A novel biomedical image indexing and retrieval system via deep preference learning

Recent Advancements in Subcellular Proteomics: Growing Impact of Organellar Protein Niches on the Understanding of Cell Biology

The mammalian cell is a complex entity, with membrane-bound and membrane-less organelles playing vital roles in regulating cellular homeostasis. Organellar protein niches drive discrete biological processes and cell functions, thus maintaining cell equilibrium. Cellular processes such as signaling, growth, proliferation, motility, and programmed cell death require dynamic protein movements between cell compartments. Aberrant protein localization is associated with a wide range of diseases. Therefore, analyzing the subcellular proteome of the cell can provide a comprehensive overview of cellular biology. With recent advancements in mass spectrometry, imaging technology, computational tools, and deep machine learning algorithms, studies pertaining to subcellular protein localization and their dynamic distributions are gaining momentum. These studies reveal changing interaction networks because of "moonlighting proteins" and serve as a discovery tool for disease network mechanisms. Consequently, this review aims to provide a comprehensive repository for recent advancements in subcellular proteomics subcontexting methods, challenges, and future perspectives for method developers. In summary, subcellular proteomics is crucial to the understanding of the fundamental cellular mechanisms and the associated diseases.

Learning with privileged and sensitive information: a gradient-boosting approach

We consider the problem of learning with sensitive features under the privileged information setting where the goal is to learn a classifier that uses features not available (or too sensitive to collect) at test/deployment time to learn a better model at training time. We focus on tree-based learners, specifically gradient-boosted decision trees for learning with privileged information. Our methods use privileged features as knowledge to guide the algorithm when learning from fully observed (usable) features. We derive the theory, empirically validate the effectiveness of our algorithms, and verify them on standard fairness metrics.

Generating Image Captions Using Bahdanau Attention Mechanism and Transfer Learning

Automatic image caption prediction is a challenging task in natural language processing. Most of the researchers have used the convolutional neural network as an encoder and decoder. However, an accurate image caption prediction requires a model to understand the semantic relationship that exists between the various objects present in an image. The attention mechanism performs a linear combination of encoder and decoder states. It emphasizes the semantic information present in the caption with the visual information present in an image. In this paper, we incorporated the Bahdanau attention mechanism with two pre-trained convolutional neural networks—Vector Geometry Group and InceptionV3—to predict the captions of a given image. The two pre-trained models are used as encoders and the Recurrent neural network is used as a decoder. With the help of the attention mechanism, the two encoders are able to provide semantic context information to the decoder and achieve a bilingual evaluation understudy score of 62.5. Our main goal is to compare the performance of the two pre-trained models incorporated with the Bahdanau attention mechanism on the same dataset.

Deep Learning Models for Fast Retrieval and Extraction of French Speech Vocabulary Applications

Due to the large French vocabulary, how quickly retrieve and accurately identify the required vocabulary is still a big challenge in French learning. In view of the above problems, we introduce a deep learning algorithm in this study to upgrade and optimize the retrieval system of French words and optimize the acquisition speed of speech words data and the recognition accuracy of speech words, so as to meet the needs of users for word retrieval. The results show that the two training methods of SGD synchronous update network and alternate update network parameters for fast retrieval and extraction of French speech vocabulary reduce from a maximum of 11.65% to 4.25% in the WER criterion, with a maximum reduction of 7.4%; the two training methods of SGD synchronous update network and alternate update network parameters for fast retrieval and extraction of French speech vocabulary reduce from a maximum of 13.52% to 4.4% in the SER criterion. The training methods of fast retrieval and extraction of the SGD synchronous update network and alternate update network parameters in French speech vocabulary reduced from the highest 582 ms to 351 ms in the response time criterion, with a maximum reduction of 8.84%; the maximum reduction of 39.7%. In French speech vocabulary, SGD synchronous updating network and alternating updating network parameter algorithm are used to quickly retrieve and extract French words. When the number of iterations reaches 120, the model fitting accuracy of the training set reaches 90.05%, while the model can reach 94.5% in the test set. The system has a stronger generalization ability and a higher speech vocabulary recognition rate to meet the practical requirements.

Precision medical image hash retrieval by interpretability and feature fusion

BACKGROUND AND OBJECTIVE

To address the problem of low accuracy of medical image retrieval due to high inter-class similarity and easy omission of lesions, a precision medical image hash retrieval method combining interpretability and feature fusion is proposed, taking chest X-ray images as an example.

