkäranta,et al.  Is it possible to diagnose acute otitis media accurately in primary health care? , 2003, Family practice.

[29]  Jay Shah,et al.  Decision fusion on image analysis and tympanometry to detect eardrum abnormalities , 2020, Medical Imaging.

[30]  Hermanus C. Myburgh,et al.  Otitis Media Diagnosis for Developing Countries Using Tympanic Membrane Image-Analysis , 2016, EBioMedicine.

[31]  Yi Yang,et al.  Random Erasing Data Augmentation , 2017, AAAI.

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

[33]  Hasan Şakir Bilge,et al.  Deep Metric Learning: A Survey , 2019, Symmetry.

[34]  Pa-Chun Wang,et al.  A hybrid feature-based segmentation and classification system for the computer aided self-diagnosis of otitis media , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.