October 17, 2019

3471 words 17 mins read

Paper Group ANR 886

Multimodal Machine Learning for Automated ICD Coding. A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation. Computer-Aided Knee Joint Magnetic Resonance Image Segmentation - A Survey. Tracking the Evolution of Words with Time-reflective Text Representations. Semantic …

Multimodal Machine Learning for Automated ICD Coding


Title	Multimodal Machine Learning for Automated ICD Coding
Authors	Keyang Xu, Mike Lam, Jingzhi Pang, Xin Gao, Charlotte Band, Piyush Mathur MD, Frank Papay MD, Ashish K. Khanna MD, Jacek B. Cywinski MD, Kamal Maheshwari MD, Pengtao Xie, Eric Xing
Abstract	This study presents a multimodal machine learning model to predict ICD-10 diagnostic codes. We developed separate machine learning models that can handle data from different modalities, including unstructured text, semi-structured text and structured tabular data. We further employed an ensemble method to integrate all modality-specific models to generate ICD-10 codes. Key evidence was also extracted to make our prediction more convincing and explainable. We used the Medical Information Mart for Intensive Care III (MIMIC -III) dataset to validate our approach. For ICD code prediction, our best-performing model (micro-F1 = 0.7633, micro-AUC = 0.9541) significantly outperforms other baseline models including TF-IDF (micro-F1 = 0.6721, micro-AUC = 0.7879) and Text-CNN model (micro-F1 = 0.6569, micro-AUC = 0.9235). For interpretability, our approach achieves a Jaccard Similarity Coefficient (JSC) of 0.1806 on text data and 0.3105 on tabular data, where well-trained physicians achieve 0.2780 and 0.5002 respectively.
Tasks
Published	2018-10-31
URL	https://arxiv.org/abs/1810.13348v3
PDF	https://arxiv.org/pdf/1810.13348v3.pdf
PWC	https://paperswithcode.com/paper/multimodal-machine-learning-for-automated-icd
Repo
Framework

A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation


Title	A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation
Authors	Ismail Irmakci, Sarfaraz Hussein, Aydogan Savran, Rita R. Kalyani, David Reiter, Chee W. Chia, Kenneth W. Fishbein, Richard G. Spencer, Luigi Ferrucci, Ulas Bagci
Abstract	Magnetic resonance imaging (MRI) is the non-invasive modality of choice for body tissue composition analysis due to its excellent soft tissue contrast and lack of ionizing radiation. However, quantification of body composition requires an accurate segmentation of fat, muscle and other tissues from MR images, which remains a challenging goal due to the intensity overlap between them. In this study, we propose a fully automated, data-driven image segmentation platform that addresses multiple difficulties in segmenting MR images such as varying inhomogeneity, non-standardness, and noise, while producing high-quality definition of different tissues. In contrast to most approaches in the literature, we perform segmentation operation by combining three different MRI contrasts and a novel segmentation tool which takes into account variability in the data. The proposed system, based on a novel affinity definition within the fuzzy connectivity (FC) image segmentation family, prevents the need for user intervention and reparametrization of the segmentation algorithms. In order to make the whole system fully automated, we adapt an affinity propagation clustering algorithm to roughly identify tissue regions and image background. We perform a thorough evaluation of the proposed algorithm’s individual steps as well as comparison with several approaches from the literature for the main application of muscle/fat separation. Furthermore, whole-body tissue composition and brain tissue delineation were conducted to show the generalization ability of the proposed system. This new automated platform outperforms other state-of-the-art segmentation approaches both in accuracy and efficiency.
Tasks	Semantic Segmentation
Published	2018-10-14
URL	http://arxiv.org/abs/1810.06071v1
PDF	http://arxiv.org/pdf/1810.06071v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-extension-to-fuzzy-connectivity-for
Repo
Framework

