Thyroid-associated Orbitopathy Research Articles

A preliminary evaluation of the diagnostic performance of a smartphone-based machine learning-assisted system for evaluation of clinical activity score in digital images of thyroid-associated orbitopathy.

We previously developed a machine learning (ML)-assisted system for predicting the clinical activity score (CAS) in thyroid-associated orbitopathy (TAO) using digital facial images taken by a DSLR camera in a studio setting. In this study, we aimed to apply this system to smartphones and detect active TAO (CAS ≥ 3) using facial images captured by smartphone cameras. We evaluated the performance of our system on various smartphone models and compared it with the performance of ophthalmologists with varying clinical experience. We applied the pre-existing ML architecture to classify photos taken with smartphones (Galaxy S21 Ultra, iPhone 12 pro, iPhone 11, iPhone SE 2020, Galaxy M20, and Galaxy A21S). The performance was evaluated with smartphone-captured images from 100 patients with TAO. Three ophthalmology residents, 3 general ophthalmologists with < 5 years of clinical experience, and 3 oculoplastic specialists independently interpreted the same set of images taken under a studio environment and compared their results with those generated by the smartphone-based ML-assisted system. Reference CAS was determined by a consensus of three oculoplastic specialists. Active TAO (CAS ≥3) was identified in 28 patients. Smartphone model used in capturing facial images influenced active TAO detection performance (f1 score 0.59 to 0.72). The smartphone-based system showed 74.5% sensitivity, 84.8% specificity, and f1 score 0.70 on top three smartphones. On images from all six smartphones, average sensitivity, specificity, and f1 score were 71.4%, 81.6%, and 0.66, respectively. Ophthalmology residents' values were 69.1%, 55.1%, and 0.46. General ophthalmologists' values were 61.9%, 79.6%, 0.55. Oculoplastic specialists' values were 73.8%, 90.7%, 0.75. This smartphone-based ML-assisted system predicted CAS within 1 point of reference CAS in 90.7% using facial images from smartphones. Our smartphone-based ML-assisted system shows reasonable accuracy in detecting active TAO, comparable to oculoplastic specialists and outperforming residents and general ophthalmologists. It may enable reliable self-monitoring for disease activity, but confirmatory research is needed for clinical application. Clinicaltrials.gov, NCT05731154.

Clinician’s approach for spectrum of orbital diseases: An overview

ABSTRACT Purpose: To study the varied clinical presentation and outcome of management of orbital diseases and to ascertain the concordance of FNAC with histopathology. Materials and Methods: This is a prospective interventional study wherein each patient’s clinical presentation was noted. Outcome of management was evaluated based on symptomatic relief, regression of signs, noting any intraoperative or postsurgical complication, recurrence, and cosmetic result in terms of surgical scar. Results: Neoplasia was commonest 33/76; (43.42%), followed by infective and inflammatory conditions 21/76; (27.63% cases), thyroid-associated orbitopathy accounting for 12/76 cases (15.78%), whereas cystic lesions and vascular malformations were 4/76 (5.26%) each. Other disorders constituted a mere 2.65%. Proptosis was the commonest mode of presentation. It was seen in seventy out of seventy-six patients (92.1%). In 86.3% of the cases, there was successful surgical outcome. Of 22 surgically managed cases, recurrence was noted in three cases (13.6%). 90% concordance was seen with histopathology in cases where FNAC was done prior to surgery for diagnosing nature of disease. Conclusions: Majority of orbital and adnexal conditions can be provisionally diagnosed based on imaging; however, an adjunct invasive investigation such as FNAC or biopsy may be required. In the present study, in seven cases (9.2%) FNAC was needed, whereas in two cases (2.63%) biopsy was needed. A definitive diagnosis was confirmed by histopathology in 22 surgically managed cases and by excision biopsy in two. 22/76 (28.94%) of the cases needed surgical treatment, and other cases required conservative or palliative approach.

