Laser Scar Detection in Fundus Images Using Convolutional Neural Networks

Wei, Qijie; Li, Xirong; Wang, Hao; Ding, Dayong; Wu, Yu; Chen, Youxin

doi:10.1007/978-3-030-20870-7_12

Cited by 11 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A CNN‐based laser damage detection method was proposed by Wei et al . [15]. They compared several different CNNs, ResNet [20], DenseNet [21], and Inception‐v3 [22].…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, to select several good feature extraction CNN models, several pretrained CNN modes were fine-tuned to perform the feature extraction task. For deep learning-based feature extraction, some efforts on transfer learning have been made [14][15][16][17][18], and these researches showed good performance compared with untrained CNN models. An automated pavement distress detection method using a pretrained VGG-16 [19] deep CNN was proposed by Gopalakrishnan et al [14].…”

Section: Related Workmentioning

confidence: 99%

“…An automated pavement distress detection method using a pretrained VGG-16 [19] deep CNN was proposed by Gopalakrishnan et al [14]. A CNN-based laser damage detection method was proposed by Wei et al [15]. They compared several different CNNs, ResNet [20], DenseNet [21], and Inception-v3 [22].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Curb Detection Using a Novel Deep Learning Framework Based on YOLO‐v2

Zou

Kageyama

Akashi

2022

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Curb detection with a monocular camera is important to assist driving by detecting curbs to avoid accidents. However, various road scenes and curb shapes make it difficult to detect curbs based on a single image. In this study, a novel image‐based curb detection method that is highly efficient, inexpensive, and less complex than LiDAR‐based solutions was developed. A deep learning framework was used to detect curbs from road images automatically. A custom convolutional neural network (CNN) model was built, and another seven pretrained models were fine‐tuned for curb patch classification. The evaluation metrics, such as accuracy, F1‐score, area under curve, and prediction time, were considered comprehensively to select the optimal CNN architecture. Three promising CNN architectures were employed as classification networks and embedded into the YOLO‐v2 framework to construct curb detectors. The detection performance was evaluated in terms of the average precision on an urban road image dataset. By configuring parameters for the optimal CNN architecture, the best detector achieved an average precision of 99.16%, which verifies the effectiveness of the proposed method. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

“…A CNN‐based laser damage detection method was proposed by Wei et al . [15]. They compared several different CNNs, ResNet [20], DenseNet [21], and Inception‐v3 [22].…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Curb Detection Using a Novel Deep Learning Framework Based on YOLO‐v2

Zou

Kageyama

Akashi

2022

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…While other CNNs can also be used, our consideration of choosing ResNet-18 is as follows. This network has relatively fewer parameters and thus needs less data for training, meanwhile its effectiveness has been justified in other fundus image recognition tasks [33], [34]. Note that for the OCT image, we convert each of its pixels from grayscale to RGB by duplicating the intensity for each RGB component.…”

Section: A Mm-cnn For Amd Categorizationmentioning

confidence: 99%

Learning Two-Stream CNN for Multi-Modal Age-related Macular Degeneration Categorization

Wang¹,

Li²,

Xu³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

This paper tackles automated categorization of Agerelated Macular Degeneration (AMD), a common macular disease among people over 50. Previous research efforts mainly focus on AMD categorization with a single-modal input, let it be a color fundus image or an OCT image. By contrast, we consider AMD categorization given a multi-modal input, a direction that is clinically meaningful yet mostly unexplored. Contrary to the prior art that takes a traditional approach of feature extraction plus classifier training that cannot be jointly optimized, we opt for end-to-end multi-modal Convolutional Neural Networks (MM-CNN). Our MM-CNN is instantiated by a two-stream CNN, with spatially-invariant fusion to combine information from the fundus and OCT streams. In order to visually interpret the contribution of the individual modalities to the final prediction, we extend the class activation mapping (CAM) technique to the multi-modal scenario. For effective training of MM-CNN, we develop two data augmentation methods. One is GAN-based fundus / OCT image synthesis, with our novel use of CAMs as conditional input of a high-resolution image-to-image translation GAN. The other method is Loose Pairing, which pairs a fundus image and an OCT image on the basis of their classes instead of eye identities. Experiments on a clinical dataset consisting of 1,099 color fundus images and 1,290 OCT images acquired from 1,099 distinct eyes verify the effectiveness of the proposed solution for multi-modal AMD categorization.

show abstract

“…Traditional detections [ 6 – 8 ] and deep learning methods [ 9 ] have put effort into detecting the existence of laser marks. However, they do not give enough attention to the exact locations of laser marks on the fundus photograph images.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of Laser Marks of Diabetic Retinopathy in the Fundus Photographs Using Lightweight U-Net

Jiang

Pan

Yuan

et al. 2021

Journal of Diabetes Research

View full text Add to dashboard Cite

Diabetic retinopathy (DR) is a prevalent vision-threatening disease worldwide. Laser marks are the scars left after panretinal photocoagulation, a treatment to prevent patients with severe DR from losing vision. In this study, we develop a deep learning algorithm based on the lightweight U-Net to segment laser marks from the color fundus photos, which could help indicate a stage or providing valuable auxiliary information for the care of DR patients. We prepared our training and testing data, manually annotated by trained and experienced graders from Image Reading Center, Zhongshan Ophthalmic Center, publicly available to fill the vacancy of public image datasets dedicated to the segmentation of laser marks. The lightweight U-Net, along with two postprocessing procedures, achieved an AUC of 0.9824, an optimal sensitivity of 94.16%, and an optimal specificity of 92.82% on the segmentation of laser marks in fundus photographs. With accurate segmentation and high numeric metrics, the lightweight U-Net method showed its reliable performance in automatically segmenting laser marks in fundus photographs, which could help the AI assist the diagnosis of DR in the severe stage.

show abstract

Laser Scar Detection in Fundus Images Using Convolutional Neural Networks

Cited by 11 publications

References 14 publications

Curb Detection Using a Novel Deep Learning Framework Based on YOLO‐v2

Curb Detection Using a Novel Deep Learning Framework Based on YOLO‐v2

Learning Two-Stream CNN for Multi-Modal Age-related Macular Degeneration Categorization

Segmentation of Laser Marks of Diabetic Retinopathy in the Fundus Photographs Using Lightweight U-Net

Contact Info

Product

Resources

About