Predicting Post-Therapeutic Visual Acuity and OCT Images in Patients With Central Serous Chorioretinopathy by Artificial Intelligence

To predict visual acuity (VA) and post-therapeutic optical coherence tomography (OCT) images 1, 3, and 6 months after laser treatment in patients with central serous chorioretinopathy (CSC) by artificial intelligence (AI). Real-world clinical and imaging data were collected at Zhongshan Ophthalmic Center (ZOC) and Xiamen Eye Center (XEC). The data obtained from ZOC (416 eyes of 401 patients) were used as the training set; the data obtained from XEC (64 eyes of 60 patients) were used as the test set. Six different machine learning algorithms and a blending algorithm were used to predict VA, and a pix2pixHD method was adopted to predict post-therapeutic OCT images in patients after laser treatment. The data for VA predictions included clinical features obtained from electronic medical records (20 features) and measured features obtained from fundus fluorescein angiography, indocyanine green angiography, and OCT (145 features). The data for OCT predictions included 480 pairs of pre- and post-therapeutic OCT images. The VA and OCT images predicted by AI were compared with the ground truth. In the VA predictions of XEC dataset, the mean absolute errors (MAEs) were 0.074–0.098 logMAR (within four to five letters), and the root mean square errors were 0.096–0.127 logMAR (within five to seven letters) for the 1-, 3-, and 6-month predictions, respectively; in the post-therapeutic OCT predictions, only about 5.15% (5 of 97) of synthetic OCT images could be accurately identified as synthetic images. The MAEs of central macular thickness of synthetic OCT images were 30.15 ± 13.28 μm and 22.46 ± 9.71 μm for the 1- and 3-month predictions, respectively. This is the first study to apply AI to predict VA and post-therapeutic OCT of patients with CSC. This work establishes a reliable method of predicting prognosis 6 months in advance; the application of AI has the potential to help reduce patient anxiety and serve as a reference for ophthalmologists when choosing optimal laser treatments.

Download Full-text

Proactive Construction of an Annotated Imaging Database for Artificial Intelligence Training

Journal of Digital Imaging ◽

10.1007/s10278-020-00384-4 ◽

2020 ◽

Author(s):

Caroline Bivik Stadler ◽

Martin Lindvall ◽

Claes Lundström ◽

Anna Bodén ◽

Karin Lindman ◽

...

Keyword(s):

Artificial Intelligence ◽

Image Data ◽

Ground Truth ◽

Lessons Learned ◽

Training Data ◽

Imaging Data ◽

High Quality ◽

High Quality Image ◽

Specific Objective ◽

Wide Range

Abstract Artificial intelligence (AI) holds much promise for enabling highly desired imaging diagnostics improvements. One of the most limiting bottlenecks for the development of useful clinical-grade AI models is the lack of training data. One aspect is the large amount of cases needed and another is the necessity of high-quality ground truth annotation. The aim of the project was to establish and describe the construction of a database with substantial amounts of detail-annotated oncology imaging data from pathology and radiology. A specific objective was to be proactive, that is, to support undefined subsequent AI training across a wide range of tasks, such as detection, quantification, segmentation, and classification, which puts particular focus on the quality and generality of the annotations. The main outcome of this project was the database as such, with a collection of labeled image data from breast, ovary, skin, colon, skeleton, and liver. In addition, this effort also served as an exploration of best practices for further scalability of high-quality image collections, and a main contribution of the study was generic lessons learned regarding how to successfully organize efforts to construct medical imaging databases for AI training, summarized as eight guiding principles covering team, process, and execution aspects.

Download Full-text

The Role of Artificial Intelligence in Endoscopic Ultrasound for Pancreatic Disorders

Diagnostics ◽

10.3390/diagnostics11010018 ◽

2020 ◽

Vol 11 (1) ◽

pp. 18

Author(s):

Ryosuke Tonozuka ◽

Shuntaro Mukai ◽

Takao Itoi

Keyword(s):