Unveiling Modern Strategies for Diagnosing and Treating Grave Orbitopathy

Graves' Orbitopathy (GO), also known as thyroid eye disease or thyroid-associated orbitopathy is characterized by inflammation, ocular muscle hypertrophy, adipogenesis, and oedema (due to glycosaminoglycan accumulation). This condition leads to remodeling, tissue expansion, and/or fibrosis within the fibroadipose tissue or extraocular muscles of the orbit. GO manifests as an extrathyroidal aspect of autoimmune thyroid diseases in both Grave's disease (GD) and Hashimoto's thyroiditis.&#x0D; The pathophysiological foundation of GO entails the infiltration of B cells, T cells, and CD34+ fibroblasts in the orbit. B cells generate IGF (insulin-like growth factor), wherein IGF and TRab (Thyroid-Receptor antibodies) stimulate the IGF receptor complex and thyrotropin receptor (respectively) on the surface of CD34+ cells which triggers orbital tissue expansion, orbital protrusion, optic nerve compression, and eyeball displacement, resulting in exophthalmos.&#x0D; GO progress through an active phase (characterized by inflammation with visible manifestations), followed by a plateau phase (stabilization of GO manifestations), and a gradual resolution of distinctive residual signs and symptoms (inactive phase). This entire process spans between 18-24 months in untreated patients, where disease manifestations significantly depend on the phase during which the disease is identified.&#x0D; GO therapy is intended to shorten the active phase and supress its residual eye manifestations during the inactive phase. In general, GO therapy is categorized into general and disease severity-specific approaches.&#x0D; GO therapy often falls short of providing satisfactory results, prompting need of surgery to address lingering clinical manifestations. This review presents the latest insights into the pathogenesis and treatment of GO for better management and outcomes.

Association of the Preoperative Fat-to-ratio on the Outcome of Endoscopic Orbital Decompression

Purpose: To investigate the association of the preoperative fat-to-orbit ratio on the outcome of endoscopic orbital decompression in patients with thyroid-associated orbitopathy (TAO).Methods: Between January 2021 and December 2022, 36 patients with TAO, 72 eyes in total, underwent endoscopic orbital decompression at our hospital’s ophthalmology department. We calculated fat-to-orbit ratios using two-dimensional facial computed tomography scans, and conducted both preoperative and postoperative measurements of proptosis and the prism cover test. We used binominal logistic regression analysis to examine the correlation between the ratios and postoperative complications (diplopia, strabismus, lid retraction) following the surgery. Furthermore, simple linear regression analysis was used to assess the relationship between the ratios and change in exophthalmos.Results: The regression indicated significant associations between the ratio and the onset of postoperative complications such as new-onset postoperative diplopia (NOPD) (β = -0.098, &lt;i&gt;p&lt;/i&gt; = 0.029), postoperative strabismus (β = -0.123, &lt;i&gt;p&lt;/i&gt; = 0.009), and eyelid retraction (β = -0.188, &lt;i&gt;p&lt;/i&gt; = 0.002), particularly in cases requiring subsequent strabismus or eyelid retraction surgery after the initial procedure.Conclusions: The preoperative fat-to-orbit ratio is a significant predictor of postoperative complications such as NOPD, strabismus surgery and eyelid retraction surgery in patients undergoing endoscopic orbital decompression for thyroid eye disease. Therefore, it should be considered a valuable indicator of surgical outcomes and complications in such patients.

Correlation between choroidal vascularity and retrobulbar ocular blood flow changes and thyroid-associated ophthalmopathy activity: a cross-sectional study

