Weronika Jakubowska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Weronika Jakubowska has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Allison L. Dorfman
Department of Ophthalmology, Centre Hospitalier Universitaire (CHU) Sainte-Justine et Centre de Recherche du CHU Sainte-Justine, Montreal, QC H3T 1C5, Canada
1 shared publication - Anna Polosa
Department of Ophthalmology, Centre Universitaire d’Ophtalmologie (CUO), Hôpital Maisonneuve-Rosemont, Université de Montréal, Montreal, QC H1T 3W5, Canada
1 shared publication Caroline Bélanger
Sainte-Justine Hospital, Montreal, Que.; University of Montreal, Montreal, Que
1 shared publicationClément Playout
Department of Ophthalmology, Université de Montréal, Montreal, Quebec, Canada
1 shared publication- Cynthia Md Xin-Ya Qian
Centre de Recherche de l’Hôpital Maisonneuve-Rosemont, Université de Montréal, Montreal, QC H1T 2M4, Canada
1 shared publication - Ellen E. Freeman
School of Epidemiology and Public Health, University of Ottawa, Ottawa, Canada
1 shared publication
Latest Publications
- 27 May 2026
- Published by Wolters Kluwer Health in Ophthalmic Plastic & Reconstructive Surgery
- Vol. 42 (6) , 683-687
Multimodal Deep Learning for Benign vs Malignant Eyelid Lesion Classification Using Optical Coherence Tomography and Clinical Images
Purpose: To evaluate the performance of deep learning models using optical coherence tomography (OCT) volumes, clinical photographs, and their multimodal fusion to classify eyelid lesions as benign or malignant, using histopathology as the reference standard. Methods: Prospective cohort study conducted between January 2023 and January 2025 at a single tertiary academic oculofacial plastic surgery center. A total of 65 patients with 71 periocular lesions undergoing routine biopsy were imaged with spectral-domain OCT and slit-lamp photography before biopsy. Images were processed into 3 Vision Transformer architectures: an OCT model, a photograph model, and a multimodal fusion model integrating both modalities. Classification performance for benign versus malignant lesions was evaluated with 5-fold cross-validation. Performance metrics included sensitivity, specificity, accuracy, kappa, and area under the receiver operating characteristic curve. Results: Of 71 lesions, 52% were benign and 48% malignant. The OCT model achieved 73.9% accuracy, 74.4% sensitivity, and an area under the receiver operating characteristic curve of 82.5%. The photograph model reached 82.3% accuracy, 89.6% sensitivity, and an area under the receiver operating characteristic curve of 91.7%. The multimodal fusion model performed best, with 83.2% accuracy, 91.8% sensitivity, 81.1% precision, kappa of 0.68, and an area under the receiver operating characteristic curve of 92.1%. Conclusions: This study demonstrates the feasibility of analyzing OCT volumes using deep learning, with diagnostic accuracy improved through multimodal integration with clinical photography. These results suggest that multimodal artificial intelligence may serve as a scalable, noninvasive, and physician-independent tool to distinguish benign from malignant periocular lesions and streamline patient triage. As models evolve to identify histopathologic features more reliably, they may also reduce dependence on incisional biopsy prior to definitive treatment.
