Inception U-Net Architecture for Semantic Segmentation to Identify Nuclei in Microscopy Cell Images

Punn, Narinder Singh; Agarwal, Sonali

doi:10.1145/3376922

Cited by 92 publications

(29 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 2020b ) AU-Net US - - AU Attention guided U-Net with total variation regularization Byra et al. ( 2020a ) SKU-Net US - - AU Attention based selective kernel U-Net Punn and Agarwal ( 2020c ) IU-Net Histopathol-ogical - - IU Inception U-Net model with hybrid spectral pooling Ibtehaz and Rahman ( 2020 ) MR-UNet Multi-modality - - IU MultiResUNet with multiple inception based skip connections Wang et al. ( 2020b ) NL-Unet Multi-modality - - - AU Non-local Unet with global context aggregation Xia et al.…”

Section: U-net Variants For Medical Imagingmentioning

confidence: 99%

“…With this approach, authors achieved significant improvement over the vanilla U-Net model across multiple datasets. In another work, Punn and Agarwal ( 2021b ) proposed residual cross-spatial attention (CSA) block in the skip connections of inception U-Net model (Punn and Agarwal 2020c ) to further improve the segmentation performance. The authors validated the performance of the model with breast cancer segmentation using ultrasound imaging.…”

Section: U-net Variants For Medical Imagingmentioning

confidence: 99%

“…For histopathological image segmentation, Punn and Agarwal ( 2020c ) proposed an inception U-Net model where standard convolution layers are replaced by inception blocks that consist of parallel convolutions of varying filter sizes and a hybrid pooling operation. The hybrid pooling operation draws the potential feature maps from the spectral domain via Hartley transform (Zhang and Ma 2018 ) to preserve more spatial information and spatial domain with the help of max pooling to aim for sharp features, by using the convolution.…”

Section: Other U-net Variants and Imagingmentioning

confidence: 99%

See 2 more Smart Citations

Modality specific U-Net variants for biomedical image segmentation: a survey

Punn

Agarwal

2022

Artif Intell Rev

Self Cite

View full text Add to dashboard Cite

With the advent of advancements in deep learning approaches, such as deep convolution neural network, residual neural network, adversarial network; U-Net architectures are most widely utilized in biomedical image segmentation to address the automation in identification and detection of the target regions or sub-regions. In recent studies, U-Net based approaches have illustrated state-of-the-art performance in different applications for the development of computer-aided diagnosis systems for early diagnosis and treatment of diseases such as brain tumor, lung cancer, alzheimer, breast cancer, etc., using various modalities. This article contributes in presenting the success of these approaches by describing the U-Net framework, followed by the comprehensive analysis of the U-Net variants by performing (1) inter-modality, and (2) intra-modality categorization to establish better insights into the associated challenges and solutions. Besides, this article also highlights the contribution of U-Net based frameworks in the ongoing pandemic, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) also known as COVID-19. Finally, the strengths and similarities of these U-Net variants are analysed along with the challenges involved in biomedical image segmentation to uncover promising future research directions in this area.

show abstract

Section: U-net Variants For Medical Imagingmentioning

confidence: 99%

Section: U-net Variants For Medical Imagingmentioning

confidence: 99%

Section: Other U-net Variants and Imagingmentioning

confidence: 99%

See 1 more Smart Citation

Modality specific U-Net variants for biomedical image segmentation: a survey

Punn

Agarwal

2022

Artif Intell Rev

Self Cite

View full text Add to dashboard Cite

show abstract

“…breast cancer, brain tumor, etc. by using different imaging modalities such as X-ray, CT, MRI, [47] and fused modalities [37] along with its future possibilities. The success of these approaches is dependent on the large amount of data availability, which however is not in the case of automated COVID-19 detection.…”

Section: Proposed Contributionmentioning

confidence: 99%

Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks

2020

Self Cite

View full text Add to dashboard Cite

The novel coronavirus 2019 (COVID-19) is a respiratory syndrome that resembles pneumonia. The current diagnostic procedure of COVID-19 follows reverse-transcriptase polymerase chain reaction (RT-PCR) based approach which however is less sensitive to identify the virus at the initial stage. Hence, a more robust and alternate diagnosis technique is desirable. Recently, with the release of publicly available datasets of corona positive patients comprising of computed tomography (CT) and chest X-ray (CXR) imaging; scientists, researchers and healthcare experts are contributing for faster and automated diagnosis of COVID-19 by identifying pulmonary infections using deep learning approaches to achieve better cure and treatment. These datasets have limited samples concerned with the positive COVID-19 cases, which raise the challenge for unbiased learning. Following from this context, this article presents the random oversampling and weighted class loss function approach for unbiased fine-tuned learning (transfer learning) in various state-of-the-art deep learning approaches such as baseline ResNet, Inception-v3, Inception ResNet-v2, DenseNet169, and NASNetLarge to perform binary classification (as normal and COVID-19 cases) and also multi-class classification (as COVID-19, pneumonia, and normal case) of posteroanterior CXR images. Accuracy, precision, recall, loss, and area under the curve (AUC) are utilized to evaluate the performance of the models. Considering the experimental results, the performance of each model is scenario dependent; however, NASNetLarge displayed better scores in contrast to other architectures, which is further compared with other recently proposed approaches. This article also added the visual explanation to illustrate the basis of model classification and perception of COVID-19 in CXR images.

show abstract

“…U-Net has been applied to various datasets, such as urine microscopic images (Aziz et al, 2018), ADF-STEM images (Ge & Xin, 2018), corneal endothelial cell images (Daniel et al, 2019), and fluorescently labeled cell nuclei images (Gudla et al, 2019). Many other works performed similar microscopy segmentation tasks on the nanoscale using modified versions of the U-Net Architecture such as EM-Net (Khadangi et al, 2020), Fully Residual U-Net (Gómez-de Mariscal et al, 2019), Inception U-Net (Punn & Agarwal, 2020), and the domain adaptive approach with two coupled U-Nets (Bermúdez-Chacón et al, 2018).…”

Section: Introductionmentioning

confidence: 99%