Full Pipeline Research Articles

Towards improved breast mass detection using dual-view mammogram matching.

Breast cancer screening benefits from the visual analysis of multiple views of routine mammograms. As for clinical practice, computer-aided diagnosis (CAD) systems could be enhanced by integrating multi-view information. In this work, we propose a new multi-tasking framework that combines craniocaudal (CC) and mediolateral-oblique (MLO) mammograms for automatic breast mass detection. Rather than addressing mass recognition only, we exploit multi-tasking properties of deep networks to jointly learn mass matching and classification, towards better detection performance. Specifically, we propose a unified Siamese network that combines patch-level mass/non-mass classification and dual-view mass matching to take full advantage of multi-view information. This model is exploited in a full image detection pipeline based on You-Only-Look-Once (YOLO) region proposals. We carry out exhaustive experiments to highlight the contribution of dual-view matching for both patch-level classification and examination-level detection scenarios. Results demonstrate that mass matching highly improves the full-pipeline detection performance by outperforming conventional single-task schemes with 94.78% as Area Under the Curve (AUC) score and a classification accuracy of 0.8791. Interestingly, mass classification also improves the performance of mass matching, which proves the complementarity of both tasks. Our method further guides clinicians by providing accurate dual-view mass correspondences, which suggests that it could act as a relevant second opinion for mammogram interpretation and breast cancer diagnosis.

Optimized permutation testing for information theoretic measures of multi-gene interactions

BackgroundPermutation testing is often considered the “gold standard” for multi-test significance analysis, as it is an exact test requiring few assumptions about the distribution being computed. However, it can be computationally very expensive, particularly in its naive form in which the full analysis pipeline is re-run after permuting the phenotype labels. This can become intractable in multi-locus genome-wide association studies (GWAS), in which the number of potential interactions to be tested is combinatorially large.ResultsIn this paper, we develop an approach for permutation testing in multi-locus GWAS, specifically focusing on SNP–SNP-phenotype interactions using multivariable measures that can be computed from frequency count tables, such as those based in Information Theory. We find that the computational bottleneck in this process is the construction of the count tables themselves, and that this step can be eliminated at each iteration of the permutation testing by transforming the count tables directly. This leads to a speed-up by a factor of over 103 for a typical permutation test compared to the naive approach. Additionally, this approach is insensitive to the number of samples making it suitable for datasets with large number of samples.ConclusionsThe proliferation of large-scale datasets with genotype data for hundreds of thousands of individuals enables new and more powerful approaches for the detection of multi-locus genotype-phenotype interactions. Our approach significantly improves the computational tractability of permutation testing for these studies. Moreover, our approach is insensitive to the large number of samples in these modern datasets. The code for performing these computations and replicating the figures in this paper is freely available at https://github.com/kunert/permute-counts.

A New Message Expansion Structure for Full Pipeline SHA-2

Once there are constant or infrequently changed bits (COIBs) in two adjacent input messages of SHA-2, the switching power of input messages data registers (IMD-REGs) used for COIBs will disappear. Meanwhile, when full pipeline SHA-2 is applied in a certain application scenario where the IMD-REGs used for COIBs can be removed, more area of full pipeline SHA-2 can be saved as the proportion of IMD-REGs in message word registers increases. This paper proposes a new message expansion structure for full pipeline SHA-2 to increase the proportion of IMD-REGs. By inserting two expanders in last part of expansion structure pipeline stages and rescheduling the expander, the consumption rate of input messages will be decreased and the proportion of IMD-REGs will be increased. Compared with normal message expansion structure, the ratio of IMD-REGs to total message word registers in the proposed structure is increased from 15.1% to 41.6% for full pipeline SHA256, and 11.2% to 32.4% for full pipeline SHA512. When COIBs exists in adjacent input messages, the power and area advantages of proposed new message expansion structure have been demonstrated by FPGA and ASIC implementations.

Multi-View Object Pose Refinement With Differentiable Renderer

This paper introduces a novel multi-view 6 DoF object pose refinement approach focusing on improving methods trained on synthetic data. It is based on the DPOD detector, which produces dense 2D-3D correspondences between the model vertices and the image pixels in each frame. We have opted for the use of multiple frames with known relative camera transformations, as it allows introduction of geometrical constraints via an interpretable ICP-like loss function. The loss function is implemented with a differentiable renderer and is optimized iteratively. We also demonstrate that a full detection and refinement pipeline, which is trained solely on synthetic data, can be used for auto-labeling real data. We perform quantitative evaluation on LineMOD, Occlusion, Homebrewed and YCB-V datasets and report excellent performance in comparison to the state-of-the-art methods trained on the synthetic and real data. We demonstrate empirically that our approach requires only a few frames and is robust to close camera locations and noise in extrinsic camera calibration, making its practical usage easier and more ubiquitous.

