ResUNet++: An Advanced Architecture for Medical Image Segmentation

Jha, Debesh; Smedsrud, Pia H.; Riegler, Michael; Johansen, Dag; Lange, Thomas de; Halvorsen, Pål; Johansen, Håvard D.

doi:10.1109/ism46123.2019.00049

Cited by 539 publications

(251 citation statements)

References 31 publications

Supporting

Mentioning

251

Contrasting

Order By: Relevance

“…During the model training, we manually tuned the hyperparameters with various hyperparameter sets and evaluated the results. Table 2 presents the results of A-DenseUNet, ResUNet [ 40 ], UNet++ [ 11 ], wide U-Net, original U-Net [ 10 ], PraNet [ 52 ] and ResUNet++ [ 6 ] on the Kvasir-SEG [ 48 ] dataset. The data indicate that the proposed architecture outperformed all current methods.…”

Section: Resultsmentioning

confidence: 99%

“…Figure 9 and Figure 10 present the qualitative results for all deep learning methods. Table 2 and Table 3 and the qualitative results show the dominance of A-DenseUNet over the baseline methods such as UNet++ [ 11 ], ResUNet [ 40 ], wide U-Net, original U-Net [ 10 ], PraNet [ 52 ] and ResUNet++ [ 6 ]. On the Kvasir-SEG dataset, the proposed architecture achieved mean improvements of 10.64%, 12.21%, 14.4%, 20.23%, 1.2%, and 9.2% as measured by the Dice coefficient, and 14.12%, 32.21%, 15.03%, 29.86%, 2.15% and 6.81% as measured by the IoU score.…”

Section: Resultsmentioning

confidence: 99%

“…There are similar inter-classes and various intra-classes for four different polyp classes: Adenoma, hyperplastic, serrated, and mixed. In addition, background objects are very similar; for example, the background mucosa can mix with a polyp or stool [ 6 ]. Even though these factors make the polyp segmentation task challenging, we surmise that there is still a great prospect to create such systems for medical use.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution

Safarov

Whangbo

2021

Sensors

View full text Add to dashboard Cite

Colon carcinoma is one of the leading causes of cancer-related death in both men and women. Automatic colorectal polyp segmentation and detection in colonoscopy videos help endoscopists to identify colorectal disease more easily, making it a promising method to prevent colon cancer. In this study, we developed a fully automated pixel-wise polyp segmentation model named A-DenseUNet. The proposed architecture adapts different datasets, adjusting for the unknown depth of the network by sharing multiscale encoding information to the different levels of the decoder side. We also used multiple dilated convolutions with various atrous rates to observe a large field of view without increasing the computational cost and prevent loss of spatial information, which would cause dimensionality reduction. We utilized an attention mechanism to remove noise and inappropriate information, leading to the comprehensive re-establishment of contextual features. Our experiments demonstrated that the proposed architecture achieved significant segmentation results on public datasets. A-DenseUNet achieved a 90% Dice coefficient score on the Kvasir-SEG dataset and a 91% Dice coefficient score on the CVC-612 dataset, both of which were higher than the scores of other deep learning models such as UNet++, ResUNet, U-Net, PraNet, and ResUNet++ for segmenting polyps in colonoscopy images.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution

Safarov

Whangbo

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Chen et al [29] introduced DeepLabV3+ formed with atrous separable convolutions for refining the segmentation results across the object boundaries. Jha et al [43] proposed a deep residual UNet known as ResUNet++ for colonoscopic image segmentation. This architecture adds on a residual connection and attention module to the existing bottleneck of UNet.…”

Section: B Deep Learning For Medical Image Segmentationmentioning

confidence: 99%

Anam-Net: Anamorphic Depth Embedding-Based Lightweight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images

Paluru¹,

Dayal

Jenssen

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

116

View full text Add to dashboard Cite

Chest computed tomography (CT) imaging has become indispensable for staging and managing coronavirus disease 2019 (COVID-19), and current evaluation of anomalies/abnormalities associated with COVID-19 has been performed majorly by the visual score. The development of automated methods for quantifying COVID-19 abnormalities in these CT images is invaluable to clinicians. The hallmark of COVID-19 in chest CT images is the presence of ground-glass opacities in the lung region, which are tedious to segment manually. We propose anamorphic depth embedding-based lightweight CNN, called Anam-Net, to segment anomalies in COVID-19 chest CT images. The proposed Anam-Net has 7.8 times fewer parameters compared to the state-of-the-art UNet (or its variants), making it lightweight capable of providing inferences in mobile or resource constraint (point-of-care) platforms. The results from chest CT images (test cases) across different experiments showed that the proposed method could provide good Dice similarity scores for abnormal and normal regions in the lung. We have benchmarked Anam-Net with other state-of-the-art architectures, such as ENet, LEDNet, UNet++, SegNet, Attention UNet, and DeepLabV3+. The proposed Anam-Net was also deployed on embedded systems, such as Raspberry Pi 4, NVIDIA Jetson Xavier, and mobile-based Android application (Cov-Seg) embedded with Anam-Net to demonstrate its suitability for point-of-care platforms. The generated codes, models, and the mobile application are available for enthusiastic users at https://github.com/NaveenPaluru/Segmentation-COVID-19.

show abstract

“…There are similar inter-classes and various intra-classes for four different polyp classes: adenoma, hyperplastic, serrated, and mixed. In addition, background objects are very similar; for example, the background mucosa can mix with a polyp or stool [43]. Even though these factors make the polyp segmentation task challenging, we surmise that there is still a great prospect to create such systems for medical use.…”

Section: Introductionmentioning

confidence: 99%

A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution

Safarov

Whangbo

2021

Preprint

View full text Add to dashboard Cite

Colon carcinoma is one of the leading causes of cancer-related death in both men and women. Automatic colorectal polyp segmentation and detection in colonoscopy videos help endoscopists to identify colorectal disease more easily, making it a promising method to prevent colon cancer. In this study, we developed a fully automated pixel-wise polyp segmentation model named A-DenseUNet. The proposed architecture adapts different datasets, adjusting for the unknown depth of the network by sharing multiscale encoding information to the different levels of the decoder side. We also used multiple dilated convolutions with various atrous rates to observe a large field of view without increasing the computational cost and prevent loss of spatial information, which would cause dimensionality reduction. We utilized an attention mechanism to remove noise and inappropriate information, leading to the comprehensive re-establishment of contextual features. Our experiments demonstrated that the proposed architecture achieved significant segmentation results on public datasets. A-DenseUNet achieved a 90% Dice coefficient score on the Kvasir-SEG dataset and a 91% Dice coefficient score on the CVC-612 dataset, both of which were higher than the scores of other deep learning models such as UNet++, ResUNet, and U-Net, for segmenting polyps in colonoscopy images.

show abstract

ResUNet++: An Advanced Architecture for Medical Image Segmentation

Cited by 539 publications

References 31 publications

A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution

A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution

Anam-Net: Anamorphic Depth Embedding-Based Lightweight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images

A-DenseUNet: Adaptive Densely Connected UNet for Polyp Segmentation in Colonoscopy Images with Atrous Convolution

Contact Info

Product

Resources

About