Extraction of Kidney Anatomy Based on a 3D U-ResNet with Overlap-Tile Strategy

Adam, Jannes; Niklas, Agethen,; Robert, Bohnsack,; René, Finzel,; Günnemann, Timo; Philipp, Lena; Rink, Markus; Xue, Tingting; Thielke, Felix; Meine, Hans

doi:10.1007/978-3-030-98385-7_2

Cited by 2 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Authors methods Kidney Dice/SD Mass Dice/SD Tumor Dice/SD Cyst Dice/SD This paper 2.5D MFFAU-Net 0.973/0.941 0.887/0.788 0.873/0.769 0.765/0.678 Shen et al [ 24 ]. COTRNet 0.923/0.885 0.553/0.369 0.506/0.355 \ Adam et al [ 25 ]. 3D U-ResNet 0.951/0.904 0.798/0.648 0.781/0.627 \ Zhao et al [ 26 ].…”

Section: Discussionmentioning

confidence: 99%

“…Adam et al [ 25 ] proposed a model with pre-processing, post-processing, and data enhancement functions. They introduced Residual Block in the U-Net structure and achieved 0.951 kidney dice, 0.798 mass dice, 0.781 tumor dice, and an 0.904 kidney SD, 0.648 mass SD, 0.627 tumor SD.…”

Section: Discussionmentioning

confidence: 99%

“…Finally, their method ranked 22 and achieved 0.923 kidney dice, 0.553 mass dice, and 0.506 tumor dice. Adam et al [ 25 ] used a 3D U-ResNet method for kidney segmentation, they introduced the Residual Block in the U-Net model and used rule-based post-processing to eliminate false positive artifacts. Ultimately, they led to the 12th position in the KiTS21.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

2.5D MFFAU-Net: a convolutional neural network for kidney segmentation

Sun

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Kidney tumors have become increasingly prevalent among adults and are now considered one of the most common types of tumors. Accurate segmentation of kidney tumors can help physicians assess tumor complexity and aggressiveness before surgery. However, segmenting kidney tumors manually can be difficult because of their heterogeneity. Methods This paper proposes a 2.5D MFFAU-Net (multi-level Feature Fusion Attention U-Net) to segment kidneys, tumors and cysts. First, we propose a 2.5D model for learning to combine and represent a given slice in 2D slices, thereby introducing 3D information to balance memory consumption and model complexity. Then, we propose a ResConv architecture in MFFAU-Net and use the high-level and low-level feature in the model. Finally, we use multi-level information to analyze the spatial features between slices to segment kidneys and tumors. Results The 2.5D MFFAU-Net was evaluated on KiTS19 and KiTS21 kidney datasets and demonstrated an average dice score of 0.924 and 0.875, respectively, and an average Surface dice (SD) score of 0.794 in KiTS21. Conclusion The 2.5D MFFAU-Net model can effectively segment kidney tumors, and the results are comparable to those obtained with high-performance 3D CNN models, and have the potential to serve as a point of reference in clinical practice.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

2.5D MFFAU-Net: a convolutional neural network for kidney segmentation

Sun

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Fabian et al [28] secured the first position with a 3D UNet-based approach, achieving impressive dice scores of 0.974 and 0.851 for kidney and tumor segmentation, resulting in a composite score of 0.912 [29]. Several other researchers [30][31][32][33][34] proposed kidney and tumor segmentation methods, achieving notable results in subsequent studies.…”

Section: Related Workmentioning

confidence: 99%

Optimizing Inference Distribution for Efficient Kidney Tumor Segmentation Using a UNet-PWP Deep-Learning Model with XAI on CT Scan Images

Rao,

Chatterjee,

Janardhan

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Kidney tumors represent a significant medical challenge, characterized by their often-asymptomatic nature and the need for early detection to facilitate timely and effective intervention. Although neural networks have shown great promise in disease prediction, their computational demands have limited their practicality in clinical settings. This study introduces a novel methodology, the UNet-PWP architecture, tailored explicitly for kidney tumor segmentation, designed to optimize resource utilization and overcome computational complexity constraints. A key novelty in our approach is the application of adaptive partitioning, which deconstructs the intricate UNet architecture into smaller submodels. This partitioning strategy reduces computational requirements and enhances the model’s efficiency in processing kidney tumor images. Additionally, we augment the UNet’s depth by incorporating pre-trained weights, therefore significantly boosting its capacity to handle intricate and detailed segmentation tasks. Furthermore, we employ weight-pruning techniques to eliminate redundant zero-weighted parameters, further streamlining the UNet-PWP model without compromising its performance. To rigorously assess the effectiveness of our proposed UNet-PWP model, we conducted a comparative evaluation alongside the DeepLab V3+ model, both trained on the “KiTs 19, 21, and 23” kidney tumor dataset. Our results are optimistic, with the UNet-PWP model achieving an exceptional accuracy rate of 97.01% on both the training and test datasets, surpassing the DeepLab V3+ model in performance. Furthermore, to ensure our model’s results are easily understandable and explainable. We included a fusion of the attention and Grad-CAM XAI methods. This approach provides valuable insights into the decision-making process of our model and the regions of interest that affect its predictions. In the medical field, this interpretability aspect is crucial for healthcare professionals to trust and comprehend the model’s reasoning.

show abstract

Extraction of Kidney Anatomy Based on a 3D U-ResNet with Overlap-Tile Strategy

Cited by 2 publications

References 3 publications

2.5D MFFAU-Net: a convolutional neural network for kidney segmentation

2.5D MFFAU-Net: a convolutional neural network for kidney segmentation

Optimizing Inference Distribution for Efficient Kidney Tumor Segmentation Using a UNet-PWP Deep-Learning Model with XAI on CT Scan Images

Contact Info

Product

Resources

About