A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.

Magnetic resonance coronary lumen and vessel wall imaging.

Coronary magnetic resonance angiography (MRA) is a technique aimed at establishing a noninvasive test for the assessment of significant coronary stenoses. There are certain boundary conditions that have hampered the clinical success of coronary MRA and coronary vessel wall imaging. Recent advances in hardware and software allow for consistent visualization of the proximal and mid portions of the native coronary arteries. Current research focuses on the use of intravascular MR contrast agents and black blood coronary angiography. One common goal is to create a noninvasive test which might allow for screening for major proximal and mid coronary artery disease. These novel approaches will represent a major step forward in diagnostic cardiology.

Comparative cost-effectiveness analyses of cardiovascular magnetic resonance and coronary angiography combined with fractional flow reserve for the diagnosis of coronary artery disease.

BACKGROUND: According to recent guidelines, patients with coronary artery disease (CAD) should undergo revascularization if significant myocardial ischemia is present. Both, cardiovascular magnetic resonance (CMR) and fractional flow reserve (FFR) allow for a reliable ischemia assessment and in combination with anatomical information provided by invasive coronary angiography (CXA), such a work-up sets the basis for a decision to revascularize or not. The cost-effectiveness ratio of these two strategies is compared. METHODS: Strategy 1) CMR to assess ischemia followed by CXA in ischemia-positive patients (CMR + CXA), Strategy 2) CXA followed by FFR in angiographically positive stenoses (CXA + FFR). The costs, evaluated from the third party payer perspective in Switzerland, Germany, the United Kingdom (UK), and the United States (US), included public prices of the different outpatient procedures and costs induced by procedural complications and by diagnostic errors. The effectiveness criterion was the correct identification of hemodynamically significant coronary lesion(s) (= significant CAD) complemented by full anatomical information. Test performances were derived from the published literature. Cost-effectiveness ratios for both strategies were compared for hypothetical cohorts with different pretest likelihood of significant CAD. RESULTS: CMR + CXA and CXA + FFR were equally cost-effective at a pretest likelihood of CAD of 62% in Switzerland, 65% in Germany, 83% in the UK, and 82% in the US with costs of CHF 5'794, euro 1'517, £ 2'680, and $ 2'179 per patient correctly diagnosed. Below these thresholds, CMR + CXA showed lower costs per patient correctly diagnosed than CXA + FFR. CONCLUSIONS: The CMR + CXA strategy is more cost-effective than CXA + FFR below a CAD prevalence of 62%, 65%, 83%, and 82% for the Swiss, the German, the UK, and the US health care systems, respectively. These findings may help to optimize resource utilization in the diagnosis of CAD.

Choledocholithiasis: repetitive thick-slab single-shot projection magnetic resonance cholangiopancreaticography versus endoscopic ultrasonography.

This prospective study compares repetitive thick-slab single-shot projection magnetic resonance cholangiopancreatography (MRCP) with endoscopic ultrasonography (EUS) for the detection of choledocholithiasis. Fifty-seven consecutive patients (36 women, mean age 61) referred for suspected choledocholithiasis underwent MRCP, followed by EUS. Each procedure was performed by different operators blinded to the results of the other investigation. MR technique included a turbo spin-echo T2-weighted axial sequence with selective fat saturation (SPIR/TSE, TE=70 ms, TR=1,600 ms), followed by coronal dynamic MRCP. The same thick-slab slice was sequentially acquired 12 times as breath-hold single-shot projection imaging (SSh, TE=900 ms, TE=8,000 ms) centred on the common bile duct (CBD). Two experienced radiologists independently and blindly evaluated MR images for the detection of CBD stones. Their inter-observer agreement kappa was determined. Secondly, the two observers read MR images in consensus again. CBD stones were demonstrated in 18 out of 57 patients (31.6 %) and confirmed by endoscopic retrograde cholangiography (ERCP, n=17) or intraoperative cholangiography (n=1). Clinical follow-up served as the "gold standard" in patients with negative results without following invasive procedure (n=28). Sensitivity, specificity, accuracy, positive and negative predictive value for MRCP resulting from consensus reading were 94.9%, 94.4%, 94.7%, 97.4% and 89.5%, respectively. Corresponding values of EUS were 97.4%, 94.4%, 96.5%, 97.4% and 94.4%. Inter-observer agreement kappa was 0.81. Repetitive thick-slab single-shot projection MRCP is an accurate non-invasive imaging modality for suspected choledocholithiasis and should be increasingly used to select those patients who require a subsequent therapeutic procedure, namely ERCP.