Computer-Aided Knee Joint Magnetic Resonance Image Segmentation - A Survey


Title	Computer-Aided Knee Joint Magnetic Resonance Image Segmentation - A Survey
Authors	Boyu Zhang, Yingtao Zhang, H. D. Cheng, Min Xian, Shan Gai, Olivia Cheng, Kuan Huang
Abstract	Osteoarthritis (OA) is one of the major health issues among the elderly population. MRI is the most popular technology to observe and evaluate the progress of OA course. However, the extreme labor cost of MRI analysis makes the process inefficient and expensive. Also, due to human error and subjective nature, the inter- and intra-observer variability is rather high. Computer-aided knee MRI segmentation is currently an active research field because it can alleviate doctors and radiologists from the time consuming and tedious job, and improve the diagnosis performance which has immense potential for both clinic and scientific research. In the past decades, researchers have investigated automatic/semi-automatic knee MRI segmentation methods extensively. However, to the best of our knowledge, there is no comprehensive survey paper in this field yet. In this survey paper, we classify the existing methods by their principles and discuss the current research status and point out the future research trend in-depth.
Tasks	Semantic Segmentation
Published	2018-02-13
URL	http://arxiv.org/abs/1802.04894v1
PDF	http://arxiv.org/pdf/1802.04894v1.pdf
PWC	https://paperswithcode.com/paper/computer-aided-knee-joint-magnetic-resonance
Repo
Framework

Tracking the Evolution of Words with Time-reflective Text Representations


Title	Tracking the Evolution of Words with Time-reflective Text Representations
Authors	Roberto Camacho Barranco, Raimundo F. Dos Santos, M. Shahriar Hossain
Abstract	More than 80% of today’s data is unstructured in nature, and these unstructured datasets evolve over time. A large part of these datasets are text documents generated by media outlets, scholarly articles in digital libraries, findings from scientific and professional communities, and social media. Vector space models were developed to analyze text data using data mining and machine learning algorithms. While ample vector space models exist for text data, the evolutionary aspect of ever-changing text corpora is still missing in vector-based representations. The advent of word embeddings has enabled us to create a contextual vector space, but the embeddings fail to consider the temporal aspects of the feature space successfully. This paper presents an approach to include temporal aspects in feature spaces. The inclusion of the time aspect in the feature space provides vectors for every natural language element, such as words or entities, at every timestamp. Such temporal word vectors allow us to track how the meaning of a word changes over time, by studying the changes in its neighborhood. Moreover, a time-reflective text representation will pave the way to a new set of text analytic abilities involving time series for text collections. In this paper, we present a time-reflective vector space model for temporal text data that is able to capture short and long-term changes in the meaning of words. We compare our approach with the limited literature on dynamic embeddings. We present qualitative and quantitative evaluations using the tracking of semantic evolution as the target application.
Tasks	Time Series, Word Embeddings
Published	2018-07-12
URL	http://arxiv.org/abs/1807.04441v2
PDF	http://arxiv.org/pdf/1807.04441v2.pdf
PWC	https://paperswithcode.com/paper/tracking-the-evolution-of-words-with-time
Repo
Framework

Semantic DMN: Formalizing and Reasoning About Decisions in the Presence of Background Knowledge


Title	Semantic DMN: Formalizing and Reasoning About Decisions in the Presence of Background Knowledge
Authors	Diego Calvanese, Marlon Dumas, Fabrizio Maria Maggi, Marco Montali
Abstract	The Decision Model and Notation (DMN) is a recent OMG standard for the elicitation and representation of decision models, and for managing their interconnection with business processes. DMN builds on the notion of decision tables, and their combination into more complex decision requirements graphs (DRGs), which bridge between business process models and decision logic models. DRGs may rely on additional, external business knowledge models, whose functioning is not part of the standard. In this work, we consider one of the most important types of business knowledge, namely background knowledge that conceptually accounts for the structural aspects of the domain of interest, and propose decision knowledge bases (DKBs), which semantically combine DRGs modeled in DMN, and domain knowledge captured by means of first-order logic with datatypes. We provide a logic-based semantics for such an integration, and formalize different DMN reasoning tasks for DKBs. We then consider background knowledge formulated as a description logic ontology with datatypes, and show how the main verification tasks for DMN in this enriched setting can be formalized as standard DL reasoning services, and actually carried out in ExpTime. We discuss the effectiveness of our framework on a case study in maritime security.
Tasks
Published	2018-07-31
URL	http://arxiv.org/abs/1807.11615v3
PDF	http://arxiv.org/pdf/1807.11615v3.pdf
PWC	https://paperswithcode.com/paper/semantic-dmn-formalizing-and-reasoning-about
Repo
Framework