Artificial Intelligence ◽

Endoscopic Ultrasound ◽

Machine Learning Algorithms ◽

Optical Biopsy ◽

Tissue Sampling ◽

Imaging Data ◽

Pancreatic Disorders ◽

Aided Diagnosis ◽

Conventional Computer

The use of artificial intelligence (AI) in various medical imaging applications has expanded remarkably, and several reports have focused on endoscopic ultrasound (EUS) images of the pancreas. This review briefly summarizes each report in order to help endoscopists better understand and utilize the potential of this rapidly developing AI, after a description of the fundamentals of the AI involved, as is necessary for understanding each study. At first, conventional computer-aided diagnosis (CAD) was used, which extracts and selects features from imaging data using various methods and introduces them into machine learning algorithms as inputs. Deep learning-based CAD utilizing convolutional neural networks has been used; in these approaches, the images themselves are used as inputs, and more information can be analyzed in less time and with higher accuracy. In the field of EUS imaging, although AI is still in its infancy, further research and development of AI applications is expected to contribute to the role of optical biopsy as an alternative to EUS-guided tissue sampling while also improving diagnostic accuracy through double reading with humans and contributing to EUS education.

Download Full-text

The Personalized Approach to the Chronic Central Serous Chorioretinopathy Treatment Based on the Navigated Micropulse Laser Technology

Ophthalmology in Russia ◽

10.18008/1816-5095-2018-4-394-404 ◽

2019 ◽

Vol 15 (4) ◽

pp. 394-404

Author(s):

P. L. Volodin ◽

A. V. Doga ◽

E. V. Ivanova ◽

V. A. Pismenskaya ◽

Iu. I. Kukharskaya ◽

...

Keyword(s):

Visual Acuity ◽

Laser Treatment ◽

Central Serous Chorioretinopathy ◽

Retinal Thickness ◽

Retinal Sensitivity ◽

Individual Selection ◽

Chronic Central Serous Chorioretinopathy ◽

Energy Parameters ◽

Micropulse Laser ◽

Selection Of

The Purpose— to develop the technology and to evaluate the clinical results of personalized laser treatment of patients with chronic central serous chorioretinopathy (CSC) in a micropulse mode with individual selection of energy parameters on the navigation system Navilas 577s.Patients and Methods. 19 patients (22 eyes) with CSC after micropulse laser treatment were analyzed. The initial best corrected visual acuity (BCVA) was 0.4 to 1.0. According to OCT, the height of the detachment of the neurosensory retina varied from 83 to 259 microns. Retinal sensitivity of the central zone was from 20.2 to 29.7 dB. Before laser treatment were individually selected the optimal energy parameters for each patient. The treatment was performed on a Navilas 577s laser system. The follow-up were 1 and 3 months.Results. 1 month after treatment the positive dynamics of functional and anatomical results in all patients was observed. Mean BCVA increased in the group to 0.81 ± 0.04. The central retinal sensitivity raised on average in the group up to 25.7 ± 0.6 dB. After 3 months, mean BCVA was 0.96 ± 0.02. Mean central retinal sensitivity increased to 26.4 ± 0.57 dB. The study revealed a high correlation between visual acuity and the central retinal thickness (0.72) and medium correlation between foveal retinal sensitivity and central retinal thickness in fovea (0.60), respectively. The correlation among visual acuity, retinal sensitivity and the symptom’s duration of the disease is negative medium (-0.63) and significant (-0.72), respectively.Conclusions. The developed personalized technology of laser treatment of chronic central serous chorioretinopathy with a micropulse mode with an individual selection of energy parameters on the Navilas 577s navigation system showed high clinical efficiency and safety. It has been established that in the course of the longstanding duration of the disease irreversible changes in the chorioretinal complex structure occured, thinning of the foveal photoreceptors layer leading to a decrease in the central retinal sensitivity and visual acuity, which substantiate the necessity for early and maximally functional-saving treatment.

Download Full-text

Intravitreal Ziv-Aflibercept in Treatment of Naïve Chronic Central Serous Chorioretinopathy Related Choroidal Neovascular Membrane

Case Reports in Ophthalmological Medicine ◽

10.1155/2017/5036248 ◽

2017 ◽

Vol 2017 ◽

pp. 1-5

Author(s):

Nishant Radke ◽

Charudutt Kalamkar ◽

Amrita Mukherjee ◽

Snehal Radke

Keyword(s):

