[HTML][HTML] Deep learning for diabetic retinopathy detection and classification based on fundus images: A review

N Tsiknakis, D Theodoropoulos, G Manikis… - Computers in biology …, 2021 - Elsevier
Diabetic Retinopathy is a retina disease caused by diabetes mellitus and it is the leading
cause of blindness globally. Early detection and treatment are necessary in order to delay or …

CLC-Net: Contextual and local collaborative network for lesion segmentation in diabetic retinopathy images

X Wang, Y Fang, S Yang, D Zhu, M Wang, J Zhang… - Neurocomputing, 2023 - Elsevier
Diabetic retinopathy (DR) is the leading cause of blindness among people of working age.
Fundus lesions are clinical signs of DR, and their recognition and delineation are important …

High-Throughput in situ Root Image Segmentation Based on the Improved DeepLabv3+ Method

C Shen, L Liu, L Zhu, J Kang, N Wang… - Frontiers in Plant …, 2020 - frontiersin.org
The Rhizotrons method is an important means of detecting dynamic growth and
development phenotypes of plant roots. However, the segmentation of root images is a …

RMCA U-net: Hard exudates segmentation for retinal fundus images

Y Fu, G Zhang, X Lu, H Wu, D Zhang - Expert Systems with Applications, 2023 - Elsevier
Hard exudate plays an important role in grading diabetic retinopathy (DR) as a critical
indicator. Therefore, the accurate segmentation of hard exudates is of clinical importance …

Dual-branch network with dual-sampling modulated dice loss for hard exudate segmentation in color fundus images

Q Liu, H Liu, Y Zhao, Y Liang - IEEE Journal of Biomedical and …, 2021 - ieeexplore.ieee.org
Automated segmentation of hard exudates in colour fundus images is a challenge task due
to issues of extreme class imbalance and enormous size variation. This paper aims to tackle …

LightEyes: A lightweight fundus segmentation network for mobile edge computing

S Guo - Sensors, 2022 - mdpi.com
Fundus is the only structure that can be observed without trauma to the human body. By
analyzing color fundus images, the diagnosis basis for various diseases can be obtained …

Hard exudate segmentation supplemented by super-resolution with multi-scale attention fusion module

J Zhang, X Chen, Z Qiu, M Yang… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
Hard exudates (HE) is the most specific biomarker for retina edema. Precise HE
segmentation is vital for disease diagnosis and treatment, but automatic segmentation is …

RPN: A region-to-pixel-mask-based convolutional network for lesion segmentation of fundus images

H Zhang, C Ouyang, W Lin, Z Shen, B Liu, Y Liu, Z Gan - Neurocomputing, 2025 - Elsevier
Lesions segmentation of fundus images play a crucial role in the field of diagnosing diabetic
retinopath. However, their performance has consistently been hindered by challenges …

Grade prediction of bleeding volume in cesarean section of patients with pernicious placenta previa based on deep learning

J Liu, T Wu, Y Peng, R Luo - Frontiers in Bioengineering and …, 2020 - frontiersin.org
In order to predict the amount of bleeding in the cesarean section of the patients with
Pernicious Placenta Previa (PPP), this study proposed an automatic blood loss prediction …

[HTML][HTML] Lightweight Frequency Recalibration Network for Diabetic Retinopathy Multi-Lesion Segmentation

Y Fu, M Liu, G Zhang, J Peng - Applied Sciences, 2024 - mdpi.com
Automated segmentation of diabetic retinopathy (DR) lesions is crucial for assessing DR
severity and diagnosis. Most previous segmentation methods overlook the detrimental …