Multi-task Learning of Hierarchical Vision-Language Representation


Title	Multi-task Learning of Hierarchical Vision-Language Representation
Authors	Duy-Kien Nguyen, Takayuki Okatani
Abstract	It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and trained them on its dedicated datasets. Although this approach has seen a certain degree of success, it comes with difficulties of understanding relations among different tasks and transferring the knowledge learned for a task to others. We propose a multi-task learning approach that enables to learn vision-language representation that is shared by many tasks from their diverse datasets. The representation is hierarchical, and prediction for each task is computed from the representation at its corresponding level of the hierarchy. We show through experiments that our method consistently outperforms previous single-task-learning methods on image caption retrieval, visual question answering, and visual grounding. We also analyze the learned hierarchical representation by visualizing attention maps generated in our network.
Tasks	Multi-Task Learning, Question Answering, Visual Question Answering
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00500v1
PDF	http://arxiv.org/pdf/1812.00500v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-learning-of-hierarchical-vision
Repo
Framework

Deep Learning Based Rib Centerline Extraction and Labeling


Title	Deep Learning Based Rib Centerline Extraction and Labeling
Authors	Matthias Lenga, Tobias Klinder, Christian Bürger, Jens von Berg, Astrid Franz, Cristian Lorenz
Abstract	Automated extraction and labeling of rib centerlines is a typically needed prerequisite for more advanced assisted reading tools that help the radiologist to efficiently inspect all 24 ribs in a CT volume. In this paper, we combine a deep learning-based rib detection with a dedicated centerline extraction algorithm applied to the detection result for the purpose of fast, robust and accurate rib centerline extraction and labeling from CT volumes. More specifically, we first apply a fully convolutional neural network (FCNN) to generate a probability map for detecting the first rib pair, the twelfth rib pair, and the collection of all intermediate ribs. In a second stage, a newly designed centerline extraction algorithm is applied to this multi-label probability map. Finally, the distinct detection of first and twelfth rib separately, allows to derive individual rib labels by simple sorting and counting the detected centerlines. We applied our method to CT volumes from 116 patients which included a variety of different challenges and achieved a centerline accuracy of 0.787 mm with respect to manual centerline annotations. This article is a preprint version of: Lenga M., Klinder T., B"urger C., von Berg J., Franz A., Lorenz C. (2019) Deep Learning Based Rib Centerline Extraction and Labeling. In: Vrtovec T., Yao J., Zheng G., Pozo J. (eds) Computational Methods and Clinical Applications in Musculoskeletal Imaging. MSKI 2018. Lecture Notes in Computer Science, vol 11404. Springer, Cham
Tasks
Published	2018-09-19
URL	http://arxiv.org/abs/1809.07082v2
PDF	http://arxiv.org/pdf/1809.07082v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-rib-centerline-extraction
Repo
Framework

Influence of Image Classification Accuracy on Saliency Map Estimation


Title	Influence of Image Classification Accuracy on Saliency Map Estimation
Authors	Taiki Oyama, Takao Yamanaka
Abstract	Saliency map estimation in computer vision aims to estimate the locations where people gaze in images. Since people tend to look at objects in images, the parameters of the model pretrained on ImageNet for image classification are useful for the saliency map estimation. However, there is no research on the relationship between the image classification accuracy and the performance of the saliency map estimation. In this paper, it is shown that there is a strong correlation between image classification accuracy and saliency map estimation accuracy. We also investigated the effective architecture based on multi scale images and the upsampling layers to refine the saliency-map resolution. Our model achieved the state-of-the-art accuracy on the PASCAL-S, OSIE, and MIT1003 datasets. In the MIT Saliency Benchmark, our model achieved the best performance in some metrics and competitive results in the other metrics.
Tasks	Image Classification
Published	2018-07-27
URL	http://arxiv.org/abs/1807.10657v1
PDF	http://arxiv.org/pdf/1807.10657v1.pdf
PWC	https://paperswithcode.com/paper/influence-of-image-classification-accuracy-on
Repo
Framework