Controlled study of 50-Hz repetitive transcranial magnetic stimulation for the treatment of Parkinson disease.

OBJECTIVE: To investigate the safety and efficacy of 50-Hz repetitive transcranial magnetic stimulation (rTMS) in the treatment of motor symptoms in Parkinson disease (PD). BACKGROUND: Progression of PD is characterized by the emergence of motor deficits that gradually respond less to dopaminergic therapy. rTMS has shown promising results in improving gait, a major cause of disability, and may provide a therapeutic alternative. Prior controlled studies suggest that an increase in stimulation frequency might enhance therapeutic efficacy. METHODS: In this randomized, double blind, sham-controlled study, the authors investigated the safety and efficacy of 50-Hz rTMS of the motor cortices in 8 sessions over 2 weeks. Assessment of safety and clinical efficacy over a 1-month period included timed tests of gait and bradykinesia, Unified Parkinson's Disease Rating Scale (UPDRS), and additional clinical, neurophysiological, and neuropsychological parameters. In addition, the safety of 50-Hz rTMS was tested with electromyography-electroencephalogram (EMG-EEG) monitoring during and after stimulation. RESULTS: The authors investigated 26 patients with mild to moderate PD: 13 received 50-Hz rTMS and 13 sham stimulation. The 50-Hz rTMS did not improve gait, bradykinesia, and global and motor UPDRS, but there appeared a short-lived "on"-state improvement in activities of daily living (UPDRS II). The 50-Hz rTMS lengthened the cortical silent period, but other neurophysiological and neuropsychological measures remained unchanged. EMG/EEG recorded no pathological increase of cortical excitability or epileptic activity. There were no adverse effects. CONCLUSION: It appears that 50-Hz rTMS of the motor cortices is safe, but it fails to improve motor performance and functional status in PD. Prolonged stimulation or other techniques with rTMS might be more efficacious but need to be established in future research.

Direct magnetic resonance arthrography of the wrist with axial traction: A feasibility study to assess joint cartilage.

PURPOSE: To assess the impact of axial traction during acquisition of direct magnetic resonance (MR) arthrography of the wrist with regard to joint space width and amount of contrast material between the opposing cartilage surfaces. MATERIALS AND METHODS: Fifteen consecutive patients (12 male, mean age 38.1 years) were included in this Institutional Review Board-approved prospective study. Three-compartment wrist MR arthrographies were performed between October and December 2009 on a 3 T unit using a fat-suppressed T1-weighted isotropic high-resolution volumetric interpolated breathhold examination (VIBE) sequence in the coronal plane, with and without axial traction (3 kg). Two radiologists measured radiocarpal (radioscaphoid, radiolunate) and midcarpal (lunocapitate, hamatolunate) joint space widths, with and without traction, and assessed the amount of contrast material between the opposing cartilage surfaces using a three-point scale: 0 = absence, 1 = partial, 2 = complete. RESULTS: With traction, joint space width increased significantly at the radioscaphoid (Delta = 0.78 mm, P < 0.01), radiolunate (Delta = 0.18 mm, P < 0.01), and lunocapitate (Delta = 0.45 mm, P < 0.01) spaces, and both observers detected significantly more contrast material between the cartilage surfaces. At the hamatolunate space, the differences in joint space width (Delta = 0.14 mm, P = 0.54) and amount of contrast material were not significant. CONCLUSION: Direct wrist MR arthrography with axial traction of 3 kg increases joint space width at the radiocarpal and lunocapitate spaces, and prompts better coverage of the articular cartilage by the contrast material. J. Magn. Reson. Imaging 2011;. (c) 2011 Wiley-Liss, Inc.

Motion compensation strategies in magnetic resonance imaging.

