Feature Selection for Automatic Tuberculosis Screening in Frontal Chest Radiographs.

To detect pulmonary abnormalities such as Tuberculosis (TB), an automatic analysis and classification of chest radiographs can be used as a reliable alternative to more sophisticated and technologically demanding methods (e.g. culture or sputum smear analysis). In target areas like Kenya TB is highly prevalent and often co-occurring with HIV combined with low resources and limited medical assistance. In these regions an automatic screening system can provide a cost-effective solution for a large rural population. Our completely automatic TB screening system is processing the incoming CXRs (chest X-ray) by applying image preprocessing techniques to enhance the image quality followed by an adaptive segmentation based on model selection. The delineated lung regions are described by a multitude of image features. These characteristics are than optimized by a feature selection strategy to provide the best description for the classifier, which will later decide if the analyzed image is normal or abnormal. Our goal is to find the optimal feature set from a larger pool of generic image features, -used originally for problems such as object detection, image retrieval, etc. For performance evaluation measures such as under the curve (AUC) and accuracy (ACC) were considered. Using a neural network classifier on two publicly available data collections, -namely the Montgomery and the Shenzhen dataset, we achieved the maximum area under the curve and accuracy of 0.99 and 97.03%, respectively. Further, we compared our results with existing state-of-the-art systems and to radiologists' decision.

A structural SVM approach for reference parsing.

BACKGROUND: Automated extraction of bibliographic data, such as article titles, author names, abstracts, and references is essential to the affordable creation of large citation databases. References, typically appearing at the end of journal articles, can also provide valuable information for extracting other bibliographic data. Therefore, parsing individual reference to extract author, title, journal, year, etc. is sometimes a necessary preprocessing step in building citation-indexing systems. The regular structure in references enables us to consider reference parsing a sequence learning problem and to study structural Support Vector Machine (structural SVM), a newly developed structured learning algorithm on parsing references. RESULTS: In this study, we implemented structural SVM and used two types of contextual features to compare structural SVM with conventional SVM. Both methods achieve above 98% token classification accuracy and above 95% overall chunk-level accuracy for reference parsing. We also compared SVM and structural SVM to Conditional Random Field (CRF). The experimental results show that structural SVM and CRF achieve similar accuracies at token- and chunk-levels. CONCLUSIONS: When only basic observation features are used for each token, structural SVM achieves higher performance compared to SVM since it utilizes the contextual label features. However, when the contextual observation features from neighboring tokens are combined, SVM performance improves greatly, and is close to that of structural SVM after adding the second order contextual observation features. The comparison of these two methods with CRF using the same set of binary features show that both structural SVM and CRF perform better than SVM, indicating their stronger sequence learning ability in reference parsing.

Interactive Publication: The document as a research tool.

The increasing prevalence of multimedia and research data generated by scientific work affords an opportunity to reformulate the idea of a scientific article from the traditional static document, or even one with links to supplemental material in remote databases, to a self-contained, multimedia-rich interactive publication. This paper describes our concept of such a document, and the design of tools for authoring (Forge) and visualization/analysis (Panorama). They are platform-independent applications written in Java, and developed in Eclipse using its Rich Client Platform (RCP) framework. Both applications operate on PDF files with links to XML files that define the media type, location, and action to be performed. We also briefly cite the challenges posed by the potentially large size of interactive publications, the need for evaluating their value to improved comprehension and learning, and the need for their long-term preservation by the National Library of Medicine and other libraries.

Locating and parsing bibliographic references in HTML medical articles.

