ELHnet: a convolutional neural network for classifying cochlear endolymphatic hydrops imaged with optical coherence tomography

Can GPT-4 revolutionize otolaryngology? Navigating opportunities and ethical considerations

Otolaryngologists can enhance workflow efficiency, provide better patient care, and advance medical research and education by integrating artificial intelligence (AI) into their practices. GPT-4 technology is a revolutionary and contemporary example of AI that may apply to otolaryngology. The knowledge of otolaryngologists should be supplemented, not replaced when using GPT-4 to make critical medical decisions and provide individualized patient care. In our thorough examination, we explore the potential uses of the groundbreaking GPT-4 technology in the field of otolaryngology, covering aspects such as potential outcomes and technical boundaries. Additionally, we delve into the intricate and intellectually challenging dilemmas that emerge when incorporating GPT-4 into otolaryngology, considering the ethical considerations inherent in its implementation. Our stance is that GPT-4 has the potential to be very helpful. Its capabilities, which include aid in clinical decision-making, patient care, and administrative job automation, present exciting possibilities for enhancing patient outcomes, boosting the efficiency of healthcare delivery, and enhancing patient experiences. Even though there are still certain obstacles and limitations, the progress made so far shows that GPT-4 can be a valuable tool for modern medicine. GPT-4 may play a more significant role in clinical practice as technology develops, helping medical professionals deliver high-quality care tailored to every patient's unique needs.

Blast Overpressures as a Military and Occupational Health Concern

PURPOSE

This tutorial reviews effects of environmental stressors like blast overpressures and other well-known acoustic contaminants (continuous, intermittent, and impulsive noise) on hearing, tinnitus, vestibular, and balance-related functions. Based on the overall outcome of these effects, detailed consideration is given to the health and well-being of individuals.

METHOD

Because hearing loss and tinnitus are consequential in affecting quality of life, novel neuromodulation paradigms are reviewed for their positive abatement and treatment-related effects. Examples of clinical data, research strategies, and methodological approaches focus on repetitive transcranial magnetic stimulation (rTMS) and electrical stimulation of the vagus nerve paired with tones (VNSt) for their unique contributions to this area.

RESULTS

Acoustic toxicants transmitted through the atmosphere are noteworthy for their propensity to induce hearing loss and tinnitus. Mounting evidence also indicates that high-level rapid onset changes in atmospheric sound pressure can significantly impact vestibular and balance function. Indeed, the risk of falling secondary to loss of, or damage to, sensory receptor cells in otolith organs (utricle and saccule) is a primary reason for this concern. As part of the complexities involved in VNSt treatment strategies, vocal dysfunction may also manifest. In addition, evaluation of temporospatial gait parameters is worthy of consideration based on their ability to detect and monitor incipient neurological disease, cognitive decline, and mortality.

CONCLUSION

Highlighting these respective areas underscores the need to enhance information exchange among scientists, clinicians, and caregivers on the benefits and complications of these outcomes.

End-to-end deep learning classification of vocal pathology using stacked vowels

Objectives

Advances in artificial intelligence (AI) technology have increased the feasibility of classifying voice disorders using voice recordings as a screening tool. This work develops upon previous models that take in single vowel recordings by analyzing multiple vowel recordings simultaneously to enhance prediction of vocal pathology.

Methods

Voice samples from the Saarbruecken Voice Database, including three sustained vowels (/a/, /i/, /u/) from 687 healthy human participants and 334 dysphonic patients, were used to train 1-dimensional convolutional neural network models for multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings. Three models were trained: (1) a baseline model that analyzed individual vowels in isolation, (2) a stacked vowel model that analyzed three vowels (/a/, /i/, /u/) in the neutral pitch simultaneously, and (3) a stacked pitch model that analyzed the /a/ vowel in three pitches (low, neutral, and high) simultaneously.

Results

For multiclass classification of healthy, hyperfunctional dysphonia, and laryngitis voice recordings, the stacked vowel model demonstrated higher performance compared with the baseline and stacked pitch models (F1 score 0.81 vs. 0.77 and 0.78, respectively). Specifically, the stacked vowel model achieved higher performance for class-specific classification of hyperfunctional dysphonia voice samples compared with the baseline and stacked pitch models (F1 score 0.56 vs. 0.49 and 0.50, respectively).