Image quality in magnetic resonance imaging (MRI) is considerably affected by motion. Therefore, motion is one of the most common sources of artifacts in contemporary cardiovascular MRI. Such artifacts in turn may easily lead to misinterpretations in the images and a subsequent loss in diagnostic quality. Hence, there is considerable research interest in strategies that help to overcome these limitations at minimal cost in time, spatial resolution, temporal resolution, and signal-to-noise ratio. This review summarizes and discusses the three principal sources of motion: the beating heart, the breathing lungs, and bulk patient movement. This is followed by a comprehensive overview of commonly used compensation strategies for these different types of motion. Finally, a summary and an outlook are provided.

Cost evaluation of cardiovascular magnetic resonance versus coronary angiography for the diagnostic work-up of coronary artery disease: Application of the European Cardiovascular Magnetic Resonance registry data to the German, United Kingdom, Swiss, and United States health care systems.

ABSTRACT: BACKGROUND: Cardiovascular magnetic resonance (CMR) has favorable characteristics for diagnostic evaluation and risk stratification of patients with known or suspected CAD. CMR utilization in CAD detection is growing fast. However, data on its cost-effectiveness are scarce. The goal of this study is to compare the costs of two strategies for detection of significant coronary artery stenoses in patients with suspected coronary artery disease (CAD): 1) Performing CMR first to assess myocardial ischemia and/or infarct scar before referring positive patients (defined as presence of ischemia and/or infarct scar to coronary angiography (CXA) versus 2) a hypothetical CXA performed in all patients as a single test to detect CAD. METHODS: A subgroup of the European CMR pilot registry was used including 2,717 consecutive patients who underwent stress-CMR. From these patients, 21% were positive for CAD (ischemia and/or infarct scar), 73% negative, and 6% uncertain and underwent additional testing. The diagnostic costs were evaluated using invoicing costs of each test performed. Costs analysis was performed from a health care payer perspective in German, United Kingdom, Swiss, and United States health care settings. RESULTS: In the public sectors of the German, United Kingdom, and Swiss health care systems, cost savings from the CMR-driven strategy were 50%, 25% and 23%, respectively, versus outpatient CXA. If CXA was carried out as an inpatient procedure, cost savings were 46%, 50% and 48%, respectively. In the United States context, cost savings were 51% when compared with inpatient CXA, but higher for CMR by 8% versus outpatient CXA. CONCLUSION: This analysis suggests that from an economic perspective, the use of CMR should be encouraged as a management option for patients with suspected CAD.

Subduction and obduction processes in the Swiss Alps

The significance of the Brianconnais domain in the Alpine orogen is reviewed in the light of data concerning its collision with the active Adriatic margin and the passive Helvetic margin. The Brianconnais which formerly belonged to the Iberian plate, was located on the northern margin of the Alpine Tethys (Liguro-Piemont ocean) since its opening in the early-Middle Jurassic. Together with the Iberian plate the Brianconnais terrane was separated from the European plate in the Late Jurassic-Early Cretaceous, following the northern Atlantic, Bay of Biscay, Valais ocean opening. This was accompanied by the onset of subduction along the northern margin of Adria and the closure of the Alpine Tethys. Stratigraphic and metamorphic data regarding this subduction and the geohistory of the Brianconnais allows the scenario of subduction-obduction processes during the Late Cretaceous-early Tertiary in the eastern and western Alps to be specified. HP-LT metamorphism record a long-lasting history of oceanic subduction-accretion, followed in the Middle Eocene by the incorporation of the Brianconnais as an exotic terrane into the accretionary prism. Middle to Late Eocene cooling ages of the Brianconnais basement and the presence of pelagic, anorogenic sedimentation lasting until the Middle Eocene on the Brianconnais preclude any sort of collision before that time between this domain and the active Adria margin or the Helvetic margin. This is confirmed by plate reconstructions constrained by magnetic anomalies in the Atlantic domain. Only a small percentage of the former Brianconnais domain was obducted, most of the crust and lithospheric roots were subducted. This applies also to domains formerly belonging to the southern Alpine Tethys margin (Austroalpine-inner Carpathian domain). It is proposed that there was a single Palaeogene subduction zone responsible for the Alpine orogen formation (from northern Spain to the East Carpathians), with the exception of a short-lived Late Cretaceous partial closure of the Valais ocean. Subduction in the western Tethyan domain originated during the closure of the Meliata ocean during the Jurassic incorporating the Austroalpine-Carpathian domain as terranes during the Cretaceous. The subduction zone propagated into the northern margin of Adria and then to the northern margin of the Iberian plate, where it gave birth to the Pyrenean-Provencal orogenic belt. This implies the absence of a separated Cretaceous subduction zone within the Austro-Carpathian Penninic ocean. Collision of Iberia with Europe forced the subduction to jump to the SE margin of Iberia in the Eocene, creating the Apenninic orogenic wedge and inverting the vergence of subduction from south- to north-directed. (C) 1998 Elsevier Science B.V. All rights reserved.