FlipDial: A Generative Model for Two-Way Visual Dialogue


Title	FlipDial: A Generative Model for Two-Way Visual Dialogue
Authors	Daniela Massiceti, N. Siddharth, Puneet K. Dokania, Philip H. S. Torr
Abstract	We present FlipDial, a generative model for visual dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an image and an associated caption summarising the contents of the image, FlipDial learns both to answer questions and put forward questions, capable of generating entire sequences of dialogue (question-answer pairs) which are diverse and relevant to the image. To do this, FlipDial relies on a simple but surprisingly powerful idea: it uses convolutional neural networks (CNNs) to encode entire dialogues directly, implicitly capturing dialogue context, and conditional VAEs to learn the generative model. FlipDial outperforms the state-of-the-art model in the sequential answering task (one-way visual dialogue) on the VisDial dataset by 5 points in Mean Rank using the generated answers. We are the first to extend this paradigm to full two-way visual dialogue, where our model is capable of generating both questions and answers in sequence based on a visual input, for which we propose a set of novel evaluation measures and metrics.
Tasks	Visual Dialog
Published	2018-02-11
URL	http://arxiv.org/abs/1802.03803v2
PDF	http://arxiv.org/pdf/1802.03803v2.pdf
PWC	https://paperswithcode.com/paper/flipdial-a-generative-model-for-two-way
Repo
Framework

Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance


Title	Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance
Authors	Soumil Mandal, Karthick Nanmaran
Abstract	Building tools for code-mixed data is rapidly gaining popularity in the NLP research community as such data is exponentially rising on social media. Working with code-mixed data contains several challenges, especially due to grammatical inconsistencies and spelling variations in addition to all the previous known challenges for social media scenarios. In this article, we present a novel architecture focusing on normalizing phonetic typing variations, which is commonly seen in code-mixed data. One of the main features of our architecture is that in addition to normalizing, it can also be utilized for back-transliteration and word identification in some cases. Our model achieved an accuracy of 90.27% on the test data.
Tasks	Transliteration
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08701v1
PDF	http://arxiv.org/pdf/1805.08701v1.pdf
PWC	https://paperswithcode.com/paper/normalization-of-transliterated-words-in-code
Repo
Framework

Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition


Title	Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition
Authors	Vivian S. Silva, André Freitas, Siegfried Handschuh
Abstract	Natural language definitions of terms can serve as a rich source of knowledge, but structuring them into a comprehensible semantic model is essential to enable them to be used in semantic interpretation tasks. We propose a method and provide a set of tools for automatically building a graph world knowledge base from natural language definitions. Adopting a conceptual model composed of a set of semantic roles for dictionary definitions, we trained a classifier for automatically labeling definitions, preparing the data to be later converted to a graph representation. WordNetGraph, a knowledge graph built out of noun and verb WordNet definitions according to this methodology, was successfully used in an interpretable text entailment recognition approach which uses paths in this graph to provide clear justifications for entailment decisions.
Tasks
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07731v1
PDF	http://arxiv.org/pdf/1806.07731v1.pdf
PWC	https://paperswithcode.com/paper/building-a-knowledge-graph-from-natural
Repo
Framework

High Dimensional Time Series Generators


Title	High Dimensional Time Series Generators
Authors	Jörg P. Bachmann, Johann-Christoph Freytag
Abstract	Multidimensional time series are sequences of real valued vectors. They occur in different areas, for example handwritten characters, GPS tracking, and gestures of modern virtual reality motion controllers. Within these areas, a common task is to search for similar time series. Dynamic Time Warping (DTW) is a common distance function to compare two time series. The Edit Distance with Real Penalty (ERP) and the Dog Keeper Distance (DK) are two more distance functions on time series. Their behaviour has been analyzed on 1-dimensional time series. However, it is not easy to evaluate their behaviour in relation to growing dimensionality. For this reason we propose two new data synthesizers generating multidimensional time series. The first synthesizer extends the well known cylinder-bell-funnel (CBF) dataset to multidimensional time series. Here, each time series has an arbitrary type (cylinder, bell, or funnel) in each dimension, thus for $d$-dimensional time series there are $3^{d}$ different classes. The second synthesizer (RAM) creates time series with ideas adapted from Brownian motions which is a common model of movement in physics. Finally, we evaluate the applicability of a 1-nearest neighbor classifier using DTW on datasets generated by our synthesizers.
Tasks	Time Series
Published	2018-04-17
URL	http://arxiv.org/abs/1804.06352v3
PDF	http://arxiv.org/pdf/1804.06352v3.pdf
PWC	https://paperswithcode.com/paper/high-dimensional-time-series-generators
Repo
Framework

