Radiomics analysis of the optic nerve for detecting dysthyroid optic neuropathy, based on water-fat imaging

Radiomics in ophthalmology: a systematic review

BACKGROUND

Radiomics holds great potential in medical image analysis for various ophthalmic diseases. In recent times, there have been numerous endeavors in this area of research. This systematic review aims to provide a comprehensive assessment of the strengths and limitations of radiomics in ophthalmology.

METHOD

Conforming to the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines, we conducted a systematic review with a pre-registered protocol (PROSPERO: CRD42023446317). We explored the PubMed, Embase, and Cochrane databases for original studies on this topic and made a comprehensive descriptive integration. Furthermore, the included studies underwent quality assessment by the radiomics quality score (RQS).

RESULTS

A total of 41 articles from an initial search of 227 studies were finally selected for further analysis. These articles included research across five disease categories and covered seven imaging modalities. The radiomics models demonstrated robust performance, with area under the curve (AUC) values mostly falling within 0.7-1.0. The moderate RQS (mean score: 11.17/36) indicated that most studies were retrospectively, single-center analyses without external validation.

CONCLUSIONS

Radiomics holds promising utility in the field of ophthalmology, assisting diagnosis, early-stage screening, and prognostication of treatment response. Artificial intelligence algorithms significantly contribute to the construction of radiomics models in ophthalmology. This study highlights the strengths and challenges of radiomics in ophthalmology and suggests potential avenues for future improvement.

CLINICAL RELEVANCE STATEMENT

Radiomics represents a valuable approach for generating innovative imaging markers, enhancing efficiency in clinical diagnosis and treatment, and aiding decision-making in clinical contexts of many ophthalmic diseases, thereby improving overall patient prognosis.

KEY POINTS

Radiomics has attracted extensive attention in the field of ophthalmology. Articles included five disease categories over seven imaging modalities, consistently yielding AUCs mostly above 0.7. Current research has few prospective and multi-center studies, underlining the necessity for future high-quality studies.

Diagnostic methods for dysthyroid optic neuropathy: A systematic review and analysis

Diagnosis of dysthyroid optic neuropathy (DON) typically relies on a set of diagnostic clinical features, including decreased visual acuity, impaired color vision, presence of relative afferent pupillary defect, optic disc swelling and ancillary tests including visual field (VF), pattern visual evoked potential (pVEP), and apical crowding or optic nerve stretching on neuroimaging. We summarize various diagnostic methods to establish or rule out DON. A total of 95 studies (involving 4619 DON eyes) met the inclusion criteria. All of the studies considered clinical features as evidence of DON, while most of the studies confirmed DON diagnosis by combining clinical features with ancillary tests. Forty studies (42.1%) used at least 2 out of the 3 tests (VF, pVEP and neuroimaging) and 13 studies (13.7%) used all 3 tests to diagnose DON. In 64 % of the published studies regarding DON, the diagnostic methods of DON were not specified. It is important to note the limitations of relying solely on clinical features for diagnosing DON. On the other hand, since some eyes with optic neuropathy can be normal in one ancillary test, but abnormal in another, using more than one ancillary test to aid diagnosis is crucial and should be interpreted in correlation with clinical features. We found that the diagnostic methods of DON in most studies involved using a combination of specific clinical features and at least 2 ancillary tests.

A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy

Purpose

Thyroid eye disease (TED) is an autoimmune condition with an array of clinical manifestations, which can be complicated by compressive optic neuropathy. It is important to identify patients with TED early to ensure close monitoring and treatment to prevent potential permanent disability or vision loss. Deep learning artificial intelligence (AI) algorithms have been utilized in ophthalmology and in other fields of medicine to detect disease. This study aims to introduce a deep learning model to evaluate orbital computed tomography (CT) images for the presence of TED and potential compressive optic neuropathy.

Design

Retrospective review and deep learning algorithm modeling.

Subjects

Patients with TED with dedicated orbital CT scans and with an examination by an oculoplastic surgeon over a 10-year period at a single academic institution. Patients with no TED and normal CTs were used as normal controls. Those with other diagnoses, such as tumors or other inflammatory processes, were excluded.

Methods

Orbital CTs were preprocessed and adopted for the Visual Geometry Group-16 network to distinguish patients with no TED, mild TED, and severe TED with compressive optic neuropathy. The primary model included training and testing of all 3 conditions. Binary model performance was also evaluated. An oculoplastic surgeon was also similarly tested with single and serial images for comparison.

Main Outcome Measures

Accuracy of deep learning model discernment of region of interest for CT scans to distinguish TED versus normal control, as well as TED with clinical signs of optic neuropathy.

