Search

Jennifer M Wang,1 Sundaresh Ram,2 Wassim W Labaki,1 MeiLan K Han,1 Craig J Galbán2 1Division of Pulmonary and Critical Care Medicine, University of Michigan, Ann Arbor, MI, USA; 2Department of Radiology, University of Michigan, Ann Arbor, MI, USACorrespondence: Craig J Galbán, Department of Radiology, University of Michigan, BSRB, Room A506, 109 Zina Pitcher Place, Ann Arbor, MI, 48109-2200, USA, Tel +1 734-764-8726, Fax +1 734-615-1599, Email cgalban@med.umich.eduAbstract: Chronic obstructive pulmonary disease (COPD) is heterogenous in its clinical manifestations and disease progression. Patients often have disease courses that are difficult to predict with readily available data, such as lung function testing. The ability to better classify COPD into well-defined groups will allow researchers and clinicians to tailor novel therapies, monitor their effects, and improve patient-centered outcomes. Different modalities of assessing these COPD phenotypes are actively being studied, and an area of great promise includes the use of quantitative computed tomography (QCT) techniques focused on key features such as airway anatomy, lung density, and vascular morphology. Over the last few decades, companies around the world have commercialized automated CT software packages that have proven immensely useful in these endeavors. This article reviews the key features of several commercial platforms, including the technologies they are based on, the metrics they can generate, and their clinical correlations and applications. While such tools are increasingly being used in research and clinical settings, they have yet to be consistently adopted for diagnostic work-up and treatment planning, and their full potential remains to be explored.Keywords: lung disease, medical imaging, phenotyping, clinical, quantitative

Early detection of lung cancer is critical for improvement of patient survival. To address the clinical need for efficacious treatments, genetically engineered mouse models (GEMM) have become integral in identifying and evaluating the molecular underpinnings of this complex disease that may be exploited as therapeutic targets. Assessment of GEMM tumor burden on histopathological sections performed by manual inspection is both time consuming and prone to subjective bias. Therefore, an interplay of needs and challenges exists for computer-aided diagnostic tools, for accurate and efficient analysis of these histopathology images. In this paper, we propose a simple machine learning approach called the graph-based sparse principal component analysis (GS-PCA) network, for automated detection of cancerous lesions on histological lung slides stained by hematoxylin and eosin (H&E). Our method comprises four steps: 1) cascaded graph-based sparse PCA, 2) PCA binary hashing, 3) block-wise histograms, and 4) support vector machine (SVM) classification. In our proposed architecture, graph-based sparse PCA is employed to learn the filter banks of the multiple stages of a convolutional network. This is followed by PCA hashing and block histograms for indexing and pooling. The meaningful features extracted from this GS-PCA are then fed to an SVM classifier. We evaluate the performance of the proposed algorithm on H&E slides obtained from an inducible K-rasG12D lung cancer mouse model using precision/recall rates, F-score, Tanimoto coefficient, and area under the curve (AUC) of the receiver operator characteristic (ROC) and show that our algorithm is efficient and provides improved detection accuracy compared to existing algorithms., Comment: 10 pages, 9 figures, 3 tables

Parametric response mapping (PRM) is a novel computed tomography (CT) technology that has shown potential for assessment of bronchiolitis obliterans syndrome (BOS) after hematopoietic stem cell transplantation (HCT). The primary aim of this study was to evaluate whether variations in image acquisition under real-world conditions affect the PRM measurements of clinically diagnosed BOS. CT scans were obtained retrospectively from 72 HCT recipients with BOS and graft-versus-host disease from Fred Hutchinson Cancer Research Center, Karolinska Institute, and the University of Michigan. Whole lung volumetric scans were performed at inspiration and expiration using site-specific acquisition and reconstruction protocols. PRM and pulmonary function measurements were assessed. Patients with moderately severe BOS at diagnosis (median forced expiratory volume at 1 second [FEV1] 53.5% predicted) had similar characteristics between sites. Variations in site-specific CT acquisition protocols had a negligible effect on the PRM-derived small airways disease (SAD), that is, BOS measurements. PRM-derived SAD was found to correlate with FEV1% predicted and FEV1/ forced vital capacity (R = −0.236, P = .046; and R = −0.689, P < .0001, respectively), which suggests that elevated levels in the PRM measurements are primarily affected by BOS airflow obstruction and not CT scan acquisition parameters. Based on these results, PRM may be applied broadly for post-HCT diagnosis and monitoring of BOS.