Hierarchical Adversarially Learned Inference


Title	Hierarchical Adversarially Learned Inference
Authors	Mohamed Ishmael Belghazi, Sai Rajeswar, Olivier Mastropietro, Negar Rostamzadeh, Jovana Mitrovic, Aaron Courville
Abstract	We propose a novel hierarchical generative model with a simple Markovian structure and a corresponding inference model. Both the generative and inference model are trained using the adversarial learning paradigm. We demonstrate that the hierarchical structure supports the learning of progressively more abstract representations as well as providing semantically meaningful reconstructions with different levels of fidelity. Furthermore, we show that minimizing the Jensen-Shanon divergence between the generative and inference network is enough to minimize the reconstruction error. The resulting semantically meaningful hierarchical latent structure discovery is exemplified on the CelebA dataset. There, we show that the features learned by our model in an unsupervised way outperform the best handcrafted features. Furthermore, the extracted features remain competitive when compared to several recent deep supervised approaches on an attribute prediction task on CelebA. Finally, we leverage the model’s inference network to achieve state-of-the-art performance on a semi-supervised variant of the MNIST digit classification task.
Tasks
Published	2018-02-04
URL	http://arxiv.org/abs/1802.01071v1
PDF	http://arxiv.org/pdf/1802.01071v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-adversarially-learned-inference
Repo
Framework

Comparison of methods for early-readmission prediction in a high-dimensional heterogeneous covariates and time-to-event outcome framework


Title	Comparison of methods for early-readmission prediction in a high-dimensional heterogeneous covariates and time-to-event outcome framework
Authors	Simon Bussy, Raphaël Veil, Vincent Looten, Anita Burgun, Stéphane Gaïffas, Agathe Guilloux, Brigitte Ranque, Anne-Sophie Jannot
Abstract	Background: Choosing the most performing method in terms of outcome prediction or variables selection is a recurring problem in prognosis studies, leading to many publications on methods comparison. But some aspects have received little attention. First, most comparison studies treat prediction performance and variable selection aspects separately. Second, methods are either compared within a binary outcome setting (based on an arbitrarily chosen delay) or within a survival setting, but not both. In this paper, we propose a comparison methodology to weight up those different settings both in terms of prediction and variables selection, while incorporating advanced machine learning strategies. Methods: Using a high-dimensional case study on a sickle-cell disease (SCD) cohort, we compare 8 statistical methods. In the binary outcome setting, we consider logistic regression (LR), support vector machine (SVM), random forest (RF), gradient boosting (GB) and neural network (NN); while on the survival analysis setting, we consider the Cox Proportional Hazards (PH), the CURE and the C-mix models. We then compare performances of all methods both in terms of risk prediction and variable selection, with a focus on the use of Elastic-Net regularization technique. Results: Among all assessed statistical methods assessed, the C-mix model yields the better performances in both the two considered settings, as well as interesting interpretation aspects. There is some consistency in selected covariates across methods within a setting, but not much across the two settings. Conclusions: It appears that learning withing the survival setting first, and then going back to a binary prediction using the survival estimates significantly enhance binary predictions.
Tasks	Readmission Prediction, Survival Analysis
Published	2018-07-25
URL	http://arxiv.org/abs/1807.09821v1
PDF	http://arxiv.org/pdf/1807.09821v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-methods-for-early-readmission
Repo
Framework

Automated dataset generation for image recognition using the example of taxonomy


Title	Automated dataset generation for image recognition using the example of taxonomy
Authors	Jaro Milan Zink
Abstract	This master thesis addresses the subject of automatically generating a dataset for image recognition, which takes a lot of time when being done manually. As the thesis was written with motivation from the context of the biodiversity workgroup at the City University of Applied Sciences Bremen, the classification of taxonomic entries was chosen as an exemplary use case. In order to automate the dataset creation, a prototype was conceptualized and implemented after working out knowledge basics and analyzing requirements for it. It makes use of an pre-trained abstract artificial intelligence which is able to sort out images that do not contain the desired content. Subsequent to the implementation and the automated dataset creation resulting from it, an evaluation was performed. Other, manually collected datasets were compared to the one the prototype produced in means of specifications and accuracy. The results were more than satisfactory and showed that automatically generating a dataset for image recognition is not only possible, but also might be a decent alternative to spending time and money in doing this task manually. At the very end of this work, an idea of how to use the principle of employing abstract artificial intelligences for step-by-step classification of deeper taxonomic layers in a productive system is presented and discussed.
Tasks
Published	2018-01-22
URL	http://arxiv.org/abs/1802.02207v1
PDF	http://arxiv.org/pdf/1802.02207v1.pdf
PWC	https://paperswithcode.com/paper/automated-dataset-generation-for-image
Repo
Framework