SuperThermal: Matching Thermal as Visible Through Thermal Feature Exploration

Infrared Radiation (IR) images that capture the reflected IR signals from the surrounding environment have been applied to pedestrian detection and rescue tasks, especially for thermal images reflecting the surface temperature of the objects at nighttime. However, feature detection, extraction and matching are particularly challenging on thermal images as there are few textures compared to normal RGB images, which brings in an enormous gap in introducing various computer vision tasks such as image matching and retrieval, visual localization and SLAM. In this letter, we propose to design a full pipeline to learn a reliable and robust feature detector and descriptor. Our model trained on cross-spectral stereo and KAIST dataset is able to realize a reliable and accurate matching without further annotations. The proposed method is demonstrated to have superior performance compared with both widely used hand-crafted features and features extracted from the most recent learning-based models on visual and quantitative experiments. It also shows a good generalization and robustness ability on FLIR thermal benchmark even without training or fine-tuning on it.

Differential Replication for Credit Scoring in Regulated Environments.

Differential replication is a method to adapt existing machine learning solutions to the demands of highly regulated environments by reusing knowledge from one generation to the next. Copying is a technique that allows differential replication by projecting a given classifier onto a new hypothesis space, in circumstances where access to both the original solution and its training data is limited. The resulting model replicates the original decision behavior while displaying new features and characteristics. In this paper, we apply this approach to a use case in the context of credit scoring. We use a private residential mortgage default dataset. We show that differential replication through copying can be exploited to adapt a given solution to the changing demands of a constrained environment such as that of the financial market. In particular, we show how copying can be used to replicate the decision behavior not only of a model, but also of a full pipeline. As a result, we can ensure the decomposability of the attributes used to provide explanations for credit scoring models and reduce the time-to-market delivery of these solutions.

Evolving Fully Automated Machine Learning via Life-Long Knowledge Anchors

Automated machine learning (AutoML) has achieved remarkable progress on various tasks, which is attributed to its minimal involvement of manual feature and model designs. However, most of existing AutoML pipelines only touch parts of the full machine learning pipeline, e.g., neural architecture search or optimizer selection. This leaves potentially important components such as data cleaning and model ensemble out of the optimization, and still results in considerable human involvement and suboptimal performance. The main challenges lie in the huge search space assembling all possibilities over all components, as well as the generalization ability over different tasks like image, text, and tabular etc. In this paper, we present a first-of-its-kind fully AutoML pipeline, to comprehensively automate data preprocessing, feature engineering, model generation/selection/training and ensemble for an arbitrary dataset and evaluation metric. Our innovation lies in the comprehensive scope of a learning pipeline, with a novel "life-long" knowledge anchor design to fundamentally accelerate the search over the full search space. Such knowledge anchors record detailed information of pipelines and integrates them with an evolutionary algorithm for joint optimization across components. Experiments demonstrate that the result pipeline achieves state-of-the-art performance on multiple datasets and modalities. Specifically, the proposed framework was extensively evaluated in the NeurIPS 2019 AutoDL challenge, and won the only champion with a significant gap against other approaches, on all the image, video, speech, text and tabular tracks.

High-throughput virtual laboratory for drug discovery using massive datasets

Time-to-solution for structure-based screening of massive chemical databases for COVID-19 drug discovery has been decreased by an order of magnitude, and a virtual laboratory has been deployed at scale on up to 27,612 GPUs on the Summit supercomputer, allowing an average molecular docking of 19,028 compounds per second. Over one billion compounds were docked to two SARS-CoV-2 protein structures with full optimization of ligand position and 20 poses per docking, each in under 24 hours. GPU acceleration and high-throughput optimizations of the docking program produced 350× mean speedup over the CPU version (50× speedup per node). GPU acceleration of both feature calculation for machine-learning based scoring and distributed database queries reduced processing of the 2.4 TB output by orders of magnitude. The resulting 50× speedup for the full pipeline reduces an initial 43 day runtime to 21 hours per protein for providing high-scoring compounds to experimental collaborators for validation assays.

Bayesian Particle Instance Segmentation for Electron Microscopy Image Quantification.

