Computer-aided diagnosis of laryngeal cancer via deep learning based on laryngoscopic images

Improving laryngeal cancer detection using chaotic metaheuristics integration with squeeze-and-excitation resnet model

Laryngeal cancer (LC) represents a substantial world health problem, with diminished survival rates attributed to late-stage diagnoses. Correct treatment for LC is complex, particularly in the final stages. This kind of cancer is a complex malignancy inside the head and neck region of patients. Recently, researchers serving medical consultants to recognize LC efficiently develop different analysis methods and tools. However, these existing tools and techniques have various problems regarding performance constraints, like lesser accuracy in detecting LC at the early stages, additional computational complexity, and colossal time utilization in patient screening. Deep learning (DL) approaches have been established that are effective in the recognition of LC. Therefore, this study develops an efficient LC Detection using the Chaotic Metaheuristics Integration with the DL (LCD-CMDL) technique. The LCD-CMDL technique mainly focuses on detecting and classifying LC utilizing throat region images. In the LCD-CMDL technique, the contrast enhancement process uses the CLAHE approach. For feature extraction, the LCD-CMDL technique applies the Squeeze-and-Excitation ResNet (SE-ResNet) model to learn the complex and intrinsic features from the image preprocessing. Moreover, the hyperparameter tuning of the SE-ResNet approach is performed using a chaotic adaptive sparrow search algorithm (CSSA). Finally, the extreme learning machine (ELM) model was applied to detect and classify the LC. The performance evaluation of the LCD-CMDL approach occurs utilizing a benchmark throat region image database. The experimental values implied the superior performance of the LCD-CMDL approach over recent state-of-the-art approaches.

Artificial intelligence based diagnosis of sulcus: assesment of videostroboscopy via deep learning

PURPOSE

To develop a convolutional neural network (CNN)-based model for classifying videostroboscopic images of patients with sulcus, benign vocal fold (VF) lesions, and healthy VFs to improve clinicians' accuracy in diagnosis during videostroboscopies when evaluating sulcus.

MATERIALS AND METHODS

Videostroboscopies of 433 individuals who were diagnosed with sulcus (91), who were diagnosed with benign VF diseases (i.e., polyp, nodule, papilloma, cyst, or pseudocyst [311]), or who were healthy (33) were analyzed. After extracting 91,159 frames from videostroboscopies, a CNN-based model was created and tested. The healthy and sulcus groups underwent binary classification. In the second phase of the study, benign VF lesions were added to the training set, and multiclassification was executed across all groups. The proposed CNN-based model results were compared with five laryngology experts' assessments.

RESULTS

In the binary classification phase, the CNN-based model achieved 98% accuracy, 98% recall, 97% precision, and a 97% F1 score for classifying sulcus and healthy VFs. During the multiclassification phase, when evaluated on a subset of frames encompassing all included groups, the CNN-based model demonstrated greater accuracy when compared with that of the five laryngologists (%76 versus 72%, 68%, 72%, 63%, and 72%).

CONCLUSION

The utilization of a CNN-based model serves as a significant aid in the diagnosis of sulcus, a VF disease that presents notable challenges in the diagnostic process. Further research could be undertaken to assess the practicality of implementing this approach in real-time application in clinical practice.

Computer Vision and Videomics in Otolaryngology-Head and Neck Surgery: Bridging the Gap Between Clinical Needs and the Promise of Artificial Intelligence

This article discusses the role of computer vision in otolaryngology, particularly through endoscopy and surgery. It covers recent applications of artificial intelligence (AI) in nonradiologic imaging within otolaryngology, noting the benefits and challenges, such as improving diagnostic accuracy and optimizing therapeutic outcomes, while also pointing out the necessity for enhanced data curation and standardized research methodologies to advance clinical applications. Technical aspects are also covered, providing a detailed view of the progression from manual feature extraction to more complex AI models, including convolutional neural networks and vision transformers and their potential application in clinical settings.

Detection of Vocal Fold Image Obstructions in High-Speed Videoendoscopy During Connected Speech in Adductor Spasmodic Dysphonia: A Convolutional Neural Networks Approach

OBJECTIVE

Adductor spasmodic dysphonia (AdSD) is a neurogenic voice disorder, affecting the intrinsic laryngeal muscle control. AdSD leads to involuntary laryngeal spasms and only reveals during connected speech. Laryngeal high-speed videoendoscopy (HSV) coupled with a flexible fiberoptic endoscope provides a unique opportunity to study voice production and visualize the vocal fold vibrations in AdSD during speech. The goal of this study is to automatically detect instances during which the image of the vocal folds is optically obstructed in HSV recordings obtained during connected speech.

METHODS

HSV data were recorded from vocally normal adults and patients with AdSD during reading of the "Rainbow Passage", six CAPE-V sentences, and production of the vowel /i/. A convolutional neural network was developed and trained as a classifier to detect obstructed/unobstructed vocal folds in HSV frames. Manually labelled data were used for training, validating, and testing of the network. Moreover, a comprehensive robustness evaluation was conducted to compare the performance of the developed classifier and visual analysis of HSV data.

RESULTS

The developed convolutional neural network was able to automatically detect the vocal fold obstructions in HSV data in vocally normal participants and AdSD patients. The trained network was tested successfully and showed an overall classification accuracy of 94.18% on the testing dataset. The robustness evaluation showed an average overall accuracy of 94.81% on a massive number of HSV frames demonstrating the high robustness of the introduced technique while keeping a high level of accuracy.

CONCLUSIONS

The proposed approach can be used for efficient analysis of HSV data to study laryngeal maneuvers in patients with AdSD during connected speech. Additionally, this method will facilitate development of vocal fold vibratory measures for HSV frames with an unobstructed view of the vocal folds. Indicating parts of connected speech that provide an unobstructed view of the vocal folds can be used for developing optimal passages for precise HSV examination during connected speech and subject-specific clinical voice assessment protocols.

Multi-instance learning based artificial intelligence model to assist vocal fold leukoplakia diagnosis: A multicentre diagnostic study

OBJECTIVE

To develop a multi-instance learning (MIL) based artificial intelligence (AI)-assisted diagnosis models by using laryngoscopic images to differentiate benign and malignant vocal fold leukoplakia (VFL).

METHODS

The AI system was developed, trained and validated on 5362 images of 551 patients from three hospitals. Automated regions of interest (ROI) segmentation algorithm was utilized to construct image-level features. MIL was used to fusion image level results to patient level features, then the extracted features were modeled by seven machine learning algorithms. Finally, we evaluated the image level and patient level results. Additionally, 50 videos of VFL were prospectively gathered to assess the system's real-time diagnostic capabilities. A human-machine comparison database was also constructed to compare the diagnostic performance of otolaryngologists with and without AI assistance.

RESULTS

In internal and external validation sets, the maximum area under the curve (AUC) for image level segmentation models was 0.775 (95 % CI 0.740-0.811) and 0.720 (95 % CI 0.684-0.756), respectively. Utilizing a MIL-based fusion strategy, the AUC at the patient level increased to 0.869 (95 % CI 0.798-0.940) and 0.851 (95 % CI 0.756-0.945). For real-time video diagnosis, the maximum AUC at the patient level reached 0.850 (95 % CI, 0.743-0.957). With AI assistance, the AUC improved from 0.720 (95 % CI 0.682-0.755) to 0.808 (95 % CI 0.775-0.839) for senior otolaryngologists and from 0.647 (95 % CI 0.608-0.686) to 0.807 (95 % CI 0.773-0.837) for junior otolaryngologists.

CONCLUSIONS

The MIL based AI-assisted diagnosis system can significantly improve the diagnostic performance of otolaryngologists for VFL and help to make proper clinical decisions.

Computer Vision Foundation Models in Endoscopy: Proof of Concept in Oropharyngeal Cancer

OBJECTIVES

To evaluate the performance of vision transformer-derived image embeddings for distinguishing between normal and neoplastic tissues in the oropharynx and to investigate the potential of computer vision (CV) foundation models in medical imaging.

METHODS

Computational study using endoscopic frames with a focus on the application of a self-supervised vision transformer model (DINOv2) for tissue classification. High-definition endoscopic images were used to extract image patches that were then normalized and processed using the DINOv2 model to obtain embeddings. These embeddings served as input for a standard support vector machine (SVM) to classify the tissues as neoplastic or normal. The model's discriminative performance was validated using an 80-20 train-validation split.

