Automated detection of glottic laryngeal carcinoma in laryngoscopic images from a multicentre database using a convolutional neural network

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.

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.

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.