Search for: All records

Nuclei segmentation is a fundamental task in histopathological image analysis. Typically, such segmentation tasks require significant effort to manually generate pixel-wise annotations for fully supervised training. To alleviate the manual effort, in this paper we propose a novel approach using points only annotation. Two types of coarse labels with complementary information are derived from the points annotation, and are then utilized to train a deep neural network. The fully- connected conditional random field loss is utilized to further refine the model without introducing extra computational complexity during inference. Experimental results on two nuclei segmentation datasets reveal that the proposed method is able to achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods while requiring significantly less annotation effort. Our code is publicly available. 

Nuclei segmentation and classification are two important tasks in the histopathology image analysis, because the mor- phological features of nuclei and spatial distributions of dif- ferent types of nuclei are highly related to cancer diagnosis and prognosis. Existing methods handle the two problems independently, which are not able to obtain the features and spatial heterogeneity of different types of nuclei at the same time. In this paper, we propose a novel deep learning based method which solves both tasks in a unified framework. It can segment individual nuclei and classify them into tumor, lymphocyte and stroma nuclei. Perceptual loss is utilized to enhance the segmentation of details. We also take advantages of transfer learning to promote the training of deep neural net- works on a relatively small lung cancer dataset. Experimental results prove the effectiveness of the proposed method. The code is publicly available 

A study of multiplicity and pseudorapidity distributions of inclusive photons measured in pp and p–Pb collisions at a center-of-mass energy per nucleon–nucleon collision of$$\sqrt{s_{\textrm{NN}}}~=~5.02$$$\sqrt{s_{\text{NN}}}=5.02$ TeV using the ALICE detector in the forward pseudorapidity region 2.3 $$<~\eta _\textrm{lab} ~<$$$<{\eta }_{\text{lab}}<$ 3.9 is presented. Measurements in p–Pb collisions are reported for two beam configurations in which the directions of the proton and lead ion beam were reversed. The pseudorapidity distributions in p–Pb collisions are obtained for seven centrality classes which are defined based on different event activity estimators, i.e., the charged-particle multiplicity measured at midrapidity as well as the energy deposited in a calorimeter at beam rapidity. The inclusive photon multiplicity distributions for both pp and p–Pb collisions are described by double negative binomial distributions. The pseudorapidity distributions of inclusive photons are compared to those of charged particles at midrapidity in pp collisions and for different centrality classes in p–Pb collisions. The results are compared to predictions from various Monte Carlo event generators. None of the generators considered in this paper reproduces the inclusive photon multiplicity distributions in the reported multiplicity range. The pseudorapidity distributions are, however, better described by the same generators.

 

Abstract The Pandora Software Development Kit and algorithm libraries provide pattern-recognition logic essential to the reconstruction of particle interactions in liquid argon time projection chamber detectors. Pandora is the primary event reconstruction software used at ProtoDUNE-SP, a prototype for the Deep Underground Neutrino Experiment far detector. ProtoDUNE-SP, located at CERN, is exposed to a charged-particle test beam. This paper gives an overview of the Pandora reconstruction algorithms and how they have been tailored for use at ProtoDUNE-SP. In complex events with numerous cosmic-ray and beam background particles, the simulated reconstruction and identification efficiency for triggered test-beam particles is above 80% for the majority of particle type and beam momentum combinations. Specifically, simulated 1 GeV/ c charged pions and protons are correctly reconstructed and identified with efficiencies of 86.1 $$\pm 0.6$$ ± 0.6 % and 84.1 $$\pm 0.6$$ ± 0.6 %, respectively. The efficiencies measured for test-beam data are shown to be within 5% of those predicted by the simulation. 

Wetlands are important sources of methane (CH₄) and sinks of carbon dioxide (CO₂). However, little is known about CH₄and CO₂fluxes and dynamics of seasonally flooded tropical forests of South America in relation to local carbon (C) balances and atmospheric exchange. We measured net ecosystem fluxes of CH₄and CO₂in the Pantanal over 2014–2017 using tower‐based eddy covariance along with C measurements in soil, biomass and water. Our data indicate that seasonally flooded tropical forests are potentially large sinks for CO₂but strong sources of CH₄, particularly during inundation when reducing conditions in soils increase CH₄production and limit CO₂release. During inundation when soils were anaerobic, the flooded forest emitted 0.11 ± 0.002 g CH₄‐C m⁻² d⁻¹and absorbed 1.6 ± 0.2 g CO₂‐C m⁻² d⁻¹(mean ± 95% confidence interval for the entire study period). Following the recession of floodwaters, soils rapidly became aerobic and CH₄emissions decreased significantly (0.002 ± 0.001 g CH₄‐C m⁻² d⁻¹) but remained a net source, while the net CO₂flux flipped from being a net sink during anaerobic periods to acting as a source during aerobic periods. CH₄fluxes were 50 times higher in the wet season; DOC was a minor component in the net ecosystem carbon balance. Daily fluxes of CO₂and CH₄were similar in all years for each season, but annual net fluxes varied primarily in relation to flood duration. While the ecosystem was a net C sink on an annual basis (absorbing 218 g C m⁻²(as CH₄‐C + CO₂‐C) in anaerobic phases and emitting 76 g C m⁻²in aerobic phases), high CH₄effluxes during the anaerobic flooded phase and modest CH₄effluxes during the aerobic phase indicate that seasonally flooded tropical forests can be a net source of radiative forcings on an annual basis, thus acting as an amplifying feedback on global warming.