Novel automated vessel pattern characterization of larynx contact endoscopic video images

Contact Endoscopy - Narrow Band Imaging (CE-NBI) data set for laryngeal lesion assessment

The endoscopic examination of subepithelial vascular patterns within the vocal fold is crucial for clinicians seeking to distinguish between benign lesions and laryngeal cancer. Among innovative techniques, Contact Endoscopy combined with Narrow Band Imaging (CE-NBI) offers real-time visualization of these vascular structures. Despite the advent of CE-NBI, concerns have arisen regarding the subjective interpretation of its images. As a result, several computer-based solutions have been developed to address this issue. This study introduces the CE-NBI data set, the first publicly accessible data set that features enhanced and magnified visualizations of subepithelial blood vessels within the vocal fold. This data set encompasses 11144 images from 210 adult patients with pathological vocal fold conditions, where CE-NBI images are annotated using three distinct label categories. The data set has proven invaluable for numerous clinical assessments geared toward diagnosing laryngeal cancer using Optical Biopsy. Furthermore, given its versatility for various image analysis tasks, we have devised and implemented diverse image classification scenarios using Machine Learning (ML) approaches to address critical clinical challenges in assessing laryngeal lesions.

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.

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.

Cyclist Effort Features: A Novel Technique for Image Texture Characterization Applied to Larynx Cancer Classification in Contact Endoscopy-Narrow Band Imaging

BACKGROUND

Feature extraction is an essential part of a Computer-Aided Diagnosis (CAD) system. It is usually preceded by a pre-processing step and followed by image classification. Usually, a large number of features is needed to end up with the desired classification results. In this work, we propose a novel approach for texture feature extraction. This method was tested on larynx Contact Endoscopy (CE)-Narrow Band Imaging (NBI) image classification to provide more objective information for otolaryngologists regarding the stage of the laryngeal cancer.

METHODS

The main idea of the proposed methods is to represent an image as a hilly surface, where different paths can be identified between a starting and an ending point. Each of these paths can be thought of as a Tour de France stage profile where a cyclist needs to perform a specific effort to arrive at the finish line. Several paths can be generated in an image where different cyclists produce an average cyclist effort representing important textural characteristics of the image. Energy and power as two Cyclist Effort Features (CyEfF) were extracted using this concept. The performance of the proposed features was evaluated for the classification of 2701 CE-NBI images into benign and malignant lesions using four supervised classifiers and subsequently compared with the performance of 24 Geometrical Features (GF) and 13 Entropy Features (EF).

RESULTS

The CyEfF features showed maximum classification accuracy of 0.882 and improved the GF classification accuracy by 3 to 12 percent. Moreover, CyEfF features were ranked as the top 10 features along with some features from GF set in two feature ranking methods.

CONCLUSION

The results prove that CyEfF with only two features can describe the textural characterization of CE-NBI images and can be part of the CAD system in combination with GF for laryngeal cancer diagnosis.

Estimation of laryngeal closure duration during swallowing without invasive X-rays

Laryngeal vestibule (LV) closure is a critical physiologic event during swallowing, since it is the first line of defense against food bolus entering the airway. Identifying the laryngeal vestibule status, including closure, reopening and closure duration, provides indispensable references for assessing the risk of dysphagia and neuromuscular function. However, commonly used radiographic examinations, known as videofluoroscopy swallowing studies, are highly constrained by their radiation exposure and cost. Here, we introduce a non-invasive sensor-based system, that acquires high-resolution cervical auscultation signals from neck and accommodates advanced deep learning techniques for the detection of LV behaviors. The deep learning algorithm, which combined convolutional and recurrent neural networks, was developed with a dataset of 588 swallows from 120 patients with suspected dysphagia and further clinically tested on 45 samples from 16 healthy participants. For classifying the LV closure and opening statuses, our method achieved 78.94% and 74.89% accuracies for these two datasets, suggesting the feasibility of implementing sensor signals for LV prediction without traditional videofluoroscopy screening methods. The sensor supported system offers a broadly applicable computational approach for clinical diagnosis and biofeedback purposes in patients with swallowing disorders without the use of radiographic examination.