ObjectiveTo evaluate the alterations in retrobulbar color Doppler imaging (CDI) parameters and retinal/choroidal optical coherence tomography angiography (OCTA) parameters and their association with the clinical activity and severity in thyroid-associated orbitopathy (TAO) patients.MethodsIn this study, the retrobulbar flow parameters including resistance index (RI), Pulsatile Index(PI), peak systolic velocity (PSV) and end diastolic velocity (EDV) in posterior ciliary artery (PCA), central retinal artery (CRA) and ophthalmic artery (OA) were determined by CDI. Moreover, the retina and choroidal vascularity including the superficial vessel density (SVD), deep vessel density (DVD), choroidal thickness (ChT) and choroidal vascularity, including total choroidal area (TCA), luminal area (LA), stromal area (SA) and Choroidal Vascularity Index (CVI), were determined by OCTA. All patients grouped as active TAO and inactive TAO based on Clinical activity score (CAS). We picked the severe eye among the subjects and compared all parameters between two groups. We analyzed the correlations among those parameters.ResultsThere was a significant difference in CAS score, proptosis value, ChT, LA, CVI between patients with active TAO and inactive TAO. In the active group, PSV and EDV of PCA were significantly higher than the inactive group. On logistic regression analysis, CAS was closely associated with PSV-PCA. On multiple linear regression, proptosis value was closely associated with ChT, LA, SA and CVI.ConclusionChoroidal vascularization and retrobulbar blood flow were concurrently higher in active TAO patients and several variables in choroid circulation was closely related to TAO clinical features.

THERMAL IMAGING ACCURACY ON CLINICAL ACTIVITY SCORE (CAS) THYROID EYE DISEASE PATIENTS

Abstract&#x0D; Introduction &amp; Objectives : Thyroid Eye Disease (TED) also known as Graves' ophthalmopathy, thyroid-associated orbitopathy, and other terms is an autoimmune inflammatory disorder with the most common extra-thyroid manifestations of Graves' Disease (GD). The disease phase is usually assessed clinically, by assessing the presence or absence of cardinal signs and symptoms of inflammation which are assessed in the form of a clinical activity score (CAS). In addition, the use of Thermal Imaging (IT) as a passive measurement technique that does not require contact with the patient (non-invasive and non- contact) and does not use ionizing radiation or contrast agents is another option. The use of TI in patients with TED still has minimal data and does not have more specific results. This study aims to determine the accuracy of TI and CAS images in TED patients.&#x0D; Methods : This study design is accuracy test at the Ophthalmology Polyclinic of RSUP Dr. Mohamad Hoesin Palembang in July 2021 until the sample is filled with 24 people. Thermal Imaging (TI) accuracy test was performed to establish active and inactive TED compared to CAS (Clinical Activity Score) in TED patients. Analysis of research results with SPSS version 22.0.&#x0D; Results : The result shown that the proportion of research subjects who were female was 17 people (70.8%) and male research subjects were 7 people (29.2%). At 7 locations the Thermal Imaging examination was found to have varying sensitivity&#x0D; Conclusion : Thermal Imaging can be used to help diagnose active and inactive TED.

[Endocrine orbitopathy].

Endocrine orbitopathy (EO), also known as Graves' orbitopathy or thyroid-associated orbitopathy, is aself-limiting, immunologically induced co-reaction of the retrobulbar tissue of the eye triggered by an autoimmune disease of the thyroid gland. It is particularly associated with Graves' disease and is its most common extrathyroidal manifestation. In addition to typical anamnestic data, characteristic local findings and laboratory changes in immunothyroidism, orbital imaging plays acentral role in the diagnosis and management of this disease. This review article provides comprehensive insight into various imaging modalities used to assess morphologic changes associated with EO. Adetailed presentation of imaging findings provides abetter understanding of orbital physiology.

Ultrasound Examination of the Orbit in Patients With Thyroid- Associated Orbitopathy – Examination Guide and Recommendations for Everyday Practice. A Review

The purpose of this study is to present the possibilities and benefits of ultrasonography (US) of the orbit in the diagnosis and treatment of thyroid-associated orbitopathy (TAO). Methods: US examination of the orbit is an essential addition to clinical and laboratory examination in TAO patients. Nevertheless, it is often neglected in clinical practice or indicated with delay. Based on previously published studies and our experience with the diagnosis and treatment of TAO patients, we aim to highlight the clear benefit of US examination of the orbit and oculomotor muscles, not only for correct TAO diagnosis but also in the monitoring of the disease over time. However, knowledge of the drawbacks and limitations of this method is also essential, as we shall point out. It is always necessary to remember that US examination must be evaluated in connection with the clinical findings. A detailed recommendation for US examination of the extraocular muscles and the orbit based on our experiences with diagnosing and treating TAO patients in daily practice is also included. Conclusion: According to our experience, US examination of the orbit is an excellent and irreplaceable tool for timely TAO diagnosis and further disease monitoring. However, considerable examiner experience and detailed knowledge of the clinical and ultrasound manifestations of TAO are essential.