Conclusions

This study demonstrates the feasibility and potential of analyzing multiple sustained vowel recordings simultaneously to improve AI-driven screening and classification of vocal pathology. The stacked vowel model architecture in particular offers promise to enhance such an approach.

Lay Summary

AI analysis of multiple vowel recordings can improve classification of voice pathologies compared with models using a single sustained vowel and offer a strategy to enhance AI-driven screening of voice disorders.

Level of Evidence

3.

Deep learning classification of inverted papilloma malignant transformation using 3D convolutional neural networks and magnetic resonance imaging

BACKGROUND

Distinguishing benign inverted papilloma (IP) tumors from those that have undergone malignant transformation to squamous cell carcinoma (IP-SCC) is important but challenging to do preoperatively. Magnetic resonance imaging (MRI) can help differentiate these 2 entities, but no established method exists that can automatically synthesize all potentially relevant MRI image features to distinguish IP and IP-SCC. We explored a deep learning approach, using 3-dimensional convolutional neural networks (CNNs), to address this challenge.

METHODS

Retrospective chart reviews were performed at 2 institutions to create a data set of preoperative MRIs with corresponding surgical pathology reports. The MRI data set included all available MRI sequences in the axial plane, which were used to train, validate, and test 3 CNN models. Saliency maps were generated to visualize areas of MRIs with greatest influence on predictions.

RESULTS

A total of 90 patients with IP (n = 64) or IP-SCC (n = 26) tumors were identified, with a total of 446 images of distinct MRI sequences for IP (n = 329) or IP-SCC (n = 117). The best CNN model, All-Net, demonstrated a sensitivity of 66.7%, specificity of 81.5%, overall accuracy of 77.9%, and receiver-operating characteristic area under the curve of 0.80 (95% confidence interval, 0.682-0.898) for test classification performance. The other 2 models, Small-All-Net and Elastic-All-Net, showed similar performance levels.

CONCLUSION

A deep learning approach with 3-dimensional CNNs can distinguish IP and IP-SCC with moderate test classification performance. Although CNNs demonstrate promise to enhance the prediction of IP-SCC using MRIs, more data are needed before they can reach the predictive value already established by human MRI evaluation.

In Vivo Cochlear imaging provides a tool to study endolymphatic hydrops

Exposure to noise trauma, such as that from improvised explosive devices, can lead to sensorineural hearing loss and a reduced quality of life. In order to elucidate the mechanisms underlying noise-induced hearing loss, we have adapted optical coherence tomography (OCT) for real-time cochlear visualization in live mice after blast exposure. We demonstrated that endolymphatic hydrops develops following blast injury, and that this phenomenon may be associated with glutamate excitotoxicity and cochlear synaptopathy. Additionally, osmotic stabilization of endolymphatic hydrops partially rescues cochlear synapses after blast trauma. OCT is thus a valuable research tool for investigating the mechanisms underlying acoustic trauma and dynamic changes in endolymph volume. It may also help with the diagnosis and treatment of human hearing loss and/or vertigo in the near future.

Deep learning architecture "LightOCT" for diagnostic decision support using optical coherence tomography images of biological samples

Optical coherence tomography (OCT) is being increasingly adopted as a label-free and non-invasive technique for biomedical applications such as cancer and ocular disease diagnosis. Diagnostic information for these tissues is manifest in textural and geometric features of the OCT images, which are used by human expertise to interpret and triage. However, it suffers delays due to the long process of the conventional diagnostic procedure and shortage of human expertise. Here, a custom deep learning architecture, LightOCT, is proposed for the classification of OCT images into diagnostically relevant classes. LightOCT is a convolutional neural network with only two convolutional layers and a fully connected layer, but it is shown to provide excellent training and test results for diverse OCT image datasets. We show that LightOCT provides 98.9% accuracy in classifying 44 normal and 44 malignant (invasive ductal carcinoma) breast tissue volumetric OCT images. Also, >96% accuracy in classifying public datasets of ocular OCT images as normal, age-related macular degeneration and diabetic macular edema. Additionally, we show ∼96% test accuracy for classifying retinal images as belonging to choroidal neovascularization, diabetic macular edema, drusen, and normal samples on a large public dataset of more than 100,000 images. The performance of the architecture is compared with transfer learning based deep neural networks. Through this, we show that LightOCT can provide significant diagnostic support for a variety of OCT images with sufficient training and minimal hyper-parameter tuning. The trained LightOCT networks for the three-classification problem will be released online to support transfer learning on other datasets.

