Utility of unsupervised deep learning using a 3D variational autoencoder in detecting inner ear abnormalities on CT images

Machine learning application in otology

This review presents a comprehensive history of Artificial Intelligence (AI) in the context of the revolutionary application of machine learning (ML) to medical research and clinical utilization, particularly for the benefit of researchers interested in the application of ML in otology. To this end, we discuss the key components of ML-input, output, and algorithms. In particular, some representation algorithms commonly used in medical research are discussed. Subsequently, we review ML applications in otology research, including diagnosis, influential identification, and surgical outcome prediction. In the context of surgical outcome prediction, specific surgical treatments, including cochlear implantation, active middle ear implantation, tympanoplasty, and vestibular schwannoma resection, are considered. Finally, we highlight the obstacles and challenges that need to be overcome in future research.

A novel radiological software prototype for automatically detecting the inner ear and classifying normal from malformed anatomy

BACKGROUND

To develop an effective radiological software prototype that could read Digital Imaging and Communications in Medicine (DICOM) files, crop the inner ear automatically based on head computed tomography (CT), and classify normal and inner ear malformation (IEM).

METHODS

A retrospective analysis was conducted on 2053 patients from 3 hospitals. We extracted 1200 inner ear CTs for importing, cropping, and training, testing, and validating an artificial intelligence (AI) model. Automated cropping algorithms based on CTs were developed to precisely isolate the inner ear volume. Additionally, a simple graphical user interface (GUI) was implemented for user interaction. Using cropped CTs as input, a deep learning convolutional neural network (DL CNN) with 5-fold cross-validation was used to classify inner ear anatomy as normal or abnormal. Five specific IEM types (cochlear hypoplasia, ossification, incomplete partition types I and III, and common cavity) were included, with data equally distributed between classes. Both the cropping tool and the AI model were extensively validated.

RESULTS

The newly developed DICOM viewer/software successfully achieved its objectives: reading CT files, automatically cropping inner ear volumes, and classifying them as normal or malformed. The cropping tool demonstrated an average accuracy of 92.25%. The DL CNN model achieved an area under the curve (AUC) of 0.86 (95% confidence interval: 0.81-0.91). Performance metrics for the AI model were: accuracy (0.812), precision (0.791), recall (0.8), and F1-score (0.766).

CONCLUSION

This study successfully developed and validated a fully automated workflow for classifying normal versus abnormal inner ear anatomy using a combination of advanced image processing and deep learning techniques. The tool exhibited good diagnostic accuracy, suggesting its potential application in risk stratification. However, it is crucial to emphasize the need for supervision by qualified medical professionals when utilizing this tool for clinical decision-making.

Advances in Image-Based Artificial Intelligence in Otorhinolaryngology-Head and Neck Surgery: A Systematic Review

OBJECTIVE

To update the literature and provide a systematic review of image-based artificial intelligence (AI) applications in otolaryngology, highlight its advances, and propose future challenges.

DATA SOURCES

Web of Science, Embase, PubMed, and Cochrane Library.

REVIEW METHODS

Studies written in English, published between January 2020 and December 2022. Two independent authors screened the search results, extracted data, and assessed studies.

RESULTS

Overall, 686 studies were identified. After screening titles and abstracts, 325 full-text studies were assessed for eligibility, and 78 studies were included in this systematic review. The studies originated from 16 countries. Among these countries, the top 3 were China (n = 29), Korea (n = 8), the United States, and Japan (n = 7 each). The most common area was otology (n = 35), followed by rhinology (n = 20), pharyngology (n = 18), and head and neck surgery (n = 5). Most applications of AI in otology, rhinology, pharyngology, and head and neck surgery mainly included chronic otitis media (n = 9), nasal polyps (n = 4), laryngeal cancer (n = 12), and head and neck squamous cell carcinoma (n = 3), respectively. The overall performance of AI in accuracy, the area under the curve, sensitivity, and specificity were 88.39 ± 9.78%, 91.91 ± 6.70%, 86.93 ± 11.59%, and 88.62 ± 14.03%, respectively.

CONCLUSION

This state-of-the-art review aimed to highlight the increasing applications of image-based AI in otorhinolaryngology head and neck surgery. The following steps will entail multicentre collaboration to ensure data reliability, ongoing optimization of AI algorithms, and integration into real-world clinical practice. Future studies should consider 3-dimensional (3D)-based AI, such as 3D surgical AI.

BX2S-Net: Learning to reconstruct 3D spinal structures from bi-planar X-ray images

Grasping good understanding of the weight-bearing spatial structure of the spine of a human subject in a standing position is critical for the treatment of spinal disorders. Such disorders are commonly diagnosed via 2D X-ray imaging of the human subject in a standing position. However, 3D reconstruction techniques based on bi-planar X-ray imaging can enable better exploration and analysis of the spinal structure. In particular, compared to earlier deformable modeling approaches, the recently-developed deep-learning-based 3D reconstruction methods exhibit higher efficiency and generalizability. But these methods usually employ simple architectures with 2D encoders and 3D decoders. Thus, these methods have several drawbacks, namely, the existence of a semantic gap between dimensionally-inconsistent feature maps, the difficulty of jointly handling multi-view inputs, and the information source limitations for the decoding process. In order to better assist clinicians and tackle these problems, we propose a novel convolutional neural network framework, which we call BX2S-Net, to effectively achieve 3D spine reconstruction based on bi-planar X-ray images. In particular, a dimensionally-consistent encoder-decoder architecture is designed in conjunction with a dimensionality enhancement method in order to reduce the semantic gap between feature maps and achieve information fusion for multi-view inputs. A feature-guided progressive decoding process is developed on the decoder side, where a full-scale feature attention guidance (FFAG) module is introduced to efficiently aggregate image features and guide the decoding process at each level. In addition, a class augmentation method and a spatially-weighted cross-entropy loss function are used for network training with improved reconstruction quality for the vertebral edge region. The experimental results demonstrate the effectiveness of our model in reconstructing high-quality 3D spinal structures from bi-planar X-ray images. The code is available at https://github.com/NBU-CVMI/bx2s-net.

Detection of abnormal extraocular muscles in small datasets of computed tomography images using a three-dimensional variational autoencoder

We sought to establish an unsupervised algorithm with a three-dimensional (3D) variational autoencoder model (VAE) for the detection of abnormal extraocular muscles in small datasets of orbital computed tomography (CT) images. 334 CT images of normal orbits and 96 of abnormal orbits diagnosed as thyroid eye disease were used for training and validation; 24 normal and 11 abnormal orbits were used for the test. A 3D VAE was developed and trained. All images were preprocessed to emphasize extraocular muscles and to suppress background noise (e.g., high signal intensity from bones). The optimal cut-off value was identified through receiver operating characteristic (ROC) curve analysis. The ability of the model to detect muscles of abnormal size was assessed by visualization. The model achieved a sensitivity of 79.2%, specificity of 72.7%, accuracy of 77.1%, F1-score of 0.667, and AUROC of 0.801. Abnormal CT images correctly identified by the model showed differences in the reconstruction of extraocular muscles. The proposed model showed potential to detect abnormalities in extraocular muscles using a small dataset, similar to the diagnostic approach used by physicians. Unsupervised learning could serve as an alternative detection method for medical imaging studies in which annotation is difficult or impossible to perform.