RESULTS

From 38 endoscopic NBI videos, 327 image patches were analyzed. The classification results in the validation cohort demonstrated high accuracy (92%) and precision (89%), with a perfect recall (100%) and an F1-score of 94%. The receiver operating characteristic (ROC) curve yielded an area under the curve (AUC) of 0.96.

CONCLUSION

The use of large vision model-derived embeddings effectively differentiated between neoplastic and normal oropharyngeal tissues. This study supports the feasibility of employing CV foundation models like DINOv2 in the endoscopic evaluation of mucosal lesions, potentially augmenting diagnostic precision in Otorhinolaryngology.

LEVEL OF EVIDENCE

4 Laryngoscope, 2024.

The Use of Deep Learning Software in the Detection of Voice Disorders: A Systematic Review

OBJECTIVE

To summarize the use of deep learning in the detection of voice disorders using acoustic and laryngoscopic input, compare specific neural networks in terms of accuracy, and assess their effectiveness compared to expert clinical visual examination.

DATA SOURCES

Embase, MEDLINE, and Cochrane Central.

REVIEW METHODS

Databases were screened through November 11, 2023 for relevant studies. The inclusion criteria required studies to utilize a specified deep learning method, use laryngoscopy or acoustic input, and measure accuracy of binary classification between healthy patients and those with voice disorders.

RESULTS

Thirty-four studies met the inclusion criteria, with 18 focusing on voice analysis, 15 on imaging analysis, and 1 both. Across the 18 acoustic studies, 21 programs were used for identification of organic and functional voice disorders. These technologies included 10 convolutional neural networks (CNNs), 6 multilayer perceptrons (MLPs), and 5 other neural networks. The binary classification systems yielded a mean accuracy of 89.0% overall, including 93.7% for MLP programs and 84.5% for CNNs. Among the 15 imaging analysis studies, a total of 23 programs were utilized, resulting in a mean accuracy of 91.3%. Specifically, the twenty CNNs achieved a mean accuracy of 92.6% compared to 83.0% for the 3 MLPs.

CONCLUSION

Deep learning models were shown to be highly accurate in the detection of voice pathology, with CNNs most effective for assessing laryngoscopy images and MLPs most effective for assessing acoustic input. While deep learning methods outperformed expert clinical exam in limited comparisons, further studies integrating external validation are necessary.

Improving Laryngoscopy Image Analysis Through Integration of Global Information and Local Features in VoFoCD Dataset

The diagnosis and treatment of vocal fold disorders heavily rely on the use of laryngoscopy. A comprehensive vocal fold diagnosis requires accurate identification of crucial anatomical structures and potential lesions during laryngoscopy observation. However, existing approaches have yet to explore the joint optimization of the decision-making process, including object detection and image classification tasks simultaneously. In this study, we provide a new dataset, VoFoCD, with 1724 laryngology images designed explicitly for object detection and image classification in laryngoscopy images. Images in the VoFoCD dataset are categorized into four classes and comprise six glottic object types. Moreover, we propose a novel Multitask Efficient trAnsformer network for Laryngoscopy (MEAL) to classify vocal fold images and detect glottic landmarks and lesions. To further facilitate interpretability for clinicians, MEAL provides attention maps to visualize important learned regions for explainable artificial intelligence results toward supporting clinical decision-making. We also analyze our model's effectiveness in simulated clinical scenarios where shaking of the laryngoscopy process occurs. The proposed model demonstrates outstanding performance on our VoFoCD dataset. The accuracy for image classification and mean average precision at an intersection over a union threshold of 0.5 (mAP50) for object detection are 0.951 and 0.874, respectively. Our MEAL method integrates global knowledge, encompassing general laryngoscopy image classification, into local features, which refer to distinct anatomical regions of the vocal fold, particularly abnormal regions, including benign and malignant lesions. Our contribution can effectively aid laryngologists in identifying benign or malignant lesions of vocal folds and classifying images in the laryngeal endoscopy process visually.

Multi-Instance Learning for Vocal Fold Leukoplakia Diagnosis Using White Light and Narrow-Band Imaging: A Multicenter Study

OBJECTIVES

Vocal fold leukoplakia (VFL) is a precancerous lesion of laryngeal cancer, and its endoscopic diagnosis poses challenges. We aim to develop an artificial intelligence (AI) model using white light imaging (WLI) and narrow-band imaging (NBI) to distinguish benign from malignant VFL.

METHODS

A total of 7057 images from 426 patients were used for model development and internal validation. Additionally, 1617 images from two other hospitals were used for model external validation. Modeling learning based on WLI and NBI modalities was conducted using deep learning combined with a multi-instance learning approach (MIL). Furthermore, 50 prospectively collected videos were used to evaluate real-time model performance. A human-machine comparison involving 100 patients and 12 laryngologists assessed the real-world effectiveness of the model.

RESULTS

The model achieved the highest area under the receiver operating characteristic curve (AUC) values of 0.868 and 0.884 in the internal and external validation sets, respectively. AUC in the video validation set was 0.825 (95% CI: 0.704-0.946). In the human-machine comparison, AI significantly improved AUC and accuracy for all laryngologists (p < 0.05). With the assistance of AI, the diagnostic abilities and consistency of all laryngologists improved.

CONCLUSIONS

Our multicenter study developed an effective AI model using MIL and fusion of WLI and NBI images for VFL diagnosis, particularly aiding junior laryngologists. However, further optimization and validation are necessary to fully assess its potential impact in clinical settings.

LEVEL OF EVIDENCE

3 Laryngoscope, 2024.

Demographic and clinical characteristics of our patients diagnosed with laryngeal dystonia

PURPOSE

Laryngeal dystonia (LD) is a focal dystonia affecting laryngeal musculature with no known etiology or cure. The present study evaluated the sociodemographic and clinical features of patients diagnosed with LD.

MATERIALS AND METHODS

All patients diagnosed with LD at our University Hospital's Ear, Nose, and Throat Department between January 2017 and July 2023 were retrospectively analyzed. The study included 43 patients.

RESULTS

Out of the 43 patients, 19 (44%) were male. At the time of diagnosis, the mean age of the patients was 35.1 years (ranging from 17 to 65 years). The mean elapsed time between the first symptom onset and the first diagnosis was 49.2 months (min. 4 months, max. 240 months). Of the participants, 94% had adductor-type LD. None of the patients had a family history of LD. Of the patients, 9 (20%) experienced a life-altering event or trauma just before the onset of symptoms. All patients who consumed alcohol reported symptom relief with alcohol intake. A total of 67.6% of patients stated that their symptoms were triggered by stress. All of our patients received at least one Botulinum toxin injection, with an average of 2.75 dosages per patient.

CONCLUSION

The gender distribution was approximately equitable between males and females. There was a tendency for men to receive a diagnosis earlier than women following the manifestation of symptoms. A significant number of patients associate the emergence of their symptoms with a stressful event or traumatic experience. This study represents the initial investigation into the sociodemographic characteristics of patients within the Turkish population.

Classification of laryngeal diseases including laryngeal cancer, benign mucosal disease, and vocal cord paralysis by artificial intelligence using voice analysis

Voice change is often the first sign of laryngeal cancer, leading to diagnosis through hospital laryngoscopy. Screening for laryngeal cancer solely based on voice could enhance early detection. However, identifying voice indicators specific to laryngeal cancer is challenging, especially when differentiating it from other laryngeal ailments. This study presents an artificial intelligence model designed to distinguish between healthy voices, laryngeal cancer voices, and those of the other laryngeal conditions. We gathered voice samples of individuals with laryngeal cancer, vocal cord paralysis, benign mucosal diseases, and healthy participants. Comprehensive testing was conducted to determine the best mel-frequency cepstral coefficient conversion and machine learning techniques, with results analyzed in-depth. In our tests, laryngeal diseases distinguishing from healthy voices achieved an accuracy of 0.85-0.97. However, when multiclass classification, accuracy ranged from 0.75 to 0.83. These findings highlight the challenges of artificial intelligence-driven voice-based diagnosis due to overlaps with benign conditions but also underscore its potential.

Vocal Cord Leukoplakia Classification Using Siamese Network Under Small Samples of White Light Endoscopy Images

OBJECTIVE

Accurate vocal cord leukoplakia classification is instructive for clinical diagnosis and surgical treatment. This article introduces a reliable very deep Siamese network for accurate vocal cord leukoplakia classification.