Laryngeal Lesion Classification Based on Vascular Patterns in Contact Endoscopy and Narrow Band Imaging: Manual Versus Automatic Approach

Longitudinal and perpendicular changes in the vocal fold’s blood vessels are associated with the development of benign and malignant laryngeal lesions. The combination of Contact Endoscopy (CE) and Narrow Band Imaging (NBI) can provide intraoperative real-time visualization of the vascular changes in the laryngeal mucosa. However, the visual evaluation of vascular patterns in CE-NBI images is challenging and highly depends on the clinicians’ experience. The current study aims to evaluate and compare the performance of a manual and an automatic approach for laryngeal lesion’s classification based on vascular patterns in CE-NBI images. In the manual approach, six observers visually evaluated a series of CE+NBI images that belong to a patient and then classified the patient as benign or malignant. For the automatic classification, an algorithm based on characterizing the level of the vessel’s disorder in combination with four supervised classifiers was used to classify CE-NBI images. The results showed that the manual approach’s subjective evaluation could be reduced by using a computer-based approach. Moreover, the automatic approach showed the potential to work as an assistant system in case of disagreements among clinicians and to reduce the manual approach’s misclassification issue.

Interrater variation of vascular classifications used in enhanced laryngeal contact endoscopy

PURPOSE

Combined use of contact endoscopy (CE) and Narrow Band Imaging (NBI, Olympus^®) is suggested for the visualization of specific vascular changes indicative of glottic neoplasia. We investigated the interrater reliability and agreement in 3 recognized classification systems of vascular changes applied to images from CE + NBI in patients suspected for glottic neoplasia.

METHODS

Six experienced head and neck surgeons familiar with NBI rated 120 images obtained by CE + NBI by 3 classification systems of vascular changes as suggested by Ni et al. (N-C), Puxeddu et al. (P-C), and the European Laryngological Society (ELS-C). Three raters were experienced in CE, and three raters had only limited experience with CE. Crude agreement and Fleiss' kappa with 95% confidence interval were estimated for all 6 raters, and for the 2 levels of expertise for each original classification system and for dichotomized versions of the N-C and the P-C based on suggested neoplastic potential.

RESULTS

The interrater crude agreement and the corresponding kappa values for the ELS-C were good and significantly higher than those for the N-C and P-C for all raters, irrespective of the level of experience with CE (p < 0.0001). There were no significant differences between the N-C and the P-C (p = 0.16). Kappa was considerably improved for both the N-C and the P-C to a level not different from the ELS-C (p = 0.21-0.71) when their 5 original categories were pooled into dichotomized classifications.

CONCLUSION

Difficulties in reliably classifying vascular changes in CE + NBI are evident. Two-tier classification systems are the most reliable.

Contact endoscopy for detection of residual or recurrent disease after radiotherapy for squamous cell carcinoma of the upper aerodigestive tract

OBJECTIVE

The aim of this study was to evaluate contact endoscopy in detecting local treatment failures post-radiotherapy in squamous cell carcinoma of the upper aerodigestive tract.

METHOD

A total of 135 consecutive patients with suspected residual or recurrent cancer after definitive radiotherapy underwent contact endoscopy before biopsy. Contact endoscopy findings were compared with histopathological examination findings. Contact endoscopy could not be completed in 7 patients (5.9 per cent) and histopathological examination was inconclusive in 5 patients (3.7 per cent). The findings of the remaining 123 patients were compared.

RESULTS

The sensitivity, specificity and accuracy of contact endoscopy were 88.75, 88.72 and 86.99 per cent, respectively, with similar results across various sites of upper aerodigestive tract. Inter-observer kappa value was 0.86 (95 per cent confidence interval: 0.79-0.93). The intra-observer kappa value was 0.93 (95 per cent confidence interval: 0.87-1.00) for the first observer and 0.95 (95 per cent confidence interval: 0.90-1.00) for second and third observers.

CONCLUSION

Contact endoscopy showed the same high sensitivity and specificity with low inter- and intra-observer variability in detecting post-radiotherapy failures in cancer of the upper aerodigestive tract as has been shown in non-irradiated tissues in earlier studies.

Evaluation of Vascular Patterns Using Contact Endoscopy and Narrow-Band Imaging (CE-NBI) for the Diagnosis of Vocal Fold Malignancy

The endoscopic detection of perpendicular vascular changes (PVC) of the vocal folds has been associated with vocal fold cancer, dysplastic lesions, and papillomatosis, according to a classification proposed by the European Laryngological Society (ELS). The combination of contact endoscopy with narrow-band imaging (NBI-CE) allows intraoperatively a highly contrasted, real-time visualization of vascular changes of the vocal folds. Aim of the present study was to determine the association of PVC to specific histological diagnoses, the level of interobserver agreement in the detection of PVC, and their diagnostic effectiveness in diagnosing laryngeal malignancy. The evaluation of our data confirmed the association of PVC to vocal fold cancer, dysplastic lesions, and papillomatosis. The level of agreement between the observers in the identification of PVC was moderate for the less-experienced observers and almost perfect for the experienced observers. The identification of PVC during NBI-CE proved to be a valuable indicator for diagnosing malignant and premalignant lesions.