Detection of laryngeal carcinoma during endoscopy using artificial intelligence

Wellenstein, David J.; Woodburn, Jonathan; Marres, H.A.M.; Broek, Guido B. van den

doi:10.1002/hed.27441

Cited by 15 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2023, Wellenstein et al reported the results of an AI model to detect carcinoma in images from flexible laryngoscopy and microlaryngoscopy recordings. 10 They were able to analyze images at an average inference frame rate of 63 but only achieved a sensitivity of 71% to 78% using a YOLO model. YOLO models employ a simplified inference algorithm for speed, sacrificing accuracy in the case of specialized datasets.…”

Section: Discussionmentioning

confidence: 99%

“…Artificial intelligence (AI) assisted computer vision during flexible laryngoscopy provides valuable insights and facilitates diagnosis. [7][8][9][10] Investigators have used deep learning models to classify vocal fold pathology, 11,12 localize lesions in the endoscopic field, 13,14 and evaluate images for diagnostic quality. [15][16][17] Most of these applications focus on static endoscopic images; there are few reports of video annotation models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Laryngeal Cancer Screening During Flexible Video Laryngoscopy Using Large Computer Vision Models

Mamidi,

Dunham,

Adkins

et al. 2024

Ann Otol Rhinol Laryngol

View full text Add to dashboard Cite

Objective: Develop an artificial intelligence assisted computer vision model to screen for laryngeal cancer during flexible laryngoscopy. Methods: Using laryngeal images and flexible laryngoscopy video recordings, we developed computer vision models to classify video frames for usability and cancer screening. A separate model segments any identified lesions on the frames. We used these computer vision models to construct a video stream annotation system. This system classifies findings from flexible laryngoscopy as “potentially malignant” or “probably benign” and segments any detected lesions. Additionally, the model provides a confidence level for each classification. Results: The overall accuracy of the flexible laryngoscopy cancer screening model was 92%. For cancer screening, it achieved a sensitivity of 97.7% and a specificity of 76.9%. The segmentation model attained an average precision at a 0.50 intersection-over-union of 0.595. The confidence level for positive screening results can assist clinicians in counseling patients regarding the findings. Conclusion: Our model is highly sensitive and adequately specific for laryngeal cancer screening. Segmentation helps endoscopists identify and describe potential lesions. Further optimization is required to enable the model’s deployment in clinical settings for real-time annotation during flexible laryngoscopy.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Laryngeal Cancer Screening During Flexible Video Laryngoscopy Using Large Computer Vision Models

Mamidi,

Dunham,

Adkins

et al. 2024

Ann Otol Rhinol Laryngol

View full text Add to dashboard Cite

show abstract

“…Now, DL states to an ML method that is dependent upon a neural network (NN) model with numerous data representation stages. Convolutional neural networks (CNNs) constitute feedforward neural networks (FFNNs) with deep architecture and convolution computation [ 8 ]. It has a model that must overcome classification and identification issues.…”

Section: Introductionmentioning

confidence: 99%

Automated Laryngeal Cancer Detection and Classification Using Dwarf Mongoose Optimization Algorithm with Deep Learning

Mohamed,

Almutairi,

Abdelrahim

et al. 2023

Cancers

View full text Add to dashboard Cite

Laryngeal cancer (LCA) is a serious disease with a concerning global rise in incidence. Accurate treatment for LCA is particularly challenging in later stages, due to its complex nature as a head and neck malignancy. To address this challenge, researchers have been actively developing various analysis methods and tools to assist medical professionals in efficient LCA identification. However, existing tools and methods often suffer from various limitations, including low accuracy in early-stage LCA detection, high computational complexity, and lengthy patient screening times. With this motivation, this study presents an Automated Laryngeal Cancer Detection and Classification using a Dwarf Mongoose Optimization Algorithm with Deep Learning (ALCAD-DMODL) technique. The main objective of the ALCAD-DMODL method is to recognize the existence of LCA using the DL model. In the presented ALCAD-DMODL technique, a median filtering (MF)-based noise removal process takes place to get rid of the noise. Additionally, the ALCAD-DMODL technique involves the EfficientNet-B0 model for deriving feature vectors from the pre-processed images. For optimal hyperparameter tuning of the EfficientNet-B0 model, the DMO algorithm can be applied to select the parameters. Finally, the multi-head bidirectional gated recurrent unit (MBGRU) model is applied for the recognition and classification of LCA. The simulation result analysis of the ALCAD-DMODL technique is carried out on the throat region image dataset. The comparison study stated the supremacy of the ALCAD-DMODL technique in terms of distinct measures.

show abstract

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

Tie,

Li,

Zhu

et al. 2024

The Laryngoscope

View full text Add to dashboard Cite

ObjectivesVocal 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.MethodsA 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.ResultsThe 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.ConclusionsOur 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 Evidence3 Laryngoscope, 2024

show abstract

Detection of laryngeal carcinoma during endoscopy using artificial intelligence

Cited by 15 publications

References 38 publications

Laryngeal Cancer Screening During Flexible Video Laryngoscopy Using Large Computer Vision Models

Laryngeal Cancer Screening During Flexible Video Laryngoscopy Using Large Computer Vision Models

Automated Laryngeal Cancer Detection and Classification Using Dwarf Mongoose Optimization Algorithm with Deep Learning

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

Contact Info

Product

Resources

About