STUDY DESIGN

A study of a classification network based on a retrospective database.

SETTING

Academic university and hospital.

METHODS

The white light image datasets of vocal cord leukoplakia used in this article were classified into 6 classes: normal tissues, inflammatory keratosis, mild dysplasia, moderate dysplasia, severe dysplasia, and squamous cell carcinoma. The classification performance was assessed by comparing it with 6 classical deep learning models, including AlexNet, VGG Net, Google Inception, ResNet, DenseNet, and Vision Transformer.

RESULTS

Experiments show the superior classification performance of our proposed network compared to state-of-the-art methods. The overall accuracy is 0.9756. The values of sensitivity and specificity are very high as well. The confusion matrix provides information for the 6-class classification task and demonstrates the superiority of our proposed network.

CONCLUSION

Our very deep Siamese network can provide accurate classification results of vocal cord leukoplakia, which facilitates early detection, clinical diagnosis, and surgical treatment. The excellent performance obtained in white light images can reduce the cost for patients, especially those living in developing countries.

A deep learning pipeline for automated classification of vocal fold polyps in flexible laryngoscopy

PURPOSE

To develop and validate a deep learning model for distinguishing healthy vocal folds (HVF) and vocal fold polyps (VFP) on laryngoscopy videos, while demonstrating the ability of a previously developed informative frame classifier in facilitating deep learning development.

METHODS

Following retrospective extraction of image frames from 52 HVF and 77 unilateral VFP videos, two researchers manually labeled each frame as informative or uninformative. A previously developed informative frame classifier was used to extract informative frames from the same video set. Both sets of videos were independently divided into training (60%), validation (20%), and test (20%) by patient. Machine-labeled frames were independently verified by two researchers to assess the precision of the informative frame classifier. Two models, pre-trained on ResNet18, were trained to classify frames as containing HVF or VFP. The accuracy of the polyp classifier trained on machine-labeled frames was compared to that of the classifier trained on human-labeled frames. The performance was measured by accuracy and area under the receiver operating characteristic curve (AUROC).

RESULTS

When evaluated on a hold-out test set, the polyp classifier trained on machine-labeled frames achieved an accuracy of 85% and AUROC of 0.84, whereas the classifier trained on human-labeled frames achieved an accuracy of 69% and AUROC of 0.66.

CONCLUSION

An accurate deep learning classifier for vocal fold polyp identification was developed and validated with the assistance of a peer-reviewed informative frame classifier for dataset assembly. The classifier trained on machine-labeled frames demonstrates improved performance compared to the classifier trained on human-labeled frames.

LEVEL OF EVIDENCE: 4

Evaluation of Vertical Level Differences Between Left and Right Vocal Folds Using Artificial Intelligence System in Excised Canine Larynx

OBJECTIVES

This study aimed to establish an artificial intelligence (AI) system to classify vertical level differences between vocal folds during vocalization and to evaluate the accuracy of the classification.

METHODS

We designed models with different depths between the right and left vocal folds using an excised canine larynx. Video files for the data set were obtained using a high-speed camera system and a color complementary metal oxide semiconductor camera with global shutter. The data sets were divided into training, validation, and testing. We used 20,000 images for building the model and 8000 images for testing. To perform deep learning multiclass classification and to estimate the vertical level difference, we introduced DenseNet121-ConvLSTM.

RESULTS

The model was trained several times using different numbers of epochs. We achieved the most optimal results at 100 epochs, and the batch size used during training was 16. The proposed DenseNet121-ConvLSTM model achieved classification accuracies of 99.5% and 88.0% for training and testing, respectively. After verification using an external data set, the overall accuracy, precision, recall, and f1-score were 90.8%, 91.6%, 90.9%, and 91.2%, respectively.

CONCLUSIONS

The newly developed AI system may be an easy and accurate method for classifying superior and inferior vertical level differences between vocal folds. Thus, this AI system can be applied and may help in the assessment of vertical level differences in patients with unilateral vocal fold paralysis.

Computer-Aided Diagnosis of Laryngeal Cancer Based on Deep Learning with Laryngoscopic Images

Laryngeal cancer poses a significant global health burden, with late-stage diagnoses contributing to reduced survival rates. This study explores the application of deep convolutional neural networks (DCNNs), specifically the Densenet201 architecture, in the computer-aided diagnosis of laryngeal cancer using laryngoscopic images. Our dataset comprised images from two medical centers, including benign and malignant cases, and was divided into training, internal validation, and external validation groups. We compared the performance of Densenet201 with other commonly used DCNN models and clinical assessments by experienced clinicians. Densenet201 exhibited outstanding performance, with an accuracy of 98.5% in the training cohort, 92.0% in the internal validation cohort, and 86.3% in the external validation cohort. The area under the curve (AUC) values consistently exceeded 92%, signifying robust discriminatory ability. Remarkably, Densenet201 achieved high sensitivity (98.9%) and specificity (98.2%) in the training cohort, ensuring accurate detection of both positive and negative cases. In contrast, other DCNN models displayed varying degrees of performance degradation in the external validation cohort, indicating the superiority of Densenet201. Moreover, Densenet201's performance was comparable to that of an experienced clinician (Clinician A) and outperformed another clinician (Clinician B), particularly in the external validation cohort. Statistical analysis, including the DeLong test, confirmed the significance of these performance differences. Our study demonstrates that Densenet201 is a highly accurate and reliable tool for the computer-aided diagnosis of laryngeal cancer based on laryngoscopic images. The findings underscore the potential of deep learning as a complementary tool for clinicians and the importance of incorporating advanced technology in improving diagnostic accuracy and patient care in laryngeal cancer diagnosis. Future work will involve expanding the dataset and further optimizing the deep learning model.

Vocal cord leukoplakia classification using deep learning models in white light and narrow band imaging endoscopy images

BACKGROUND

Accurate vocal cord leukoplakia classification is critical for the individualized treatment and early detection of laryngeal cancer. Numerous deep learning techniques have been proposed, but it is unclear how to select one to apply in the laryngeal tasks. This article introduces and reliably evaluates existing deep learning models for vocal cord leukoplakia classification.

METHODS

We created white light and narrow band imaging (NBI) image datasets of vocal cord leukoplakia which were classified into six classes: normal tissues (NT), inflammatory keratosis (IK), mild dysplasia (MiD), moderate dysplasia (MoD), severe dysplasia (SD), and squamous cell carcinoma (SCC). Vocal cord leukoplakia classification was performed using six classical deep learning models, AlexNet, VGG, Google Inception, ResNet, DenseNet, and Vision Transformer.

RESULTS

GoogLeNet (i.e., Google Inception V1), DenseNet-121, and ResNet-152 perform excellent classification. The highest overall accuracy of white light image classification is 0.9583, while the highest overall accuracy of NBI image classification is 0.9478. These three neural networks all provide very high sensitivity, specificity, and precision values.

CONCLUSION

GoogLeNet, ResNet, and DenseNet can provide accurate pathological classification of vocal cord leukoplakia. It facilitates early diagnosis, providing judgment on conservative treatment or surgical treatment of different degrees, and reducing the burden on endoscopists.

Deep Learning Techniques and Imaging in Otorhinolaryngology-A State-of-the-Art Review

Over the last decades, the field of medicine has witnessed significant progress in artificial intelligence (AI), the Internet of Medical Things (IoMT), and deep learning (DL) systems. Otorhinolaryngology, and imaging in its various subspecialties, has not remained untouched by this transformative trend. As the medical landscape evolves, the integration of these technologies becomes imperative in augmenting patient care, fostering innovation, and actively participating in the ever-evolving synergy between computer vision techniques in otorhinolaryngology and AI. To that end, we conducted a thorough search on MEDLINE for papers published until June 2023, utilizing the keywords 'otorhinolaryngology', 'imaging', 'computer vision', 'artificial intelligence', and 'deep learning', and at the same time conducted manual searching in the references section of the articles included in our manuscript. Our search culminated in the retrieval of 121 related articles, which were subsequently subdivided into the following categories: imaging in head and neck, otology, and rhinology. Our objective is to provide a comprehensive introduction to this burgeoning field, tailored for both experienced specialists and aspiring residents in the domain of deep learning algorithms in imaging techniques in otorhinolaryngology.

