Joel Barajas

In-Vivo IVUS tissue classification: a comparison between RF signal analysis and reconstructed images

In this paper we present a novel framework for classification of the different kind of tissues in intravascular ultrasound (IVUS) data. We expose a normalized reconstruction of the IVUS images from radio frequency (RF) signals, and the use of these signals for classification. The reconstructed data is described in terms of texture based features and feeds an ECOC-Adaboost learning process. In the same manner, the RF signals are characterize using Autoregressive models, and classified with a similar learning process. A comparison is performed among these techniques and with DICOM based classification ones obtaining very promising results.

Using Reconstructed IVUS Images for Coronary Plaque Classification

Coronary plaque rupture is one of the principal causes of sudden death in western societies. Reliable diagnostic of the different plaque types are of great interest for the medical community the predicting their evolution and applying an effective treatment. To achieve this, a tissue classification must be performed. Intravascular ultrasound (IVUS) represents a technique to explore the vessel walls and to observe its histological properties. In this paper, a method to reconstruct IVUS images from the raw radio frequency (RF) data coming from ultrasound catheter is proposed. This framework offers a normalization scheme to compare accurately different patient studies. The automatic tissue classification is based on texture analysis and adapting boosting (Adaboost) learning technique combined with error correcting output codes (ECOC). In this study, 9 in-vivo cases are reconstructed with 7 different parameter set. This method improves the classification rate based on images, yielding a 91% of well-detected tissue using the best parameter set. It also reduces the inter-patient variability compared with the analysis of DICOM images, which are obtained from the commercial equipment.

The generalized dirichlet distribution in enhanced topic detection

We present a new, robust and computationally efficient Hierarchical Bayesian model for effective topic correlation modeling. We model the prior distribution of topics by a Generalized Dirichlet distribution (GD) rather than a Dirichlet distribution as in Latent Dirichlet Allocation (LDA). We define this model as GD-LDA. This framework captures correlations between topics, as in the Correlated Topic Model (CTM) and Pachinko Allocation Model (PAM), and is faster to infer than CTM and PAM. GD-LDA is effective to avoid over-fitting as the number of topics is increased. As a tree model, it accommodates the most important set of topics in the upper part of the tree based on their probability mass. Thus, GD-LDA provides the ability to choose significant topics effectively. To discover topic relationships, we perform hyper-parameter estimation based on Monte Carlo EM Estimation. We provide results using Empirical Likelihood(EL) in 4 public datasets from TREC and NIPS. Then, we present the performance of GD-LDA in ad hoc information retrieval (IR) based on MAP, P@10, and Discounted Gain. We discuss an empirical comparison of the fitting time. We demonstrate significant improvement over CTM, LDA, and PAM for EL estimation. For all the IR measures, GD-LDA shows higher performance than LDA, the dominant topic model in IR. All these improvements with a small increase in fitting time than LDA, as opposed to CTM and PAM.

Marketing campaign evaluation in targeted display advertising

In this paper, we develop an experimental analysis to estimate the causal effect of online marketing campaigns as a whole, and not just the media ad design. We analyze the causal effects on user conversion probability. We run experiments based on A/B testing to perform this evaluation. We also estimate the causal effect of the media ad design given this randomization approach. We discuss the framework of a marketing campaign in the context of targeted display advertising, and incorporate the main elements of this framework in the evaluation. We consider budget constraints, the auction process, and the targeting engine in the analysis and the experimental set up. For the effects of this evaluation, we assume the targeting engine to be a black box that incorporates the impression delivery policy, the budget constraints, and the bidding process. Our method to disaggregate the campaign causal analysis is inspired on randomized experiments with imperfect compliance and the intention-to-treat (ITT) analysis. In this framework, individuals assigned randomly to the study group might refuse to take the treatment. For estimation, we present a Bayesian approach and provide credible intervals for the causal estimates. We analyze the effects of 2 independent campaigns for different products from the Advertising.com ad network for 20M+ users each campaign.

