21 research outputs found
A radial self-calibrated (RASCAL) generalized autocalibrating partially parallel acquisition (GRAPPA) method using weight interpolation
No full textVideo Event Detection Using Temporal Pyramids of Visual Semantics with Kernel Optimization and Model Subspace Boosting
No full textUnsupervised Learning of Endoscopy Video Frames’ Correspondences from Global and Local Transformation
No full textOR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis
No full textThe OR 2.0 papers cover a wide range of topics such as machine vision and perception, robotics, surgical simulation and modeling, multi-modal data fusion and visualization, image analysis, advanced imaging, advanced display technologies, human-computer interfaces, sensors. The CARE papers cover topics to advance the field of computer-assisted and robotic endoscopy. The CLIP papers cover topics to fill gaps between basic science and clinical applications. The ISIC papers cover topics to facilitate knowledge dissemination in the field of skin image analysis, as well as to host a melanoma detection challenge, raising awareness and interest for these socially valuable tasks
Expert agreement on the presence and spatial localization of melanocytic features in dermoscopy
No full text: Dermoscopy aids in melanoma detection; however, agreement on dermoscopic features, including those of high clinical relevance, remains poor. Herein we attempted to evaluate agreement among experts on 'exemplar images' not only for the presence of melanocytic-specific features but also for spatial localization. This was a cross-sectional, multicenter, observational study. Dermoscopy images exhibiting at least one of 31 melanocytic-specific features were submitted by 25 world experts as 'exemplars'. Using a web-based platform that allows for image mark-up of specific contrast-defined regions (superpixels), 20 expert readers annotated 248 dermoscopic images in collections of 62 images. Each collection was reviewed by five independent readers. A total of 4,507 feature observations were performed. Good-to-excellent agreement was found for 14 of 31 features (45.2%), with 8 achieving excellent agreement (Gwet's AC >0.75) and 7 of them being melanoma-specific features. These features were: 'Peppering /Granularity' (0.91); 'Shiny White Streaks' (0.89); 'Typical Pigment network' (0.83); 'Blotch Irregular' (0.82); 'Negative Network' (0.81); 'Irregular Globules' (0.78); 'Dotted Vessels' (0.77) and 'Blue Whitish Veil' (0.76). By utilizing an exemplar dataset, good-to-excellent agreement was found for 14 features that have previously been shown useful in discriminating nevi from melanoma. All images are public (www.isic-archive.com) and can be used for education, scientific communication and machine learning experiments
Improved Left Ventricular Mass Quantification with Partial Voxel Interpolation – In-Vivo and Necropsy Validation of a Novel Cardiac MRI Segmentation Algorithm
No full textBackground—CMR typically quantifies LV mass (LVM) via manual planimetry (MP), but this approach is time consuming and does not account for partial voxel components - myocardium admixed with blood in a single voxel. Automated segmentation (AS) can account for partial voxels, but this has not been used for LVM quantification. This study used automated CMR segmentation to test the influence of partial voxels on quantification of LVM. Methods and Results—LVM was quantified by AS and MP in 126 consecutive patients and 10 laboratory animals undergoing CMR. AS yielded both partial voxel (ASPV) and full voxel (ASFV) measurements. Methods were independently compared to LVM quantified on echocardiography (echo) and an ex-vivo standard of LVM at necropsy. AS quantified LVM in all patients, yielding a 12-fold decrease in processing time vs. MP (0:21±0:04 vs. 4:18±1:02 min; pFV mass (136±35gm) was slightly lower than MP (139±35; Δ=3±9gm, pPV yielded higher LVM (159±38gm) than MP (Δ=20±10gm) and ASFV (Δ=23±6gm, both pPV and ASFV correlated with larger voxel size (partial r=0.37, pPV yielded better agreement with echo (Δ=20±25gm) than did ASFV (Δ=43±24gm) or MP (Δ=40±22gm, both pPV and ex-vivo results were similar (Δ=1±3gm, p=0.3), whereas ASFV (6±3g, P\u3c0.001) and MP (4±5 g, P=0.02) yielded small but significant differences with LVM at necropsy
Getting out of the vicious traffic circle: attemps at restructuring the cultural ambience of the automobile throughout the 20th century
No full textFor years, alternative vehicle and propulsion concepts have had a very difficult time catching on, even though technicians and engineers have repeatedly pointed out that the design quality of electric propulsion systems or other novel vehicle concepts is available and feasible. Often enough, this state of affairs allowed free rein for various conspiracy theories, in which extraneous issues were made responsible for the lack of technological breakthrough. This paper agues, however, that innovation research has itself focused too narrowly on the process of the establishment of new products. On the basis of five case examples —the implementation of diesel engine propulsion for street vehicles; the EV1, the first electrically propelled standard car by General Motors; Ford’s prototype electric car study “Pivco”; the NSU Wankel engine; and the “Smart” car manufactured by DaimlerChrysler — an attempt is made to develop a comprehensive understanding of innovation processes which does not stop at the “technical invention” of a device. The thesis is that a new device requires a relevant cultural ambience, which must be more or less invented alongside it in multiple dimensions. Technical-constructive work is thus only one part of a successful innovation process; parallel to this, complementary measures must be taken with regard to the overall sectoral environment, law-making, user perceptions and attributions of meaning, as well as the cultural appropriation of a given device. Without the appropriate “adaptive measures”, even the most interesting technical projects runs the risk of sinking onto oblivion for lack of relevance. -- Alternative Antriebs- und Fahrzeugkonzepte tun sich in der Durchsetzung schon seit Jahren