An automated approach for real-time informative frames classification in laryngeal endoscopy using deep learning.

PURPOSE: Informative image selection in laryngoscopy has the potential for improving automatic data extraction alone, for selective data storage and a faster review process, or in combination with other artificial intelligence (AI) detection or diagnosis models. This paper aims to demonstrate the feasibility of AI in providing automatic informative laryngoscopy frame selection also capable of working in real-time providing visual feedback to guide the otolaryngologist during the examination. METHODS: Several deep learning models were trained and tested on an internal dataset (n = 5147 images) and then tested on an external test set (n = 646 images) composed of both white light and narrow band images. Four videos were used to assess the real-time performance of the best-performing model. RESULTS: ResNet-50, pre-trained with the pretext strategy, reached a precision = 95% vs. 97%, recall = 97% vs, 89%, and the F1-score = 96% vs. 93% on the internal and external test set respectively (p = 0.062). The four testing videos are provided in the supplemental materials. CONCLUSION: The deep learning model demonstrated excellent performance in identifying diagnostically relevant frames within laryngoscopic videos. With its solid accuracy and real-time capabilities, the system is promising for its development in a clinical setting, either autonomously for objective quality control or in conjunction with other algorithms within a comprehensive AI toolset aimed at enhancing tumor detection and diagnosis.

Real-Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow-Band Imaging Laryngoscopy with Deep Learning.

OBJECTIVE: To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos. METHODS: A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos. RESULTS: A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70-0.90), Intersection over Union (IoU) = 0.83 (0.73-0.90), Accuracy = 0.97 (0.95-0.99), Inference Speed = 25.6 (25.1-26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos. CONCLUSION: SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement. LEVEL OF EVIDENCE: III Laryngoscope, 134:2826-2834, 2024.

Efficient quality assurance for isocentric stability in stereotactic body radiation therapy using machine learning.

This study aims to predict isocentric stability for stereotactic body radiation therapy (SBRT) treatments using machine learning (ML), covers the challenges of manual assessment and computational time for quality assurance (QA), and supports medical physicists to enhance accuracy. The isocentric parameters for collimator (C), gantry (G), and table (T) tests were conducted with the RUBY phantom during QA using TrueBeam linac for SBRT. This analysis combined statistical features from the IsoCheck EPID software. Five ML models, including logistic regression (LR), decision tree (DT), random forest (RF), naive Bayes (NB), and support vector machines (SVM), were used to predict the outcome of the QA procedure. 247 Winston-Lutz (WL) tests were collected from 2020 to 2022. In our study, both DT and RF achieved the highest score on test accuracy (Acc. test) ranging from 93.5% to 99.4%, and area under curve (AUC) values from 90 to 100% on three modes (C, G, and T). The precision, recall, and F1 scores indicate the DT model consistently outperforms other ML models in predicting isocenter stability deviation in QA. The QA assessment using ML models can assist error prediction early to avoid potential harm during SBRT and ensure safe and effective patient treatments.

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.

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images.

Introduction: Narrow Band Imaging (NBI) is an endoscopic visualization technique useful for upper aero-digestive tract (UADT) cancer detection and margins evaluation. However, NBI analysis is strongly operator-dependent and requires high expertise, thus limiting its wider implementation. Recently, artificial intelligence (AI) has demonstrated potential for applications in UADT videoendoscopy. Among AI methods, deep learning algorithms, and especially convolutional neural networks (CNNs), are particularly suitable for delineating cancers on videoendoscopy. This study is aimed to develop a CNN for automatic semantic segmentation of UADT cancer on endoscopic images. Materials and Methods: A dataset of white light and NBI videoframes of laryngeal squamous cell carcinoma (LSCC) was collected and manually annotated. A novel DL segmentation model (SegMENT) was designed. SegMENT relies on DeepLabV3+ CNN architecture, modified using Xception as a backbone and incorporating ensemble features from other CNNs. The performance of SegMENT was compared to state-of-the-art CNNs (UNet, ResUNet, and DeepLabv3). SegMENT was then validated on two external datasets of NBI images of oropharyngeal (OPSCC) and oral cavity SCC (OSCC) obtained from a previously published study. The impact of in-domain transfer learning through an ensemble technique was evaluated on the external datasets. Results: 219 LSCC patients were retrospectively included in the study. A total of 683 videoframes composed the LSCC dataset, while the external validation cohorts of OPSCC and OCSCC contained 116 and 102 images. On the LSCC dataset, SegMENT outperformed the other DL models, obtaining the following median values: 0.68 intersection over union (IoU), 0.81 dice similarity coefficient (DSC), 0.95 recall, 0.78 precision, 0.97 accuracy. For the OCSCC and OPSCC datasets, results were superior compared to previously published data: the median performance metrics were, respectively, improved as follows: DSC=10.3% and 11.9%, recall=15.0% and 5.1%, precision=17.0% and 14.7%, accuracy=4.1% and 10.3%. Conclusion: SegMENT achieved promising performances, showing that automatic tumor segmentation in endoscopic images is feasible even within the highly heterogeneous and complex UADT environment. SegMENT outperformed the previously published results on the external validation cohorts. The model demonstrated potential for improved detection of early tumors, more precise biopsies, and better selection of resection margins.

A review on multimodal medical image fusion: Compendious analysis of medical modalities, multimodal databases, fusion techniques and quality metrics.

BACKGROUND AND OBJECTIVES: Over the past two decades, medical imaging has been extensively apply to diagnose diseases. Medical experts continue to have difficulties for diagnosing diseases with a single modality owing to a lack of information in this domain. Image fusion may be use to merge images of specific organs with diseases from a variety of medical imaging systems. Anatomical and physiological data may be included in multi-modality image fusion, making diagnosis simpler. It is a difficult challenge to find the best multimodal medical database with fusion quality evaluation for assessing recommended image fusion methods. As a result, this article provides a complete overview of multimodal medical image fusion methodologies, databases, and quality measurements. METHODS: In this article, a compendious review of different medical imaging modalities and evaluation of related multimodal databases along with the statistical results is provided. The medical imaging modalities are organized based on radiation, visible-light imaging, microscopy, and multimodal imaging. RESULTS: The medical imaging acquisition is categorized into invasive or non-invasive techniques. The fusion techniques are classified into six main categories: frequency fusion, spatial fusion, decision-level fusion, deep learning, hybrid fusion, and sparse representation fusion. In addition, the associated diseases for each modality and fusion approach presented. The quality assessments fusion metrics are also encapsulated in this article. CONCLUSIONS: This survey provides a baseline guideline to medical experts in this technical domain that may combine preoperative, intraoperative, and postoperative imaging, Multi-sensor fusion for disease detection, etc. The advantages and drawbacks of the current literature are discussed, and future insights are provided accordingly.

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, 132:1798-1806, 2022.