Efficiency and Safety of Tocilizumab for the Treatment of Thyroid Eye Disease: A Systematic Review.

To review existing literature concerning the effectiveness and safety of tocilizumab (TCZ) for managing thyroid eye disease. A systematic search was conducted across the PubMed and Embase databases to identify studies on TCZ therapy, from inception to May 2023. The search included the keywords "Graves orbitopathy," "thyroid ophthalmopathy," "thyroid eye disease," "thyroid-associated orbitopathy," "thyroid-associated ophthalmopathy," "Graves ophthalmopathy," "endocrine ophthalmopathy," and "Tocilizumab." Only articles written in English, Spanish, or French were considered. Among the 1,013 articles initially screened, a total of 29 fulfilled the eligibility criteria and were selected. Most studies were case reports or case series, and only one randomized clinical trial was found. TCZ has been used mainly in glucocorticoid-resistant or relapsing cases, with a dosage ranging from 4 or 8 mg/kg every 4 weeks when intravenous or a weekly subcutaneous dose of 162 mg. Treatment duration is usually adjusted to the clinical response. TCZ is mostly effective in reducing inflammatory signs during the active phase of thyroid eye disease, with an improvement of at least 3 points in clinical activity score and an overall relapsing rate of 8.2%. Numerous studies have shown marked reductions in proptosis; although the only available randomized controlled trial reported a nonstatistically significant improvement 6 months after treatment, a recent meta-analysis indicated that TCZ seems to be the most effective treatment for reducing proptosis. No severe side effects related to intravenous or subcutaneous TCZ administration were reported. Despite these promising findings, randomized clinical trials to directly compare the efficacy and safety of TCZ and other currently available therapeutic options are needed.

Multihead Neural Network for Multiple Segmented Images-Based Diagnosis of Thyroid-Associated Orbitopathy Activity

Multihead Neural Network for Multiple Segmented Images-Based Diagnosis of Thyroid-Associated Orbitopathy Activity

Differentially expressed genes in orbital adipose/connective tissue of thyroid-associated orbitopathy.

Thyroid-associated orbitopathy (TAO) is a disease associated with autoimmune thyroid disorders and it can lead to proptosis, diplopia, and vision-threatening compressive optic neuropathy. To comprehensively understand the molecular mechanisms underlying orbital adipogenesis in TAO, we characterize the intrinsic molecular properties of orbital adipose/connective tissue from patients with TAO and control individuals. RNA sequencing analysis (RNA-seq) was performed to measure the gene expression of orbital adipose/connective tissues of TAO patients. Differentially expressed genes (DEGs) were detected and analyzed through Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis, and Gene Set Enrichment Analysis (GSEA). The protein-protein interaction (PPI) network was constructed using the STRING database, and hub genes were identified by the Cytoscape plug-in, cytoHubba. We validated several top DEGs through quantitative real-time polymerase chain reaction (qRT-PCR). We identified 183 DEGs in adipose tissue between TAO patients (n=3) and control patients (n=3) through RNA sequencing, including 114 upregulated genes and 69 downregulated genes. The PPI network of these DEGs had 202 nodes and 743 edges. PCR-based validation results of orbital adipose tissue showed multiple top-ranked genes in TAO patients (n=4) are immune and inflammatory response genes compared with the control individual (n=4). They include ceruloplasmin isoform x3 (CP), alkaline tissue-nonspecific isozyme isoform x1 (ALPL), and angiotensinogen (AGT), which were overrepresented by 2.27- to 6.40-fold. Meanwhile, protein mab-21-like 1 (MAB21L1), phosphoinositide 3-kinase gamma-subunit (PIK3C2G), and clavesin-2 (CLVS2) decreased by 2.6% to 32.8%. R-spondin 1 (RSPO1), which is related to oogonia differentiation and developmental angiogenesis, was significantly downregulated in the orbital muscle tissues of patients with TAO compared with the control groups (P=0.024). Our results suggest that there are genetic differences in orbital adipose-connective tissues derived from TAO patients. The upregulation of the inflammatory response in orbital fat of TAO may be consistent with the clinical phenotype like eyelid edema, exophthalmos, and excess tearing. Downregulation of MAB21L1, PIK3C2G, and CLVS2 in TAO tissue demonstrates dysregulation of differentiation, oxidative stress, and developmental pathways.

