OtoPair: Combining Right and Left Eardrum Otoscopy Images to Improve the Accuracy of Automated Image Analysis

Color Dependence Analysis in a CNN-Based Computer-Aided Diagnosis System for Middle and External Ear Diseases

Artificial intelligence-assisted otologic diagnosis has been of growing interest in the scientific community, where middle and external ear disorders are the most frequent diseases in daily ENT practice. There are some efforts focused on reducing medical errors and enhancing physician capabilities using conventional artificial vision systems. However, approaches with multispectral analysis have not yet been addressed. Tissues of the tympanic membrane possess optical properties that define their characteristics in specific light spectra. This work explores color wavelengths dependence in a model that classifies four middle and external ear conditions: normal, chronic otitis media, otitis media with effusion, and earwax plug. The model is constructed under a computer-aided diagnosis system that uses a convolutional neural network architecture. We trained several models using different single-channel images by taking each color wavelength separately. The results showed that a single green channel model achieves the best overall performance in terms of accuracy (92%), sensitivity (85%), specificity (95%), precision (86%), and F1-score (85%). Our findings can be a suitable alternative for artificial intelligence diagnosis systems compared to the 50% of overall misdiagnosis of a non-specialist physician.

Emerging artificial intelligence applications in otological imaging

PURPOSE OF REVIEW

To highlight the recent literature on artificial intelligence (AI) pertaining to otological imaging and to discuss future directions, obstacles and opportunities.

RECENT FINDINGS

The main themes in the recent literature centre around automated otoscopic image diagnosis and automated image segmentation for application in virtual reality surgical simulation and planning. Other applications that have been studied include identification of tinnitus MRI biomarkers, facial palsy analysis, intraoperative augmented reality systems, vertigo diagnosis and endolymphatic hydrops ratio calculation in Meniere's disease. Studies are presently at a preclinical, proof-of-concept stage.

SUMMARY

The recent literature on AI in otological imaging is promising and demonstrates the future potential of this technology in automating certain imaging tasks in a healthcare environment of ever-increasing demand and workload. Some studies have shown equivalence or superiority of the algorithm over physicians, albeit in narrowly defined realms. Future challenges in developing this technology include the compilation of large high quality annotated datasets, fostering strong collaborations between the health and technology sectors, testing the technology within real-world clinical pathways and bolstering trust among patients and physicians in this new method of delivering healthcare.

Convolutional Neural Network-Based Clinical Predictors of Oral Dysplasia: Class Activation Map Analysis of Deep Learning Results

Oral cancer/oral squamous cell carcinoma is among the top ten most common cancers globally, with over 500,000 new cases and 350,000 associated deaths every year worldwide. There is a critical need for objective, novel technologies that facilitate early, accurate diagnosis. For this purpose, we have developed a method to classify images as "suspicious" and "normal" by performing transfer learning on Inception-ResNet-V2 and generated automated heat maps to highlight the region of the images most likely to be involved in decision making. We have tested the developed method's feasibility on two independent datasets of clinical photographic images of 30 and 24 patients from the UK and Brazil, respectively. Both 10-fold cross-validation and leave-one-patient-out validation methods were performed to test the system, achieving accuracies of 73.6% (±19%) and 90.9% (±12%), F1-scores of 97.9% and 87.2%, and precision values of 95.4% and 99.3% at recall values of 100.0% and 81.1% on these two respective cohorts. This study presents several novel findings and approaches, namely the development and validation of our methods on two datasets collected in different countries showing that using patches instead of the whole lesion image leads to better performance and analyzing which regions of the images are predictive of the classes using class activation map analysis.