METHODS

Firstly, the DenseNet-121 network is pre-trained on a large dataset of medical images without manual annotation using the comparison to learn (C2L) method to obtain a backbone network model containing more medical representations with training weights. Then, a global network is constructed by using global image learning to acquire an interpretable saliency map as attention mechanisms, which can generate a mask crop to get a local discriminant region. Thirdly, the local discriminant regions are used as local network inputs to obtain local features, and the global features are used with the local features by dimension in the pooling layer. Finally, a hash layer is added between the fully connected layer and the classification layer of the backbone network, defining classification loss, quantization loss and bit-balanced loss functions to generate high-quality hash codes. The final retrieval result is output by calculating the similarity metric of the hash codes.

RESULTS

Experiments on the Chest X-ray8 dataset demonstrate that our proposed interpretable saliency map can effectively locate focal regions, the fusion of features can avoid information omission, and the combination of three loss functions can generate more accurate hash codes. Compared with the current advanced medical image retrieval methods, this method can effectively improve the accuracy of medical image retrieval.

CONCLUSIONS

The proposed hash retrieval approach combining interpretability and feature fusion can effectively improve the accuracy of medical image retrieval which can be potentially applied in computer-aided-diagnosis systems.

A disease category feature database construction method of brain image based on deep convolutional neural network

BACKGROUND

Constructing a medical image feature database according to the category of disease can achieve a quick retrieval of images with similar pathological features. Therefore, this approach has important application values in the fields such as auxiliary diagnosis, teaching, research, and telemedicine.

METHODS

Based on the deep convolutional neural network, an image classifier applicable to brain disease was designed to distinguish between the image features of the different brain diseases with similar anatomical structures. Through the extraction and analysis of visual features, the images were labelled with the corresponding semantic features of a specific disease category, which can establish an association between the visual features of brain images and the semantic features of the category of disease which will permit to construct a disease category feature database of brain images.

RESULTS

Based on the similarity measurement and the matching strategy of high-dimensional visual feature, a high-precision retrieval of brain image with semantics category was achieved, and the constructed disease category feature database of brain image was tested and evaluated through large numbers of pathological image retrieval experiments, the accuracy and the effectiveness of the proposed approach was verified.

CONCLUSION

The disease category feature database of brain image constructed by the proposed approach achieved a quick and effective retrieval of images with similar pathological features, which is beneficial to the categorization and analysis of intractable brain diseases. This provides an effective application tool such as case-based image data management, evidence-based medicine and clinical decision support.

An efficient architecture for medical high-resolution images transmission in mobile telemedicine systems

BACKGROUND AND OBJECTIVE

The medical high-resolution image is very important in image processing and computer vision applications, which plays a critical role in image-guided diagnosis, clinical trials, consultation, and case discussion. How to efficiently access medical high-resolution images in mobile telemedicine systems is becoming a big challenge. Therefore, this work proposes an efficient pyramid architecture for optimizing medical high-resolution images transmission and rendering.

METHODS

The proposed architecture consists of three core schemes: (1) unbalance pyramid scheme based on geometric relationship, (2) indexing scheme based on hash table and lattice partitioning and (3) query scheme based on similar matching. Then, we design the responsive service components: generating service, indexing service, and query service. Finally, these services are combined into a prototype system that enables efficient transmission and rendering of medical high-resolution images.

RESULTS

The result shows that the unbalance pyramid scheme can quickly generate the pyramid structure and the corresponding image files. The indexing scheme can create the index structure and the index file in real-time. The query scheme can not only match the best layer to which the image block belongs in real-time, but also can accurately capture the query image block.

CONCLUSIONS

The prototype system based on proposed architecture is fully compliant with the DICOM standard, which can be seamlessly integrated with other existing medical systems or mobile applications, and used in various scenarios such as diagnosis, research, and education.

Overview on subjective similarity of images for content-based medical image retrieval

Computer-aided diagnosis systems for assisting the classification of various diseases have the potential to improve radiologists' diagnostic accuracy and efficiency, as reported in several studies. Conventional systems generally provide the probabilities of disease types in terms of numerical values, a method that may not be efficient for radiologists who are trained by reading a large number of images. Presentation of reference images similar to those of a new case being diagnosed can supplement the probability outputs based on computerized analysis as an intuitive guide, and it can assist radiologists in their diagnosis, reporting, and treatment planning. Many studies on content-based medical image retrievals have been reported on. For retrieval of perceptually similar and diagnostically relevant images, incorporation of perceptual similarity data by radiologists has been suggested. In this paper, studies on image retrieval methods are reviewed with a special focus on quantification, utilization, and the evaluation of subjective similarities between pairs of images.