Crossbar-Net: A Novel Convolutional Neural Network for Kidney Tumor Segmentation in CT Images

Yu, Qian; Shi, Yinghuan; Sun, Jinquan; Gao, Yang; Zhu, Jianbing; Dai, Yakang

doi:10.1109/tip.2019.2905537

Cited by 88 publications

(36 citation statements)

References 51 publications

(96 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…V-Net [9], for example, claimed 551×551×551 designed receptive field but used 64×128×128 patch sliding scheme, making the large designed receptive field not fully effective. To enlarge the effective receptive field under current part based frameworks, Crossbar-Net [20] proposed to train segmentation networks using non-squared patches with different aspect ratios to add more global contexts to local details.…”

Section: Introductionmentioning

confidence: 99%

3-D RoI-Aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation

Huang

Dou

Wang

et al. 2021

IEEE Trans. Cybern.

View full text Add to dashboard Cite

Segmentation of colorectal cancerous regions from 3DMagnetic Resonance (MR) images is a crucial procedure for radiotherapy which conventionally requires accurate delineation of tumour boundaries at an expense of labor, time and reproducibility. While deep learning based methods serve good baselines in 3D image segmentation tasks, small applicable patch size limits effective receptive field and degrades segmentation performance. In addition, Regions of interest (RoIs) localization from large whole volume 3D images serves as a preceding operation that brings about multiple benefits in terms of speed, target completeness, reduction of false positives. Distinct from sliding window or non-joint localizationsegmentation based models, we propose a novel multitask framework referred to as 3D RoI-aware U-Net (3D RU-Net), for RoI localization and in-region segmentation where the two tasks share one backbone encoder network. With the region proposals from the encoder, we crop multi-level RoI in-region features from the encoder to form a GPU memory-efficient decoder for detailpreserving segmentation and therefore enlarged applicable volume size and effective receptive field. To effectively train the model, we designed a Dice formulated loss function for the global-to-local multi-task learning procedure. Based on the efficiency gains demonstrated by the proposed method, we went on to ensemble models with different receptive fields to achieve even higher performance costing minor extra computational expensiveness. Extensive experiments were subsequently conducted on 64 cancerous cases with a four-fold cross-validation, and the results showed significant superiority in terms of accuracy and efficiency over conventional state-of-the art frameworks. In conclusion, the proposed method has a huge potential for extension to other 3D object segmentation tasks from medical images due to its inherent generalizability. The code for the proposed method is publicly available.3D CNN, region of interest, multi-task learning, tumor segmentation, colorectal cancer.

show abstract

Section: Introductionmentioning

confidence: 99%

3-D RoI-Aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation

Huang

Dou

Wang

et al. 2021

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…Our future directions include: 1) extending to other medical image segmentation tasks to validate the generalization of the proposed method [23,24], 2) combining with GAN-based methods [15,20] to increase the diversity of generated data.…”

Section: Resultsmentioning

confidence: 99%

Automatic Data Augmentation Via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation

Qin

Wang

et al. 2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Conventional data augmentation realized by performing simple pre-processing operations (e.g., rotation, crop, etc.) has been validated for its advantage in enhancing the performance for medical image segmentation. However, the data generated by these conventional augmentation methods are random and sometimes harmful to the subsequent segmentation. In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement learning (DRL). In our method, we innovatively combine the data augmentation module and the subsequent segmentation module in an end-to-end training manner with a consistent loss. Specifically, the best sequential combination of different basic operations is automatically learned by directly maximizing the performance improvement (i.e., Dice ratio) on the available validation set. We extensively evaluated our method on CT kidney tumor segmentation which validated the promising results of our method.

show abstract

“…These weakly learned-based methods have achieved comparable accuracy on normal organs but have not yet been applied to lesions. The approaches for renal tumor segmentation are mainly based on traditional methods such as level-set [22], SVM [23] and fully-supervised deep neural networks [24,25]. To the best of our knowledge, there is no weakly-supervised deep learning technique reported for renal tumor segmentation.…”

Section: Introductionmentioning

confidence: 99%

Weakly-supervised convolutional neural networks of renal tumor segmentation in abdominal CTA images

et al. 2020

View full text Add to dashboard Cite

Background: Renal cancer is one of the 10 most common cancers in human beings. The laparoscopic partial nephrectomy (LPN) is an effective way to treat renal cancer. Localization and delineation of the renal tumor from pre-operative CT Angiography (CTA) is an important step for LPN surgery planning. Recently, with the development of the technique of deep learning, deep neural networks can be trained to provide accurate pixel-wise renal tumor segmentation in CTA images. However, constructing the training dataset with a large amount of pixel-wise annotations is a time-consuming task for the radiologists. Therefore, weakly-supervised approaches attract more interest in research.Methods: In this paper, we proposed a novel weakly-supervised convolutional neural network (CNN) for renal tumor segmentation. A three-stage framework was introduced to train the CNN with the weak annotations of renal tumors, i.e. the bounding boxes of renal tumors. The framework includes pseudo masks generation, group and weighted training phases. Clinical abdominal CT angiographic images of 200 patients were applied to perform the evaluation.Results: Extensive experimental results show that the proposed method achieves a higher dice coefficient (DSC) of 0.826 than the other two existing weakly-supervised deep neural networks. Furthermore, the segmentation performance is close to the fully supervised deep CNN. Conclusions:The proposed strategy improves not only the efficiency of network training but also the precision of the segmentation.

show abstract

Crossbar-Net: A Novel Convolutional Neural Network for Kidney Tumor Segmentation in CT Images

Cited by 88 publications

References 51 publications

3-D RoI-Aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation

3-D RoI-Aware U-Net for Accurate and Efficient Colorectal Tumor Segmentation

Automatic Data Augmentation Via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation

Weakly-supervised convolutional neural networks of renal tumor segmentation in abdominal CTA images

Contact Info

Product

Resources

About