Optical Coherence Tomography ◽

Visual Acuity ◽

Case Report ◽

Fluorescein Angiography ◽

Male Patient ◽

Visual Function ◽

Central Serous Chorioretinopathy ◽

Choroidal Neovascular Membrane ◽

Fundus Fluorescein Angiography ◽

Chronic Central Serous Chorioretinopathy

Purpose. To study the effect and outcome of intravitreal Ziv-Aflibercept (IVZ) in treatment of Chronic Central Serous Chorioretinopathy (CSCR) related Choroidal Neovascular Membrane (CNVM). Methods. A case report of 48-year-old male patient treated with 1.25 mg/0.05 ml IVZ (total 3 doses at monthly intervals) in CSCR related CNVM. Pre- and posttreatment fundus fluorescein angiography (FFA) and Optical Coherence Tomography (OCT) were done to document response along with improvement in visual acuity. Patients. Single eye of a 48-year-old male patient. Results. Regression of CNVM was noted with improvement of macular contour and thickness on OCT and cessation of leakage on FFA. Visual acuity improved from 3/60, <N36 to 6/12, N12. Discussion. Anti-VEGF injections have shown benefit in treatment of CNVM. There is very little information about benefit of IVZ in CSCR related CNVM. Conclusion. IVZ is effective in regression of CSCR related CNVM and is associated with better macular anatomy and improved visual function.

Download Full-text

Transfoveal Micropulse Laser Treatment of Central Serous Chorioretinopathy within Six Months of Disease Onset

Journal of Clinical Medicine ◽

10.3390/jcm8091398 ◽

2019 ◽

Vol 8 (9) ◽

pp. 1398 ◽

Cited By ~ 2

Author(s):

Maciej Gawęcki ◽

Agnieszka Jaszczuk-Maciejewska ◽

Anna Jurska-Jaśko ◽

Małgorzata Kneba ◽

Andrzej Grzybowski

Keyword(s):

Visual Acuity ◽

Laser Treatment ◽

Central Serous Chorioretinopathy ◽

Disease Onset ◽

Rank Correlation ◽

Subretinal Fluid ◽

Spearman Rank Correlation ◽

Invasive Treatment ◽

Spearman Rank ◽

Micropulse Laser

Background: It has been recommended that any invasive treatment performed in patients with central serous chorioretinopathy (CSCR) not be initiated earlier than four months after disease onset due to the potential for spontaneous remission of symptoms. The goal of this study was to examine the outcome of transfoveal subthreshold micropulse laser treatment (SMPLT) of CSCR performed at six months or less after disease onset. Materials and methods: The study included 32 cases of CSCR lasting between three weeks and six months (mean: 3.4 ± 2.3 months). All patients had transfoveal SMPLT applied and were followed for at least three months after each session of SMPLT. Two sessions of SMPLT in total were planned in case of an insufficient response to the first instance of treatment. Evaluation parameters included any change in best-corrected visual acuity (BCVA) and retinal morphology. Results: Total resolution of subretinal fluid (SRF) was noted in 26 cases (81.25%). Final BCVA improved significantly from 0.37 ± 0.22 logMAR to 0.22 ± 0.20 logMAR after treatment. Overall, early SMPLT correlated with better final BCVA (p = 0.0005, Spearman rank correlation). For eyes achieving a total resolution of SRF, BCVA improved from 0.33 ± 0.21 logMAR to 0.17 ± 0.14 logMAR (p = 0.004, Spearman rank correlation). The analysis of SMPLT nonresponders revealed a tendency for poorer baseline visual acuity. Conclusions: Patients with CSCR lasting six months or less treated with transfoveal SMPLT achieve better functional results with early application of this procedure. As baseline BCVA predicts final visual acuity, earlier treatment, permitted by the safety of SMPLT, may improve final visual outcomes.

Download Full-text

Diabetic retinopathy classification for supervised machine learning algorithms

International Journal of Retina and Vitreous ◽

10.1186/s40942-021-00352-2 ◽

2022 ◽

Vol 8 (1) ◽

Author(s):

Luis Filipe Nakayama ◽

Lucas Zago Ribeiro ◽

Mariana Batista Gonçalves ◽

Daniel A. Ferraz ◽

Helen Nazareth Veloso dos Santos ◽

...