Real-time detection of laryngopharyngeal cancer using an artificial intelligence-assisted system with multimodal data

BACKGROUND

Laryngopharyngeal cancer (LPC) includes laryngeal and hypopharyngeal cancer, whose early diagnosis can significantly improve the prognosis and quality of life of patients. Pathological biopsy of suspicious cancerous tissue under the guidance of laryngoscopy is the gold standard for diagnosing LPC. However, this subjective examination largely depends on the skills and experience of laryngologists, which increases the possibility of missed diagnoses and repeated unnecessary biopsies. We aimed to develop and validate a deep convolutional neural network-based Laryngopharyngeal Artificial Intelligence Diagnostic System (LPAIDS) for real-time automatically identifying LPC in both laryngoscopy white-light imaging (WLI) and narrow-band imaging (NBI) images to improve the diagnostic accuracy of LPC by reducing diagnostic variation among on-expert laryngologists.

METHODS

All 31,543 laryngoscopic images from 2382 patients were categorised into training, verification, and test sets to develop, validate, and internal test LPAIDS. Another 25,063 images from five other hospitals were used as external tests. Overall, 551 videos were used to evaluate the real-time performance of the system, and 200 randomly selected videos were used to compare the diagnostic performance of the LPAIDS with that of laryngologists. Two deep-learning models using either WLI (model W) or NBI (model N) images were constructed to compare with LPAIDS.

RESULTS

LPAIDS had a higher diagnostic performance than models W and N, with accuracies of 0·956 and 0·949 in the internal image and video tests, respectively. The robustness and stability of LPAIDS were validated in external sets with the area under the receiver operating characteristic curve values of 0·965-0·987. In the laryngologist-machine competition, LPAIDS achieved an accuracy of 0·940, which was comparable to expert laryngologists and outperformed other laryngologists with varying qualifications.

CONCLUSIONS

LPAIDS provided high accuracy and stability in detecting LPC in real-time, which showed great potential for using LPAIDS to improve the diagnostic accuracy of LPC by reducing diagnostic variation among on-expert laryngologists.

Artificial Intelligence for Upper Aerodigestive Tract Endoscopy and Laryngoscopy: A Guide for Physicians and State-of-the-Art Review

OBJECTIVE

The endoscopic and laryngoscopic examination is paramount for laryngeal, oropharyngeal, nasopharyngeal, nasal, and oral cavity benign lesions and cancer evaluation. Nevertheless, upper aerodigestive tract (UADT) endoscopy is intrinsically operator-dependent and lacks objective quality standards. At present, there has been an increased interest in artificial intelligence (AI) applications in this area to support physicians during the examination, thus enhancing diagnostic performances. The relative novelty of this research field poses a challenge both for the reviewers and readers as clinicians often lack a specific technical background.

DATA SOURCES

Four bibliographic databases were searched: PubMed, EMBASE, Cochrane, and Google Scholar.

REVIEW METHODS

A structured review of the current literature (up to September 2022) was performed. Search terms related to topics of AI, machine learning (ML), and deep learning (DL) in UADT endoscopy and laryngoscopy were identified and queried by 3 independent reviewers. Citations of selected studies were also evaluated to ensure comprehensiveness.

CONCLUSIONS

Forty-one studies were included in the review. AI and computer vision techniques were used to achieve 3 fundamental tasks in this field: classification, detection, and segmentation. All papers were summarized and reviewed.

IMPLICATIONS FOR PRACTICE

This article comprehensively reviews the latest developments in the application of ML and DL in UADT endoscopy and laryngoscopy, as well as their future clinical implications. The technical basis of AI is also explained, providing guidance for nonexpert readers to allow critical appraisal of the evaluation metrics and the most relevant quality requirements.

Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives

Head and neck tumors (HNTs) constitute a multifaceted ensemble of pathologies that primarily involve regions such as the oral cavity, pharynx, and nasal cavity. The intricate anatomical structure of these regions poses considerable challenges to efficacious treatment strategies. Despite the availability of myriad treatment modalities, the overall therapeutic efficacy for HNTs continues to remain subdued. In recent years, the deployment of artificial intelligence (AI) in healthcare practices has garnered noteworthy attention. AI modalities, inclusive of machine learning (ML), neural networks (NNs), and deep learning (DL), when amalgamated into the holistic management of HNTs, promise to augment the precision, safety, and efficacy of treatment regimens. The integration of AI within HNT management is intricately intertwined with domains such as medical imaging, bioinformatics, and medical robotics. This article intends to scrutinize the cutting-edge advancements and prospective applications of AI in the realm of HNTs, elucidating AI's indispensable role in prevention, diagnosis, treatment, prognostication, research, and inter-sectoral integration. The overarching objective is to stimulate scholarly discourse and invigorate insights among medical practitioners and researchers to propel further exploration, thereby facilitating superior therapeutic alternatives for patients.

Point-wise spatial network for identifying carcinoma at the upper digestive and respiratory tract

PROBLEM

Artificial intelligence has been widely investigated for diagnosis and treatment strategy design, with some models proposed for detecting oral pharyngeal, nasopharyngeal, or laryngeal carcinoma. However, no comprehensive model has been established for these regions.

AIM

Our hypothesis was that a common pattern in the cancerous appearance of these regions could be recognized and integrated into a single model, thus improving the efficacy of deep learning models.

METHODS

We utilized a point-wise spatial attention network model to perform semantic segmentation in these regions.

RESULTS

Our study demonstrated an excellent outcome, with an average mIoU of 86.3%, and an average pixel accuracy of 96.3%.

CONCLUSION

The research confirmed that the mucosa of oral pharyngeal, nasopharyngeal, and laryngeal regions may share a common appearance, including the appearance of tumors, which can be recognized by a single artificial intelligence model. Therefore, a deep learning model could be constructed to effectively recognize these tumors.

Detection of laryngeal carcinoma during endoscopy using artificial intelligence

BACKGROUND

The objective of this study was to assess the performance and application of a self-developed deep learning (DL) algorithm for the real-time localization and classification of both vocal cord carcinoma and benign vocal cord lesions.

METHODS

The algorithm was trained and validated upon a dataset of videos and photos collected from our own department, as well as an open-access dataset named "Laryngoscope8".

RESULTS

The algorithm correctly localizes and classifies vocal cord carcinoma on still images with a sensitivity between 71% and 78% and benign vocal cord lesions with a sensitivity between 70% and 82%. Furthermore, the best algorithm had an average frame per second rate of 63, thus making it suitable to use in an outpatient clinic setting for real-time detection of laryngeal pathology.

CONCLUSION

We have demonstrated that our developed DL algorithm is able to localize and classify benign and malignant laryngeal pathology during endoscopy.

Gender, Smoking History, and Age Prediction from Laryngeal Images

Flexible laryngoscopy is commonly performed by otolaryngologists to detect laryngeal diseases and to recognize potentially malignant lesions. Recently, researchers have introduced machine learning techniques to facilitate automated diagnosis using laryngeal images and achieved promising results. The diagnostic performance can be improved when patients' demographic information is incorporated into models. However, the manual entry of patient data is time-consuming for clinicians. In this study, we made the first endeavor to employ deep learning models to predict patient demographic information to improve the detector model's performance. The overall accuracy for gender, smoking history, and age was 85.5%, 65.2%, and 75.9%, respectively. We also created a new laryngoscopic image set for the machine learning study and benchmarked the performance of eight classical deep learning models based on CNNs and Transformers. The results can be integrated into current learning models to improve their performance by incorporating the patient's demographic information.

A Novel Framework of Manifold Learning Cascade-Clustering for the Informative Frame Selection

Narrow band imaging is an established non-invasive tool used for the early detection of laryngeal cancer in surveillance examinations. Most images produced from the examination are useless, such as blurred, specular reflection, and underexposed. Removing the uninformative frames is vital to improve detection accuracy and speed up computer-aided diagnosis. It often takes a lot of time for the physician to manually inspect the informative frames. This issue is commonly addressed by a classifier with task-specific categories of the uninformative frames. However, the definition of the uninformative categories is ambiguous, and tedious labeling still cannot be avoided. Here, we show that a novel unsupervised scheme is comparable to the current benchmarks on the dataset of NBI-InfFrames. We extract feature embedding using a vanilla neural network (VGG16) and introduce a new dimensionality reduction method called UMAP that distinguishes the feature embedding in the lower-dimensional space. Along with the proposed automatic cluster labeling algorithm and cost function in Bayesian optimization, the proposed method coupled with UMAP achieves state-of-the-art performance. It outperforms the baseline by 12% absolute. The overall median recall of the proposed method is currently the highest, 96%. Our results demonstrate the effectiveness of the proposed scheme and the robustness of detecting the informative frames. It also suggests the patterns embedded in the data help develop flexible algorithms that do not require manual labeling.