- 27 May 2026
- Published by Wolters Kluwer Health in Ophthalmic Plastic & Reconstructive Surgery
- Vol. 42 (6) , 683-687
Multimodal Deep Learning for Benign vs Malignant Eyelid Lesion Classification Using Optical Coherence Tomography and Clinical Images
Purpose: To evaluate the performance of deep learning models using optical coherence tomography (OCT) volumes, clinical photographs, and their multimodal fusion to classify eyelid lesions as benign or malignant, using histopathology as the reference standard. Methods: Prospective cohort study conducted between January 2023 and January 2025 at a single tertiary academic oculofacial plastic surgery center. A total of 65 patients with 71 periocular lesions undergoing routine biopsy were imaged with spectral-domain OCT and slit-lamp photography before biopsy. Images were processed into 3 Vision Transformer architectures: an OCT model, a photograph model, and a multimodal fusion model integrating both modalities. Classification performance for benign versus malignant lesions was evaluated with 5-fold cross-validation. Performance metrics included sensitivity, specificity, accuracy, kappa, and area under the receiver operating characteristic curve. Results: Of 71 lesions, 52% were benign and 48% malignant. The OCT model achieved 73.9% accuracy, 74.4% sensitivity, and an area under the receiver operating characteristic curve of 82.5%. The photograph model reached 82.3% accuracy, 89.6% sensitivity, and an area under the receiver operating characteristic curve of 91.7%. The multimodal fusion model performed best, with 83.2% accuracy, 91.8% sensitivity, 81.1% precision, kappa of 0.68, and an area under the receiver operating characteristic curve of 92.1%. Conclusions: This study demonstrates the feasibility of analyzing OCT volumes using deep learning, with diagnostic accuracy improved through multimodal integration with clinical photography. These results suggest that multimodal artificial intelligence may serve as a scalable, noninvasive, and physician-independent tool to distinguish benign from malignant periocular lesions and streamline patient triage. As models evolve to identify histopathologic features more reliably, they may also reduce dependence on incisional biopsy prior to definitive treatment.
- Open Access
Long-Term Sequelae of Retinopathy of Prematurity—A Scoping Review
Purpose: This study aimed to comprehensively map the structural impacts of ROP on all ocular structures, including and extending beyond the inner retina and the associated long-term sequelae that manifest into adulthood. Methods: This scoping review identified studies on animal oxygen-induced retinopathy and clinical retinopathy of prematurity using a multi-database search. Study selection and data extraction were performed independently by multiple reviewers using Covidence software. Results: ROP results in lasting ocular complications. Posterior segment findings include choroidal insufficiency, photoreceptor dysfunction, and retinal detachment. Anterior segment complications involve a higher incidence of angle-closure glaucoma, strabismus, and significant myopia. Conclusions: This scoping review was conducted and reported in accordance with the PRISMA-ScR guidelines, though it is limited by the exclusion of non-English studies. Lifelong ophthalmic monitoring is essential for ROP patients due to persistent anterior and posterior segment complications. This study also identifies key future research priorities, including elucidating mechanisms of foveal development and conducting longitudinal studies. Furthermore, as neonatal intensive care expands in low and middle-income regions, international collaboration is vital to guide screening and treatment and prevent a debilitating surge of ROP.
Open AccessLong-Term Sequelae of Retinopathy of Prematurity—A Scoping Review
Purpose: This study aimed to comprehensively map the structural impacts of ROP on all ocular structures, including and extending beyond the inner retina and the associated long-term sequelae that manifest into adulthood. Methods: This scoping review identified studies on animal oxygen-induced retinopathy and clinical retinopathy of prematurity using a multi-database search. Study selection and data extraction were performed independently by multiple reviewers using Covidence software. Results: ROP results in lasting ocular complications. Posterior segment findings include choroidal insufficiency, photoreceptor dysfunction, and retinal detachment. Anterior segment complications involve a higher incidence of angle-closure glaucoma, strabismus, and significant myopia. Conclusions: This scoping review was conducted and reported in accordance with the PRISMA-ScR guidelines, though it is limited by the exclusion of non-English studies. Lifelong ophthalmic monitoring is essential for ROP patients due to persistent anterior and posterior segment complications. This study also identifies key future research priorities, including elucidating mechanisms of foveal development and conducting longitudinal studies. Furthermore, as neonatal intensive care expands in low and middle-income regions, international collaboration is vital to guide screening and treatment and prevent a debilitating surge of ROP.