Multispectral Imaging for Automated Tissue Identification of Normal Human Surgical Specimens

OBJECTIVE

Safe surgery requires the accurate discrimination of tissue intraoperatively. We assess the feasibility of using multispectral imaging and deep learning to enhance surgical vision by automated identification of normal human head and neck tissues.

STUDY DESIGN

Construction and feasibility testing of novel multispectral imaging system for surgery.

SETTING

Academic university hospital.

SUBJECTS AND METHODS

Multispectral images of fresh-preserved human cadaveric tissues were captured with our adapted digital operating microscope. Eleven tissue types were sampled, each sequentially exposed to 6 lighting conditions. Two convolutional neural network machine learning models were developed to classify tissues based on multispectral and white-light color images (ARRInet-M and ARRInet-W, respectively). Blinded otolaryngology residents were asked to identify tissue specimens from white-light color images, and their performance was compared with that of the ARRInet models.

RESULTS

A novel multispectral imaging system was developed with minimal adaptation to an existing digital operating microscope. With 81.8% accuracy in tissue identification of full-size images, the multispectral ARRInet-M classifier outperformed the white-light-only ARRInet-W model (45.5%) and surgical residents (69.7%). Challenges with discrimination occurred with parotid vs fat and blood vessels vs nerve.

CONCLUSIONS

A deep learning model using multispectral imaging outperformed a similar model and surgical residents using traditional white-light imaging at the task of classifying normal human head and neck tissue ex vivo. These results suggest that multispectral imaging can enhance surgical vision and augment surgeons' ability to identify tissues during a procedure.

Optical coherence tomography: current and future clinical applications in otology

PURPOSE OF REVIEW

This article reviews literature on the use of optical coherence tomography (OCT) in otology and provides the reader with a timely update on its current clinical and research applications. The discussion focuses on the principles of OCT, the use of the technology for the diagnosis of middle ear disease and for the delineation of in-vivo cochlear microarchitecture and function.

RECENT FINDINGS

Recent advances in OCT include the measurement of structural and vibratory properties of the tympanic membrane, ossicles and inner ear in healthy and diseased states. Accurate, noninvasive diagnosis of middle ear disease, such as otosclerosis and acute otitis media using OCT, has been validated in clinical studies, whereas inner ear OCT imaging remains at the preclinical stage. The development of recent microscopic, otoscopic and endoscopic systems to address clinical and research problems is reviewed.

SUMMARY

OCT is a real-time, noninvasive, nonionizing, point-of-care imaging modality capable of imaging ear structures in vivo. Although current clinical systems are mainly focused on middle ear imaging, OCT has also been shown to have the ability to identify inner ear disease, an exciting possibility that will become increasingly relevant with the advent of targeted inner ear therapies.

Artificial Intelligence Applications in Otology: A State of the Art Review

Objective

Recent advances in artificial intelligence (AI) are driving innovative new health care solutions. We aim to review the state of the art of AI in otology and provide a discussion of work underway, current limitations, and future directions.

Data Sources

Two comprehensive databases, MEDLINE and EMBASE, were mined using a directed search strategy to identify all articles that applied AI to otology.

Review Methods

An initial abstract and title screening was completed. Exclusion criteria included nonavailable abstract and full text, language, and nonrelevance. References of included studies and relevant review articles were cross-checked to identify additional studies.

Conclusion

The database search identified 1374 articles. Abstract and title screening resulted in full-text retrieval of 96 articles. A total of N = 38 articles were retained. Applications of AI technologies involved the optimization of hearing aid technology (n = 5; 13% of all articles), speech enhancement technologies (n = 4; 11%), diagnosis and management of vestibular disorders (n = 11; 29%), prediction of sensorineural hearing loss outcomes (n = 9; 24%), interpretation of automatic brainstem responses (n = 5; 13%), and imaging modalities and image-processing techniques (n = 4; 10%). Publication counts of the included articles from each decade demonstrated a marked increase in interest in AI in recent years.

Implications for Practice

This review highlights several applications of AI that otologists and otolaryngologists alike should be aware of given the possibility of implementation in mainstream clinical practice. Although there remain significant ethical and regulatory challenges, AI powered systems offer great potential to shape how healthcare systems of the future operate and clinicians are key stakeholders in this process.

Artificial intelligence to detect tympanic membrane perforations

OBJECTIVE

To explore the feasibility of constructing a proof-of-concept artificial intelligence algorithm to detect tympanic membrane perforations, for future application in under-resourced rural settings.