Transcriptional activation of the utrophin promoter B by a constitutively active Ets-transcription factor.

Duchenne muscular dystrophy is an X-linked genetic disease caused by the absence of functional dystrophin. Pharmacological upregulation of utrophin, the autosomal homologue of dystrophin, offers a potential therapeutic approach to treat Duchenne patients. Full-length utrophin mRNA is transcribed from two alternative promoters, called A and B. In contrast to the utrophin promoter A, little is known about the factors regulating the activity of the utrophin promoter B. Computer analysis of this second promoter revealed the presence of several conserved binding motives for Ets-transcription factors. Using electrotransfer of cDNA into mouse muscles, we demonstrate that a genetically modified beta-subunit of the Ets-transcription factor GA-binding protein potently activates a utrophin promoter B reporter construct in innervated muscle fibers in vivo. These results make the GA-binding protein and the signaling cascade regulating its activity in muscle cells, potential targets for the pharmacological modulation of utrophin expression in Duchenne patients.

A gene-rich, transcriptionally active environment and the pre-deposition of repressive marks are predictive of susceptibility to KRAB/KAP1-mediated silencing.

AbstractBACKGROUND: KRAB-ZFPs (Krüppel-associated box domain-zinc finger proteins) are vertebrate-restricted transcriptional repressors encoded in the hundreds by the mouse and human genomes. They act via an essential cofactor, KAP1, which recruits effectors responsible for the formation of facultative heterochromatin. We have recently shown that KRAB/KAP1 can mediate long-range transcriptional repression through heterochromatin spreading, but also demonstrated that this process is at times countered by endogenous influences.METHOD: To investigate this issue further we used an ectopic KRAB-based repressor. This system allowed us to tether KRAB/KAP1 to hundreds of euchromatic sites within genes, and to record its impact on gene expression. We then correlated this KRAB/KAP1-mediated transcriptional effect to pre-existing genomic and chromatin structures to identify specific characteristics making a gene susceptible to repression.RESULTS: We found that genes that were susceptible to KRAB/KAP1-mediated silencing carried higher levels of repressive histone marks both at the promoter and over the transcribed region than genes that were insensitive. In parallel, we found a high enrichment in euchromatic marks within both the close and more distant environment of these genes.CONCLUSION: Together, these data indicate that high levels of gene activity in the genomic environment and the pre-deposition of repressive histone marks within a gene increase its susceptibility to KRAB/KAP1-mediated repression.

Best practice in the management of mild-to-moderately active ulcerative colitis and achieving maintenance of remission using mesalazine.

Optimizing treatment goals in ulcerative colitis requires recognizing the needs of patients. It is increasingly recognized that adapting treatment strategies aligned with patient needs can improve patient compliance and consequently minimize relapse rates. Tailoring of treatment strategies can improve not only patient quality of life, and decrease the number harmed by adverse events from more potent drugs, but can also save valuable healthcare costs by avoiding high-cost treatment interventions associated with acute ulcerative colitis. This review will consider several elements of mesalazine management from the patient perspective based on a range of clinical and patient-focused evidence. By highlighting patient preferences in disease management it is envisaged that this review will aid physicians to optimize treatment decisions with the different mesalazine preparations available.