Keyword(s):

Artificial Intelligence ◽

Diabetic Retinopathy ◽

Fundamental Problem ◽

Ground Truth ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Main Body ◽

Workflow Optimization ◽

Artificial Intelligence Technology ◽

Automated Technology

Abstract Background Artificial intelligence and automated technology were first reported more than 70 years ago and nowadays provide unprecedented diagnostic accuracy, screening capacity, risk stratification, and workflow optimization. Diabetic retinopathy is an important cause of preventable blindness worldwide, and artificial intelligence technology provides precocious diagnosis, monitoring, and guide treatment. High-quality exams are fundamental in supervised artificial intelligence algorithms, but the lack of ground truth standards in retinal exams datasets is a problem. Main body In this article, ETDRS, NHS, ICDR, SDGS diabetic retinopathy grading, and manual annotation are described and compared in publicly available datasets. The various DR labeling systems generate a fundamental problem for AI datasets. Possible solutions are standardization of DR classification and direct retinal-finding identifications. Conclusion Reliable labeling methods also need to be considered in datasets with more trustworthy labeling.

Download Full-text

Longtime Vision Function Prediction in Childhood Cataract Patients Based on Optical Coherence Tomography Images

Frontiers in Bioengineering and Biotechnology ◽

10.3389/fbioe.2021.646479 ◽

2021 ◽

Vol 9 ◽

Author(s):

Yifan Xiang ◽

Jingjing Chen ◽

Fabao Xu ◽

Zhuoling Lin ◽

Jun Xiao ◽

...

Keyword(s):

Optical Coherence Tomography ◽

Intelligent System ◽

Ground Truth ◽

Visual Development ◽

Machine Learning Algorithms ◽

Optical Coherence ◽

Visual Prognosis ◽

Intervention Plan ◽

Long Term Prediction ◽

Mean Square Errors

The results of visual prediction reflect the tendency and speed of visual development during a future period, based on which ophthalmologists and guardians can know the potential visual prognosis in advance, decide on an intervention plan, and contribute to visual development. In our study, we developed an intelligent system based on the features of optical coherence tomography images for long-term prediction of best corrected visual acuity (BCVA) 3 and 5 years in advance. Two hundred eyes of 132 patients were included. Six machine learning algorithms were applied. In the BCVA predictions, small errors within two lines of the visual chart were achieved. The mean absolute errors (MAEs) between the prediction results and ground truth were 0.1482–0.2117 logMAR for 3-year predictions and 0.1198–0.1845 logMAR for 5-year predictions; the root mean square errors (RMSEs) were 0.1916–0.2942 logMAR for 3-year predictions and 0.1692–0.2537 logMAR for 5-year predictions. This is the first study to predict post-therapeutic BCVAs in young children. This work establishes a reliable method to predict prognosis 5 years in advance. The application of our research contributes to the design of visual intervention plans and visual prognosis.

Download Full-text

Efficacy of oral rifampicin in chronic central serous chorioretinopathy

Therapeutic Advances in Ophthalmology ◽

10.1177/2515841418807130 ◽

2018 ◽

Vol 10 ◽

pp. 251584141880713 ◽

Cited By ~ 2

Author(s):

Ramesh Venkatesh ◽

Manisha Agarwal ◽

Meha Kantha

Keyword(s):

Visual Acuity ◽

Fluorescein Angiography ◽

Central Serous Chorioretinopathy ◽

Pigment Epithelium ◽

Retinal Pigment ◽

Subretinal Fluid ◽

Fundus Fluorescein Angiography ◽

Chronic Central Serous Chorioretinopathy ◽

Duration Of Symptoms ◽

Diffuse Retinal Pigment Epitheliopathy

Objective: To evaluate the role of oral rifampicin in the management of chronic central serous chorioretinopathy. Methods: Retrospective analysis of patients diagnosed with chronic central serous chorioretinopathy (duration >3 months) and treated with oral rifampicin 600 mg daily for a maximum period of 3 months was carried out. Baseline visual acuity, fundus fluorescein angiography, and optical coherence tomography were recorded and the patients were followed up. Resolution of subretinal fluid and improvement in visual acuity were the main outcome measures. Recurrence of subretinal fluid was noted. Any adverse reaction to the drug was monitored. Results: Nine eyes of eight patients were included in the study. The average age of the patients was 41.90 years (range 32–52 years). Mean duration of symptoms was 16 months (range 3–60 months). Mean duration of follow-up was 10.11 months (range 3–33 months). Fluorescein angiography showed four eyes with subfoveal leaks and five eyes with diffuse retinal pigment epitheliopathy. Complete resolution of subretinal fluid was achieved in four of the nine eyes – two patients at the end of 1 month, one patient each at the end of 2 and 3 months, respectively. Visual acuity improvement was noted in four of the nine eyes. Three patients had one-line improvement and one patient had a two-line visual improvement. None of the patients had severe adverse events for which the drug had to be discontinued. None of the patients had recurrence of subretinal fluid after the discontinuation of the drug. Conclusion: Oral rifampicin could provide a useful, effective, and cost-effective alternative for treatment of patients with chronic central serous choroidopathy and evidence of healthier retinal pigment epithelium, those with focal leakage. It was not effective in eyes with diffuse retinal pigment epitheliopathy.

