1
|
El Habib Daho M, Li Y, Zeghlache R, Boité HL, Deman P, Borderie L, Ren H, Mannivanan N, Lepicard C, Cochener B, Couturier A, Tadayoni R, Conze PH, Lamard M, Quellec G. DISCOVER: 2-D multiview summarization of Optical Coherence Tomography Angiography for automatic diabetic retinopathy diagnosis. Artif Intell Med 2024; 149:102803. [PMID: 38462293 DOI: 10.1016/j.artmed.2024.102803] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 12/19/2023] [Accepted: 02/03/2024] [Indexed: 03/12/2024]
Abstract
Diabetic Retinopathy (DR), an ocular complication of diabetes, is a leading cause of blindness worldwide. Traditionally, DR is monitored using Color Fundus Photography (CFP), a widespread 2-D imaging modality. However, DR classifications based on CFP have poor predictive power, resulting in suboptimal DR management. Optical Coherence Tomography Angiography (OCTA) is a recent 3-D imaging modality offering enhanced structural and functional information (blood flow) with a wider field of view. This paper investigates automatic DR severity assessment using 3-D OCTA. A straightforward solution to this task is a 3-D neural network classifier. However, 3-D architectures have numerous parameters and typically require many training samples. A lighter solution consists in using 2-D neural network classifiers processing 2-D en-face (or frontal) projections and/or 2-D cross-sectional slices. Such an approach mimics the way ophthalmologists analyze OCTA acquisitions: (1) en-face flow maps are often used to detect avascular zones and neovascularization, and (2) cross-sectional slices are commonly analyzed to detect macular edemas, for instance. However, arbitrary data reduction or selection might result in information loss. Two complementary strategies are thus proposed to optimally summarize OCTA volumes with 2-D images: (1) a parametric en-face projection optimized through deep learning and (2) a cross-sectional slice selection process controlled through gradient-based attribution. The full summarization and DR classification pipeline is trained from end to end. The automatic 2-D summary can be displayed in a viewer or printed in a report to support the decision. We show that the proposed 2-D summarization and classification pipeline outperforms direct 3-D classification with the advantage of improved interpretability.
Collapse
Affiliation(s)
- Mostafa El Habib Daho
- Univ Bretagne Occidentale, Brest, F-29200, France; Inserm, UMR 1101, Brest, F-29200, France
| | - Yihao Li
- Univ Bretagne Occidentale, Brest, F-29200, France; Inserm, UMR 1101, Brest, F-29200, France
| | - Rachid Zeghlache
- Univ Bretagne Occidentale, Brest, F-29200, France; Inserm, UMR 1101, Brest, F-29200, France
| | - Hugo Le Boité
- Sorbonne University, Paris, F-75006, France; Service d'Ophtalmologie, Hôpital Lariboisière, APHP, Paris, F-75475, France
| | - Pierre Deman
- ADCIS, Saint-Contest, F-14280, France; Evolucare Technologies, Le Pecq, F-78230, France
| | | | - Hugang Ren
- Carl Zeiss Meditec, Dublin, CA 94568, USA
| | | | - Capucine Lepicard
- Service d'Ophtalmologie, Hôpital Lariboisière, APHP, Paris, F-75475, France
| | - Béatrice Cochener
- Univ Bretagne Occidentale, Brest, F-29200, France; Inserm, UMR 1101, Brest, F-29200, France; Service d'Ophtalmologie, CHRU Brest, Brest, F-29200, France
| | - Aude Couturier
- Service d'Ophtalmologie, Hôpital Lariboisière, APHP, Paris, F-75475, France
| | - Ramin Tadayoni
- Service d'Ophtalmologie, Hôpital Lariboisière, APHP, Paris, F-75475, France; Paris Cité University, Paris, F-75006, France
| | - Pierre-Henri Conze
- Inserm, UMR 1101, Brest, F-29200, France; IMT Atlantique, Brest, F-29200, France
| | - Mathieu Lamard
- Univ Bretagne Occidentale, Brest, F-29200, France; Inserm, UMR 1101, Brest, F-29200, France
| | | |
Collapse
|
2
|
Zhang Y, Liu M, Yu F, Zeng T, Wang Y. An O-shape Neural Network With Attention Modules to Detect Junctions in Biomedical Images Without Segmentation. IEEE J Biomed Health Inform 2021; 26:774-785. [PMID: 34197332 DOI: 10.1109/jbhi.2021.3094187] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/05/2022]
Abstract
Junction plays an important role in biomedical research such as retinal biometric identification, retinal image registration, eye-related disease diagnosis and neuron reconstruction. However, junction detection in original biomedical images is extremely challenging. For example, retinal images contain many tiny blood vessels with complicated structures and low contrast, which makes it challenging to detect junctions. In this paper, we propose an O-shape Network architecture with Attention modules (Attention O-Net), which includes Junction Detection Branch (JDB) and Local Enhancement Branch (LEB) to detect junctions in biomedical images without segmentation. In JDB, the heatmap indicating the probabilities of junctions is estimated and followed by choosing the positions with the local highest value as the junctions, whereas it is challenging to detect junctions when the images contain weak filament signals. Therefore, LEB is constructed to enhance the thin branch foreground and make the network pay more attention to the regions with low contrast, which is helpful to alleviate the imbalance of the foreground between thin and thick branches and to detect the junctions of the thin branch. Furthermore, attention modules are utilized to introduce the feature maps from LEB to JDB, which can establish a complementary relationship and further integrate local features and contextual information between the two branches. The proposed method achieves the highest average F1-scores of 0.82, 0.73 and 0.94 in two retinal datasets and one neuron dataset, respectively. The experimental results confirm that Attention O-Net outperforms other state-of-the-art detection methods, and is helpful for retinal biometric identification.
Collapse
|