To help prevent motor vehicle accidents, there has been significant interest in finding an automated method to recognize signs of driver distraction, such as talking to passengers, fixing hair and makeup, eating and drinking, and using a mobile phone. In this paper, we present an automated supervised learning method called Drive-Net for driver distraction detection. Drive-Net uses a combination of a convolutional neural network (CNN) and a random decision forest for classifying images of a driver. We compare the performance of our proposed Drive-Net to two other popular machine-learning approaches: a recurrent neural network (RNN), and a multi-layer perceptron (MLP). We test the methods on a publicly available database of images acquired under a controlled environment containing about 22425 images manually annotated by an expert. Results show that Drive-Net achieves a detection accuracy of 95%, which is 2% more than the best results obtained on the same database using other methods

For object detection in wide-area aerial imagery, post-processing is usually needed to reduce false detections. We propose a two-stage post-processing scheme which comprises an area-thresholding sieving process and a morphological closing operation. We use two wide-area aerial videos to compare the performance of five object detection algorithms in the absence and in the presence of our post-processing scheme. The automatic detection results are compared with the ground-truth objects. Several metrics are used for performance comparison., Comment: 5 Pages, Submitted to 2016 23rd International Conference of Image Processing (ICIP), September 23-28, Phoenix, AZ, USA (Paper ID: 3218)

We propose a 3D convolutional neural network to simultaneously segment and detect cell nuclei in confocal microscopy images. Mirroring the co-dependency of these tasks, our proposed model consists of two serial components: the first part computes a segmentation of cell bodies, while the second module identifies the centers of these cells. Our model is trained end-to-end from scratch on a mouse parotid salivary gland stem cell nuclei dataset comprising 107 image stacks from three independent cell preparations, each containing several hundred individual cell nuclei in 3D. In our experiments, we conduct a thorough evaluation of both detection accuracy and segmentation quality, on two different datasets. The results show that the proposed method provides significantly improved detection and segmentation accuracy compared to state-of-the-art and benchmark algorithms. Finally, we use a previously described test-time drop-out strategy to obtain uncertainty estimates on our predictions and validate these estimates by demonstrating that they are strongly correlated with accuracy., Comment: We were not able to reproduce the results

This work applies sparse representations and nonlinear image processing to two inverse imaging problems. The first problem involves image restoration, where the aim is to reconstruct an unknown high-quality image from a low-quality observed image. Sparse representations of images have drawn a considerable amount of interest in recent years. The assumption that natural signals, such as images, admit a sparse decomposition over a redundant dictionary leads to efficient algorithms for handling such sources of data. The standard sparse representation, however, does not consider the intrinsic geometric structure present in the data, thereby leading to sub-optimal results. Using the concept that a signal is block sparse in a given basis —i.e., the non-zero elements occur in clusters of varying sizes — we present a novel and efficient algorithm for learning a sparse representation of natural images, called graph regularized block sparse dictionary (GRBSD) learning. We apply the proposed method towards two image restoration applications: 1) single-Image super-resolution, where we propose a local regression model that uses learned dictionaries from the GRBSD algorithm for super-resolving a low-resolution image without any external training images, and 2) image inpainting, where we use GRBSD algorithm to learn a multiscale dictionary to generate visually plausible pixels to fill missing regions in an image. Experimental results validate the performance of the GRBSD learning algorithm for single-image super-resolution and image inpainting applications. The second problem addressed in this work involves image enhancement for detection and segmentation of objects in images. We exploit the concept that even though data from various imaging modalities have high dimensionality, the data is sufficiently well described using low-dimensional geometrical structures. To facilitate the extraction of objects having such structure, we have developed general structure enhancement methods th