G-Net Light: A Lightweight Modified Google Net for Retinal Vessel Segmentation

Iqbal, Shahzaib; Naqvi, Syed S.; Khan, Hamid; Saadat, Ahsan; Khan, Tariq M.

doi:10.3390/photonics9120923

Cited by 20 publications

(16 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ratio of truly segmented observation is called accuracy (Iqbal et al, 2022) and AUC (Guo et al, 2020), which summarizes the overall performance of the model.

Accuracy = \frac{T N + TP}{(TN + TP + FN + FP)}

TP: correctly segmented exudates pixels; FP: incorrectly segmented non‐exudates pixels; TN: correctly segmented non‐exudates pixels; FN: exudes pixels incorrectly as non‐exuding pixels.…”

Section: Resultsmentioning

confidence: 99%

Semantic segmentation of retinal exudates using a residual encoder–decoder architecture in diabetic retinopathy

Manan,

Jinchao,

Khan

et al. 2023

Microscopy Res & Technique

Self Cite

View full text Add to dashboard Cite

Exudates are a common sign of diabetic retinopathy, which is a disease that affects the blood vessels in the retina. Early detection of exudates is critical to avoiding vision problems through continuous screening and treatment. In traditional clinical practice, the involved lesions are manually detected using photographs of the fundus. However, this task is cumbersome and time‐consuming and requires intense effort due to the small size of the lesion and the low contrast of the images. Thus, computer‐assisted diagnosis of retinal disease based on the detection of red lesions has been actively explored recently. In this paper, we present a comparison of deep convolutional neural network (CNN) architectures and propose a residual CNN with residual skip connections to reduce the parameter for the semantic segmentation of exudates in retinal images. A suitable image augmentation technique is used to improve the performance of network architecture. The proposed network can robustly segment exudates with high accuracy, which makes it suitable for diabetic retinopathy screening. A comparative performance analysis of three benchmark databases: E‐ophtha, DIARETDB1, and Hamilton Ophthalmology Institute's Macular Edema, is presented. The proposed method achieves a precision of 0.95, 0.92, 0.97, accuracy of 0.98, 0.98, 0.98, sensitivity of 0.97, 0.95, 0.95, specificity of 0.99, 0.99, 0.99, and area under the curve of 0.97, 0.94, and 0.96, respectively.Research Highlights The research focuses on the detection and segmentation of exudates in diabetic retinopathy, a disease affecting the retina. Early detection of exudates is important to avoid vision problems and requires continuous screening and treatment. Currently, manual detection is time‐consuming and requires intense effort. The authors compare qualitative results of the state‐of‐the‐art convolutional neural network (CNN) architectures and propose a computer‐assisted diagnosis approach based on deep learning, using a residual CNN with residual skip connections to reduce parameters. The proposed method is evaluated on three benchmark databases and demonstrates high accuracy and suitability for diabetic retinopathy screening.

show abstract

“…The ratio of truly segmented observation is called accuracy (Iqbal et al, 2022) and AUC (Guo et al, 2020), which summarizes the overall performance of the model.

Accuracy = \frac{T N + TP}{(TN + TP + FN + FP)}

TP: correctly segmented exudates pixels; FP: incorrectly segmented non‐exudates pixels; TN: correctly segmented non‐exudates pixels; FN: exudes pixels incorrectly as non‐exuding pixels.…”

Section: Resultsmentioning

confidence: 99%

Semantic segmentation of retinal exudates using a residual encoder–decoder architecture in diabetic retinopathy

Manan,

Jinchao,

Khan

et al. 2023

Microscopy Res & Technique

Self Cite

View full text Add to dashboard Cite

show abstract

“…Nonetheless, its inference speed is low. G-Net Light [44], PLVS-Net [48], and MKIS-Net [49] are effective CNN architectures for segmenting retinal blood vessels, while also being lightweight.…”

Section: Related Workmentioning

confidence: 99%

“…For comparative analysis, we include several wellestablished methods, namely MobileNet-V3-small [86], ERFNet [87], MultiRes UNet [88], VessNet [89], PLVS-Net [48], M2U-Net [60], and G-Net Light [44]. These methods have been widely recognized in the field and are commonly used as benchmarks for performance evaluation.…”

Section: A Comparison With Sota Lightweight Networkmentioning

confidence: 99%

“…The details of retinal fundus image datasets (publicly available) used for the performance evaluation of LDMRes-Net compared to more complex models. The development of lightweight segmentation networks specifically for medical images has been explored by researchers, as stated by Iqbal et al[44]. Nonetheless, creating networks that have low model complexity, high inference speed, and excellent performance still poses a challenge in most medical image segmentation tasks.…”

mentioning

confidence: 99%

See 1 more Smart Citation

MDA-Net: Multiscale dual attention-based network for breast lesion segmentation using ultrasound images

Iqbal

Sharif

2022

Journal of King Saud University - Computer and Information Scie

View full text Add to dashboard Cite

“…Deep learning has emerged as the most effective among supervised approaches, facilitating end-to-end segmentation with enhanced accuracy and generalisation. Several convolutional neural networks (CNNs) have been specifically designed and developed for medical image segmentation, demonstrating the versatility and potential of these techniques within the field of medical imaging [5], [11], [12], [13], [14], [15], [16], [17], [18], [19], [20].…”

mentioning

confidence: 99%

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation

Khan

Naqvi

Meijering

2022

Preprint

View full text Add to dashboard Cite

Recent progress in encoder-decoder neural network architecture design has led to significant performance improvements in a wide range of medical image segmentation tasks. However, state-of-the-art networks for a given task may be too computationally demanding to run on affordable hardware, and thus users often resort to practical workarounds by modifying various macro-level design aspects. Two common examples are downsampling of the input images and reducing the network depth or size to meet computer memory constraints. In this paper, we investigate the effects of these changes on segmentation performance and show that image complexity can be used as a guideline in choosing what is best for a given dataset. We consider four statistical measures to quantify image complexity and evaluate their suitability on ten different public datasets. For the purpose of our illustrative experiments, we use DeepLabV3+ (deep large-size), M2U-Net (deep lightweight), U-Net (shallow large-size), and U-Net Lite (shallow lightweight). Our results suggest that median frequency is the best complexity measure when deciding on an acceptable input down-sampling factor and using a deep versus shallow, large-size versus lightweight network. For high-complexity datasets, a lightweight network running on the original images may yield better segmentation results than a large-size network running on downsampled images, whereas the opposite may be the case for low-complexity images.

show abstract

G-Net Light: A Lightweight Modified Google Net for Retinal Vessel Segmentation

Cited by 20 publications

References 68 publications

Semantic segmentation of retinal exudates using a residual encoder–decoder architecture in diabetic retinopathy

Semantic segmentation of retinal exudates using a residual encoder–decoder architecture in diabetic retinopathy

MDA-Net: Multiscale dual attention-based network for breast lesion segmentation using ultrasound images

Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation

Contact Info

Product

Resources

About