1
|
Li Z, Huang G, Zou B, Chen W, Zhang T, Xu Z, Cai K, Wang T, Sun Y, Wang Y, Jin K, Huang X. Segmentation of Low-Light Optical Coherence Tomography Angiography Images under the Constraints of Vascular Network Topology. SENSORS (BASEL, SWITZERLAND) 2024; 24:774. [PMID: 38339491 PMCID: PMC10856982 DOI: 10.3390/s24030774] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/28/2023] [Revised: 12/27/2023] [Accepted: 01/03/2024] [Indexed: 02/12/2024]
Abstract
Optical coherence tomography angiography (OCTA) offers critical insights into the retinal vascular system, yet its full potential is hindered by challenges in precise image segmentation. Current methodologies struggle with imaging artifacts and clarity issues, particularly under low-light conditions and when using various high-speed CMOS sensors. These challenges are particularly pronounced when diagnosing and classifying diseases such as branch vein occlusion (BVO). To address these issues, we have developed a novel network based on topological structure generation, which transitions from superficial to deep retinal layers to enhance OCTA segmentation accuracy. Our approach not only demonstrates improved performance through qualitative visual comparisons and quantitative metric analyses but also effectively mitigates artifacts caused by low-light OCTA, resulting in reduced noise and enhanced clarity of the images. Furthermore, our system introduces a structured methodology for classifying BVO diseases, bridging a critical gap in this field. The primary aim of these advancements is to elevate the quality of OCTA images and bolster the reliability of their segmentation. Initial evaluations suggest that our method holds promise for establishing robust, fine-grained standards in OCTA vascular segmentation and analysis.
Collapse
Affiliation(s)
- Zhi Li
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; (Z.L.); (G.H.); (B.Z.); (W.C.); (T.Z.); (T.W.); (Y.S.)
| | - Gaopeng Huang
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; (Z.L.); (G.H.); (B.Z.); (W.C.); (T.Z.); (T.W.); (Y.S.)
| | - Binfeng Zou
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; (Z.L.); (G.H.); (B.Z.); (W.C.); (T.Z.); (T.W.); (Y.S.)
| | - Wenhao Chen
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; (Z.L.); (G.H.); (B.Z.); (W.C.); (T.Z.); (T.W.); (Y.S.)
| | - Tianyun Zhang
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; (Z.L.); (G.H.); (B.Z.); (W.C.); (T.Z.); (T.W.); (Y.S.)
| | - Zhaoyang Xu
- Department of Paediatrics, University of Cambridge, Cambridge CB2 1TN, UK;
| | - Kunyan Cai
- Faculty of Applied Sciences, Macao Polytechnic University, Macao SAR 999078, China;
| | - Tingyu Wang
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; (Z.L.); (G.H.); (B.Z.); (W.C.); (T.Z.); (T.W.); (Y.S.)
| | - Yaoqi Sun
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; (Z.L.); (G.H.); (B.Z.); (W.C.); (T.Z.); (T.W.); (Y.S.)
- Lishui Institute, Hangzhou Dianzi University, Lishui 323000, China
| | - Yaqi Wang
- College of Media Engineering, Communication University of Zhejiang, Hangzhou 310018, China;
| | - Kai Jin
- Eye Center, The Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou 310027, China;
| | - Xingru Huang
- School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China; (Z.L.); (G.H.); (B.Z.); (W.C.); (T.Z.); (T.W.); (Y.S.)
- School of Electronic Engineering and Computer Science, Queen Mary University of London, London E3 4BL, UK
| |
Collapse
|
2
|
Messinis L, Nasios G, Ioannidis P, Patrikelis P. Detection and Prevention of Mild Cognitive Impairment and Dementia. Healthcare (Basel) 2023; 11:2232. [PMID: 37628430 PMCID: PMC10454669 DOI: 10.3390/healthcare11162232] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2023] [Accepted: 08/07/2023] [Indexed: 08/27/2023] Open
Abstract
Mild cognitive impairment (MCI) is characterized by cognitive deficits alongside essentially preserved competence in activities of daily living [...].
Collapse
Affiliation(s)
- Lambros Messinis
- Laboratory of Cognitive Neuroscience, School of Psychology, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
| | - Grigorios Nasios
- Department of Speech and Language Therapy, School of Health Sciences, University of Ioannina, 45500 Ioannina, Greece;
| | - Panagiotis Ioannidis
- B’ Department of Neurology, AHEPA University Hospital, 1st Kyriakides Str., Aristotle University, 54124 Thessaloniki, Greece
| | - Panayiotis Patrikelis
- Laboratory of Cognitive Neuroscience, School of Psychology, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
| |
Collapse
|
3
|
DS6, Deformation-Aware Semi-Supervised Learning: Application to Small Vessel Segmentation with Noisy Training Data. J Imaging 2022; 8:jimaging8100259. [PMID: 36286353 PMCID: PMC9605070 DOI: 10.3390/jimaging8100259] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2022] [Revised: 09/11/2022] [Accepted: 09/16/2022] [Indexed: 11/24/2022] Open
Abstract
Blood vessels of the brain provide the human brain with the required nutrients and oxygen. As a vulnerable part of the cerebral blood supply, pathology of small vessels can cause serious problems such as Cerebral Small Vessel Diseases (CSVD). It has also been shown that CSVD is related to neurodegeneration, such as Alzheimer’s disease. With the advancement of 7 Tesla MRI systems, higher spatial image resolution can be achieved, enabling the depiction of very small vessels in the brain. Non-Deep Learning-based approaches for vessel segmentation, e.g., Frangi’s vessel enhancement with subsequent thresholding, are capable of segmenting medium to large vessels but often fail to segment small vessels. The sensitivity of these methods to small vessels can be increased by extensive parameter tuning or by manual corrections, albeit making them time-consuming, laborious, and not feasible for larger datasets. This paper proposes a deep learning architecture to automatically segment small vessels in 7 Tesla 3D Time-of-Flight (ToF) Magnetic Resonance Angiography (MRA) data. The algorithm was trained and evaluated on a small imperfect semi-automatically segmented dataset of only 11 subjects; using six for training, two for validation, and three for testing. The deep learning model based on U-Net Multi-Scale Supervision was trained using the training subset and was made equivariant to elastic deformations in a self-supervised manner using deformation-aware learning to improve the generalisation performance. The proposed technique was evaluated quantitatively and qualitatively against the test set and achieved a Dice score of 80.44 ± 0.83. Furthermore, the result of the proposed method was compared against a selected manually segmented region (62.07 resultant Dice) and has shown a considerable improvement (18.98%) with deformation-aware learning.
