Autoscope: automated otoscopy image analysis to diagnose ear pathology and use of clinically motivated eardrum features

Şenaras, Çağlar; Moberly, Aaron C.; Teknos, Theodoros N.; Essig, Garth; Elmaraghy, Charles; Taj-Schaal, Nazhat; Yu, Lianbo; Gürcan, Metin N.

doi:10.1117/12.2250592

Cited by 18 publications

(34 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To perform the classification tests, we randomly splitted the images into a training set (576 images, 80%) and a validation set (144 images, 20%) as can be seen in Table 1. Such random splitting was performed 100 times, following the guidelines previously published in [26,47]. For each split, we trained the machine learning models using training data set and evaluated each model performance on the validation data set.…”

Section: Resultsmentioning

confidence: 99%

“…A more complete study to classify middle ear diseases was presented in [26]. Although the results were presented as a binary classification like a normal and abnormal case, the methodology included specific information for each disease such as tympanosclerosis, perforation, cerumen, retraction and post-injection crust.…”

Section: Plos Onementioning

confidence: 99%

“…Furthermore, the classification stage was made using classical SVM approach. A more complete study to classify middle ear diseases was presented in [26], which included specific information for diseases such as tympanosclerosis, perforation, cerumen, retraction and post-injection crust. Other studies such as [27] and [28] proposed smartphone-based diagnostic system.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computer-aided diagnosis of external and middle ear conditions: A machine learning approach

et al. 2020

View full text Add to dashboard Cite

In medicine, a misdiagnosis or the absence of specialists can affect the patient's health, leading to unnecessary tests and increasing the costs of healthcare. In particular, the lack of specialists in otolaryngology in third world countries forces patients to seek medical attention from general practitioners, whom might not have enough training and experience for making correct diagnosis in this field. To tackle this problem, we propose and test a computer-aided system based on machine learning models and image processing techniques for otoscopic examination, as a support for a more accurate diagnosis of ear conditions at primary care before specialist referral; in particular, for myringosclerosis, earwax plug, and chronic otitis media. To characterize the tympanic membrane and ear canal for each condition, we implemented three different feature extraction methods: color coherence vector, discrete cosine transform, and filter bank. We also considered three machine learning algorithms: support vector machine (SVM), k-nearest neighbor (k-NN) and decision trees to develop the ear condition predictor model. To conduct the research, our database included 160 images as testing set and 720 images as training and validation sets of 180 patients. We repeatedly trained the learning models using the training dataset and evaluated them using the validation dataset to thus obtain the best feature extraction method and learning model that produce the highest validation accuracy. The results showed that the SVM and k-NN presented the best performance followed by decision trees model. Finally, we performed a classification stage-i.e., diagnosis-using testing data, where the SVM model achieved an average classification accuracy of 93.9%, average sensitivity of 87.8%, average specificity of 95.9%, and average positive predictive value of 87.7%. The results show that this system might be used for general practitioners as a reference to make better decisions in the ear pathologies diagnosis.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Plos Onementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computer-aided diagnosis of external and middle ear conditions: A machine learning approach

et al. 2020

View full text Add to dashboard Cite

show abstract

“…19 Continued developments in technology that provide improved otoscopic visualization and automated feedback may provide better ways both to enhance clinicians' otoscopic diagnostic performance and assist trainees in refining their otoscopic skills. 20,21 Specifically, although this study assessed student ability to diagnose common ear pathologies, trainees need to develop a skillset that enables them to differentiate with otoscopy many important ear pathologies, including AOM, middle ear effusion, and cholesteatoma.…”

Section: Discussionmentioning

confidence: 99%

Diagnostic accuracy and confidence for otoscopy: Are medical students receiving sufficient training?

et al. 2018

Self Cite

View full text Add to dashboard Cite

Objectives/Hypothesis To assess the confidence and abilities of medical students to diagnose specific types of otologic pathology, and to determine how different training experiences in medical school impact these outcomes. Study Design Survey analysis. Methods Sixty third‐ and fourth‐year medical students completed a computerized online survey. Participants answered questions about their otoscopic training experience and confidence, and provided diagnoses for 72 digital images taken with a high‐definition video otoscope that showed common otologic pathologies of the tympanic membrane and middle ear space. Results Most participants (65%) had received less exposure to otoscopic training in medical school than they expected. Confidence in diagnostic ability was low. For diagnostic ability, the mean percent correct across pathologies was 54% ± 7.7%. Medical school year (P = .006), intended specialty (P = .022), and total number of otolaryngology rotations (P = .048) were predictive of diagnostic accuracy on univariable logistic regression analyses, but medical school year (P = .039) was the only significant independent predictor in multivariable analysis. Intended specialty (P = .047) and total number of otolaryngology rotations (P = .035) were predictive of prequiz diagnostic confidence on univariable logistic regression analyses. Conclusions Medical students were not satisfied with their exposure to otoscopic training. Intended specialty, total number of otolaryngology rotations, and year in medical school predicted diagnostic accuracy. Intended specialty and total number of otolaryngology rotations predicted diagnostic confidence. Additional studies are needed to investigate how training experiences can be improved to optimize otoscopy training during medical school. Level of Evidence NA Laryngoscope, 129:1891–1897, 2019

show abstract

“…Unlike most existing medical image retrieval studies, our proposed system is based on deep learning techniques [13]. To date, there have been a few studies regarding the classification of otoscopic images using binary classifiers [14][15][16], which are deep neural network-based systems to classify images, but these have been limited to providing "normal" versus "abnormal" distinctions of the images [5,17]. However, in these systems, similar images are not shown after the diagnostic decision.…”

Section: Introductionmentioning

confidence: 99%

OtoMatch: Content-based eardrum image retrieval using deep learning

et al. 2020

Self Cite

View full text Add to dashboard Cite

Acute infections of the middle ear are the most commonly treated childhood diseases. Because complications affect children's language learning and cognitive processes, it is essential to diagnose these diseases in a timely and accurate manner. The prevailing literature suggests that it is difficult to accurately diagnose these infections, even for experienced ear, nose, and throat (ENT) physicians. Advanced care practitioners (e.g., nurse practitioners, physician assistants) serve as first-line providers in many primary care settings and may benefit from additional guidance to appropriately determine the diagnosis and treatment of ear diseases. For this purpose, we designed a content-based image retrieval (CBIR) system (called OtoMatch) for normal, middle ear effusion, and tympanostomy tube conditions, operating on eardrum images captured with a digital otoscope. We present a method that enables the conversion of any convolutional neural network (trained for classification) into an image retrieval model. As a proof of concept, we converted a pre-trained deep learning model into an image retrieval system. We accomplished this by changing the fully connected layers into lookup tables. A database of 454 labeled eardrum images (179 normal, 179 effusion, and 96 tube cases) was used to train and test the system. On a 10fold cross validation, the proposed method resulted in an average accuracy of 80.58% (SD 5.37%), and maximum F1 score of 0.90 while retrieving the most similar image from the database. These are promising results for the first study to demonstrate the feasibility of developing a CBIR system for eardrum images using the newly proposed methodology.

show abstract

Autoscope: automated otoscopy image analysis to diagnose ear pathology and use of clinically motivated eardrum features

Cited by 18 publications

References 7 publications

Computer-aided diagnosis of external and middle ear conditions: A machine learning approach

Computer-aided diagnosis of external and middle ear conditions: A machine learning approach

Diagnostic accuracy and confidence for otoscopy: Are medical students receiving sufficient training?

OtoMatch: Content-based eardrum image retrieval using deep learning

Contact Info

Product

Resources

About