METHODS

A retrospective review was conducted of otoscopic images analysed using transfer learning with Google's Inception-V3 convolutional neural network architecture. The 'gold standard' 'ground truth' was defined by otolaryngologists. Perforation size was categorised as less than one-third (small), one-third to two-thirds (medium), or more than two-thirds (large) of the total tympanic membrane diameter.

RESULTS

A total of 233 tympanic membrane images were used (183 for training, 50 for testing). The algorithm correctly identified intact and perforated tympanic membranes (overall accuracy = 76.0 per cent, 95 per cent confidence interval = 62.1-86.0 per cent); the area under the curve was 0.867 (95 per cent confidence interval = 0.771-0.963).

CONCLUSION

A proof-of-concept image-classification artificial intelligence algorithm can be used to detect tympanic membrane perforations and, with further development, may prove to be a valuable tool for ear disease screening. Future endeavours are warranted to develop a point-of-care tool for healthcare workers in areas distant from otolaryngology.

Phase unwrapping based on a residual en-decoder network for phase images in Fourier domain Doppler optical coherence tomography

To solve the phase unwrapping problem for phase images in Fourier domain Doppler optical coherence tomography (DOCT), we propose a deep learning-based residual en-decoder network (REDN) method. In our approach, we reformulate the definition for obtaining the true phase as obtaining an integer multiple of 2π at each pixel by semantic segmentation. The proposed REDN architecture can provide recognition performance with pixel-level accuracy. To address the lack of phase images that are noise and wrapping free from DOCT systems for training, we used simulated images synthesized with DOCT phase image background noise features. An evaluation study on simulated images, DOCT phase images of phantom milk flowing in a plastic tube and a mouse artery, was performed. Meanwhile, a comparison study with recently proposed deep learning-based DeepLabV3+ and PhaseNet methods for signal phase unwrapping and traditional modified networking programming (MNP) method was also performed. Both visual inspection and quantitative metrical evaluation based on accuracy, specificity, sensitivity, root-mean-square-error, total-variation, and processing time demonstrate the robustness, effectiveness and superiority of our method. The proposed REDN method will benefit accurate and fast DOCT phase image-based diagnosis and evaluation when the detected phase is wrapped and will enrich the deep learning-based image processing platform for DOCT images.

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

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.

The use of optical coherence tomography and convolutional neural networks to distinguish normal and abnormal oral mucosa

Incomplete surgical resection of head and neck squamous cell carcinoma (HNSCC) is the most common cause of local HNSCC recurrence. Currently, surgeons rely on preoperative imaging, direct visualization, palpation and frozen section to determine the extent of tissue resection. It has been demonstrated that optical coherence tomography (OCT), a minimally invasive, nonionizing near infrared mesoscopic imaging modality can resolve subsurface differences between normal and abnormal head and neck mucosa. Previous work has utilized two-dimensional OCT imaging which is limited to the evaluation of small regions of interest generated frame by frame. OCT technology is capable of performing rapid volumetric imaging, but the capacity and expertise to analyze this massive amount of image data is lacking. In this study, we evaluate the ability of a retrained convolutional neural network to classify three-dimensional OCT images of head and neck mucosa to differentiate normal and abnormal tissues with sensitivity and specificity of 100% and 70%, respectively. This method has the potential to serve as a real-time analytic tool in the assessment of surgical margins.

A contemporary review of machine learning in otolaryngology-head and neck surgery

One of the key challenges with big data is leveraging the complex network of information to yield useful clinical insights. The confluence of massive amounts of health data and a desire to make inferences and insights on these data has produced a substantial amount of interest in machine-learning analytic methods. There has been a drastic increase in the otolaryngology literature volume describing novel applications of machine learning within the past 5 years. In this timely contemporary review, we provide an overview of popular machine-learning techniques, and review recent machine-learning applications in otolaryngology-head and neck surgery including neurotology, head and neck oncology, laryngology, and rhinology. Investigators have realized significant success in validated models with model sensitivities and specificities approaching 100%. Challenges remain in the implementation of machine-learning algorithms. This may be in part the unfamiliarity of these techniques to clinician leaders on the front lines of patient care. Spreading awareness and confidence in machine learning will follow with further validation and proof-of-value analyses that demonstrate model performance superiority over established methods. We are poised to see a greater influx of machine-learning applications to clinical problems in otolaryngology-head and neck surgery, and it is prudent for providers to understand the potential benefits and limitations of these technologies. Laryngoscope, 130:45-51, 2020.

