Diffusion kurtosis imaging provides quantitative assessment of the microstructure changes of disc degeneration: an in vivo experimental study.

OBJECTIVE: Our aim was to assess the microstructural changes of intervertebral disc degeneration induced by annulus needle puncture in rats by diffusion kurtosis imaging (DKI). METHODS: Eighteen rats (36 discs) were punctured percutaneously at the intervertebral disc between C6/7, C7/8 (C-coccygeal vertebrae) with a 21-gauge needle. The rats were divided into six groups according to the time after the puncture: 3 h, 48 h, 3 days, 7 days, 10 days and 14 days. There were six discs in three rats in the control group. The rats' tail was imaged at 3T MRI with T2-weighted and diffusion-weighted and diffusion kurtosis imaging (DWI)/DKI sequences. The discs were categorized using a five-grade degeneration system based on the T2 images. The height of the discs and the parameters in DWI/DKI were measured and compared between the different time points. The histological images were also obtained from the discs. RESULTS: The histological study revealed that the discs in the rat of the punctured groups were degenerated. The T2 grades of different groups presented an increasing trend from 7 to 10 days after puncture (R2 = 0.9424, P < 0.001), while the DWI/DKI parameters changes were consistent with the histological changes at the different time points and showed significant differences between the different groups (P < 0.05). CONCLUSIONS: DKI provides quantitative assessment of the microstructure changes of disc degeneration, and it is a non-invasive method. The DKI multi-parameter analysis is sensitive to discs changes caused by puncture. These slides can be retrieved under Electronic Supplementary Material.

Label propagation via local geometry preserving for deep semi-supervised image recognition.

In this paper, we propose a novel transductive pseudo-labeling based method for deep semi-supervised image recognition. Inspired from the superiority of pseudo labels inferred by label propagation compared with those inferred from network, we argue that information flow from labeled data to unlabeled data should be kept noiseless and with minimum loss. Previous research works use scarce labeled data for feature learning and solely consider the relationship between two feature vectors to construct the similarity graph in feature space, which causes two problems that ultimately lead to noisy and incomplete information flow from labeled data to unlabeled data. The first problem is that the learned feature mapping is highly likely to be biased and can easily over-fit noise. The second problem is the loss of local geometry information in feature space during label propagation. Accordingly, we firstly propose to incorporate self-supervised learning into feature learning for cleaner information flow in feature space during subsequent label propagation. Secondly, we propose to use reconstruction concept to measure pairwise similarity in feature space, such that local geometry information can be preserved. Ablation study confirms synergistic effects from features learned with self-supervision and similarity graph with local geometry preserving. Extensive experiments conducted on benchmark datasets have verified the effectiveness of our proposed method.

End-to-end novel visual categories learning via auxiliary self-supervision.

Semi-supervised learning has largely alleviated the strong demand for large amount of annotations in deep learning. However, most of the methods have adopted a common assumption that there is always labeled data from the same class of unlabeled data, which is impractical and restricted for real-world applications. In this research work, our focus is on semi-supervised learning when the categories of unlabeled data and labeled data are disjoint from each other. The main challenge is how to effectively leverage knowledge in labeled data to unlabeled data when they are independent from each other, and not belonging to the same categories. Previous state-of-the-art methods have proposed to construct pairwise similarity pseudo labels as supervising signals. However, two issues are commonly inherent in these methods: (1) All of previous methods are comprised of multiple training phases, which makes it difficult to train the model in an end-to-end fashion. (2) Strong dependence on the quality of pairwise similarity pseudo labels limits the performance as pseudo labels are vulnerable to noise and bias. Therefore, we propose to exploit the use of self-supervision as auxiliary task during model training such that labeled data and unlabeled data will share the same set of surrogate labels and overall supervising signals can have strong regularization. By doing so, all modules in the proposed algorithm can be trained simultaneously, which will boost the learning capability as end-to-end learning can be achieved. Moreover, we propose to utilize local structure information in feature space during pairwise pseudo label construction, as local properties are more robust to noise. Extensive experiments have been conducted on three frequently used visual datasets, i.e., CIFAR-10, CIFAR-100 and SVHN, in this paper. Experiment results have indicated the effectiveness of our proposed algorithm as we have achieved new state-of-the-art performance for novel visual categories learning for these three datasets.