Block Level Skip Connections Across Cascaded V-Net for Multi-Organ Segmentation

Abstract

Multi-organ segmentation is a challenging task due to the label imbalance and structural differences between different organs. In this work, we propose an efficient cascaded V-Net model to improve the performance of multi-organ segmentation by establishing dense Block Level Skip Connections (BLSC) across cascaded V-Net. Our model can take full advantage of features from the first stage network and make the cascaded structure more efficient. We also combine stacked small and large kernels with an inception-like structure to help our model to learn more patterns, which produces superior results for multi-organ segmentation. In addition, some small organs are commonly occluded by large organs and have unclear boundaries with other surrounding tissues, which makes them hard to be segmented. We therefore first locate the small organs through a multi-class network and crop them randomly with the surrounding region, then segment them with a single-class network. We evaluated our model on SegTHOR 2019 challenge unseen testing set and Multi-Atlas Labeling Beyond the Cranial Vault challenge validation set. Our model has achieved an average dice score gain of 1.62 percents and 3.90 percents compared to traditional cascaded networks on these two datasets, respectively. For hard-to-segment small organs, such as the esophagus in SegTHOR 2019 challenge, our technique has achieved a gain of 5.

A deep learning-based quantitative computed tomography model for predicting the severity of COVID-19: a retrospective study of 196 patients

“…The infected regions on CT were quantified by uAI- Discover-NCP (beta version) developed by Shanghai United Imaging Intelligence Inc., China. The software utilized the V-shaped neural network (V-Net) (Figure 2), which is a convolutional neural network (CNN) (18), and combined it with transfer learning to segment the lung fields and infected regions on images. The procedure was carried out in two steps.…”

“…No significant differences were found in the frequency of opacities and the distribution preference in the inferior and peripheral parts of the lung between the two groups. More pulmonary segments were involved in the severe group [15 (IQR,[12][13][14][15][16][17][18] 3,4). There was no significant difference in the percentage of consolidation between the two groups.…”

Cross-Dataset Multiple Organ Segmentation From CT Imagery Using FBP-Derived Domain Adaptation

“…The V-Net [46] has achieved advanced performance in many multi-organ segmentation tasks and proposed some V-Netbased variants [47]- [49]. In this sub-section, we compared the segmentation effects on different organs without domain adaptation, histogram-based domain adaptation, and the proposed domain adaptation method under the V-Net segmentation framework.…”

CovSegNet: A Multi Encoder–Decoder Architecture for Improved Lesion Segmentation of COVID-19 Chest CT Scans

“…However, such slice-based processing loses inter-slice contextual information that results in sub-optimal performance. In [17]- [20], smaller sub-volumes are extracted from the original 3D volumes to minimize the computational burden as well as to utilize 3D contextual information. However, such methods suffer from inter-volume contextual information loss by considering a smaller portion of the whole set at a time as well as increases complexity to process sub-volume level prediction into the final result.…”

“…But, it increases computational complexity considerably which makes convergence difficult. In [19], Vnet is proposed that utilizes residual building blocks in Unet architecture, while in [20], cascaded-Vnet is presented for performance improvement that utilizes a dual-stack of the cascaded encoder-decoder module. Nevertheless, with existing numerous architectural limitations of traditional U-shaped architecture in each stage, it increases semantic gaps with the additional encoding-decoding stage as well as increases vanishing gradient issues with contextual information loss that open up opportunities for further optimization.…”