Artificial Intelligence and Laryngeal Cancer: From Screening to Prognosis: A State of the Art Review

OBJECTIVE

This state of the art review aims to examine contemporary advances in applications of artificial intelligence (AI) to the screening, detection, management, and prognostication of laryngeal cancer (LC).

DATA SOURCES

Four bibliographic databases were searched: PubMed, EMBASE, Cochrane, and IEEE.

REVIEW METHODS

A structured review of the current literature (up to January 2022) was performed. Search terms related to topics of AI in LC were identified and queried by 2 independent reviewers. Citations of selected studies and review articles were also evaluated to ensure comprehensiveness.

CONCLUSIONS

AI applications in LC have encompassed a variety of data modalities, including radiomics, genomics, acoustics, clinical data, and videomics, to support screening, diagnosis, therapeutic decision making, and prognosis. However, most studies remain at the proof-of-concept level, as AI algorithms are trained on single-institution databases with limited data sets and a single data modality.

IMPLICATIONS FOR PRACTICE

AI algorithms in LC will need to be trained on large multi-institutional data sets and integrate multimodal data for optimal performance and clinical utility from screening to prognosis. Out of the data types reviewed, genomics has the most potential to provide generalizable models thanks to available large multi-institutional open access genomic data sets. Voice acoustic data represent an inexpensive and accurate biomarker, which is easy and noninvasive to capture, offering a unique opportunity for screening and monitoring of LA, especially in low-resource settings.

HISMD: A Novel Immune Subtyping System for HNSCC

Immune subtyping is an important way to reveal immune heterogeneity, which may contribute to the diversity of the progression and treatment in head and neck squamous cell carcinoma (HNSCC). However, reported immune subtypes mainly focus on levels of immune infiltration and are mostly based on a mono-omics profile. This study aimed to identify a comprehensive immune subtype for HNSCC via multi-omics clustering and build a novel subtype prediction system for clinical application. Data were obtained from The Cancer Genome Atlas database and our independent multicenter cohort. Multi-omics clustering was performed to identify 3 clusters of 499 patients in The Cancer Genome Atlas based on immune-related gene expression and somatic mutations. The immune characteristics and biological features of the obtained clusters were revealed by bioinformatics, and 3 immune subtypes were identified: 1) adaptive immune activation subtype predominantly enriched in T cells, 2) innate immune activation subtype predominantly enriched in macrophages, and 3) immune desert subtype. Subsequently, the clinical implications of each subtype were analyzed per clinical epidemiology. We found that adaptive immune activation showed better survival outcomes and had a similar response to chemotherapy with innate immune activation, whereas immune desert might be relatively resistant to chemotherapy. Moreover, a subtype prediction system was developed by deep learning with whole slide images and named HISMD: HNSCC Immune Subtypes via Multi-omics and Deep Learning. We endowed HISMD with interpretability through image-based key feature extraction. The clinical implications, biological significances, and predictive stability of HISMD were successfully verified by using our independent multicenter cohort data set. In summary, this study revealed the immune heterogeneity of HNSCC and obtained a novel, highly accurate, and interpretable immune subtyping prediction system. For clinical implementation in the future, additional validation and utility studies are warranted.

Convolutional neural network based anatomical site identification for laryngoscopy quality control: A multicenter study

OBJECTIVES

Video laryngoscopy is an important diagnostic tool for head and neck cancers. The artificial intelligence (AI) system has been shown to monitor blind spots during esophagogastroduodenoscopy. This study aimed to test the performance of AI-driven intelligent laryngoscopy monitoring assistant (ILMA) for landmark anatomical sites identification on laryngoscopic images and videos based on a convolutional neural network (CNN).

MATERIALS AND METHODS

The laryngoscopic images taken from January to December 2018 were retrospectively collected, and ILMA was developed using the CNN model of Inception-ResNet-v2 + Squeeze-and-Excitation Networks (SENet). A total of 16,000 laryngoscopic images were used for training. These were assigned to 20 landmark anatomical sites covering six major head and neck regions. In addition, the performance of ILMA in identifying anatomical sites was validated using 4000 laryngoscopic images and 25 videos provided by five other tertiary hospitals.

RESULTS

ILMA identified the 20 anatomical sites on the laryngoscopic images with a total accuracy of 97.60 %, and the average sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 100 %, 99.87 %, 97.65 %, and 99.87 %, respectively. In addition, multicenter clinical verification displayed that the accuracy of ILMA in identifying the 20 targeted anatomical sites in 25 laryngoscopic videos from five hospitals was ≥95 %.

CONCLUSION

The proposed CNN-based ILMA model can rapidly and accurately identify the anatomical sites on laryngoscopic images. The model can reflect the coverage of anatomical regions of the head and neck by laryngoscopy, showing application potential in improving the quality of laryngoscopy.

Support of deep learning to classify vocal fold images in flexible laryngoscopy

PURPOSE

To collect a dataset with adequate laryngoscopy images and identify the appearance of vocal folds and their lesions in flexible laryngoscopy images by objective deep learning models.

METHODS

We adopted a number of novel deep learning models to train and classify 4549 flexible laryngoscopy images as no vocal fold, normal vocal folds, and abnormal vocal folds. This could help these models recognize vocal folds and their lesions within these images. Ultimately, we made a comparison between the results of the state-of-the-art deep learning models, and another comparison of the results between the computer-aided classification system and ENT doctors.

RESULTS

This study exhibited the performance of the deep learning models by evaluating laryngoscopy images collected from 876 patients. The efficiency of the Xception model was higher and steadier than almost the rest of the models. The accuracy of no vocal fold, normal vocal folds, and vocal fold abnormalities on this model were 98.90 %, 97.36 %, and 96.26 %, respectively. Compared to our ENT doctors, the Xception model produced better results than a junior doctor and was near an expert.

CONCLUSION

Our results show that current deep learning models can classify vocal fold images well and effectively assist physicians in vocal fold identification and classification of normal or abnormal vocal folds.

[Automatic anatomical site recognition of laryngoscopic images using convolutional neural network]

Objective:To explore the automatic recognition and classification of 20 anatomical sites in laryngoscopy by an artificial intelligence（AI） quality control system using convolutional neural network（CNN）. Methods: Laryngoscopic image data archived from laryngoscopy examinations at the Department of Endoscopy, Cancer Hospital, Chinese Academy of Medical Sciences from January to December 2018 were collected retrospectively, and a CNN model was constructed using Inception-ResNet-V2+SENet. Using 14000 electronic laryngoscope images as the training set, these images were classified into 20 specific anatomical sites including the whole head and neck, and their performance was tested by 2000 laryngoscope images and 10 laryngoscope videos. Results:The average time of the trained CNN model for recognition of each laryngoscopic image was（20.59 ± 1.55） ms, and the overall accuracy of recognition of 20 anatomical sites in laryngoscopic images was 97.75%（1955/2000）, with average sensitivity, specificity, positive predictive value, and negative predictive value of 100%, 99.88%, 97.76%, and 99.88%, respectively. The model had an accuracy of ≥ 99% for the identification of 20 anatomical sites in laryngoscopic videos. Conclusion:This study confirms that the CNN-based AI system can perform accurate and fast classification and identification of anatomical sites in laryngoscopic pictures and videos, which can be used for quality control of photo documentation in laryngoscopy and shows potential application in monitoring the performance of laryngoscopy.

