Related papers: A Finely Segmented Semi-Monolithic Detector tailor…
Millimetre-wave observations represent an important tool for Cosmology studies. The Line Intensity Mapping (LIM) technique has been proposed to map in three dimensions the specific intensity due to line (e.g. [CII], CO) emission, for…
Large imaging arrays of detectors at millimeter and submillimeter wavelengths have applications that include measurements of the faint polarization signal in the Cosmic Microwave Background (CMB), and submillimeter astrophysics. We are…
Positron emission tomography (PET) scanners continue to increase sensitivity and axial coverage by adding an ever expanding array of block detectors. As they age, one or more block detectors may lose sensitivity due to a malfunction or…
A high-resolution beam telescope is essential for the precise characterization of silicon pixel sensors. As part of the CSNS-II upgrade project, a High-Energy Proton Beam Telescope (HEPTel) based on monolithic active pixel sensors (MAPS)…
Bent monolithic active pixel sensors are the basis for the planned fully cylindrical ultra low material budget tracking detector ITS3 of the ALICE experiment. This paper presents results from testbeam campaigns using high-energy particles…
The Optically Segmented Single Volume Scatter Camera (OS-SVSC) aims to image neutron sources for non-proliferation applications using the kinematic reconstruction of elastic double-scatter events. Our prototype system consists of 64 EJ-204…
Segmentation is an important analysis task for biomedical images, enabling the study of individual organelles, cells or organs. Deep learning has massively improved segmentation methods, but challenges remain in generalization to new…
Element segmentation is a key step in nondestructive testing of Printed Circuit Boards (PCB) based on Computed Tomography (CT) technology. In recent years, the rapid development of self-supervised pretraining technology can obtain general…
Cancer detection and prognosis relies heavily on medical imaging, particularly CT and PET scans. Deep Neural Networks (DNNs) have shown promise in tumor segmentation by fusing information from these modalities. However, a critical…
Recognition of objects with subtle differences has been used in many practical applications, such as car model recognition and maritime vessel identification. For discrimination of the objects in fine-grained detail, we focus on deep…
Detecting ships in synthetic aperture radar (SAR) images is challenging due to strong speckle noise, complex surroundings, and varying scales. This paper proposes MLDet, a multitask learning framework for SAR ship detection, consisting of…
In this study, we implemented a two-stage deep learning-based approach to segment lesions in PET/CT images for the AutoPET III challenge. The first stage utilized a DynUNet model for coarse segmentation, identifying broad regions of…
Integrated photonic sensors can provide large scale, flexible detection schemes. Photonic crystal slabs (PCS) offer a miniaturized platform for wideband, sensitive ultrasound detection by exploiting the photoelastic effect in water.…
Electron matter interactions in electron microscopy produce both elastic and inelastic scattering, forming the basis for imaging and spectroscopy. However, the integration of electron energy loss spectroscopy (EELS) with 4D-STEM and…
Heterogeneous catalysts possess complex surface and bulk structures, relatively poor intrinsic contrast, and often a sparse distribution of the catalytic nanoparticles (NPs), posing a significant challenge for image segmentation, including…
We present the development of a segmented fast neutron spectrometer (FaNS-2) based upon plastic scintillator and $^3$He proportional counters. It was designed to measure both the flux and spectrum of fast neutrons in the energy range of few…
When testing and calibrating particle detectors in a test beam, accurate tracking information independent of the detector being tested is extremely useful during the offline analysis of the data. A general-purpose Silicon Beam Tracker (SBT)…
Total-Body PET (TB-PET) scanners represent a significant advancement in medical diagnostics, exemplified by the uEXPLORER, the world's first TB-PET system with an axial span of 194 cm, which exhibits exceptional sensitivity and spatial…
The "pre-training then fine-tuning (FT)" paradigm is widely adopted to boost the model performance of deep learning-based methods for medical volumetric segmentation. However, conventional full FT incurs high computational and memory costs.…
Semantic segmentation is a fundamental perception task in autonomous driving, particularly for identifying drivable areas and lane markings to enable safe navigation. However, most state-of-the-art (SOTA) models are computationally…