Validation of a deep learning model for automatic detection and quantification of five OCT critical retinal features associated with neovascular age-related macular degeneration.

PURPOSE: To develop and validate a deep learning model for the segmentation of five retinal biomarkers associated with neovascular age-related macular degeneration (nAMD). METHODS: 300 optical coherence tomography volumes from subject eyes with nAMD were collected. Images were manually segmented for the presence of five crucial nAMD features: intraretinal fluid, subretinal fluid, subretinal hyperreflective material, drusen/drusenoid pigment epithelium detachment (PED) and neovascular PED. A deep learning architecture based on a U-Net was trained to perform automatic segmentation of these retinal biomarkers and evaluated on the sequestered data. The main outcome measures were receiver operating characteristic curves for detection, summarised using the area under the curves (AUCs) both on a per slice and per volume basis, correlation score, enface topography overlap (reported as two-dimensional (2D) correlation score) and Dice coefficients. RESULTS: The model obtained a mean (±SD) AUC of 0.93 (±0.04) per slice and 0.88 (±0.07) per volume for fluid detection. The correlation score (R2) between automatic and manual segmentation obtained by the model resulted in a mean (±SD) of 0.89 (±0.05). The mean (±SD) 2D correlation score was 0.69 (±0.04). The mean (±SD) Dice score resulted in 0.61 (±0.10). CONCLUSIONS: We present a fully automated segmentation model for five features related to nAMD that performs at the level of experienced graders. The application of this model will open opportunities for the study of morphological changes and treatment efficacy in real-world settings. Furthermore, it can facilitate structured reporting in the clinic and reduce subjectivity in clinicians' assessments.

Ocular Surface Disease in Patients With Atopic Dermatitis Treated With Dupilumab: A Prospective Case-Control Study.

PURPOSE: The aim of this study was to evaluate the variation of dry eye disease (DED) prevalence in patients with atopic dermatitis (AD) treated with dupilumab. METHODS: This prospective case-control study included consecutive patients with moderate-to-severe AD scheduled for dupilumab between May and December 2021 and healthy subjects. DED prevalence, the Ocular Surface Disease Index, tear film breakup time test, osmolarity, Oxford staining score, and Schirmer test results were collected at baseline, 1 month, and 6 months after dupilumab therapy. The Eczema Area and Severity Index was assessed at baseline. Ocular side effects and discontinuation of dupilumab were also recorded. RESULTS: Seventy-two eyes from 36 patients with AD treated with dupilumab and 36 healthy controls were included. Prevalence of DED increased from 16.7% at baseline to 33.3% at 6 months in the dupilumab group ( P = 0.001), whereas it remained unchanged in the control group ( P = 0.110). At 6 months, the Ocular Surface Disease Index and Oxford score increased (from 8.5 ± 9.8 to 11.0 ± 13.0, P = 0.068, and from 0.1 ± 0.5 to 0.3 ± 0.6, P = 0.050, respectively), the tear film breakup time test and Schirmer test results decreased (from 7.8 ± 2.6 s to 7.1 ± 2.7 s, P < 0.001, and from 15.4 ± 9.6 mm to 13.2 ± 7.9 mm, P = 0.036, respectively) in the dupilumab group, whereas they remained stable in the control group ( P > 0.05). Osmolarity was unchanged (dupilumab P = 0.987 and controls P = 0.073). At 6 months after dupilumab therapy, 42% of patients had conjunctivitis, 36% blepharitis, and 2.8% keratitis. No severe side effects were reported, and none of the patients discontinued dupilumab. No association between Eczema Area and Severity Index and DED prevalence was shown. CONCLUSIONS: DED prevalence increased in patients with AD treated with dupilumab at 6 months. However, no severe ocular side effects were found and no patient discontinued therapy.

Visual symptoms in a patient treated with MEK inhibitors.

PURPOSE: to report an uncommon presentation of Encorafenib-Binimetinib retinal side effects. CASE REPORT: A 56-year-old Caucasian woman, naïve to previous chemotherapies, was started on Encorafenib/Binimetinib for metastatic melanoma. After seven hours from the first 45 mg Binimetinib dose, the patient developed blurry vision with coloured halos. The symptoms were transient and the following day a complete ophthalmological examination revealed the presence of subretinal fluid (SRF) at Optical coherence tomography (OCT). After one week, the patient remained asymptomatic, with no signs of SRF at the follow up reevaluation. However, six weeks later, the symptoms originally experienced with the first drug intake appeared again. This time fundus examination revealed an irregular macular region. At infrared OCT an almond shaped hyporeflective lesion, surrounded by hyperreflectivity, was demonstrated without signs of SRF. Encorafenib/Binimetinib was continued at the same dose and strict monitoring was scheduled, according to the European Medicine's Agency indication to withhold the drug only in presence of symptomatic retinal pigment epithelial detachment. CONCLUSION: Visual symptoms associated with SRF induced by Binimetinib have been described in the literature. In our case, visual symptoms were experienced by the patient at different times, both with and without evidence of SRF. This finding seems to suggest that while Binimetinib-induced SRF is an asymptomatic finding in most cases, with excellent outcome and rapid resolution, visual symptoms could be initially triggered by detectable SRF, yet persist without any further evidence of abnormal fluid accumulation and manifest intermittently.

Retinoid-associated myopia in dermatologic patients: a systematic review.

PURPOSE: Systemic retinoids are among the most prescribed drugs in dermatology, thanks to their activity as proliferation modulators and keratinisation normalisers. Common side effects such as blood lipid disorders, xerosis and photosensitivity are well established and usually dose dependent. Conversely, retinoid-associated ocular disturbances have been reported, yet with differences in terms of frequency and manifestations As data regarding a potential correlation with refractive errors are heterogenous and have not been previously thoroughly addressed, we performed a systematic review of the literature with the aim of comprehensively evaluating the current evidence regarding retinoid-associated myopia in dermatologic patients. MATERIALS AND METHODS: A systematic review of the literature was carried out according to the PRISMA guidelines. A search on MEDLINE, Pubmed, Scopus, Cochrane Library was conducted using the MeSH terms: retinoid, isotretinoin, acitretin, bexarotene, etretinate, alitretinoin, myopia, refractive errors, via the Boolean term AND. Only manuscripts in English were considered, there was no restriction on type of article. Animal research and in vitro studies were excluded. RESULTS: Six articles were finally included in this systematic review. One well designed prospective study was able to show a slight myopic shift in the first six months, but id did not evaluate further development of the refractive error nor the effects of drug discontinuation. Another prospective study, with a smaller sample size showed no myopic progression at 12 months. Two case reports showed a myopic shift after two weeks from therapy start. Another case report showed a myopic shift associated with narrowing of the anterior chamber after one week from therapy start. Finally a large retrospective study based on spontaneous reporting systems and world's literature classified myopia as a certain side effect. CONCLUSION: Considering the current literature, it is not possible to define a clear correlation between the use of retinoids and the development or worsening of myopia. Some studies suggest that retinoids may cause a myopic shift and the pathophysiologyical mechanism is supported by some animal and in vitro studies, but there is a lack of large prospective and well-controlled studies. In case of ocular disturbances after retinoid use a prompt ophthalmological referral is advisable and in case of the detection of a myopic refractive error a relationship to retinoids should be ruled out, considering also other possible causes such as age and previous refractive status.