Download Full-text

Bullous central serous chorioretinopathy and retinal pigment epithelium sequelae postblunt trauma

BMJ Case Reports ◽

10.1136/bcr-2020-235882 ◽

2020 ◽

Vol 13 (9) ◽

pp. e235882

Author(s):

Nithin Teja Gunna ◽

Deepika C Parameswarappa ◽

Padmaja Kumari Rani

Keyword(s):

Visual Acuity ◽

Retinal Pigment Epithelium ◽

Central Serous Chorioretinopathy ◽

Pigment Epithelium ◽

Retinal Pigment ◽

Specific Treatment ◽

Subretinal Fluid ◽

Fundus Fluorescein Angiography ◽

Near Vision ◽

The Right

A 68-year-old man presented with diminution of distance and near vision in the right eye for a duration of 1 month postblunt trauma with a stick. On examination, his visual acuity in the right eye was 20/320 and near vision was <N36. Right eye fundus showed bullous neurosensory retinal detachment at posterior pole and retinal pigment epithelium (RPE) atrophic area temporal to fovea. Optical coherence tomography showed subretinal fluid with pigment epithelial detachment and an area of RPE and photoreceptor loss temporal to fovea. Fundus fluorescein angiography and indocyanine green angiography showed focal leaks and transmitted hyperfluorescence corresponding to the area of RPE loss. Left eye examination was unremarkable except for senile cataract of nuclear opalescence grade 3. A diagnosis of right eye bullous central serous chorioretinopathy (CSCR) and RPE sequelae postblunt trauma was made. Our patient was managed conservatively with no specific treatment for CSCR. One month later, there was improvement in vision with decrease in neurosensory detachment. The area of RPE loss remained the same with photoreceptor loss. Since this area of RPE and photoreceptor loss were temporal to fovea, our patient’s visual acuity was not affected significantly.

Download Full-text

Laser treatment of chronic central serous chorioretinopathy with a point of leakage in the subfoveolar zone without fluorescein angiography

Kazan medical journal ◽

10.17816/kmj2019-601 ◽

2019 ◽

Vol 100 (4) ◽

pp. 601-605

Author(s):

A N Samoylov ◽

A N Korobitsin

Keyword(s):

Optical Coherence Tomography ◽

Visual Acuity ◽

Laser Treatment ◽

Central Serous Chorioretinopathy ◽

Central Zone ◽

Laser Exposure ◽

Optical Coherence ◽

Chronic Central Serous Chorioretinopathy ◽

Corrected Visual Acuity ◽

Best Corrected Visual Acuity

Aim. Develop a methodology and evaluate the clinical results of laser treatment of patients with chronic central serous chorioretinopathy in the presence of a leakage point in the foveola zone. Methods. The results of patients (32 eyes) with central serous chorioretinopathy after laser exposure in the avascular area were analyzed. The best-corrected visual acuity in these patients before treatment was 0.7 to 1.0 (average 0.78±0.15) with a height of neuroepithelial detachment of 162 to 328 μm according to optical coherence tomography. No signs of choroidal neovascularization was detected in angio mode on optical coherence tomography. The treatment was performed with an Ellex Integre Pro Scan 561 nm. The follow-up examination was performed in 1 and 6 months. Results. In 1 month, positive dynamics of both functional and anatomical parameters was noted in all eyes. According to the optical coherence tomography, a complete attachment of the neuroepithelium in the central zone of the retina occurred, detachment of the neuroepithelium was absent. Best-corrected visual acuity in 1 month after treatment increased to 0.89±0.08, in 6 months to 0.92±0.04. The study revealed a correlation between visual acuity and the central thickness of the retina in the fovea, there were no complaints about the appearance of scotomas after laser treatment in the foveola zone. Conclusion. The developed techniqe of laser exposure on the foveola zone in case of chronic central serous chorioretinopathy with a 561 nm laser demonstrated high clinical efficacy and safety and can be recommended to all patients with central serous chorioretinopathy.

Download Full-text