Increasing stimulus similarity drives nonmonotonic representational change in hippocampus

Studies of hippocampal learning have obtained seemingly contradictory results, with manipulations that increase coactivation of memories sometimes leading to differentiation of these memories, but sometimes not. These results could potentially be reconciled using the nonmonotonic plasticity hypothesis, which posits that representational change (memories moving apart or together) is a U-shaped function of the coactivation of these memories during learning. Testing this hypothesis requires manipulating coactivation over a wide enough range to reveal the full U-shape. To accomplish this, we used a novel neural network image synthesis procedure to create pairs of stimuli that varied parametrically in their similarity in high-level visual regions that provide input to the hippocampus. Sequences of these pairs were shown to human participants during high-resolution fMRI. As predicted, learning changed the representations of paired images in the dentate gyrus as a U-shaped function of image similarity, with neural differentiation occurring only for moderately similar images.

Discrete Protein Metric (DPM): A new image similarity metric to calculate accuracy of deep learning-generated cell focal adhesion predictions

Understanding cell behaviors can provide new knowledge on the development of different pathologies. Focal adhesion (FA) sites are important sub-cellular structures that are involved in these processes. To better facilitate the study of FA sites, deep learning (DL) can be used to predict FA site morphology based on limited datasets (e.g., cell membrane images). However, calculating the accuracy score of these predictions can be challenging due to the discrete/point pattern like nature of FA sites. In the present work, a new image similarity metric, discrete protein metric (DPM), was developed to calculate FA prediction accuracy. This metric measures differences in distribution (d), shape/size (s), and angle (a) of FA sites between the predicted image and its ground truth image. Performance of the DPM was evaluated by comparing it to three other commonly used image similarity metrics: Pearson correlation coefficient (PCC), feature similarity index (FSIM), and Intersection over Union (IoU). A sensitivity analysis was performed by comparing changes in each metric value due to quantifiable changes in FA site location, number, aspect ratio, area, or orientation. Furthermore, accuracy score of DL-generated predictions was calculated using all four metrics to compare their ability to capture variation across samples. Results showed better sensitivity and range of variation for DPM compared to the other metrics tested. Most importantly, DPM had the ability to determine which FA predictions were quantitatively more accurate and consistent with qualitative assessments. The proposed DPM hence provides a method to validate DL-generated FA predictions and can be extended to evaluating other predicted or segmented discrete structures of biomedical relevance.

Automatic Algorithm for Fractal Plant Art Image Similarity Feature Generation

With the popularity of smart devices and the Internet, the volume of multimedia data is growing rapidly, and content-based image retrieval (CBIR) can search for similar images from large-scale images to realize the utilization of the data. For data owners, outsourcing the management and maintenance of image data to cloud service providers can effectively reduce costs, but there is a privacy leakage problem. In this paper, we focus on image feature extraction, index design, and image similarity recognition methods under a dual server model with content-based image security similarity recognition as the research topic, the work done such as proposing a BOVW (Bag of Visual Word) feature-based image security similarity recognition scheme. The scheme combines SIFT (scale-invariant feature transform) feature secure extraction and locally sensitive hashing algorithm to achieve secure extraction of BOVW features of images. To protect the BOVW features of images, an inverted index based on word frequency division is designed, the index is stored in chunks, and an image secure similarity recognition scheme based on CNN (convolutional neural networks) features is proposed. The scalable hash index based on dimensional division is designed based on the image CNN features secure extraction algorithm. The security and performance of the proposed scheme are theoretically analyzed and experimentally verified. Based on different image datasets, the impact of different parameters on the performance of the scheme is tested, and optimized parameters are given. The experimental results show that the proposed scheme in this paper can effectively improve the efficiency of analyzing the similarity of plant botanical art images compared to the existing schemes.

ENRICH: Exploiting Image Similarity to Maximize Efficient Machine Learning in Medical Imaging

Deep learning (DL) requires labeled data. Labeling medical images requires medical expertise, which is often a bottleneck. It is therefore useful to prioritize labeling those images that are most likely to improve a model's performance, a practice known as instance selection. Here we introduce ENRICH, a method that selects images for labeling based on how much novelty each image adds to the growing training set. In our implementation, we use cosine similarity between autoencoder embeddings to measure that novelty. We show that ENRICH achieves nearly maximal performance on classification and segmentation tasks using only a fraction of available images, and outperforms the default practice of selecting images at random. We also present evidence that instance selection may perform categorically better on medical vs. non-medical imaging tasks. In conclusion, ENRICH is a simple, computationally efficient method for prioritizing images for expert labeling for DL.

Symmetry-aware recursive image similarity exploration for materials microscopy

In pursuit of scientific discovery, vast collections of unstructured structural and functional images are acquired; however, only an infinitesimally small fraction of this data is rigorously analyzed, with an even smaller fraction ever being published. One method to accelerate scientific discovery is to extract more insight from costly scientific experiments already conducted. Unfortunately, data from scientific experiments tend only to be accessible by the originator who knows the experiments and directives. Moreover, there are no robust methods to search unstructured databases of images to deduce correlations and insight. Here, we develop a machine learning approach to create image similarity projections to search unstructured image databases. To improve these projections, we develop and train a model to include symmetry-aware features. As an exemplar, we use a set of 25,133 piezoresponse force microscopy images collected on diverse materials systems over five years. We demonstrate how this tool can be used for interactive recursive image searching and exploration, highlighting structural similarities at various length scales. This tool justifies continued investment in federated scientific databases with standardized metadata schemas where the combination of filtering and recursive interactive searching can uncover synthesis-structure-property relations. We provide a customizable open-source package (https://github.com/m3-learning/Recursive_Symmetry_Aware_Materials_Microstructure_Explorer) of this interactive tool for researchers to use with their data.

Research and Modeling Electronic Data Tracing Scheme Based on Blockchain

From the point of view that the traditional electronic data (documents in image, PDF, etc) is difficult to track and trace, taking image copyright as an example, this paper studies a new scheme to solve the problem of replication detection and traceability based on blockchain. With the decentralization and trust removing of blockchain, both copyright storage and evidence of infringement are stored in a tamper proof and transparent way. Based on the judgment of image similarity, a “resource reverse tracing strategy” is designed to control the infringement timely. The infringement evidence can reach the creator quickly, which provides convenience for the creator’s rights protection. This method changes traditional tracing methods of image copyright. Also, it can be applied to the tracing problem of reuse of electronic invoice, short video, music, etc, and brings new ideas for the related problem.