A study on the clinical profile of patients with thyroid-related orbitopathy presenting to a tertiary eye care institute

Thyroid-associated orbitopathy is an autoimmune disorder that is the most frequent extrathyroidal involvement of Graves’ disease but sometimes occurs in euthyroid or hypothyroid patients. Patients with Thyroid associated disease present with chemosis, superior limbic keratoconjunctivitis, proptosis, lid retraction and oedema, restricted extraocular muscle, and dysthyroid optic neuropathy. This study was an observational cross-sectional study which included all the patients with all age groups who attended the Outpatient Department of a Tertiary Care Hospital, Ajmer, with signs and symptoms of thyroid-associated orbitopathy or diagnosed with thyroid-associated orbitopathy with no history of multiple endocrine disorder. 95 subjects satisfying the inclusion and exclusion criteria were enrolled in the study.The mean age of study participants was 43.93± 12.25 years. Age ranges from 21 years to 80 years. 59 (62.1%) were female. Among all patients 69 (72.6%) were hyperthyroid, 19 (20.0%) were euthyroid and 7 (7.4%) were euthyroid. 5 (5.2%) presented with dysthyroid optic neuropathy. 40(42.10%) cases were of active thyroid eye disease (TED) and the remaining 55 (57.8%) were inactive cases. Out of all active presenters, 30% were having Clinical Active Scoring (CAS) ≥4.Middleage group and female sex were the common clinical profile of the patients of TED. When active and Inactive TED groups were compared, findings such as Average CAS, dysthyroid optic neuropathy, average Hertel’s value, and presenting signs were significantly higher in the active group.

Carotid-cavernous fistula masquerading as thyroid associated orbitopathy (TAO)

Carotid-cavernous fistula masquerading as thyroid associated orbitopathy (TAO)

Comparison of Three Methods of Tonometry in Patients With Inactive Thyroid-Associated Orbitopathy

Introduction: Intraocular pressure (IOP) measurement in patients with thyroid-associated orbitopathy (TAO) can be difficult and misleading, particularly in patients with diplopia and eye deviation (esotropia or hypotropia). However, when measuring IOP, it is also necessary to pay sufficient attention to TAO patients without diplopia in primary gaze direction and without motility disorder that might not be readily apparent. Purpose: The aim of this study was to evaluate the accuracy of measurement of intraocular pressure (IOP) using three different types of tonometers: the rebound tonometer (iCARE), the Goldmann applanation tonometer (GAT) and the non-contact airpuff tonometer (NCT) in patients with inactive TAO. Materials and Methods: A total of 98 eyes of 49 adult patients with TAO were examined. The study group included 36 females and 13 males, with an age range of 19–70 years and a median age of 55.0. All the patients had evidence of thyroid disease, a history of mild to moderate TAO, no clinical signs or symptoms of active disease, and no diplopia in direct gaze direction. In addition to a comprehensive eye examination, all the patients underwent measurement of intraocular pressure with three tonometers: NCT, iCARE, and GAT. The measurements with these three devices were compared. Results: The mean IOP was 18.1 ± 2.4 mmHg (range 13–25 mmHg) with GAT, 22.3 ±5.0 mmHg (range 13–35 mmHg) with NCT, and 18.0 ±2.4 mmHg (range 13.3–26 mmHg) with iCARE. The mean difference between the GAT and iCARE measurements (using the Bland-Altman analysis) was -0.1 ±1.16 mmHg (limits of agreement -2.4 to 2.1). The mean difference between the GAT and NCT measurements was 4.2 ±3.6 mmHg (limits of agreement -2.8 to 11.2). The mean difference between the iCARE and NCT measurements was -4.3 ±3.7 mmHg (limits of agreement -11.6 to 2.9). No significant difference was found between GAT and iCARE (p = 1.000). However, there was a significant difference between GAT and NCT (p &lt; 0.0001), as well as between iCARE and NCT (p &lt; 0.0001). Conclusions: In patients with TAO, NCT significantly overestimates IOP values compared to the GAT and ICare. By contrast, the iCARE rebound tonometer provides IOP measurements comparable to the gold standard GAT in these patients.