Clinical value of video-assisted single-lumen endotracheal intubation and application of artificial intelligence in it

Visualization techniques and artificial intelligence (AI) are currently used for intubation device. By providing airway visualization during tracheal intubation, the technologies provide safe and accurate access to the trachea. The ability of AI to automatically identify airways from images of intubation device makes it attractive for use in intubation devices. The purpose of this review is to introduce the state of application of visualization techniques and AI in certain intubation devices. We reviewed the evidence of clinical implications of the use of video-assisted intubation device in the intubation time, first attempt success rate, and intubation of the difficult airway. Especially, VivaSight single-lumen tube with an incorporated optics allows direct viewing of the airway. VivaSight single-lumen tube has more advantages in tracheal intubation. AI has been applied to fiberoptic bronchoscopy (FOB) and video laryngoscope with automatic airway image recognition, and has achieved certain accomplishment. Further, we discussed the possibility of applying AI to the VivaSight single-lumen tube and proposed future directions of research and application.

An Improvised Deep-Learning-Based Mask R-CNN Model for Laryngeal Cancer Detection Using CT Images

Recently, laryngeal cancer cases have increased drastically across the globe. Accurate treatment for laryngeal cancer is intricate, especially in the later stages. This type of cancer is an intricate malignancy inside the head and neck area of patients. In recent years, diverse diagnosis approaches and tools have been developed by researchers for helping clinical experts to identify laryngeal cancer effectively. However, these existing tools and approaches have diverse issues related to performance constraints such as lower accuracy in the identification of laryngeal cancer in the initial stage, more computational complexity, and large time consumption in patient screening. In this paper, the authors present a novel and enhanced deep-learning-based Mask R-CNN model for the identification of laryngeal cancer and its related symptoms by utilizing diverse image datasets and CT images in real time. Furthermore, our suggested model is capable of capturing and detecting minor malignancies of the larynx portion in a significant and faster manner in the real-time screening of patients, and it saves time for the clinicians, allowing for more patient screening every day. The outcome of the suggested model is enhanced and pragmatic and obtained an accuracy of 98.99%, precision of 98.99%, F1 score of 97.99%, and recall of 96.79% on the ImageNet dataset. Several studies have been performed in recent years on laryngeal cancer detection by using diverse approaches from researchers. For the future, there are vigorous opportunities for further research to investigate new approaches for laryngeal cancer detection by utilizing diverse and large dataset images.

Artificial intelligence in clinical endoscopy: Insights in the field of videomics

Artificial intelligence is being increasingly seen as a useful tool in medicine. Specifically, these technologies have the objective to extract insights from complex datasets that cannot easily be analyzed by conventional statistical methods. While promising results have been obtained for various -omics datasets, radiological images, and histopathologic slides, analysis of videoendoscopic frames still represents a major challenge. In this context, videomics represents a burgeoning field wherein several methods of computer vision are systematically used to organize unstructured data from frames obtained during diagnostic videoendoscopy. Recent studies have focused on five broad tasks with increasing complexity: quality assessment of endoscopic images, classification of pathologic and nonpathologic frames, detection of lesions inside frames, segmentation of pathologic lesions, and in-depth characterization of neoplastic lesions. Herein, we present a broad overview of the field, with a focus on conceptual key points and future perspectives.

Diagnosis of Early Glottic Cancer Using Laryngeal Image and Voice Based on Ensemble Learning of Convolutional Neural Network Classifiers

OBJECTIVES

The purpose of study is to improve the classification accuracy by comparing the results obtained by applying decision tree ensemble learning, which is one of the methods to increase the classification accuracy for a relatively small dataset, with the results obtained by the convolutional neural network (CNN) algorithm for the diagnosis of glottal cancer.

METHODS

Pusan National University Hospital (PNUH) dataset were used to establish classifiers and Pusan National University Yangsan Hospital (PNUYH) dataset were used to verify the classifier's performance in the generated model. For the diagnosis of glottic cancer, deep learning-based CNN models were established and classified using laryngeal image and voice data. Classification accuracy was obtained by performing decision tree ensemble learning using probability through CNN classification algorithm. In this process, the classification and regression tree (CART) method was used. Then, we compared the classification accuracy of decision tree ensemble learning with CNN individual classifiers by fusing the laryngeal image with the voice decision tree classifier.

RESULTS

We obtained classification accuracy of 81.03 % and 99.18 % in the established laryngeal image and voice classification models using PNUH training dataset, respectively. However, the classification accuracy of CNN classifiers decreased to 73.88 % in voice and 68.92 % in laryngeal image when using an external dataset of PNUYH. To solve this problem, decision tree ensemble learning of laryngeal image and voice was used, and the classification accuracy was improved by integrating data of laryngeal image and voice of the same person. The classification accuracy was 87.88 % and 89.06 % for the individualized laryngeal image and voice decision tree model respectively, and the fusion of the laryngeal image and voice decision tree results represented a classification accuracy of 95.31 %.

CONCLUSION

The results of our study suggest that decision tree ensemble learning aimed at training multiple classifiers is useful to obtain an increased classification accuracy despite a small dataset. Although a large data amount is essential for AI analysis, when an integrated approach is taken by combining various input data high diagnostic classification accuracy can be expected.

AI-based analysis of oral lesions using novel deep convolutional neural networks for early detection of oral cancer

Artificial intelligence (AI) applications in oncology have been developed rapidly with reported successes in recent years. This work aims to evaluate the performance of deep convolutional neural network (CNN) algorithms for the classification and detection of oral potentially malignant disorders (OPMDs) and oral squamous cell carcinoma (OSCC) in oral photographic images. A dataset comprising 980 oral photographic images was divided into 365 images of OSCC, 315 images of OPMDs and 300 images of non-pathological images. Multiclass image classification models were created by using DenseNet-169, ResNet-101, SqueezeNet and Swin-S. Multiclass object detection models were fabricated by using faster R-CNN, YOLOv5, RetinaNet and CenterNet2. The AUC of multiclass image classification of the best CNN models, DenseNet-196, was 1.00 and 0.98 on OSCC and OPMDs, respectively. The AUC of the best multiclass CNN-base object detection models, Faster R-CNN, was 0.88 and 0.64 on OSCC and OPMDs, respectively. In comparison, DenseNet-196 yielded the best multiclass image classification performance with AUC of 1.00 and 0.98 on OSCC and OPMD, respectively. These values were inline with the performance of experts and superior to those of general practictioners (GPs). In conclusion, CNN-based models have potential for the identification of OSCC and OPMDs in oral photographic images and are expected to be a diagnostic tool to assist GPs for the early detection of oral cancer.

Hierarchical dynamic convolutional neural network for laryngeal disease classification

Laryngeal disease classification is a relatively hard task in medical image processing resulting from its complex structures and varying viewpoints in data collection. Some existing methods try to tackle this task via the convolutional neural network, but they more or less ignore the intrinsic difficulty differences among different input samples and suffer from high training complexity. In order to better resolve these problems, an end-to-end Hierarchical Dynamic Convolutional Network (HDCNet) is proposed, which can dynamically process the input samples based on their difficulty. For the easy-classified samples, the HDCNet processes them with a smaller resolution and a relatively small network, while the difficult samples are passed to a large network with a larger resolution for more accurate classification results. Furthermore, a Feature Reuse Module (FRM) is designed to transfer the features learned by the small network to the corresponding block in the deep network to enhance the overall performance of some rather complicated samples. To validate the effectiveness of the proposed HDCNet, comprehensive experiments are conducted on the public available laryngeal disease classification dataset and HDCNet provides superior performances compared with other current state-of-the-art methods.

[Application and development of voice analysis and endoscopic technology combined with artificial intelligence in the diagnosis and treatment of throat disease]

In the diagnosis and treatment of throat disease, the application and development of combining voice analysis or endoscopic technology with artificial intelligence has developed rapidly. This paper reviews the history and principles of the combination of voice analysis or endoscopic technology with artificial intelligence, summarizes its status of application and development, and sums up its advantages that lie in the strong learning and interpretation ability, amazing speed and tolerance, and stable replication and expansion. The key to restrict its development is the uncertainty in the process of machine learning, the error caused by small samples, and the ethical philosophical thinking. Future development direction should be that the surgeons in otolaryngology head and neck department on the basis of excellent professional knowledge, learn related knowledge of epidemiology, classic statistics, strengthen the exchanges and cooperation with machine learning developers. Eventually, advanced science and technology can be truly used in clinical practice to maximize the benefit of the majority of patients.