Collapse
|
4
|
López-Cuenca I, Salobrar-García E, Sánchez-Puebla L, Espejel E, García del Arco L, Rojas P, Elvira-Hurtado L, Fernández-Albarral JA, Ramírez-Toraño F, Barabash A, Salazar JJ, Ramírez JM, de Hoz R, Ramírez AI. Retinal Vascular Study Using OCTA in Subjects at High Genetic Risk of Developing Alzheimer’s Disease and Cardiovascular Risk Factors. J Clin Med 2022; 11:jcm11113248. [PMID: 35683633 PMCID: PMC9181641 DOI: 10.3390/jcm11113248] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2022] [Revised: 06/02/2022] [Accepted: 06/05/2022] [Indexed: 02/01/2023] Open
Abstract
In 103 subjects with a high genetic risk of developing Alzheimer’s disease (AD), family history (FH) of AD and ApoE ɛ4 characterization (ApoE ɛ4)) were analyzed for changes in the retinal vascular network by OCTA (optical coherence tomography angiography), and AngioTool and Erlangen-Angio-Tool (EA-Tool) as imaging analysis software. Retinal vascularization was analyzed by measuring hypercholesterolemia (HCL) and high blood pressure (HBP). Angio-Tool showed a statistically significant higher percentage of area occupied by vessels in the FH+ ApoE ɛ4- group vs. in the FH+ ApoE ɛ4+ group, and EA-Tool showed statistically significant higher vascular densities in the C3 ring in the FH+ ApoE ɛ4+ group when compared with: i)FH- ApoE ɛ4- in sectors H3, H4, H10 and H11; and ii) FH+ ApoE ɛ4- in sectors H4 and H12. In participants with HCL and HBP, statistically significant changes were found, in particular using EA-Tool, both in the macular area, mainly in the deep plexus, and in the peripapillary area. In conclusion, OCTA in subjects with genetic risk factors for the development of AD showed an apparent increase in vascular density in some sectors of the retina, which was one of the first vascular changes detectable. These changes constitute a promising biomarker for monitoring the progression of pathological neuronal degeneration.
Collapse
Affiliation(s)
- Inés López-Cuenca
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
| | - Elena Salobrar-García
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
- Department of Immunology, Ophthalmology and ENT, Faculty of Optics and Optometry, Complutense University of Madrid, 28037 Madrid, Spain
| | - Lidia Sánchez-Puebla
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
| | - Eva Espejel
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
| | - Lucía García del Arco
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
| | - Pilar Rojas
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
- Madrid Eye Institute, Gregorio Marañón General University Hospital, 28007 Madrid, Spain
| | - Lorena Elvira-Hurtado
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
| | - José A. Fernández-Albarral
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
| | - Federico Ramírez-Toraño
- Laboratory of Cognitive and Computational Neuroscience, Center for Biomedical Technology, Technical University of Madrid, 28233 Madrid, Spain;
- Department of Experimental Psychology, Complutense University of Madrid, 28223 Madrid, Spain
| | - Ana Barabash
- Department of Endocrinology and Nutrition, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), 28040 Madrid, Spain;
- Diabetes and Associated Metabolic Diseases Networking Biomedical Research Centre, Carlos III Health Institute, 28029 Madrid, Spain
- Department of Medicine II, School of Medicine, Complutense University of Madrid, 28040 Madrid, Spain
| | - Juan J. Salazar
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
- Department of Immunology, Ophthalmology and ENT, Faculty of Optics and Optometry, Complutense University of Madrid, 28037 Madrid, Spain
| | - José M. Ramírez
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
- Department of Immunology, Ophthalmology and ENT, School of Medicine, Complutense University of Madrid, 28040 Madrid, Spain
| | - Rosa de Hoz
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
- Department of Immunology, Ophthalmology and ENT, Faculty of Optics and Optometry, Complutense University of Madrid, 28037 Madrid, Spain
- Correspondence: (R.d.H.); (A.I.R.)
| | - Ana I. Ramírez
- Ramon Castroviejo Institute of Ophthalmologic Research, Group UCM 920105, Health Research Institute of the Hospital Clínico San Carlos (IdISSC), Complutense University of Madrid, 28040 Madrid, Spain; (I.L.-C.); (E.S.-G.); (L.S.-P.); (E.E.); (L.G.d.A.); (P.R.); (L.E.-H.); (J.A.F.-A.); (J.J.S.); (J.M.R.)
- Department of Immunology, Ophthalmology and ENT, Faculty of Optics and Optometry, Complutense University of Madrid, 28037 Madrid, Spain
- Correspondence: (R.d.H.); (A.I.R.)
| |
Collapse
|