Automating the analysis portion of materials characterization by electron microscopy (EM) has the potential to accelerate the process of scientific discovery. To this end, we present a Bayesian deep-learning model for semantic segmentation and localization of particle instances in EM images. These segmentations can subsequently be used to compute quantitative measures such as particle-size distributions, radial- distribution functions, average sizes, and aspect ratios of the particles in an image. Moreover, by making use of the epistemic uncertainty of our model, we obtain uncertainty estimates of its outputs and use these to filter out false-positive predictions and hence produce more accurate quantitative measures. We incorporate our method into the ImageDataExtractor package, as ImageDataExtractor 2.0, which affords a full pipeline to automatically extract particle information for large-scale data-driven materials discovery. Finally, we present and make publicly available the Electron Microscopy Particle Segmentation (EMPS) data set. This is the first human-labeled particle instance segmentation data set, consisting of 465 EM images and their corresponding semantic instance segmentation maps.

Spoken Instruction Understanding in Air Traffic Control: Challenge, Technique, and Application

In air traffic control (ATC), speech communication with radio transmission is the primary way to exchange information between the controller and aircrew. A wealth of contextual situational dynamics is embedded implicitly; thus, understanding the spoken instruction is particularly significant to the ATC research. In this paper, a comprehensive review related to spoken instruction understanding (SIU) in the ATC domain is provided from the perspective of the challenges, techniques, and applications. Firstly, a full pipeline is represented to achieve the SIU task, including automatic speech recognition, language understanding, and voiceprint recognition. A total of 10 technique challenges are analyzed based on the ATC task specificities. In succession, the common techniques for SIU tasks are categorized from common applications, and extensive works in the ATC domain are also reviewed. Finally, a series of future research topics are also prospected based on the corresponding challenges. The author sincerely hopes that this work is able to provide a clear technical roadmap for the SIU tasks in the ATC domain and further make contributions to the research community.

Hierarchical Inference with Bayesian Neural Networks: An Application to Strong Gravitational Lensing

Abstract In the past few years, approximate Bayesian Neural Networks (BNNs) have demonstrated the ability to produce statistically consistent posteriors on a wide range of inference problems at unprecedented speed and scale. However, any disconnect between training sets and the distribution of real-world objects can introduce bias when BNNs are applied to data. This is a common challenge in astrophysics and cosmology, where the unknown distribution of objects in our universe is often the science goal. In this work, we incorporate BNNs with flexible posterior parameterizations into a hierarchical inference framework that allows for the reconstruction of population hyperparameters and removes the bias introduced by the training distribution. We focus on the challenge of producing posterior PDFs for strong gravitational lens mass model parameters given Hubble Space Telescope–quality single-filter, lens-subtracted, synthetic imaging data. We show that the posterior PDFs are sufficiently accurate (statistically consistent with the truth) across a wide variety of power-law elliptical lens mass distributions. We then apply our approach to test data sets whose lens parameters are drawn from distributions that are drastically different from the training set. We show that our hierarchical inference framework mitigates the bias introduced by an unrepresentative training set’s interim prior. Simultaneously, we can precisely reconstruct the population hyperparameters governing our test distributions. Our full pipeline, from training to hierarchical inference on thousands of lenses, can be run in a day. The framework presented here will allow us to efficiently exploit the full constraining power of future ground- and space-based surveys (https://github.com/swagnercarena/ovejero).

Robust Uncalibrated Rectification With Low Geometric Distortion Under Unbalanced Field of View Circumstances

Rectification is a standard process in every system that requires multiviews. Existing algorithms largely work on similar field of view (FoV) cases where the two views are mostly identical. Dissimilarities between different FoVs can generate unexpected errors during the optimization process, resulting in a large amount of rectification errors and unwanted geometric distortion. In this study, we present a full pipeline to rectify uncalibrated images captured by cameras that have dissimilar FoVs under the constraints of geometric distortion. The proposed method contains two main parts: Field of View Neutralization and Rectification with Adaptive Geometric Constraints. The Field of View Neutralization module estimates the transformation matrix to compensate for the imbalance between different views. In addition, this module improves the overall quality of correspondences by removing misleading feature matching pairs. Finally, by applying an adaptive optimization process with the geometric constraints involved, our method addresses the overdistortion issue while maintaining small rectification errors. Extensive experiments are conducted to demonstrate the robust performance of the proposed method. Besides the existing datasets, we provide our dissimilar FoVs dataset with multiple baselines to examine the performance. Our method outperforms the existing algorithms in terms of both rectification errors and geometric distortion rates.