Computed Tomography and Magnetic Resonance Imaging of the Orbit in the Diagnosis and Treatment of Thyroid-Associated Orbitopathy – Experience from Practice. A Review

The purpose is to acquaint readers with the contribution of imaging methods (IMs) of the orbit, specifically computed tomography (CT) and magnetic resonance imaging (MRI), in the diagnosis of thyroid-associated orbitopathy (TAO). Methods: IMs of the orbit are an indispensable accessory in the clinical and laboratory examination of TAO patients. The most frequently used and probably most accessible method is an ultrasound examination of the orbit (US), which, however, has a number of limitations. Other methods are CT and MRI. Based on the published knowledge implemented in our practice and several years of experience with the diagnosis and treatment of TAO patients, we would like to point out the benefits of CT and MRI in the given indications: visualisation of the extraocular muscles, assessment of disease activity, diagnosis of dysthyroid optic neuropathy and differential diagnosis of other pathologies in the orbit. Our recommendation for an ideal MRI protocol for disease activity evaluation is also included. Conclusion: IMs play an irreplaceable role not only in the early diagnosis of TAO, but also in the monitoring of the disease and the response to the applied treatment. When choosing a suitable IM for this diagnosis, a number of factors must always be taken into account; not only availability, cost and burden for the patient, but especially the sensitivity and specificity of the given method for the diagnosis of TAO.

Assessment of retinal and choroidal vessel density and nerve fibre layer thickness changes after orbitotomy in patients with severe non-active thyroid orbitopathy: a prospective study.

To evaluate the optical coherence tomography angiogram changes in non-active severe thyroid-related ophthalmopathy patients after cosmetic bone decompression. Eighteen patients (25 eyes) with severe not active not compressive (NANC) TED who were candidates for decompression surgery for cosmetic reasons were included in this study, and a 3 × 3mm macular scan was used to measure vessel density and RNFL thickness. Whole macular vessel density in its superficial, deep and choriocapillaris layers was evaluated. The following data were extracted for each of layers: superior and inferior hemispheres, fovea, parafoveal vessel density, its superior and inferior hemispheres, and temporal, superior, nasal and inferior quadrant. The mean RPC increased postoperatively, which was statistically significant in small vessels of peripapillary area (p-value = 0.045). The mean RNFL thickness decreased after surgery and it was statistically significant in the peripapillary (p-value = 0.032) and Inferior-Hemifield area (p-value = 0.036). The choriocapillaris changes were significant in Superior-Hemifield (p-value = 0.031) and Fovea (p-value = 0.03). Thyroid-associated orbitopathy patients have a tendency to decrease vascular density and correlated with disease activity more than stage of orbitopathy. There was not a strong and even discrepant result in linkage of RNFL thickness and other optic nerve function tests and TED patient status and it is needed to do studies with more epidemiologic power and same methodology of study to be more comparable.

