Classification of urban multi-angular image sequences by aligning their manifolds

When dealing with multi-angular image sequences, problems of reflectance changes due either to illumination and acquisition geometry, or to interactions with the atmosphere, naturally arise. These phenomena interplay with the scene and lead to a modification of the measured radiance: for example, according to the angle of acquisition, tall objects may be seen from top or from the side and different light scatterings may affect the surfaces. This results in shifts in the acquired radiance, that make the problem of multi-angular classification harder and might lead to catastrophic results, since surfaces with the same reflectance return significantly different signals. In this paper, rather than performing atmospheric or bi-directional reflection distribution function (BRDF) correction, a non-linear manifold learning approach is used to align data structures. This method maximizes the similarity between the different acquisitions by deforming their manifold, thus enhancing the transferability of classification models among the images of the sequence.

Vascular postpneumonectomy syndrome: inferior vena cava and pulmonary vein compression as unusual cause for platypnea-orthodeoxia following pneumonectomy

Background: Excessive mediastinal shift into the vacated thoracic cavity after pneumonectomy can result in dyspnea without hypoxemia by compression of the tracheobronchial tree, a phenomenon called postpneumonectomy syndrome. More rarely hypoxemia in upright position (platypnea-orthodeoxia syndrome, POS) after pneumonectomy can result from re-opening of an atrial right-to-left shunt through a patent foramen ovale (PFO) due to mediastinal distorsion. Review of literature also shows a unique report of pulmonary veins stenosis resulting in POS without intracardiac shunt after pneumonectomy. Methods: We report the case of a 32-year-old woman who presented POS 6 months after right pneumonectomy for destroyed lung post tuberculosis. Results: The patient described severe dyspnea disappearing when lying. SpO2 decreased from 94% when lying to 60% sitting. Transthoracic echocardiography (TTE) suspected a possible PFO. We first tried to highlight clinical repercussions of PFO by noninvasive exams. Hyperoxia shunt quantification was not tolerated because of increased dyspnea in sitting position. Contrast bubbles TTE was difficult because of the important mediastinal shift but identified only rare left heart bubbles with/without Valsalva both in lying and sitting position, excluding a significant right-to-left shunt. A lung perfusion scintigraphy (injection while sitting) confirmed the absence of systemic isotope uptake. Computed tomographic pulmonary angiography (angio-CT) revealed a stretched but not stenosed left main bronchus, while the shift of the heart into the right cavity was major. Pulmonary angiography did not show embolism but revealed compression of the inferior vena cava (IVC) with impaired venous return to the right heart, as well as compression of the left pulmonary veins. There was no arteriovenous shunt. Cardiac MRI showed torsion of IVC at the level of the diaphragm, and strong atrial contraction contributing to a passive filling of the RV, while the right ventricle was normal. Right catheterism showed major hemodynamic disturbances with negative diastolic pressure in right heart cavities (atrium -12 mm Hg ventricle pressure -7 mm Hg). SaO2 measured in the pulmonary artery decreased from 58% when lying to 45% sitting. Conclusion: We described here an exceedingly rare and complex mechanism explaining POS after right pneumonectomy. Mediastinal repositioning with a silicone breast implant of appropriate size has been scheduled.

Laparoscopic surgery for coeliac artery compression syndrome: current management and technical aspects.

Objectives: The study aims to assess the feasibility and midterm outcome of trans-peritoneal laparoscopy for coeliac artery compression syndrome (CACS).Design: Retrospective chart review involving four European vascular surgery departments and two surgical teams.Materials and methods: charts for patients who underwent laparoscopy for symptomatic CACS between December 2003 and November 2009 were reviewed. Preoperative computed tomography (CT) angiography and postoperative duplex scan and/or CT angiography were performed.Results: Eleven consecutive patients (nine women) with a median age of 52 years (interquartile range: 42.5-59 years) underwent trans-peritoneal laparoscopy for CACS. All patients had a history of postprandial abdominal pain; weight loss exceeded 10% of the body mass in eight cases. Preoperative CT angiography revealed coeliac trunk stenosis >70% in all cases. One patient had additional aortitis and inferior mesenteric artery occlusion, while another patient presented with an occluded superior mesenteric artery. Two conversions occurred (one difficult dissection and one aorto-hepatic bypass needed for incomplete release of CACS). The median blood loss was 195 ml (range: 50-900 ml) and median operative time was 80 min (interquartile range: 65-162.5 years). Symptoms improved immediately in 10/11 patients (no residual stenosis) while one remained unchanged despite a residual stenosis treated by a percutaneous angioplasty. Symptoms reappeared in one patient due to coeliac axis occlusion. The mean follow-up period was 35 +/- 23 months (range: 12-78 months).Conclusion: Our study demonstrates that trans-peritoneal laparoscopy for treating median arcuate ligament syndrome is safe and feasible. Additional patients and a longer follow-up are needed for long-term assessment of this laparoscopic technique. (C) 2011 European Society for Vascular Surgery. Published by Elsevier Ltd. All rights reserved.

Objective assessment of image quality in conventional and digital mammography taking into account dynamic range.

The goal of this work is to develop a method to objectively compare the performance of a digital and a screen-film mammography system in terms of image quality. The method takes into account the dynamic range of the image detector, the detection of high and low contrast structures, the visualisation of the images and the observer response. A test object, designed to represent a compressed breast, was constructed from various tissue equivalent materials ranging from purely adipose to purely glandular composition. Different areas within the test object permitted the evaluation of low and high contrast detection, spatial resolution and image noise. All the images (digital and conventional) were captured using a CCD camera to include the visualisation process in the image quality assessment. A mathematical model observer (non-prewhitening matched filter), that calculates the detectability of high and low contrast structures using spatial resolution, noise and contrast, was used to compare the two technologies. Our results show that for a given patient dose, the detection of high and low contrast structures is significantly better for the digital system than for the conventional screen-film system studied. The method of using a test object with a large tissue composition range combined with a camera to compare conventional and digital imaging modalities can be applied to other radiological imaging techniques. In particular it could be used to optimise the process of radiographic reading of soft copy images.

MBIS: multivariate Bayesian image segmentation tool.

We present MBIS (Multivariate Bayesian Image Segmentation tool), a clustering tool based on the mixture of multivariate normal distributions model. MBIS supports multichannel bias field correction based on a B-spline model. A second methodological novelty is the inclusion of graph-cuts optimization for the stationary anisotropic hidden Markov random field model. Along with MBIS, we release an evaluation framework that contains three different experiments on multi-site data. We first validate the accuracy of segmentation and the estimated bias field for each channel. MBIS outperforms a widely used segmentation tool in a cross-comparison evaluation. The second experiment demonstrates the robustness of results on atlas-free segmentation of two image sets from scan-rescan protocols on 21 healthy subjects. Multivariate segmentation is more replicable than the monospectral counterpart on T1-weighted images. Finally, we provide a third experiment to illustrate how MBIS can be used in a large-scale study of tissue volume change with increasing age in 584 healthy subjects. This last result is meaningful as multivariate segmentation performs robustly without the need for prior knowledge.

Calibration of a desktop scanner and digital image analysis procedure for quantification of a root morphology

Selostus: Tasoskannerin ja digitaalisen kuva-analyysimenetelmän kalibrointi juurten morfologian kvantifioimiseksi