OCTAve: 2D <i>En Face</i> Optical Coherence Tomography Angiography Vessel Segmentation in Weakly-Supervised Learning With Locality Augmentation

Chinkamol, Amrest; Kanjaras, Vetit; Sawangjai, Phattarapong; Zhao, Yitian; Sudhawiyangkul, Thapanun; Chantrapornchai, Chantana; Guan, Cuntai; Wilaiprasitporn, Theerawit

doi:10.1109/tbme.2022.3232102

Cited by 5 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, even small changes and differences between the segmentation output and ground truth of the OCTA 6mm dataset result in lower accuracy metrics than the OCTA 3mm dataset [9]. This trend is also observed in many other recent publications [1,2,8,20]. Moreover, it is observed from Table 2 that the accuracy metrics for FAZ segmentation are higher than those of the retinal vasculature (namely, arteries, veins, and capillaries).…”

Section: Quantitative Segmentation Resultssupporting

confidence: 74%

“…Unlike several existing techniques [1,5,11,[14][15][16][17][18][19], the proposed work separately delineates the different blood vessels (namely, artery, vein and capillary) and FAZ. This can be used to detect anomalies like artery and vein occlusion.…”

Section: Advantages Of the Proposed Methodsmentioning

confidence: 99%

“…Optical coherence tomography angiography (OCTA) is a relatively recent, noninvasive imaging technique that provides accurate retinal visualization and volumetric information. It portrays the various retinal layers and their constituent blood vessels [1,2]. OCTA is currently viewed as a viable alternative to traditional imaging approaches like fluorescein angiography and indocyanine green angiography.…”

Section: Introductionmentioning

confidence: 99%

“…Various methods are available in the state-of-the-art literature for retinal blood vessels and FAZ segmentation. This includes delineation of the retinal vasculature alone [1,4,11,16] or combined retinal vessel and FAZ detection [5,14,15,[17][18][19]. Some studies further segment the retinal blood vessels into arteries, veins, and capillaries [2,8,20].…”

Section: Introductionmentioning

confidence: 99%

“…The performance was slightly reduced for combined retinal vessel and FAZ demarcation with a Dice coefficient of 0.87 and an IoU value of 0.79. As the manual labeling of OCTA images is a cumbersome and time-consuming task, Chinkamol et al [1] reduced the dependence on extensive manual annotations by incorporating the weakly supervised learning technique. The network was tested on all three projections of the OCTA-500 database, namely, FULL, ILM-OPL, and OPL-BM.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

DeepVasNet: Retinal Vasculature and FAZ Segmentation in OCTA with EfficientNet-Enhanced U-Net

Raja,

Gopi,

Francis

et al. 2024

Preprint

View full text Add to dashboard Cite

The study and analysis of retinal blood vessels and foveal avascular zone (FAZ) are clinically significant as they help in the early diagnosis of several diseases like diabetic retinopathy, glaucoma, neovasculariza-tion, artery or vein occlusion, and age-related macular degeneration. Recently, optical coherence tomography angiography (OCTA) imaging has been used to visualize the retina due to its non-invasive nature and fast imaging. However, manual retinal vasculature and FAZ segmentation are tedious and time-consuming. In this context, we propose an automated deep-learning-based segmentation method. The traditional U-Net is modified with a pre-trained EfficientNet-B0 in the encoder and a combined spatial, channel attention, squeeze, and excitation mechanism in the decoder. The proposed algorithm is validated on the publicly available OCTA-500 database. Mean Dice coefficients of 88.38, 88.40, 88.48, and 94.55 are obtained for capillary, artery, vein, and FAZ segmenta-tion in the OCTA 6 mm dataset. Whereas mean Dice scores of 90.48, 90.70, 89.59, and 97.98 are reported in the OCTA 3 mm subset for capillary , artery, vein, and FAZ segmentation, respectively. This segmentation performance is superior to other recent methods in the state-of-the-art literature. Overall, the contributions of our work are summarized as DRL-ASOCT follows. The proposed architecture is simple, easy to implement, and requires less memory and time than other networks. Further, we separately segment the retinal vessels (arteries, veins, and capillaries) and achieve improved segmentation accuracy relative to other approaches.

show abstract

Section: Quantitative Segmentation Resultssupporting

confidence: 74%