Radiological images and machine learning: Trends, perspectives, and prospects.

3D mesh subdivision is essential for geometry modeling of complex surfaces, which benefits many important applications in the fields of multimedia such as computer animation. However, in the ordinary adaptive subdivision, with the deepening of the subdivision level, the benefits gained from the improvement of smoothness cannot keep pace with the cost caused by the incremental number of faces. To mitigate the gap between the smoothness and the number of faces, this paper devises a novel improved mesh subdivision method to coordinate the smoothness and the number of faces in a harmonious way. First, this paper introduces a variable threshold, rather than a constant threshold used in existing adaptive subdivision methods, to reduce the number of redundant faces while keeping the smoothness in each subdivision iteration. Second, to achieve the above goal, a new crack-solving method is developed to remove the cracks by refining the adjacent faces of the subdivided area. Third, as a result, the problem of coordinating the smoothness and the number of faces can be formulated as a multi-objective optimization problem, in which the possible threshold sequences constitute the solution space. Finally, the Non-dominated sorting genetic algorithm II (NSGA-II) is improved to efficiently search the Pareto frontier. Extensive experiments demonstrate that the proposed method consistently outperforms existing mesh subdivision methods in different settings.

An improved Loop subdivision to coordinate the smoothness and the number of faces via multi-objective optimization

A deep community based approach for large scale content based X-ray image retrieval.

The fine-grained classification or grading of breast cancer pathological images is of great value in clinical application. However, the manual feature extraction methods not only require professional knowledge, but also the cost of feature extraction is high, especially the high quality features. In this paper, we devise an improved deep convolution neural network model to achieve accurate fine-grained classification or grading of breast cancer pathological images. Meanwhile, we use online data augmentation and transfer learning strategy to avoid model overfitting. According to the issue that small inter-class variance and large intra-class variance exist in breast cancer pathological images, multi-class recognition task and verification task of image pair are combined in the representation learning process; in addition, the prior knowledge (different subclasses with relatively large distance and small distance between the same subclass) are embedded in the process of feature extraction. At the same time, the prior information that pathological images with different magnification belong to the same subclass will be embedded in the feature extraction process, which will lead to less sensitive with image magnification. Experimental results on two different pathological image datasets show that the performance of our method is better than that of state-of-the-arts, with good robustness and generalization ability.

Multi-task Deep Learning for Fine-Grained Classification/Grading in Breast Cancer Histopathological Images

Computed tomography image (CTI) sequence is essentially a time-series data that typically consists of a large amount of nearby and similar CTIs. Due to the high communication and computational costs, it is difficult to perform a progressive distributed similarity retrieval of the large CTI sequence (CTIS)s, particularly in resource-constraint mobile telemedicine network (MTN)s. In this paper, we present a Dprs method—progressive distributed and parallel similarity retrieval scheme for the CTISs in the MTN. To the best of our knowledge, there is little research on the Dprs processing, especially in the MTN. Four supporting techniques (i.e., (1) PCTI-based similarity measurement, (2) lightweight privacy-preserving strategy, (3) SSL-based data distribution scheme, and (4) the UDI framework) are developed. The experimental evaluation indicates that our proposed Dprs method is more progressive than the state of the art, with a significant reduction in response time.

/pdf/progressive-distributed-and-parallel-similarity-retrieval-of-1yng1ojs.pdf

Progressive Distributed and Parallel Similarity Retrieval of Large CT Image Sequences in Mobile Telemedicine Networks

Texture characteristic is an important attribute of medical images, and has been applied in many medical image applications. This paper proposes a simple approach to employ the texture features of medical images for retrieval. The developed approach first conducts image filtering to medical images using different Gabor and Schmid filters, and then uniformly partitions the filtered images into non-overlapping patches. These operations provide extensive local texture information of medical images. The bag-of-words model is finally used to obtain feature representations of the images. Compared with several existing features, the proposed one is more discriminative and efficient. Experiments on two benchmark medical CT image databases have demonstrated the effectiveness of the proposed approach.

https://link.springer.com/content/pdf/10.1007%2Fs11042-017-5341-2.pdf

A simple texture feature for retrieval of medical images

It is a challenging task to distinguish between numerous species of flowers due to their visually similarities and variations of the pose and structure. Thanks to properly modeling of the local feature interactions, bilinear CNN has succeeded in classifying of many non-rigid fine-grained species including flowers. However, bilinear CNN only computes the feature in a straightforward way without exploring the interactions between features from multiple layers in the network. In this paper, we present a novel Bilinear Pyramid Network (BPN) for flower categorization. Instead of passing through the network and directly feeding the final classifier, features from a convolutional layer are resized and multiplied with that from the former layer, which alternates multiple times to generates prediction vectors using the features from distinct layers. These features encoded from the feature pyramid spontaneously carry multi-level semantic cues, which yields stronger discriminative powers than single-layer features. Experiments show that the proposed network obtains superior classification results on the challenging dataset of flowers.

Bilinear pyramid network for flower species categorization

In this paper, we propose a fast and accurate dihedral interpolation Loop subdivision scheme for subdivision surfaces based on triangular meshes. In order to solve the problem of surface shrinkage, we keep the limit condition unchanged, which is important. Extraordinary vertices are handled using modified Butterfly rules. Subdivision schemes are computationally costly as the number of faces grows exponentially at higher levels of subdivision. To address this problem, our approach is to use local surface information to adaptively refine the model. This is achieved simply by changing the threshold value of the dihedral angle parameter, i.e., the angle between the normals of a triangular face and its adjacent faces. We then demonstrate the effectiveness of the proposed method for various 3D graphic triangular meshes, and extensive experimental results show that it can match or exceed the expected results at lower computational cost.

Zhuo Shi

Papers

A simple texture feature for retrieval of medical images

Bilinear pyramid network for flower species categorization

A fast and accurate dihedral interpolation loop subdivision scheme

NPIPVis: A Visualization System Involving NBA Visual Analysis and Integrated Learning Model Prediction