Residues in Succession U-Net for Fast and Efficient Segmentation

Sultana, Aqsa; Asari, Vijayan K.; Aspiras, Theus

doi:10.1117/12.2634286

Cited by 3 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2022, Residues in Succession U-Net was introduced for fast and efficient segmentation of the retinal blood vessels. The network used U-Net as its base model [32,33].…”

Section: Related Workmentioning

confidence: 99%

“…The extraction and representation of low-level features are efficient by using time steps due to feature accumulation [1]. The addition of residual connection from input to output in the unit increases the efficacy of segmentation, improves the learning and prevents the loss of information [32,33].…”

Section: Model Architecturementioning

confidence: 99%

“…By emphasizing the pixels associated with the target lesion or pattern, we can determine its position [1,4]. Popular neural networks used for semantic segmentation include U-Net [2], ResU-Net [29], R2U-Net [1], Ladder-Net [16], Fusion Net [17] and recently introduced Residues in Succession U-Net [32,33] models, and these models consists of two units: encoders and decoders as their base network [3,5].…”

Section: Introductionmentioning

confidence: 99%

“…The feature maps on both encoding and decoding units are concatenated for better extraction of features [6]. [32,33] Another architecture inspired by U-Net and R2U-Net was Residues in Succession U-Net [32,33]. The unfolded architecture of Residues in Succession U-Net is shown in Figures 3(a) and 3(b).…”

Section: Introductionmentioning

confidence: 99%

“…The decoder is similar to the encoder, however, there is no residual connection from the input to the final integrated layer as shown in Figure 3(b). Here, the feature maps are concatenated from the encoding unit to the decoding unit to retain relevant [32,33].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Residues in succession recurrent U-Net for segmentation of retinal blood vessels

Sultana

Asari

Aspiras

2023

Pattern Recognition and Tracking XXXIV

View full text Add to dashboard Cite

The use of deep learning is particularly effective for biomedical applications involving semantic segmentation. In semantic segmentation, one of the most popular deep learning architectures is U-Net, which is specifically designed for feature cascading for pixel classification. There are several versions of U-Net, such as Residual U-Net (ResU-Net), Recurrent U-Net (RU-Net), and Recurrent Residual U-Net (R2U-Net), which have been proposed for improved performance. The recurrent connection in a layer of the neural network can create a cycle of transferring the output information of a layer back to itself as an input. Each layer's output responses can thus be thought of as additional input variables. The new model is based on Residues in Succession U-Net where the residues from successive layers extract reinforced information from the previous layers in addition to the recurrent feedback loop exhibiting several advantages. The improved learning and accumulation of the features in subsequent layers play a major part. The proposed model produces precise extraction and accumulation of features from each layer reinforcing the learning. The outputs of the combination of recurrent and residues in successive layers ensure better feature representation for segmentation tasks. We use a benchmark expert-annotated dataset viz. Structured Analysis of Retina (STARE) for measuring the abilities of the Residues in Succession Recurrent U-Net (RSR U-Net) to segment blood vessels in retinal images. The testing and evaluation results show that the new model provides improved performance when compared to U-Net, R2U-Net and Residues in Succession U-Net in the same experimentation setup.

show abstract

“…In 2022, Residues in Succession U-Net was introduced for fast and efficient segmentation of the retinal blood vessels. The network used U-Net as its base model [32,33].…”

Section: Related Workmentioning

confidence: 99%

Section: Model Architecturementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Residues in succession recurrent U-Net for segmentation of retinal blood vessels

Sultana

Asari

Aspiras

2023

Pattern Recognition and Tracking XXXIV

View full text Add to dashboard Cite

show abstract

NABLA-N for meltpond detection

Sultana,

Asari,

Aspiras

et al. 2024

Pattern Recognition and Tracking XXXV

View full text Add to dashboard Cite

With increasing global temperatures due to anthropogenic climate change, seasonal sea ice in the Arctic has experienced rapid retreat, with increasing areal extent of meltponds that occur on the surface of retreating sea ice. Because meltponds have a much lower albedo than sea ice or snow, more solar radiation is absorbed by the underlying water, further accelerating the melting rate of sea ice. However, the dynamic nature of meltponds, which exhibit complex shapes and boundaries, makes manual analysis of their effects on underlying light and water temperatures tedious and taxing. Several classical image processing approaches have been extensively used for the detection of meltpond regions in the Arctic area. We propose a Convolutional Neural Network (CNN) based multiclass segmentation model termed NABLA-N (∇ N ) for automated detection and segmentation of meltponds. The architectural framework of NABLA-N consists of an encoding unit and multiple decoding units that decode from several latent spaces. The fusion of multiple feature spaces in the decoding units enables better representation of features due to the combination of low and high-level feature maps. The proposed model is evaluated on high-resolution aerial photographs of Arctic sea ice obtained during the Healy-Oden Trans Arctic Expedition (HOTRAX) in 2005 and NASA's Operation IceBridge DMS L1B Geolocated and Orthorectified image data in 2016. These images are classified into three classes: meltpond, open water and sea ice. We determined that NABLA-N demonstrates superior performance on segmentation of meltpond data compared to other state-of-the-art networks such as UNet and Recurrent Residual UNet (R2UNet).

show abstract

Diffusion model-based generation of sea ice data

Sultana,

Abouzahra,

Asari

et al. 2024

Multimodal Image Exploitation and Learning 2024

View full text Add to dashboard Cite

One of the important indicators of cryospheric transitions in the Arctic is the formation of meltponds on sea ice, and much of the interest in these features is in the context of climate change. The scarcity of annotated arctic sea ice data is a major challenge in training a deep learning model for the prediction of the dynamics of the melt ponds. We use a diffusion model, a class of generative models, to generate synthetic arctic sea ice data for further analysis of meltponds. Based on the training data, diffusion models can generate new and realistic data that are not present in the original dataset by focusing on the data distribution from a simple to a more complex distribution. First, the simple distribution is transformed into a complex distribution by adding noise, such as a Gaussian distribution and through a series of invertible operations. Once trained, the model can generate new samples by starting from a simple distribution and diffusing it to the complex distribution, capturing the underlying features of the data. During inference, when generating new samples, the conditioning information is provided as input alongside the starting noise vector. This guides the diffusion process to produce samples that adhere to the specified conditions. We used high-resolution aerial photographs of the Arctic region obtained during the Healy-Oden Trans Arctic Expedition (HOTRAX) in 2005 and NASA's Operation IceBridge DMS L1B Geolocated and Orthorectified data acquired in 2016 for the initial training of the generative model. The original image and synthetic image are assessed based on their chromatic similarity. We employed an evaluation metric, the Chromatic Similarity Index (CSI) for these assessments.

show abstract

Residues in Succession U-Net for Fast and Efficient Segmentation

Cited by 3 publications

References 0 publications

Residues in succession recurrent U-Net for segmentation of retinal blood vessels

Residues in succession recurrent U-Net for segmentation of retinal blood vessels

NABLA-N for meltpond detection

Diffusion model-based generation of sea ice data

Contact Info

Product

Resources

About