FACTORS ASSOCIATED WITH THYROID ASSOCIATED ORBITOPATHY DUE TO GRAVES’ DISEASE

Background: Thyroid associated orbitopathy (TAO) is the principal extrathyroidal manifestation of Graves’ disease (GD). TAO is described as chronic inflammation of orbital and periorbital tissue. Environmental risk factors variably influence development of TAO and risk factors vary with ethnicity and geographical region. Aims: To evaluate the clinical factors for TAO in patients with GD. Setting and Design: This was a hospital-based cross-sectional study done on consecutive 76 newly diagnosed patients of GD documented by thyroid 99mTechnetium-pertechnetate scan. Materials and Methods: Patients were subjected to complete clinical workup and thyroid profile. The diagnosis of TAO was based on the criteria of Bartley and Gorman. Fifty two TAO patients were compared with twenty four non TAO patients (controls) for risk. Statistical Analysis Used: All analyses were performed with SPSS software (version 21.0). Results: TAO was present in 52 (68%) of patients with GD. TAO was bilateral in 50 (96%) of patients. Majority of patients had mild orbitopathy 34 (65.4%) and none of the patients showed any signs of sight-threatening disease. Clinical activity score (CAS) was active in 13.5% of the study group. There was significant female preponderance in TAO. Current smoking increased the risk of TAO (P = 0.023). Total triiodothyronine (T3) and mean intraocular pressure (IOP) in primary and upward gaze was significantly elevated at baseline in TAO patients. Braley’s sign was seen in 30.7% of patients with TAO and in 8.3% of patients in the control group (P = 0.033). Current smoking, total T3 &gt; 4ng/dl and differential IOP &gt; 6 mmHg were found to be associated with risk of TAO. Conclusion: TAO was clinically inactive and of mild severity in most cases. This study identified current smoking, total T3 &gt; 4 ng/dl and differential IOP &gt; 6 mmHg as risk factors for TAO.

Eagle's syndrome mimicking thyroid-associated orbitopathy.

Not required for Clinical Vignette.

Macular retinal and choroidal thickness profile in patients with thyroid-associated orbitopathy compared to healthy individuals: A cross-sectional study.

To evaluate the macular thickness profile and central subfoveal choroidal thickness in patients with thyroid-associated orbitopathy (TAO) compared to healthy subjects. We used the convenience sampling method and divided all participants into the patients and control groups. Based on the clinical activity score (CAS) in the first examination, the patient group was divided to two subgroups: the patients with CAS < 3 and the patients with CAS ≥ 3. Complete ophthalmologic examinations and optical coherence tomographyimaging were performed for all participants. The mean ± SD of central choroidal thickness was 277 ± 76.58 microns for the control and 326.07 ± 56.574 micron for the patient group which was statistically significant (p = 0.003). We also found that the parafoveal inner thickness is significantly lower in patients compared to healthy subjects (p = 0.02). A comparison of neuro-structural data between the two subgroups of patients showed a significant difference in central choroidal thickness (p = 0.05). This study showed that central choroidal thickness in patients with CAS ≥ 3 compared to those with CAS < 3 and also in the patient group compared to healthy individuals have a significantly increasing trend.

Neural network application for assessing thyroid-associated orbitopathy activity using orbital computed tomography

This study aimed to propose a neural network (NN)-based method to evaluate thyroid-associated orbitopathy (TAO) patient activity using orbital computed tomography (CT). Orbital CT scans were obtained from 144 active and 288 inactive TAO patients. These CT scans were preprocessed by selecting eleven slices from axial, coronal, and sagittal planes and segmenting the region of interest. We devised an NN employing information extracted from 13 pipelines to assess these slices and clinical patient age and sex data for TAO activity evaluation. The proposed NN’s performance in evaluating active and inactive TAO patients achieved a 0.871 area under the receiver operating curve (AUROC), 0.786 sensitivity, and 0.779 specificity values. In contrast, the comparison models CSPDenseNet and ConvNeXt were significantly inferior to the proposed model, with 0.819 (p = 0.029) and 0.774 (p = 0.04) AUROC values, respectively. Ablation studies based on the Sequential Forward Selection algorithm identified vital information for optimal performance and evidenced that NNs performed best with three to five active pipelines. This study establishes a promising TAO activity diagnosing tool with further validation.