Cardiac Phase Extraction in IVUS Sequences using 1-D Gabor Filters

A main issue in the automatic analysis of Intravascular Ultrasound (IVUS) images is the presence of periodic changes provoked by heart motion during the cardiac cycle. Although the Electrocardiogram (ECG) signal can be used to gate the sequence, few IVUS systems incorporate the ECG- gating option, and the synchronization between them implies several issues. In this paper, we present a fast and robust method to assign a phase in the cardiac cycle to each image in the sequence directly from in vivo clinical IVUS sequences. It is based on the assumption that the vessel wall is significantly brighter than the blood in each IVUS beam. To guarantee stability in this assumption, we use normalized reconstructed images. Then, the wall boundary is extracted for all the radial beams in the sequence and a matrix with these positions is formed. This matrix is filtered using a bank of 1-D Gabor filters centered at the predominant frequency of a given number of windows in the sequence. After filtering, we combine the responses to obtain a unique phase within the cardiac cycle for each image. For this study, we gate the sequence to make the sequence comparable with other ones of the same patient. The method is tested with 12 pull backs of real patients and 15 synthetic tests.

Experimental designs and estimation for online display advertising attribution in marketplaces

Online Display Advertising’s importance as a marketing channel is partially due to its ability to attribute conversions to campaigns. Current industry practice to measure ad effectiveness is to run randomized experiments using placebo ads, assuming external validity for future exposures. We identify two different effects, i.e., a strategic effect of the campaign presence in marketplaces, and a selection effect due to user targeting; these are confounded in current practices. We propose two novel randomized designs to: (1) estimate the overall campaign attribution without placebo ads, (2) disaggregate the campaign presence and ad effects. Using the Potential Outcomes Causal Model, we address the selection effect by estimating the probability of selecting influenceable users. We show the ex-ante value of continuing evaluation to enhance the user selection for ad exposure mid-flight. We analyze two performance-based (CPA) and one Cost-Per-Impression (CPM) campaigns with 20 million users each. We estimate a negative CPM campaign presence effect due to cross product spillovers. Experimental evidence suggests that CPA campaigns incentivize selection of converting users regardless of the ad, up to 96% more than CPM campaigns, thus challenging the standard practice of targeting most likely converting users.Data, as supplemental material, are available at http://dx.doi.org/10.1287/mksc.2016.0982 .

Measuring the effectiveness of display advertising: a time series approach

We develop an approach for measuring the effectiveness of online display advertising at the campaign level. We present a Kalman filtering approach to deseasonalize and estimate the percentage changes of online sales on a daily basis. For this study, we analyze 3828 campaigns for 961 products on the Advertising.com network.

Dynamic effects of ad impressions on commercial actions in display advertising

In this paper, we develop a time series approach, based on Dynamic Linear Models (DLM), to estimate the impact of ad impressions on the daily number of commercial actions when no user tracking is possible. The proposed method uses aggregate data, and hence it is simple to implement without expensive infrastructure. Specifically, we model the impact of daily number of ad impressions in daily number of commercial actions. We incorporate persistence of campaign effects on actions assuming a decay factor. We relax the assumption of a linear impact of ads on actions using the log-transformation. We also account for outliers with long-tailed distributions fitted and estimated automatically without a pre-defined threshold. This is applied to observational data post-campaign and does not require an experimental set-up. We apply the method to data from one commercial ad network on 2,885 campaigns for 1,251 products during six months, to calibrate and perform model selection. We set up a randomized experiment for two campaigns where user tracking is feasible. We find that the output of the proposed method is consistent with the results of A/B testing with similar confidence intervals.

Knowledge sciences in services automation: Integration models and perspectives for service centers

We provide an automation perspective on modeling knowledge services. We consider a service center as the atomic unit for building networks of enterprises, suppliers, and customers. We provide an approach to integrate knowledge and resource management in service centers. We describe specific models and solutions for optimized information and knowledge retrieval, relevance feedback and active learning and associated performance results. We also outline an approach for incorporating topic detection, context, social networks and collaboration, and combined document and expert ranking/identification. We also sketch an approach for combining knowledge retrieval with system resource optimization of the service engineers and experts to provide optimized responsiveness.

Dynamic evaluation of online display advertising with randomized experiments: an aggregated approach

We perform a randomized experiment to estimate the effects of a display advertising campaign on online user conversions. We present a time series approach using Dynamic Linear Models to decompose the daily aggregated conversions into seasonal and trend components. We attribute the difference between control and study trends to the campaign. We test the method using two real campaigns run for 28 and 21 days respectively from the Advertising.com ad network.