Target-aware U-Net with fuzzy skip connections for refined pancreas segmentation

Chen, Yufei; Xu, Chang; Ding, Weiping; Sun, Shuang; Yue, Xiaodong; Fujita, Hamido

doi:10.1016/j.asoc.2022.109818

Cited by 12 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although Recall is less widely employed compared to DSC, [60] also leads with a superior score of 91.13%±1.48 in this metric. Utilization of the Jaccard index is relatively infrequent; nonetheless, [46] scores 78.52%±4.14, demonstrating robust performance. As for processing time, significant variations are present across different studies, governed by the variation in hardware and software configurations used; notably, [30] reports a processing time of just 0.179 seconds, while [50] extends up to 1.26 minutes.…”

Section: B Performance Metric Analysismentioning

confidence: 99%

“…This not only suppresses irrelevant background features but also enhances features relevant to the target. This modification leads to an approximate 5% improvement in segmentation accuracy [46].…”

Section: Skip Connection Variationsmentioning

confidence: 99%

“…Upon closer analysis, the study by Chen et al introduce a Target-Aware U-Net (tU-Net) distinguished by two innovative modules: fuzzy skip connections and target attention mechanisms [46]. These two modules run in parallel to the standard U-Net and aim to enhance the accuracy of pancreatic target segmentation.…”

Section: B Parallel U-netsmentioning

confidence: 99%

See 2 more Smart Citations

State-of-the-Art and Challenges in Pancreatic CT Segmentation: A Systematic Review of U-Net and Its Variants

Zhang,

Achuthan,

Himel

2024

IEEE Access

View full text Add to dashboard Cite

In medical image analysis, segmenting pancreatic CT images presents a significant challenge due to the complex anatomy of the pancreas and the generally low contrast of these images. Accurate pancreas segmentation is crucial in clinical scenarios, particularly for the diagnosis and treatment of pancreatic cancer. The U-Net architecture and its variations have achieved significant progress in deep learningbased image segmentation, especially in the context of pancreatic CT image segmentation. However, there is a noticeable gap in the comprehensive evaluation of their performance, limitations, and potential improvements specifically in this area. This systematic review aims to address this gap in the literature, focusing particularly on U-Net and its variants in pancreatic CT image segmentation. Adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, this review includes relevant studies published since 2019 in the field of pancreatic segmentation. The findings illuminate the current limitations of these methods and establish a theoretical foundation for future research directions.

show abstract

Section: B Performance Metric Analysismentioning

confidence: 99%

Section: Skip Connection Variationsmentioning

confidence: 99%

See 1 more Smart Citation

State-of-the-Art and Challenges in Pancreatic CT Segmentation: A Systematic Review of U-Net and Its Variants

Zhang,

Achuthan,

Himel

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…All submissions will be thoroughly reviewed through a single-blind peer-review process. Currently, MI and MIP entail several challenges [30], such as low-resolution quality, high-level noise, low contrast, geometric deformations, presence of artifacts [31], small-size dataset [32], large computational burdens [33], long training time, etc. In our previous successful Special Issues, 'Medical Imaging & Image Processing' in 2015 and 'Medical Imaging & Image Processing II' in 2018, the authors partially solved the aforementioned challenges and reported their research outputs.…”

mentioning

confidence: 99%

Medical Imaging and Image Processing

Zhang

Dong

2023

Technologies

View full text Add to dashboard Cite

show abstract

Reinforcement learning‐based anatomical maps for pancreas subregion and duct segmentation

Amiri,

Vrtovec,

Mustafaev

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundThe pancreas is a complex abdominal organ with many anatomical variations, and therefore automated pancreas segmentation from medical images is a challenging application.PurposeIn this paper, we present a framework for segmenting individual pancreatic subregions and the pancreatic duct from three‐dimensional (3D) computed tomography (CT) images.MethodsA multiagent reinforcement learning (RL) network was used to detect landmarks of the head, neck, body, and tail of the pancreas, and landmarks along the pancreatic duct in a selected target CT image. Using the landmark detection results, an atlas of pancreases was nonrigidly registered to the target image, resulting in anatomical probability maps for the pancreatic subregions and duct. The probability maps were augmented with multilabel 3D U‐Net architectures to obtain the final segmentation results.ResultsTo evaluate the performance of our proposed framework, we computed the Dice similarity coefficient (DSC) between the predicted and ground truth manual segmentations on a database of 82 CT images with manually segmented pancreatic subregions and 37 CT images with manually segmented pancreatic ducts. For the four pancreatic subregions, the mean DSC improved from 0.38, 0.44, and 0.39 with standard 3D U‐Net, Attention U‐Net, and shifted windowing (Swin) U‐Net architectures, to 0.51, 0.47, and 0.49, respectively, when utilizing the proposed RL‐based framework. For the pancreatic duct, the RL‐based framework achieved a mean DSC of 0.70, significantly outperforming the standard approaches and existing methods on different datasets.ConclusionsThe resulting accuracy of the proposed RL‐based segmentation framework demonstrates an improvement against segmentation with standard U‐Net architectures.

show abstract

Target-aware U-Net with fuzzy skip connections for refined pancreas segmentation

Cited by 12 publications

References 34 publications

State-of-the-Art and Challenges in Pancreatic CT Segmentation: A Systematic Review of U-Net and Its Variants

State-of-the-Art and Challenges in Pancreatic CT Segmentation: A Systematic Review of U-Net and Its Variants

Medical Imaging and Image Processing

Reinforcement learning‐based anatomical maps for pancreas subregion and duct segmentation

Contact Info

Product

Resources

About