sehr schwer, obwohl immer wieder von Technikern und Ingenieuren darauf verwiesen wird, dass die konstruktive Qualität von elektrischen Antriebssystemen oder anderen neuartigen Fahrzeugkonzepten vorhanden sei. Oft genug konnten daher Verschwörungstheorien Raum greifen, in denen sachfremde Tatbestände für die fehlenden technischen Durchbrüche verantwortlich gemacht wurden. Im vorliegenden Beitrag wird argumentiert, dass die Innovationsforschung selbst einen zu engen Blick auf die Prozesse der Etablierung neuer Produkte eingenommen hat. Anhand von fünf Fallbeispielen, der Durchsetzung des dieselmotorischen Antriebes für Strassenfahrzeuge, des EV1, des ersten elektrisch betriebenen Serienfahrzeuges von General Motors, der Konzeptstudie Pivco, einem Elektroautomobilprojekt des Ford-Konzerns, des NSU-Wankelmotors sowie des neuartigen Fahrzeugkonzeptes Smart wird hingegen versucht, ein umfassendes Verständnis von Innovationsprozessen zu entwickeln, das nicht bei der technischen Erfindung eines Gerätes halt macht. Die These ist, dass neue Geräte zur Durchsetzung am Markt auch einen entsprechenden Funktionsraum benötigen (cultural ambience), der mehrdimensional sozusagen immer gleich miterfunden werden muss. Die technisch-konstruktive Arbeit ist daher nur ein Teilbereich eines erfolgreichen Innovationsprozesses. Parallel müssen weitere Vorkehrungen im Branchenumfeld, bei der Gesetzgebung, bei den Nutzerperzeptionen und Bedeutungszuschreibungen sowie den kulturellen Aneignungsweisen vorgenommen werden. Ohne die entsprechenden Anpassungsmassnahmen droht auch den interessantesten technischen Projekten aus Mangel an Relevanz die Bedeutungslosigkeit.
Predicting adherence to antiretroviral therapy and retention to HIV care : effects of baseline biopsychosocial status and neuropsychological functioning
No full textThese drugs have demonstrated efficacy in improving immune function and reducing HIV-related morbidity and mortality, and while a cure is not available, patients on treatment may live longer, healthier lives. However, early optimism has been tempered by the growing recognition that meticulous adherence is a prerequisite for optimal clinical response and prevention of drug resistance
High performance latent dirichlet allocation for text mining
No full textThis thesis was submitted for the degree of Doctor of Philosophy and awarded by Brunel University.Latent Dirichlet Allocation (LDA), a total probability generative model, is a three-tier Bayesian model. LDA computes the latent topic structure of the data and obtains the significant information of documents. However, traditional LDA has several limitations in practical applications. LDA cannot be directly used in classification because it is a non-supervised learning model. It needs to be embedded into appropriate classification algorithms. LDA is a generative model as it normally generates the latent topics in the categories where the target documents do not belong to, producing the deviation in computation and reducing the classification accuracy. The number of topics in LDA influences the learning process of model parameters greatly. Noise samples in the training data also affect the final text classification result. And, the quality of LDA based classifiers depends on the quality of the training samples to a great extent. Although parallel LDA algorithms are proposed to deal with huge amounts of data, balancing computing loads in a computer cluster poses another challenge. This thesis presents a text classification method which combines the LDA model and Support Vector Machine (SVM) classification algorithm for an improved accuracy in classification when reducing the dimension of datasets. Based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN), the algorithm automatically optimizes the number of topics to be selected which reduces the number of iterations in computation. Furthermore, this thesis presents a noise data reduction scheme to process noise data. When the noise ratio is large in the training data set, the noise reduction scheme can always produce a high level of accuracy in classification. Finally, the thesis parallelizes LDA using the MapReduce model which is the de facto computing standard in supporting data intensive applications. A genetic algorithm based load balancing algorithm is designed to balance the workloads among computers in a heterogeneous MapReduce cluster where the computers have a variety of computing resources in terms of CPU speed, memory space and hard disk space
Results of the 2016 International Skin Imaging Collaboration International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images
No full textComputer vision may aid in melanoma detection.
We sought to compare melanoma diagnostic accuracy of computer algorithms to dermatologists using dermoscopic images.
We conducted a cross-sectional study using 100 randomly selected dermoscopic images (50 melanomas, 44 nevi, and 6 lentigines) from an international computer vision melanoma challenge dataset (n = 379), along with individual algorithm results from 25 teams. We used 5 methods (nonlearned and machine learning) to combine individual automated predictions into “fusion” algorithms. In a companion study, 8 dermatologists classified the lesions in the 100 images as either benign or malignant.
The average sensitivity and specificity of dermatologists in classification was 82% and 59%. At 82% sensitivity, dermatologist specificity was similar to the top challenge algorithm (59% vs. 62%, P = .68) but lower than the best-performing fusion algorithm (59% vs. 76%, P = .02). Receiver operating characteristic area of the top fusion algorithm was greater than the mean receiver operating characteristic area of dermatologists (0.86 vs. 0.71, P = .001).
The dataset lacked the full spectrum of skin lesions encountered in clinical practice, particularly banal lesions. Readers and algorithms were not provided clinical data (eg, age or lesion history/symptoms). Results obtained using our study design cannot be extrapolated to clinical practice.
Deep learning computer vision systems classified melanoma dermoscopy images with accuracy that exceeded some but not all dermatologists