Automated classification of osteomeatal complex inflammation on computed tomography using convolutional neural networks

BACKGROUND

Convolutional neural networks (CNNs) are advanced artificial intelligence algorithms well suited to image classification tasks with variable features. These have been used to great effect in various real-world applications including handwriting recognition, face detection, image search, and fraud prevention. We sought to retrain a robust CNN with coronal computed tomography (CT) images to classify osteomeatal complex (OMC) occlusion and assess the performance of this technology with rhinologic data.

METHODS

The Google Inception-V3 CNN trained with 1.28 million images was used as the base model. Preoperative coronal sections through the OMC were obtained from 239 patients enrolled in 2 prospective chronic rhinosinusitis (CRS) outcomes studies, labeled according to OMC status, and mirrored to obtain a set of 956 images. Using this data, the classification layer of Inception-V3 was retrained in Python using a transfer learning method to adapt the CNN to the task of interpreting sinonasal CT images.

RESULTS

The retrained neural network achieved 85% classification accuracy for OMC occlusion, with a 95% confidence interval for algorithm accuracy of 78% to 92%. Receiver operating characteristic (ROC) curve analysis on the test set confirmed good classification ability of the CNN with an area under the ROC curve (AUC) of 0.87, significantly different than both random guessing and a dominant classifier that predicts the most common class (p < 0.0001).

CONCLUSION

Current state-of-the-art CNNs may be able to learn clinically relevant information from 2-dimensional sinonasal CT images with minimal supervision. Future work will extend this approach to 3-dimensional images in order to further refine this technology for possible clinical applications.

Evaluation of segmentation algorithms for optical coherence tomography images of ovarian tissue

Ovarian cancer has the lowest survival rate among all gynecologic cancers predominantly due to late diagnosis. Early detection of ovarian cancer can increase 5-year survival rates from 40% up to 92%, yet no reliable early detection techniques exist. Optical coherence tomography (OCT) is an emerging technique that provides depth-resolved, high-resolution images of biological tissue in real-time and demonstrates great potential for imaging of ovarian tissue. Mouse models are crucial to quantitatively assess the diagnostic potential of OCT for ovarian cancer imaging; however, due to small organ size, the ovaries must first be separated from the image background using the process of segmentation. Manual segmentation is time-intensive, as OCT yields three-dimensional data. Furthermore, speckle noise complicates OCT images, frustrating many processing techniques. While much work has investigated noise-reduction and automated segmentation for retinal OCT imaging, little has considered the application to the ovaries, which exhibit higher variance and inhomogeneity than the retina. To address these challenges, we evaluate a set of algorithms to segment OCT images of mouse ovaries. We examine five preprocessing techniques and seven segmentation algorithms. While all preprocessing methods improve segmentation, Gaussian filtering is most effective, showing an improvement of 32 % ± 1.2 % . Of the segmentation algorithms, active contours performs best, segmenting with an accuracy of 94.8 % ± 1.2 % compared with manual segmentation. Even so, further optimization could lead to maximizing the performance for segmenting OCT images of the ovaries.

Deep longitudinal transfer learning-based automatic segmentation of photoreceptor ellipsoid zone defects on optical coherence tomography images of macular telangiectasia type 2

Photoreceptor ellipsoid zone (EZ) defects visible on optical coherence tomography (OCT) are important imaging biomarkers for the onset and progression of macular diseases. As such, accurate quantification of EZ defects is paramount to monitor disease progression and treatment efficacy over time. We developed and trained a novel deep learning-based method called Deep OCT Atrophy Detection (DOCTAD) to automatically segment EZ defect areas by classifying 3-dimensional A-scan clusters as normal or defective. Furthermore, we introduce a longitudinal transfer learning paradigm in which the algorithm learns from segmentation errors on images obtained at one time point to segment subsequent images with higher accuracy. We evaluated the performance of this method on 134 eyes of 67 subjects enrolled in a clinical trial of a novel macular telangiectasia type 2 (MacTel2) therapeutic agent. Our method compared favorably to other deep learning-based and non-deep learning-based methods in matching expert manual segmentations. To the best of our knowledge, this is the first automatic segmentation method developed for EZ defects on OCT images of MacTel2.