Results

A total of 1187 photos from 141 patients were used to develop the AI model. The primary model trained on patients with no TED, mild TED, and severe TED had 89.5% accuracy (area under the curve: range, 0.96-0.99) in distinguishing patients with these clinical categories. In comparison, testing of an oculoplastic surgeon in these 3 categories showed decreased accuracy (70.0% accuracy in serial image testing).

Conclusions

The deep learning model developed in the study can accurately detect TED and further detect TED with clinical signs of optic neuropathy based on orbital CT. The model proved superior compared with human expert grading. With further optimization and validation, this TED deep learning model could help guide frontline health care providers in the detection of TED and help stratify the urgency of a referral to an oculoplastic surgeon and endocrinologist.

Financial Disclosures

The authors have no proprietary or commercial interest in any materials discussed in this article.

Application of Quantitative MRI in Thyroid Eye Disease: Imaging Techniques and Clinical Practices

Thyroid eye disease (TED) is a complex autoimmune disorder that impairs various orbital structures, leading to cosmetic damage and vision loss. Magnetic resonance imaging (MRI) is a fundamental diagnostic tool utilized in clinical settings of TED, for its accurate demonstration of orbital lesions and indication of disease conditions. The application of quantitative MRI has brought a new prospect to the management and research of TED, offering more detailed information on morphological and functional changes in the orbit. Therefore, many researchers concentrated on the implementation of different quantitative MRI techniques on TED for the exploration of clinical practices. Despite the abundance of studies utilizing quantitative MRI in TED, there remain considerable barriers and disputes on the best exploitation of this tool. This could possibly be attributed to the complexity of TED and the fast development of MRI techniques. It is necessary that clinical and radiological aspects of quantitative MRI in TED be better integrated into comprehensive insights. Hence, this review traces back 30 years of publications regarding quantitative MRI utilized in TED and elucidates this promising application in the facets of imaging techniques and clinical practices. We believe that a deeper understanding of the application of quantitative MRI in TED will enhance the efficacy of the multidisciplinary management of TED. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY: Stage 3.

The Potential of Ultrasound Radiomics in Carpal Tunnel Syndrome Diagnosis: A Systematic Review and Meta-Analysis

Background: Carpal tunnel syndrome (CTS) is the most common entrapment neuropathy for which ultrasound imaging has recently emerged as a valuable diagnostic tool. This meta-analysis aims to investigate the role of ultrasound radiomics in the diagnosis of CTS and compare it with other diagnostic approaches. Methods: We conducted a comprehensive search of electronic databases from inception to September 2023. The included studies were assessed for quality using the Quality Assessment Tool for Diagnostic Accuracy Studies. The primary outcome was the diagnostic performance of ultrasound radiomics compared to radiologist evaluation for diagnosing CTS. Results: Our meta-analysis included five observational studies comprising 840 participants. In the context of radiologist evaluation, the combined statistics for sensitivity, specificity, and diagnostic odds ratio were 0.78 (95% confidence interval (CI), 0.71 to 0.83), 0.72 (95% CI, 0.59 to 0.81), and 9 (95% CI, 5 to 15), respectively. In contrast, the ultrasound radiomics training mode yielded a combined sensitivity of 0.88 (95% CI, 0.85 to 0.91), a specificity of 0.88 (95% CI, 0.84 to 0.92), and a diagnostic odds ratio of 58 (95% CI, 38 to 87). Similarly, the ultrasound radiomics testing mode demonstrated an aggregated sensitivity of 0.85 (95% CI, 0.78 to 0.89), a specificity of 0.80 (95% CI, 0.73 to 0.85), and a diagnostic odds ratio of 22 (95% CI, 12 to 41). Conclusions: In contrast to assessments by radiologists, ultrasound radiomics exhibited superior diagnostic performance in detecting CTS. Furthermore, there was minimal variability in the diagnostic accuracy between the training and testing sets of ultrasound radiomics, highlighting its potential as a robust diagnostic tool in CTS.

Orbital and eyelid diseases: The next breakthrough in artificial intelligence?

Orbital and eyelid disorders affect normal visual functions and facial appearance, and precise oculoplastic and reconstructive surgeries are crucial. Artificial intelligence (AI) network models exhibit a remarkable ability to analyze large sets of medical images to locate lesions. Currently, AI-based technology can automatically diagnose and grade orbital and eyelid diseases, such as thyroid-associated ophthalmopathy (TAO), as well as measure eyelid morphological parameters based on external ocular photographs to assist surgical strategies. The various types of imaging data for orbital and eyelid diseases provide a large amount of training data for network models, which might be the next breakthrough in AI-related research. This paper retrospectively summarizes different imaging data aspects addressed in AI-related research on orbital and eyelid diseases, and discusses the advantages and limitations of this research field.