Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical data science is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of surgical data science, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) technical infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. Drawing from this extensive review, we present current challenges for technology development and (4) describe a roadmap for faster clinical translation and exploitation of the full potential of surgical data science.
Convolutional neural networks (CNN) have achieved great success in analyzing tropical cyclones (TC) with satellite images in several tasks, such as TC intensity estimation. In contrast, TC structure, which is conventionally described by a few parameters estimated subjectively by meteorology specialists, is still hard to be profiled objectively and routinely. This study applies CNN on satellite images to create the entire TC structure profiles, covering all the structural parameters. By utilizing the meteorological domain knowledge to construct TC wind profiles based on historical structure parameters, we provide valuable labels for training in our newly released benchmark dataset. With such a dataset, we hope to attract more attention to this crucial issue among data scientists. Meanwhile, a baseline is established with a specialized convolutional model operating on polar-coordinates. We discovered that it is more feasible and physically reasonable to extract structural information on polar-coordinates, instead of Cartesian coordinates, according to a TC's rotational and spiral natures. Experimental results on the released benchmark dataset verified the robustness of the proposed model and demonstrated the potential for applying deep learning techniques for this barely developed yet important topic.
Multi-view subspace clustering is an important and hot topic in machine learning field, which aims to promote clustering results based on multi-view data, which are collected from different domains or various measurements. In this paper, we propose a novel tensor-based intrinsic subspace representation learning for multi-view clustering. Specifically, to investigate the underlying subspace representation, the rank preserving decomposition accompanied with the tensor-singular value decomposition based low-rank tensor constraint is introduced and applied on the subspace representation matrices of multiple views. The specific information of different views can be considered by the rank preserving decomposition and the high-order correlations of multi-view data are fully explored by the low-rank tensor constraint in our method. Based on the learned subspace representation, clustering results can be obtained by employing the standard spectral clustering algorithm. The objective function is efficiently optimized by utilizing the augmented Lagrangian multiplier based alternating direction minimization algorithm. Experimental results on nine real-world datasets illustrate the superiority of our method compared to several state-of-the-arts.
There is a need to build intelligence in operating machinery and use data analysis on monitored signals in order to quantify the health of the operating system and self-diagnose any initiations of fault. Built-in control procedures can automatically take corrective actions in order to avoid catastrophic failure when a fault is diagnosed. This paper presents a Temporal Clustering Network (TCN) capability for processing acceleration measurement(s) made on the operating system (i.e. machinery foundation, machinery casing, etc.), or any other type of temporal signals, and determine based on the monitored signal when a fault is at its onset. The new capability uses: one-dimensional convolutional neural networks (1D-CNN) for processing the measurements; unsupervised learning (i.e. no labeled signals from the different operating conditions and no signals at pristine vs. damaged conditions are necessary for training the 1D-CNN); clustering (i.e. grouping signals in different clusters reflective of the operating conditions); and statistical analysis for identifying fault signals that are not members of any of the clusters associated with the pristine operating conditions. A case study demonstrating its operation is included in the paper. Finally topics for further research are identified.
Numerical integration and emulation are fundamental topics across scientific fields. We propose novel adaptive quadrature schemes based on an active learning procedure. We consider an interpolative approach for building a surrogate posterior density, combining it with Monte Carlo sampling methods and other quadrature rules. The nodes of the quadrature are sequentially chosen by maximizing a suitable acquisition function, which takes into account the current approximation of the posterior and the positions of the nodes. This maximization does not require additional evaluations of the true posterior. We introduce two specific schemes based on Gaussian and Nearest Neighbors (NN) bases. For the Gaussian case, we also provide a novel procedure for fitting the bandwidth parameter, in order to build a suitable emulator of a density function. With both techniques, we always obtain a positive estimation of the marginal likelihood (a.k.a., Bayesian evidence). An equivalent importance sampling interpretation is also described, which allows the design of extended schemes. Several theoretical results are provided and discussed. Numerical results show the advantage of the proposed approach, including a challenging inference problem in an astronomic dynamical model, with the goal of revealing the number of planets orbiting a star.
Domain adaptation (DA) is an emerging research topic in the field of machine learning and pattern recognition, which aims to assist the learning of target domains by transferring model knowledge from the source domains. To perform DA, a variety of methods have been proposed, most of which concentrate on the scenario of single source and single target domain (1S1T). However, in real applications, usually multiple domains, especially target domains, are involved, which cannot be handled directly by those 1S1T models. Although related works on multi-target domains have been proposed, they are quite rare, and more unfortunately, nearly none of them model the source domain knowledge and leverage the target-relatedness jointly. To overcome these shortcomings, in this paper we propose a kind of DA model through TrAnsferring both the source-KnowlEdge and TargEt-Relatedness, DATAKETER for short. In this way, not only the supervision knowledge from the source domain, but also the potential relatedness among the target domains are simultaneously modeled for exploitation in the process of 1SmT DA. In addition, we construct an alternating optimization algorithm to solve the variables of the proposed model with convergence guarantee. Finally, through extensive experiments on both benchmark and real datasets, we validate the effectiveness and superiority of the proposed method.
Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy and economics, for decades. Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well known causal inference framework. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.
High throughput analysis of samples has been a topic increasingly discussed in both light and electron microscopy. Deep learning can help implement high throughput analysis by segmenting images in a pixel-by-pixel fashion and classifying these regions. However, to date, relatively little has been done in the realm of automated high resolution transmission electron microscopy (HRTEM) micrograph analysis. Neural networks for HRTEM have, so far, focused on identification of single atomic columns in single materials systems. For true high throughput analysis, networks will need to not only recognize atomic columns but also segment out regions of interest from background for a wide variety of materials. We therefore analyze the requirements for achieving a high performance convolutional neural network for segmentation of nanoparticle regions from amorphous carbon in HRTEM images. We also examine how to achieve generalizability of the neural network to a range of materials. We find that networks trained on micrographs of a single material system result in worse segmentation outcomes than one which is trained on a variety of materials' micrographs. Our final network is able to segment nanoparticle regions from amorphous background with 91% pixelwise accuracy.