Background Accurate segmentation of head and neck squamous cell cancer (HNSCC) is important for radiotherapy treatment planning. Manual segmentation of these tumors is time-consuming and vulnerable to inconsistencies ...
详细信息
Background Accurate segmentation of head and neck squamous cell cancer (HNSCC) is important for radiotherapy treatment planning. Manual segmentation of these tumors is time-consuming and vulnerable to inconsistencies between experts, especially in the complex head and neck region. The aim of this study is to introduce and evaluate an automatic segmentation pipeline for HNSCC using a multi-view CNN (MV-CNN). Methods The dataset included 220 patients with primary HNSCC and availability of T1-weighted, STIR and optionally contrast-enhanced T1-weighted MR images together with a manual reference segmentation of the primary tumor by an expert. A T1-weighted standard space of the head and neck region was created to register all MRI sequences to. An MV-CNN was trained with these three MRI sequences and evaluated in terms of volumetric and spatial performance in a cross-validation by measuring intra-class correlation (ICC) and dice similarity score (DSC), respectively. Results The average manual segmented primary tumor volume was 11.8 +/- 6.70 cm(3) with a median [IQR] of 13.9 [3.22-15.9] cm(3). The tumor volume measured by MV-CNN was 22.8 +/- 21.1 cm(3) with a median [IQR] of 16.0 [8.24-31.1] cm(3). Compared to the manual segmentations, the MV-CNN scored an average ICC of 0.64 +/- 0.06 and a DSC of 0.49 +/- 0.19. Improved segmentation performance was observed with increasing primary tumor volume: the smallest tumor volume group (<3 cm(3)) scored a DSC of 0.26 +/- 0.16 and the largest group (>15 cm(3)) a DSC of 0.63 +/- 0.11 (p<0.001). The automated segmentation tended to overestimate compared to the manual reference, both around the actual primary tumor and in false positively classified healthy structures and pathologically enlarged lymph nodes. Conclusion An automatic segmentation pipeline was evaluated for primary HNSCC on MRI. The MV-CNN produced reasonable segmentation results, especially on large tumors, but overestimation decreased overall performance. In further res
To make full use of the effective discriminative information of the non-rigid 3D model, we propose a novel multi-feature fusion method to fuse the multi-view feature and the 3D shape feature and apply it in a non-rigi...
详细信息
To make full use of the effective discriminative information of the non-rigid 3D model, we propose a novel multi-feature fusion method to fuse the multi-view feature and the 3D shape feature and apply it in a non-rigid 3D model retrieval. First, we compute the canonical form of the non-rigid 3D model using the biharmonic distance-based least-squares multidimensional scaling (LS-MDS) algorithm and generate multiple projective depth images. The learning-based multiple pooling fusion methods is used in the multi-view convolutional neural network to reduce the information loss and extract more effective multi-view feature. Then, we compute the wave kernel signature of each vertex and construct the multi-energy shape distribution of the non-rigid 3D model. The convolutionalneuralnetwork is used for learning the 3D shape feature. Finally, we use the kernel canonical correlation analysis (KCCA) algorithm to fuse the multi-view feature and the 3D shape feature for retrieval. Our experimental results have shown that compared with the geodesic distance-based LS-MDS algorithm, the biharmonic distance-based LS-MDS algorithm has higher computation efficiency and better performance. Compared with other state-of-the-art methods, our proposed method can make better use of the two kinds of features and has achieved better retrieval results.
This paper presents a multi-view deep metric learning (MVDML) architecture for the recognition of volumetric image stacks. Different from existing metric learning methods which aim to learn a Mahalanobis distance metr...
详细信息
ISBN:
(纸本)9781538617373
This paper presents a multi-view deep metric learning (MVDML) architecture for the recognition of volumetric image stacks. Different from existing metric learning methods which aim to learn a Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, the proposed multi-view deep metric learning approach learns a function that maps input volumetric images into a compact Euclidean space where distances approximate the "semantic" distances in the input space. The learning process minimizes a contrastive loss function that drives the similarity metric to be small for pairs of samples from same class, and large for pairs from different classes. The mapping from input to the target space is a multi-view convolutional neural network (MVCNN) which combines information from multiple views of a volumetric image into a single and compact feature descriptor. The experimental results on the nematode volumetric image database show that our proposed method outperforms models based on hand-crafted visual features, conventional metric learning methods and deep classification models.
This paper presents a multi-view deep metric learning (MVDML) architecture for the recognition of volumetric image stacks. Different from existing metric learning methods which aim to learn a Mahalanobis distance metr...
详细信息
This paper presents a multi-view deep metric learning (MVDML) architecture for the recognition of volumetric image stacks. Different from existing metric learning methods which aim to learn a Mahalanobis distance metric to maximize the inter-class variations and minimize the intra-class variations, the proposed multi-view deep metric learning approach learns a function that maps input volumetric images into a compact Euclidean space where distances approximate the "semantic" distances in the input space. The learning process minimizes a contrastive loss function that drives the similarity metric to be small for pairs of samples from same class, and large for pairs from different classes. The mapping from input to the target space is a multi-view convolutional neural network (MVCNN) which combines information from multiple views of a volumetric image into a single and compact feature descriptor. The experimental results on the nematode volumetric image database show that our proposed method outperforms models based on hand-crafted visual features, conventional metric learning methods and deep classification models.
暂无评论