The set of references that typically appear toward the end of journal articles is sometimes, though not always, a field in bibliographic (citation) databases. But even if references do not constitute such a field, they can be useful as a preprocessing step in the automated extraction of other bibliographic data from articles, as well as in computer-assisted indexing of articles. Automation in data extraction and indexing to minimize human labor is key to the affordable creation and maintenance of large bibliographic databases. Extracting the components of references, such as author names, article title, journal name, publication date and other entities, is therefore a valuable and sometimes necessary task. This paper describes a two-step process using statistical machine learning algorithms, to first locate the references in HTML medical articles and then to parse them. Reference locating identifies the reference section in an article and then decomposes it into individual references. We formulate this step as a two-class classification problem based on text and geometric features. An evaluation conducted on 500 articles drawn from 100 medical journals achieves near-perfect precision and recall rates for locating references. Reference parsing identifies the components of each reference. For this second step, we implement and compare two algorithms. One relies on sequence statistics and trains a Conditional Random Field. The other focuses on local feature statistics and trains a Support Vector Machine to classify each individual word, followed by a search algorithm that systematically corrects low confidence labels if the label sequence violates a set of predefined rules. The overall performance of these two reference-parsing algorithms is about the same: above 99% accuracy at the word level, and over 97% accuracy at the chunk level.

EpithNet: Deep Regression for Epithelium Segmentation in Cervical Histology Images.

BACKGROUND: Automated pathology techniques for detecting cervical cancer at the premalignant stage have advantages for women in areas with limited medical resources. METHODS: This article presents EpithNet, a deep learning approach for the critical step of automated epithelium segmentation in digitized cervical histology images. EpithNet employs three regression networks of varying dimensions of image input blocks (patches) surrounding a given pixel, with all blocks at a fixed resolution, using varying network depth. RESULTS: The proposed model was evaluated on 311 digitized histology epithelial images and the results indicate that the technique maximizes region-based information to improve pixel-wise probability estimates. EpithNet-mc model, formed by intermediate concatenation of the convolutional layers of the three models, was observed to achieve 94% Jaccard index (intersection over union) which is 26.4% higher than the benchmark model. CONCLUSIONS: EpithNet yields better epithelial segmentation results than state-of-the-art benchmark methods.

Neural networks versus Logistic regression for 30 days all-cause readmission prediction.

Heart failure (HF) is one of the leading causes of hospital admissions in the US. Readmission within 30 days after a HF hospitalization is both a recognized indicator for disease progression and a source of considerable financial burden to the healthcare system. Consequently, the identification of patients at risk for readmission is a key step in improving disease management and patient outcome. In this work, we used a large administrative claims dataset to (1) explore the systematic application of neural network-based models versus logistic regression for predicting 30 days all-cause readmission after discharge from a HF admission, and (2) to examine the additive value of patients' hospitalization timelines on prediction performance. Based on data from 272,778 (49% female) patients with a mean (SD) age of 73 years (14) and 343,328 HF admissions (67% of total admissions), we trained and tested our predictive readmission models following a stratified 5-fold cross-validation scheme. Among the deep learning approaches, a recurrent neural network (RNN) combined with conditional random fields (CRF) model (RNNCRF) achieved the best performance in readmission prediction with 0.642 AUC (95% CI, 0.640-0.645). Other models, such as those based on RNN, convolutional neural networks and CRF alone had lower performance, with a non-timeline based model (MLP) performing worst. A competitive model based on logistic regression with LASSO achieved a performance of 0.643 AUC (95% CI, 0.640-0.646). We conclude that data from patient timelines improve 30 day readmission prediction, that a logistic regression with LASSO has equal performance to the best neural network model and that the use of administrative data result in competitive performance compared to published approaches based on richer clinical datasets.

Size-invariant descriptors for detecting regions of abnormal growth in cervical vertebrae.

Digitized spinal X-ray images exhibiting specific pathological conditions such as osteophytes can be retrieved from large databases using Content Based Image Retrieval (CBIR) techniques. For efficient image retrieval, it is important that the pathological features of interest be detected with high accuracy. In this study, new size-invariant features were investigated for the detection of anterior osteophytes, including claw and traction in cervical vertebrae. Using a K-means clustering and nearest neighbor classification approach, average correct classification rates of 85.80%, 86.04% and 84.44% were obtained for claw, traction and anterior osteophytes, respectively.

Visualization and Interpretation of Convolutional Neural Network Predictions in Detecting Pneumonia in Pediatric Chest Radiographs.