- Open Access
Impact of the COVID-19 Pandemic on Mental Health among Patients with Chronic Ocular Conditions
The COVID-19 pandemic had significant impacts on the mental and visual health of patients. This cross-sectional, survey-based, multicentric study evaluates the state of mental and visual health among patients with chronic ocular diseases such as glaucoma, neovascular age-related macular degeneration, diabetic retinopathy, or chronic uveitis during the lockdown period of the COVID-19 pandemic. Mental health was assessed using three questionnaires: the Patient Health Questionnaire-9 (PHQ-9), the Impact of Event Scale-Revised (IES-R), and the National Eye Institute Visual Function Questionnaire-25 (VFQ-25). A total of 145 patients completed the questionnaires. The PHQ-9 showed that most respondents (n = 89, 61%) had none or minimal depressive symptoms, while 31 (21%) had mild depressive symptoms, 19 (13%) had moderate depressive symptoms, 5 (3%) had moderately severe depressive symptoms, and 1 (1%) had severe depressive symptoms. Regarding stress surrounding the pandemic, the median IES-R showed mild distress in 16 (11%), moderate distress in 7 (5%), and severe distress in 4 (3%). The COVID-19 pandemic lockdowns had a negative impact on patients’ mental health with close to 20% of the patients reporting at least moderately depressive symptoms and 19% reporting at least mildly distressful symptoms.
Open AccessImpact of the COVID-19 Pandemic on Mental Health among Patients with Chronic Ocular Conditions
The COVID-19 pandemic had significant impacts on the mental and visual health of patients. This cross-sectional, survey-based, multicentric study evaluates the state of mental and visual health among patients with chronic ocular diseases such as glaucoma, neovascular age-related macular degeneration, diabetic retinopathy, or chronic uveitis during the lockdown period of the COVID-19 pandemic. Mental health was assessed using three questionnaires: the Patient Health Questionnaire-9 (PHQ-9), the Impact of Event Scale-Revised (IES-R), and the National Eye Institute Visual Function Questionnaire-25 (VFQ-25). A total of 145 patients completed the questionnaires. The PHQ-9 showed that most respondents (n = 89, 61%) had none or minimal depressive symptoms, while 31 (21%) had mild depressive symptoms, 19 (13%) had moderate depressive symptoms, 5 (3%) had moderately severe depressive symptoms, and 1 (1%) had severe depressive symptoms. Regarding stress surrounding the pandemic, the median IES-R showed mild distress in 16 (11%), moderate distress in 7 (5%), and severe distress in 4 (3%). The COVID-19 pandemic lockdowns had a negative impact on patients’ mental health with close to 20% of the patients reporting at least moderately depressive symptoms and 19% reporting at least mildly distressful symptoms.
- 22 February 2023
- Published by Taylor & Francis in Orbit
- Vol. 43 (4) , 480-485
Seminoma-associated orbitopathy mimicking thyroid-associated orbitopathy: report of a case and literature review
The authors describe a case of bilateral diffuse paraneoplastic orbital myositis induced by a stage IA left testicular pure seminoma. The patient presented with findings typical of thyroid-associated orbitopathy (TAO) and was thought to have TAO until discovery of the malignancy. Treatment included an urgent orchiectomy, as well as 7 weeks of therapeutic plasma exchange. This is the fifth reported case of seminoma-associated orbitopathy, and the second to occur while cancer was in the occult phase. Although seminoma-associated orbitopathy is exceedingly rare, it can masquerade as TAO and should be considered in the differential diagnosis of any young male with atypical TAO findings.
- 22 February 2023
- Published by Taylor & Francis in Orbit
- Vol. 43 (4) , 480-485
Seminoma-associated orbitopathy mimicking thyroid-associated orbitopathy: report of a case and literature review
The authors describe a case of bilateral diffuse paraneoplastic orbital myositis induced by a stage IA left testicular pure seminoma. The patient presented with findings typical of thyroid-associated orbitopathy (TAO) and was thought to have TAO until discovery of the malignancy. Treatment included an urgent orchiectomy, as well as 7 weeks of therapeutic plasma exchange. This is the fifth reported case of seminoma-associated orbitopathy, and the second to occur while cancer was in the occult phase. Although seminoma-associated orbitopathy is exceedingly rare, it can masquerade as TAO and should be considered in the differential diagnosis of any young male with atypical TAO findings.
- 1 February 2022
- Published by Elsevier in Canadian Journal of Ophthalmology
- Vol. 57 (1) , e22-e24
Childhood Burkitt lymphoma manifesting as cavernous sinus syndrome
- 1 February 2022
- Published by Elsevier in Canadian Journal of Ophthalmology
- Vol. 57 (1) , e22-e24
Childhood Burkitt lymphoma manifesting as cavernous sinus syndrome