Diabetes detection using deep learning techniques with oversampling and feature augmentation

Background and objective: Diabetes is a chronic pathology which is affecting more and more people over the years. It gives rise to a large number of deaths each year. Furthermore, many people living with the disease do not realize the seriousness of their health status early enough. Late diagnosis brings about numerous health problems and a large number of deaths each year so the development of methods for the early diagnosis of this pathology is essential.Methods: In this paper, a pipeline based on deep learning techniques is proposed to predict diabetic people. It includes data augmentation using a variational autoencoder (VAE), feature augmentation using an sparse autoencoder (SAE) and a convolutional neural network for classification. Pima Indians Diabetes Database, which takes into account information on the patients such as the number of pregnancies, glucose or insulin level, blood pressure or age, has been evaluated.Results: A 92.31% of accuracy was obtained when CNN classifier is trained jointly the SAE for featuring augmentation over a well balanced dataset. This means an increment of 3.17% of accuracy with respect the state-of-the-art.Conclusions: Using a full deep learning pipeline for data preprocessing and classification has demonstrate to be very promising in the diabetes detection field outperforming the state-of-the-art proposals.

Multithreaded variant calling in elPrep 5.

We present elPrep 5, which updates the elPrep framework for processing sequencing alignment/map files with variant calling. elPrep 5 can now execute the full pipeline described by the GATK Best Practices for variant calling, which consists of PCR and optical duplicate marking, sorting by coordinate order, base quality score recalibration, and variant calling using the haplotype caller algorithm. elPrep 5 produces identical BAM and VCF output as GATK4 while significantly reducing the runtime by parallelizing and merging the execution of the pipeline steps. Our benchmarks show that elPrep 5 speeds up the runtime of the variant calling pipeline by a factor 8-16x on both whole-exome and whole-genome data while using the same hardware resources as GATK4. This makes elPrep 5 a suitable drop-in replacement for GATK4 when faster execution times are needed.

A privacy‐focused approach for anomaly detection in IoT networks

SummaryIoT devices present a series of liabilities to administrators that aim for fully secure networks. Owing to their heterogeneity and limited processing power, administrators often implement monitoring mechanisms to prevent unauthorized use of resources and data exfiltration. However, most approaches allow for easy discrimination of private behavioral patterns of its users or nodes by their MAC or IP addresses. Inferring data exchange patterns at the physical layer is a more complex task, as a single signal power indicator may correspond to a mixture of simultaneous data transmissions. This article proposes privacy‐focused mechanisms by resorting to physical layer data analysis and one‐class classification models to perform anomaly detection in IoT networks. We present a full processing pipeline that considers the signal that identifies and models patterns on the channel activity and silence periods. We train our models with data captured from interactions with an Amazon Echo with devices generating background noise and test them against a similar scenario with a tampered network node periodically uploading data. Our data show that the best performing model, kernel density estimation, is able to detect anomalies with a 99% precision rate, even surpassing the tested neural networks approaches. We also propose a framework that aims to deploy validated models into production IoT environments. We designed an end‐to‐end data flow that autonomously extracts data and classifies them at the anomaly detection server. The envisioned components were designed to be horizontally scaled for a myriad of data streams and machine learning algorithms working in parallel.

MIScnn: a framework for medical image segmentation with convolutional neural networks and deep learning

BackgroundThe increased availability and usage of modern medical imaging induced a strong need for automatic medical image segmentation. Still, current image segmentation platforms do not provide the required functionalities for plain setup of medical image segmentation pipelines. Already implemented pipelines are commonly standalone software, optimized on a specific public data set. Therefore, this paper introduces the open-source Python library MIScnn.ImplementationThe aim of MIScnn is to provide an intuitive API allowing fast building of medical image segmentation pipelines including data I/O, preprocessing, data augmentation, patch-wise analysis, metrics, a library with state-of-the-art deep learning models and model utilization like training, prediction, as well as fully automatic evaluation (e.g. cross-validation). Similarly, high configurability and multiple open interfaces allow full pipeline customization.ResultsRunning a cross-validation with MIScnn on the Kidney Tumor Segmentation Challenge 2019 data set (multi-class semantic segmentation with 300 CT scans) resulted into a powerful predictor based on the standard 3D U-Net model.ConclusionsWith this experiment, we could show that the MIScnn framework enables researchers to rapidly set up a complete medical image segmentation pipeline by using just a few lines of code. The source code for MIScnn is available in the Git repository: https://github.com/frankkramer-lab/MIScnn.