Pneumonia affects 7% of the global population, resulting in 2 million pediatric deaths every year. Chest X-ray (CXR) analysis is routinely performed to diagnose the disease. Computer-aided diagnostic (CADx) tools aim to supplement decision-making. These tools process the handcrafted and/or convolutional neural network (CNN) extracted image features for visual recognition. However, CNNs are perceived as black boxes since their performance lack explanations. This is a serious bottleneck in applications involving medical screening/diagnosis since poorly interpreted model behavior could adversely affect the clinical decision. In this study, we evaluate, visualize, and explain the performance of customized CNNs to detect pneumonia and further differentiate between bacterial and viral types in pediatric CXRs. We present a novel visualization strategy to localize the region of interest (ROI) that is considered relevant for model predictions across all the inputs that belong to an expected class. We statistically validate the models' performance toward the underlying tasks. We observe that the customized VGG16 model achieves 96.2% and 93.6% accuracy in detecting the disease and distinguishing between bacterial and viral pneumonia respectively. The model outperforms the state-of-the-art in all performance metrics and demonstrates reduced bias and improved generalization.

Image analysis and machine learning for detecting malaria.

Malaria remains a major burden on global health, with roughly 200 million cases worldwide and more than 400,000 deaths per year. Besides biomedical research and political efforts, modern information technology is playing a key role in many attempts at fighting the disease. One of the barriers toward a successful mortality reduction has been inadequate malaria diagnosis in particular. To improve diagnosis, image analysis software and machine learning methods have been used to quantify parasitemia in microscopic blood slides. This article gives an overview of these techniques and discusses the current developments in image analysis and machine learning for microscopic malaria diagnosis. We organize the different approaches published in the literature according to the techniques used for imaging, image preprocessing, parasite detection and cell segmentation, feature computation, and automatic cell classification. Readers will find the different techniques listed in tables, with the relevant articles cited next to them, for both thin and thick blood smear images. We also discussed the latest developments in sections devoted to deep learning and smartphone technology for future malaria diagnosis.

Detecting drug-resistant tuberculosis in chest radiographs.

PURPOSE: Tuberculosis is a major global health threat claiming millions of lives each year. While the total number of tuberculosis cases has been decreasing over the last years, the rise of drug-resistant tuberculosis has reduced the chance of controlling the disease. The purpose is to implement a timely diagnosis of drug-resistant tuberculosis, which is essential to administering adequate treatment regimens and stopping the further transmission of drug-resistant tuberculosis. METHODS: A main tool for diagnosing tuberculosis is the conventional chest X-ray. We are investigating the possibility of discriminating automatically between drug-resistant and drug-sensitive tuberculosis in chest X-rays by means of image analysis and machine learning methods. RESULTS: For discriminating between drug-sensitive and drug-resistant tuberculosis, we achieve an area under the receiver operating characteristic curve (AUC) of up to 66%, using an artificial neural network in combination with a set of shape and texture features. We did not observe any significant difference in the results when including follow-up X-rays for each patient. CONCLUSION: Our results suggest that a chest X-ray contains information about the likelihood of a drug-resistant tuberculosis infection, which can be exploited computationally. We therefore suggest to repeat the experiments of our pilot study on a larger set of chest X-rays.

Malaria parasite detection and cell counting for human and mouse using thin blood smear microscopy.

Despite the remarkable progress that has been made to reduce global malaria mortality by 29% in the past 5 years, malaria is still a serious global health problem. Inadequate diagnostics is one of the major obstacles in fighting the disease. An automated system for malaria diagnosis can help to make malaria screening faster and more reliable. We present an automated system to detect and segment red blood cells (RBCs) and identify infected cells in Wright-Giemsa stained thin blood smears. Specifically, using image analysis and machine learning techniques, we process digital images of thin blood smears to determine the parasitemia in each smear. We use a cell extraction method to segment RBCs, in particular overlapping cells. We show that a combination of RGB color and texture features outperforms other features. We evaluate our method on microscopic blood smear images from human and mouse and show that it outperforms other techniques. For human cells, we measure an absolute error of 1.18% between the true and the automatic parasite counts. For mouse cells, our automatic counts correlate well with expert and flow cytometry counts. This makes our system the first one to work for both human and mouse.

Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images.

Malaria is a blood disease caused by the Plasmodium parasites transmitted through the bite of female Anopheles mosquito. Microscopists commonly examine thick and thin blood smears to diagnose disease and compute parasitemia. However, their accuracy depends on smear quality and expertise in classifying and counting parasitized and uninfected cells. Such an examination could be arduous for large-scale diagnoses resulting in poor quality. State-of-the-art image-analysis based computer-aided diagnosis (CADx) methods using machine learning (ML) techniques, applied to microscopic images of the smears using hand-engineered features demand expertise in analyzing morphological, textural, and positional variations of the region of interest (ROI). In contrast, Convolutional Neural Networks (CNN), a class of deep learning (DL) models promise highly scalable and superior results with end-to-end feature extraction and classification. Automated malaria screening using DL techniques could, therefore, serve as an effective diagnostic aid. In this study, we evaluate the performance of pre-trained CNN based DL models as feature extractors toward classifying parasitized and uninfected cells to aid in improved disease screening. We experimentally determine the optimal model layers for feature extraction from the underlying data. Statistical validation of the results demonstrates the use of pre-trained CNNs as a promising tool for feature extraction for this purpose.

Understanding the learned behavior of customized convolutional neural networks toward malaria parasite detection in thin blood smear images.

Convolutional neural networks (CNNs) have become the architecture of choice for visual recognition tasks. However, these models are perceived as black boxes since there is a lack of understanding of the learned behavior from the underlying task of interest. This lack of transparency is a serious drawback, particularly in applications involving medical screening and diagnosis since poorly understood model behavior could adversely impact subsequent clinical decision-making. Recently, researchers have begun working on this issue and several methods have been proposed to visualize and understand the behavior of these models. We highlight the advantages offered through visualizing and understanding the weights, saliencies, class activation maps, and region of interest localizations in customized CNNs applied to the challenge of classifying parasitized and uninfected cells to aid in malaria screening. We provide an explanation for the models' classification decisions. We characterize, evaluate, and statistically validate the performance of different customized CNNs keeping every training subject's data separate from the validation set.

Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels.

BACKGROUND: Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades. METHODS: In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network. RESULTS: The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques. CONCLUSIONS: The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods.

Using wireless handheld computers to seek information at the point of care: an evaluation by clinicians.

OBJECTIVE: To evaluate: (1) the effectiveness of wireless handheld computers for online information retrieval in clinical settings; (2) the role of MEDLINE in answering clinical questions raised at the point of care. DESIGN: A prospective single-cohort study: accompanying medical teams on teaching rounds, five internal medicine residents used and evaluated MD on Tap, an application for handheld computers, to seek answers in real time to clinical questions arising at the point of care. MEASUREMENTS: All transactions were stored by an intermediate server. Evaluators recorded clinical scenarios and questions, identified MEDLINE citations that answered the questions, and submitted daily and summative reports of their experience. A senior medical librarian corroborated the relevance of the selected citation to each scenario and question. RESULTS: Evaluators answered 68% of 363 background and foreground clinical questions during rounding sessions using a variety of MD on Tap features in an average session length of less than four minutes. The evaluator, the number and quality of query terms, the total number of citations found for a query, and the use of auto-spellcheck significantly contributed to the probability of query success. CONCLUSION: Handheld computers with Internet access are useful tools for healthcare providers to access MEDLINE in real time. MEDLINE citations can answer specific clinical questions when several medical terms are used to form a query. The MD on Tap application is an effective interface to MEDLINE in clinical settings, allowing clinicians to quickly find relevant citations.

Geographically distributed complementary content-based image retrieval systems for biomedical image informatics.