Artificial Intelligence in Laryngeal Endoscopy: Systematic Review and Meta-Analysis

Background: Early diagnosis of laryngeal lesions is necessary to begin treatment of patients as soon as possible to preserve optimal organ functions. Imaging examinations are often aided by artificial intelligence (AI) to improve quality and facilitate appropriate diagnosis. The aim of this study is to investigate diagnostic utility of AI in laryngeal endoscopy. Methods: Five databases were searched for studies implementing artificial intelligence (AI) enhanced models assessing images of laryngeal lesions taken during laryngeal endoscopy. Outcomes were analyzed in terms of accuracy, sensitivity, and specificity. Results: All 11 studies included presented an overall low risk of bias. The overall accuracy of AI models was very high (from 0.806 to 0.997). The accuracy was significantly higher in studies using a larger database. The pooled sensitivity and specificity for identification of healthy laryngeal tissue were 0.91 and 0.97, respectively. The same values for differentiation between benign and malignant lesions were 0.91 and 0.94, respectively. The comparison of the effectiveness of AI models assessing narrow band imaging and white light endoscopy images revealed no statistically significant differences (p = 0.409 and 0.914). Conclusion: In assessing images of laryngeal lesions, AI demonstrates extraordinarily high accuracy, sensitivity, and specificity.

Prospects and Pitfalls of Machine Learning in Nutritional Epidemiology

Nutritional epidemiology employs observational data to discover associations between diet and disease risk. However, existing analytic methods of dietary data are often sub-optimal, with limited incorporation and analysis of the correlations between the studied variables and nonlinear behaviours in the data. Machine learning (ML) is an area of artificial intelligence that has the potential to improve modelling of nonlinear associations and confounding which are found in nutritional data. These opportunities notwithstanding, the applications of ML in nutritional epidemiology must be approached cautiously to safeguard the scientific quality of the results and provide accurate interpretations. Given the complex scenario around ML, judicious application of such tools is necessary to offer nutritional epidemiology a novel analytical resource for dietary measurement and assessment and a tool to model the complexity of dietary intake and its relation to health. This work describes the applications of ML in nutritional epidemiology and provides guidelines to avoid common pitfalls encountered in applying predictive statistical models to nutritional data. Furthermore, it helps unfamiliar readers better assess the significance of their results and provides new possible future directions in the field of ML in nutritional epidemiology.

Automatic classification of informative laryngoscopic images using deep learning

Objective

This study aims to develop and validate a convolutional neural network (CNN)‐based algorithm for automatic selection of informative frames in flexible laryngoscopic videos. The classifier has the potential to aid in the development of computer‐aided diagnosis systems and reduce data processing time for clinician‐computer scientist teams.

Methods

A dataset of 22,132 laryngoscopic frames was extracted from 137 flexible laryngostroboscopic videos from 115 patients. 55 videos were from healthy patients with no laryngeal pathology and 82 videos were from patients with vocal fold polyps. The extracted frames were manually labeled as informative or uninformative by two independent reviewers based on vocal fold visibility, lighting, focus, and camera distance, resulting in 18,114 informative frames and 4018 uninformative frames. The dataset was split into training and test sets. A pre‐trained ResNet‐18 model was trained using transfer learning to classify frames as informative or uninformative. Hyperparameters were set using cross‐validation. The primary outcome was precision for the informative class and secondary outcomes were precision, recall, and F1‐score for all classes. The processing rate for frames between the model and a human annotator were compared.

Results

The automated classifier achieved an informative frame precision, recall, and F1‐score of 94.4%, 90.2%, and 92.3%, respectively, when evaluated on a hold‐out test set of 4438 frames. The model processed frames 16 times faster than a human annotator.

Conclusion

The CNN‐based classifier demonstrates high precision for classifying informative frames in flexible laryngostroboscopic videos. This model has the potential to aid researchers with dataset creation for computer‐aided diagnosis systems by automatically extracting relevant frames from laryngoscopic videos.

Deep Convolution Neural Network for Laryngeal Cancer Classification on Contact Endoscopy-Narrow Band Imaging

(1) Background: Contact Endoscopy (CE) and Narrow Band Imaging (NBI) are optical imaging modalities that can provide enhanced and magnified visualization of the superficial vascular networks in the laryngeal mucosa. The similarity of vascular structures between benign and malignant lesions causes a challenge in the visual assessment of CE-NBI images. The main objective of this study is to use Deep Convolutional Neural Networks (DCNN) for the automatic classification of CE-NBI images into benign and malignant groups with minimal human intervention. (2) Methods: A pretrained Res-Net50 model combined with the cut-off-layer technique was selected as the DCNN architecture. A dataset of 8181 CE-NBI images was used during the fine-tuning process in three experiments where several models were generated and validated. The accuracy, sensitivity, and specificity were calculated as the performance metrics in each validation and testing scenario. (3) Results: Out of a total of 72 trained and tested models in all experiments, Model 5 showed high performance. This model is considerably smaller than the full ResNet50 architecture and achieved the testing accuracy of 0.835 on the unseen data during the last experiment. (4) Conclusion: The proposed fine-tuned ResNet50 model showed a high performance to classify CE-NBI images into the benign and malignant groups and has the potential to be part of an assisted system for automatic laryngeal cancer detection.

Deep Learning Applied to White Light and Narrow Band Imaging Videolaryngoscopy: Toward Real-Time Laryngeal Cancer Detection

OBJECTIVES

To assess a new application of artificial intelligence for real-time detection of laryngeal squamous cell carcinoma (LSCC) in both white light (WL) and narrow-band imaging (NBI) videolaryngoscopies based on the You-Only-Look-Once (YOLO) deep learning convolutional neural network (CNN).

STUDY DESIGN

Experimental study with retrospective data.

METHODS

Recorded videos of LSCC were retrospectively collected from in-office transnasal videoendoscopies and intraoperative rigid endoscopies. LSCC videoframes were extracted for training, validation, and testing of various YOLO models. Different techniques were used to enhance the image analysis: contrast limited adaptive histogram equalization, data augmentation techniques, and test time augmentation (TTA). The best-performing model was used to assess the automatic detection of LSCC in six videolaryngoscopies.

RESULTS

Two hundred and nineteen patients were retrospectively enrolled. A total of 624 LSCC videoframes were extracted. The YOLO models were trained after random distribution of images into a training set (82.6%), validation set (8.2%), and testing set (9.2%). Among the various models, the ensemble algorithm (YOLOv5s with YOLOv5m-TTA) achieved the best LSCC detection results, with performance metrics in par with the results reported by other state-of-the-art detection models: 0.66 Precision (positive predicted value), 0.62 Recall (sensitivity), and 0.63 mean Average Precision at 0.5 intersection over union. Tests on the six videolaryngoscopies demonstrated an average computation time per videoframe of 0.026 seconds. Three demonstration videos are provided.

CONCLUSION

This study identified a suitable CNN model for LSCC detection in WL and NBI videolaryngoscopies. Detection performances are highly promising. The limited complexity and quick computational times for LSCC detection make this model ideal for real-time processing.

LEVEL OF EVIDENCE

3 Laryngoscope, 2021.

Vocal cord lesions classification based on deep convolutional neural network and transfer learning

PURPOSE

Laryngoscopy, the most common diagnostic method for vocal cord lesions (VCLs), is based mainly on the visual subjective inspection of otolaryngologists. This study aimed to establish a highly objective computer-aided VCLs diagnosis system based on deep convolutional neural network (DCNN) and transfer learning.

METHODS

To classify VCLs, our method combined the DCNN backbone with transfer learning on a system specifically finetuned for a laryngoscopy image dataset. Laryngoscopy image database was collected to train the proposed system. The diagnostic performance was compared with other DCNN-based models. Analysis of F1 score and receiver operating characteristic curves were conducted to evaluate the performance of the system.

RESULTS

Beyond the existing VCLs diagnosis method, the proposed system achieved an overall accuracy of 80.23%, an F1 score of 0.7836, and an area under the curve (AUC) of 0.9557 for four fine-grained classes of VCLs, namely, normal, polyp, keratinization, and carcinoma. It also demonstrated robust classification capacity for detecting urgent (keratinization, carcinoma) and non-urgent (normal, polyp), with an overall accuracy of 0.939, a sensitivity of 0.887, a specificity of 0.993, and an AUC of 0.9828. The proposed method also outperformed clinicians in the classification of normal, polyps, and carcinoma at an extremely low time cost.