Image-Based Automatic Watermeter Reading under Challenging Environments.

With the rapid development of artificial intelligence and fifth-generation mobile network technologies, automatic instrument reading has become an increasingly important topic for intelligent sensors in smart cities. We propose a full pipeline to automatically read watermeters based on a single image, using deep learning methods to provide new technical support for an intelligent water meter reading. To handle the various challenging environments where watermeters reside, our pipeline disentangled the task into individual subtasks based on the structures of typical watermeters. These subtasks include component localization, orientation alignment, spatial layout guidance reading, and regression-based pointer reading. The devised algorithms for orientation alignment and spatial layout guidance are tailored to improve the robustness of our neural network. We also collect images of watermeters in real scenes and build a dataset for training and evaluation. Experimental results demonstrate the effectiveness of the proposed method even under challenging environments with varying lighting, occlusions, and different orientations. Thanks to the lightweight algorithms adopted in our pipeline, the system can be easily deployed and fully automated.

Experimental Research on the Performance of Environmental Friendly Refrigerant Mixtures in a Vapour Compression Refrigeration System

Today's refrigeration and air-conditioning industry is adopting chlorine- and fluorine-free working fluids, because chlorine is the cause of depleting the ozone layer, and fluorine is the cause of global warming. CFC12 is a more suitable refrigerant recognized in vapor compression refrigeration systems. It was phased out in developed countries in 1996. It is recommended to use HFC134a for replacing CFC12 in vapor compression refrigeration systems. But HFCs have a high global warming potential. The Kyoto Protocol aims to reduce the whole GHG emissions by at least 5-times over the 1990 level during the commitment period from 2008 to 2012. Therefore, in the near future, the production and utilization of HFC134a will be ended. There are millions of heat pumps and air-conditioners in refrigeration systems that use CFC12 and HFC134a in the world that must be properly retrofitted under the aforementioned phase-out. However, there are few studies on the replacement of HFC134a refrigerant. This motivates the use of some available environmentally friendly fluids to replace the new product lines of CFC12 and HFC134a to study the performance of the new product line of vapor compression refrigeration systems. But none of them are environmentally acceptable substitutes. In the work of this project, refrigerant R290/R600a (68/32% by weight), R290/R600 (79/21% by weight) is used for the performance of vapor compression refrigeration system), LPG (R290/R600/R600a-33/53)/14 wt.%) and LPG/R134a (60/40 wt.%) have been experimentally studied as modifications of CFC12 and HFC134a. Finally try to predict system performance under the action of a magnetic field. Six magnets are placed on the full liquid pipeline at the outlet of the condenser, and each magnet has a level of 4000 Gauss. Due to the magnetic field, the power consumption of the compressor is decreased by 2.5%, and the COP is reduced by 2.4%. The results of this study prove that the new alternative refrigerants R290/R600a (68/32 wt.%) and R290/R600 (79/21 wt.%) mixtures can well replace CFC12 and HFC134a, and can be used without any modification. It can be used to transform the old system. The refrigerants LPG and LPG/R134a (60/40% by weight) can be used for higher evaporation temperature applications.

Extracting and modeling geographic information from scientific articles.

Scientific articles often contain relevant geographic information such as where field work was performed or where patients were treated. Most often, this information appears in the full-text article contents as a description in natural language including place names, with no accompanying machine-readable geographic metadata. Automatically extracting this geographic information could help conduct meta-analyses, find geographical research gaps, and retrieve articles using spatial search criteria. Research on this problem is still in its infancy, with many works manually processing corpora for locations and few cross-domain studies. In this paper, we develop a fully automatic pipeline to extract and represent relevant locations from scientific articles, applying it to two varied corpora. We obtain good performance, with full pipeline precision of 0.84 for an environmental corpus, and 0.78 for a biomedical corpus. Our results can be visualized as simple global maps, allowing human annotators to both explore corpus patterns in space and triage results for downstream analysis. Future work should not only focus on improving individual pipeline components, but also be informed by user needs derived from the potential spatial analysis and exploration of such corpora.

Shifting Coronavirus Disease 2019 Testing Policy and Research to Include the Full Translation Pipeline.

The current severe acute respiratory syndrome coronavirus 2 testing policy and practice limits testing as a prevention tool. Radical shifts are required to increase the scale of rapid testing strategies and improve dissemination and implementation of venue-based and self-testing approaches. Attention to the full translation pipeline is required to reach high-risk segments of the population.