There is a significant increase in the use of medical images in clinical medicine, disease research, and education. While the literature lists several successful systems for content-based image retrieval and image management methods, they have been unable to make significant inroads in routine medical informatics. This can be attributed to the following: (i) the challenging nature of medical images, (ii) need for specialized methods specific to each image type and detail, (iii) lack of advances in image indexing methods, and (iv) lack of a uniform data and resource exchange framework between complementary systems. Most systems tend to focus on varying degrees of the first two items, making them very versatile in a small sampling of the variety of medical images but unable to share their strengths. This paper proposes to overcome these shortcomings by defining a data and resource exchange framework using open standards and software to develop geographically distributed toolkits. As proof-of-concept, we describe the coupling of two complementary geographically separated systems: the IRMA system at Aachen University of Technology in Germany, and the SPIRS system at the U. S. National Library of Medicine in the United States of America.

Automatically identifying health outcome information in MEDLINE records.

OBJECTIVE: Understanding the effect of a given intervention on the patient's health outcome is one of the key elements in providing optimal patient care. This study presents a methodology for automatic identification of outcomes-related information in medical text and evaluates its potential in satisfying clinical information needs related to health care outcomes. DESIGN: An annotation scheme based on an evidence-based medicine model for critical appraisal of evidence was developed and used to annotate 633 MEDLINE citations. Textual, structural, and meta-information features essential to outcome identification were learned from the created collection and used to develop an automatic system. Accuracy of automatic outcome identification was assessed in an intrinsic evaluation and in an extrinsic evaluation, in which ranking of MEDLINE search results obtained using PubMed Clinical Queries relied on identified outcome statements. MEASUREMENTS: The accuracy and positive predictive value of outcome identification were calculated. Effectiveness of the outcome-based ranking was measured using mean average precision and precision at rank 10. RESULTS: Automatic outcome identification achieved 88% to 93% accuracy. The positive predictive value of individual sentences identified as outcomes ranged from 30% to 37%. Outcome-based ranking improved retrieval accuracy, tripling mean average precision and achieving 389% improvement in precision at rank 10. CONCLUSION: Preliminary results in outcome-based document ranking show potential validity of the evidence-based medicine-model approach in timely delivery of information critical to clinical decision support at the point of service.

Edge map analysis in chest X-rays for automatic pulmonary abnormality screening.

PURPOSE: Our particular motivator is the need for screening HIV+ populations in resource-constrained regions for the evidence of tuberculosis, using posteroanterior chest radiographs (CXRs). METHOD: The proposed method is motivated by the observation that abnormal CXRs tend to exhibit corrupted and/or deformed thoracic edge maps. We study histograms of thoracic edges for all possible orientations of gradients in the range [Formula: see text] at different numbers of bins and different pyramid levels, using five different regions-of-interest selection. RESULTS: We have used two CXR benchmark collections made available by the U.S. National Library of Medicine and have achieved a maximum abnormality detection accuracy (ACC) of 86.36 % and area under the ROC curve (AUC) of 0.93 at 1 s per image, on average. CONCLUSION: We have presented an automatic method for screening pulmonary abnormalities using thoracic edge map in CXR images. The proposed method outperforms previously reported state-of-the-art results.

Atlas-based rib-bone detection in chest X-rays.

This paper investigates using rib-bone atlases for automatic detection of rib-bones in chest X-rays (CXRs). We built a system that takes patient X-ray and model atlases as input and automatically computes the posterior rib borders with high accuracy and efficiency. In addition to conventional atlas, we propose two alternative atlases: (i) automatically computed rib bone models using Computed Tomography (CT) scans, and (ii) dual energy CXRs. We test the proposed approach with each model on 25 CXRs from the Japanese Society of Radiological Technology (JSRT) dataset and another 25 CXRs from the National Library of Medicine CXR dataset. We achieve an area under the ROC curve (AUC) of about 95% for Montgomery and 91% for JSRT datasets. Using the optimal operating point of the ROC curve, we achieve a segmentation accuracy of 88.91±1.8% for Montgomery and 85.48±3.3% for JSRT datasets. Our method produces comparable results with the state-of-the-art algorithms. The performance of our method is also excellent on challenging X-rays as it successfully addressed the rib-shape variance between patients and number of visible rib-bones due to patient respiration.