CONCLUSION

The VCLs diagnosis system succeeded in using DCNN to distinguish the most common VCLs and normal cases, holding a practical potential for improving the overall diagnostic efficacy in VCLs examinations. The proposed VCLs diagnosis system could be appropriately integrated into the conventional workflow of VCLs laryngoscopy as a highly objective auxiliary method.

Laryngeal Squamous Cell Carcinoma: Clinical Significance and Potential Mechanism of Cell Division Cycle 45

Background: Cell division cycle 45 (CDC45) plays an important role in the occurrence and development of numerous carcinomas, but its effect in laryngeal squamous cell carcinoma (LSCC) remains unclear. Materials and Methods: The messenger RNA and protein expression levels of CDC45 in LSCC were evaluated with a t test and the standard mean difference (SMD). The ability of CDC45 expression to distinguish the LSCC was assessed through receiver operating characteristic (ROC) curves. Gene set enrichment analysis (GSEA), protein-protein interaction, public databases, and online tools were used to explore the potential molecular mechanism of CDC45 in LSCC. Results: A high expression of CDC45 was identified in LSCC (SMD = 2.61, 95% confidence interval [1.62-3.61]). Through ROC curves, the expression of CDC45 makes it feasible to distinguish the LSCC group from the non-LSCC counterpart. CDC45 was relevant to the progression-free interval of LSCC patients (log-rank p = 0.03). GSEAs show that CDC45 is related to the cell cycle. CDC45, CDC6, KIF2C, and AURKB were identified as hub genes of LSCC. E2F1 may be the regulatory transcription factor of CDC45. Conclusions: High expression of CDC45 likely demonstrates carcinogenic effects in LSCC, and CDC45 is a potential target in screening and treatment of LSCC.

Applications of Artificial Intelligence to Office Laryngoscopy: A Scoping Review

OBJECTIVES/HYPOTHESIS

This scoping review aims to provide a broad overview of the applications of artificial intelligence (AI) to office laryngoscopy to identify gaps in knowledge and guide future research.

STUDY DESIGN

Scoping Review.

METHODS

Searches for studies on AI and office laryngoscopy were conducted in five databases. Title and abstract and then full-text screening were performed. Primary research studies published in English of any date were included. Studies were summarized by: AI applications, targeted conditions, imaging modalities, author affiliations, and dataset characteristics.

RESULTS

Studies focused on vocal fold vibration analysis (43%), lesion recognition (24%), and vocal fold movement determination (19%). The most frequently automated tasks were recognition of vocal fold nodules (19%), polyp (14%), paralysis (11%), paresis (8%), and cyst (7%). Imaging modalities included high-speed laryngeal videos (45%), stroboscopy (29%), and narrow band imaging endoscopy (7%). The body of literature was primarily authored by science, technology, engineering, and math (STEM) specialists (76%) with only 30 studies (31%) involving co-authorship by STEM specialists and otolaryngologists. Datasets were mostly from single institution (84%) and most commonly originated from Germany (23%), USA (16%), Spain (9%), Italy (8%), and China (8%). Demographic information was only reported in 39 studies (40%), with age and sex being the most commonly reported, whereas race/ethnicity and gender were not reported in any studies.

CONCLUSION

More interdisciplinary collaboration between STEM and otolaryngology research teams improved demographic reporting especially of race and ethnicity to ensure broad representation, and larger and more geographically diverse datasets will be crucial to future research on AI in office laryngoscopy.

LEVEL OF EVIDENCE

N/A Laryngoscope, 2021.

Performance of deep convolutional neural network for classification and detection of oral potentially malignant disorders in photographic images

Oral potentially malignant disorders (OPMDs) are a group of conditions that can transform into oral cancer. The purpose of this study was to evaluate convolutional neural network (CNN) algorithms to classify and detect OPMDs in oral photographs. In this study, 600 oral photograph images were collected retrospectively and grouped into 300 images of OPMDs and 300 images of normal oral mucosa. CNN-based classification models were created using DenseNet-121 and ResNet-50. The detection models were created using Faster R-CNN and YOLOv4. The image data were randomly selected and assigned as training, validating, and testing data. The testing data were evaluated to compare the performance of the CNN models with the diagnosis results produced by oral and maxillofacial surgeons. DenseNet-121 and ResNet-50 were found to produce high efficiency in diagnosis of OPMDs, with an area under the receiver operating characteristic curve (AUC) of 95%. Faster R-CNN yielded the highest detection performance, with an AUC of 74.34%. For the CNN-based classification model, the sensitivity and specificity were 100% and 90%, respectively. For the oral and maxillofacial surgeons, these values were 91.73% and 92.27%, respectively. In conclusion, the DenseNet-121, ResNet-50 and Faster R-CNN models have potential for the classification and detection of OPMDs in oral photographs.

Diagnostic value of autofluorescence laryngoscope in early laryngeal carcinoma and precancerous lesions: A systematic review and meta-analysis

OBJECTIVE

We aim to evaluate the diagnostic value of autofluorescence laryngoscope (AFL) in early laryngeal carcinoma and precancerous lesions. aWe also assess the value of AFL in diagnosis of early laryngeal carcinoma and precancerous lesions in comparison with that of white light laryngoscope (WL).

METHODS

The databases consisting of PubMed, Cochrane Library, Web of science and CNKI were systematically searched to find pertinent literatures of AFL in diagnosing early laryngeal carcinoma and precancerous lesions. We made a quality evaluation of every study we included using the modified Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). The pooled sensitivities, specificities were calculated using Meta-Disc 1.4. And we estimated the summary receiver operating characteristic curves (SROC) and area under the curves (AUC).

RESULTS

We finally included 23 studies. The results of AFL in diagnosing early laryngeal carcinoma and precancerous lesions showed higher sensitivity of 0.91 (95%CI: 0.89-0.93; χ²=43.78, p = 0.0025) and specificity of 0.80 (95%CI: 0.77-0.82; χ²=130.64, p = 0.000), and the weighted AUC of AFL was 0.948 ± 0.013 (95%CI: 0.921-0.974) and the diagnostic accuracy (Q*) was 0.887 ± 0.018. The sensitivity and specificity of WL were 0.74 (95%CI: 0.70-0.77; χ²=52.40, p = 0.000) and 0.89 (95%CI: 0.87-0.90; χ²=299.22, p = 0.000), and the weighted AUC of WL was 0.835 ± 0.029 (95%CI: 0.777-0.892) and the diagnostic accuracy (Q*) was 0.767 ± 0.027.

CONCLUSION

The meta-analysis and systematic review suggested that AFL had high diagnostic value in early laryngeal carcinoma and precancerous lesions, and its diagnostic value was higher than that of WL. These results indicated that AFL can provide good guidance for the early detection of laryngeal carcinoma and precancerous lesions.

Feasibility of a deep learning-based algorithm for automated detection and classification of nasal polyps and inverted papillomas on nasal endoscopic images

BACKGROUND

Discrimination of nasal cavity mass lesions is a challenging work requiring extensive experience. A deep learning-based automated diagnostic system may help clinicians to classify nasal cavity mass lesions. We demonstrated the feasibility of a convolutional neural network (CNN)-based diagnosis system for automatic detection and classification of nasal polyps (NP) and inverted papillomas (IP).

METHODS

We developed a CNN-based algorithm using a transfer learning strategy and trained it on nasal endoscopic images. A total of 99 nasal endoscopic images with normal findings, 98 images with NP, and 100 images with IP were analyzed using the developed CNN. Six otolaryngologists participated in clinical visual assessment. Image-based classification performance was measured by calculating the accuracy and area under the receiver operating characteristic curve (AUC). The diagnostic performance was compared between the CNN and clinical visual assessment by human experts.

RESULTS

The algorithm achieved an overall accuracy of 0.742 ± 0.058 with the following class accuracies: normal, 0.81± 0.14; IP, 0.57 ± 0.07; and NP, 0.83 ± 0.21. The AUC values for normal, IP, and NP were 0.91 ± 0.06, 0.82 ± 0.09, and 0.84 ± 0.06, respectively. The overall accuracy of the CNN model was comparable with the average performance of human experts (0.742 vs. 0.749; p = 0.11).

CONCLUSIONS

The trained CNN model appears to reliably classify NP and IP of the nasal cavity from nasal endoscopic images; it also yields a reliable reference for diagnosing nasal cavity mass lesions during nasal endoscopy. However, further studies with more test data are warranted to improve the diagnostic accuracy of our CNN model.