1
|
Deep learning-based hemorrhage detection for diabetic retinopathy screening. Sci Rep 2023; 13:1479. [PMID: 36707608 PMCID: PMC9883230 DOI: 10.1038/s41598-023-28680-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Accepted: 01/23/2023] [Indexed: 01/29/2023] Open
Abstract
Diabetic retinopathy is a retinal compilation that causes visual impairment. Hemorrhage is one of the pathological symptoms of diabetic retinopathy that emerges during disease development. Therefore, hemorrhage detection reveals the presence of diabetic retinopathy in the early phase. Diagnosing the disease in its initial stage is crucial to adopt proper treatment so the repercussions can be prevented. The automatic deep learning-based hemorrhage detection method is proposed that can be used as the second interpreter for ophthalmologists to reduce the time and complexity of conventional screening methods. The quality of the images was enhanced, and the prospective hemorrhage locations were estimated in the preprocessing stage. Modified gamma correction adaptively illuminates fundus images by using gradient information to address the nonuniform brightness levels of images. The algorithm estimated the locations of potential candidates by using a Gaussian match filter, entropy thresholding, and mathematical morphology. The required objects were segmented using the regional diversity at estimated locations. The novel hemorrhage network is propounded for hemorrhage classification and compared with the renowned deep models. Two datasets benchmarked the model's performance using sensitivity, specificity, precision, and accuracy metrics. Despite being the shallowest network, the proposed network marked competitive results than LeNet-5, AlexNet, ResNet50, and VGG-16. The hemorrhage network was assessed using training time and classification accuracy through synthetic experimentation. Results showed promising accuracy in the classification stage while significantly reducing training time. The research concluded that increasing deep network layers does not guarantee good results but rather increases training time. The suitable architecture of a deep model and its appropriate parameters are critical for obtaining excellent outcomes.
Collapse
|
2
|
Huang Y, Tian B, Wei W. Timely Vitrectomy and Inner Limiting Membrane Peeling Is Effective and Safe for Terson Syndrome With Vitreous Hemorrhage and Sub-Inner Limiting Membrane Hemorrhage. Asia Pac J Ophthalmol (Phila) 2022; 11:392-393. [PMID: 36041152 DOI: 10.1097/apo.0000000000000534] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2021] [Accepted: 03/15/2022] [Indexed: 11/26/2022] Open
Affiliation(s)
- Yao Huang
- Beijing Tongren Eye Center, Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Laboratory, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Hospital, Capital Medical University, Beijing, China
| | | | | |
Collapse
|
3
|
Aboulhosn R, Raju B, Jumah F, Majmundar N, Prenner J, Matin T, Roychowdhury S, Singla A, Khandelwal P, Nanda A, Gupta G. Terson's syndrome, the current concepts and management strategies: A review of literature. Clin Neurol Neurosurg 2021; 210:107008. [PMID: 34775364 DOI: 10.1016/j.clineuro.2021.107008] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2021] [Revised: 10/03/2021] [Accepted: 10/21/2021] [Indexed: 10/20/2022]
Abstract
Terson's Syndrome describes intraocular hemorrhage secondary to an acutely raised intracranial pressure (ICP). Although Terson's Syndrome is common amongst patients with subarachnoid hemorrhage (SAH), it is underdiagnosed and often overlooked. This review discusses the current understanding of the etiopathogenesis, clinical features, and management of Terson's Syndrome and highlights the visual and prognostic implications to stress the importance of timely diagnosis and management. The origin of intraocular hemorrhage in Terson's Syndrome has been debated. A recognized theory suggests that an acutely raised ICP induces effusion of cerebrospinal fluid into the optic nerve sheath which dilates the retrobulbar aspect of the sheath in the orbit. Dilatation mechanically compresses the central retinal vein and retinochoroidal veins resulting in venous hypertension and rupture of thin retinal vessels. A commonly reported clinical feature is decreased visual acuity and blurred vision. These may be accompanied by symptoms of increased ICP including loss of consciousness and headache. Diagnosis is established using evidence from the clinical presentation, ophthalmoscopy, and, when required, imaging including B-mode ultrasound, CT, MRI, and fluorescein angiography. Terson's Syndrome is managed conservatively by observation for mild cases and with vitrectomy for bilateral cases and for patients whose hemorrhage has not spontaneously resolved after an observational period. Terson's Syndrome can be used as a prognostic indicator of morbidity and mortality in underlying pathology like SAH. Fundoscopy of patients with SAH, acutely raised ICP or visual disturbance with unknown etiology can help establish a timely Terson's Syndrome diagnosis. This may avoid the risk of permanent visual impairment.
Collapse
Affiliation(s)
- Rabii Aboulhosn
- School of Medicine, Medical Sciences and Nutrition, University of Aberdeen, Forester Hill, Aberdeen, UK
| | - Bharath Raju
- Department of Neurosurgery, Rutgers, Robert Wood Johnson Medical School & University, Hospital, New Brunswick, NJ, USA
| | - Fareed Jumah
- Department of Neurosurgery, Rutgers, Robert Wood Johnson Medical School & University, Hospital, New Brunswick, NJ, USA
| | - Neil Majmundar
- Department of Neurosurgery, Rutgers, Robert Wood Johnson Medical School & University, Hospital, New Brunswick, NJ, USA
| | - Jonathan Prenner
- Department of Ophthalmology, Rutgers, Robert Wood Johnson Medical School & University, Hospital, New Brunswick, NJ, USA
| | - Tariq Matin
- Department of Interventional Radiology, Narayana Superspecialty Hospital, Nathupur, Gurugram, Haryana 122002, India
| | - Sudipta Roychowdhury
- Department of Neurosurgery, Rutgers, Robert Wood Johnson Medical School & University, Hospital, New Brunswick, NJ, USA
| | - Amit Singla
- Department of Neurosurgery, Rutgers New Jersey Medical School, Newark, NJ, USA
| | - Priyank Khandelwal
- Department of Neurosurgery, Rutgers New Jersey Medical School, Newark, NJ, USA
| | - Anil Nanda
- Department of Neurosurgery, Rutgers, Robert Wood Johnson Medical School & University, Hospital, New Brunswick, NJ, USA
| | - Gaurav Gupta
- Department of Neurosurgery, Rutgers, Robert Wood Johnson Medical School & University, Hospital, New Brunswick, NJ, USA.
| |
Collapse
|
4
|
Ghoraba HH, Johnson MW, Leila M, Wasfy T, Ghoraba HH. Limited Vitrectomy versus Observation for Bilateral Terson Syndrome in a Child. Ophthalmol Retina 2020; 5:312-314. [PMID: 32920207 DOI: 10.1016/j.oret.2020.09.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/16/2020] [Revised: 08/31/2020] [Accepted: 09/04/2020] [Indexed: 11/19/2022]
Affiliation(s)
| | - Mark W Johnson
- Kellogg Eye Center, Department of Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan
| | - Mahmoud Leila
- Retina Department, Research Institute of Ophthalmology, Cairo, Egypt
| | - Tamer Wasfy
- Department of Ophthalmology, Faculty of Medicine, Tanta University, Tanta, Egypt
| | - Hammouda Hamdi Ghoraba
- Magrabi Eye Hospital, Tanta, Egypt; Department of Ophthalmology, Faculty of Medicine, Tanta University, Tanta, Egypt
| |
Collapse
|