Istanbul Technical University

Controlling light absorption in digital light processing (DLP) via pigment incorporation offers a versatile approach to tuning curing dynamics, shrinkage behaviour, and mechanical performance in ceramic additive manufacturing. In this study, black pigment (BP) was systematically introduced into a silica-based photopolymer suspension to modulate optical attenuation and enhance the geometric fidelity, surface quality, and dimensional accuracy of printed parts. An optimal 2 wt% BP formulation reduced peeling forces by ≈40% and eliminated recoating resistance, enabling smoother layer separation and improved print stability. Cure uniformity was enhanced, suppressing overcuring artefacts and sharpening lateral features. The degree of polymer conversion increased from ≈50% (no pigment) to ≈76%, correlating with reduced early-stage mass loss during thermogravimetric analysis, indicating a more complete crosslinked network and reduced low-temperature volatilization. These effects led to significantly improved mechanical performance, with green strength reaching ≈36 MPa and sintered strength ≈12 MPa, alongside minimized shrinkage anisotropy (ΔZ–XY ≈ 0.12%). Microstructural and profilometric analyses confirmed improved microstructural integrity and surface quality, with lateral surface roughness reduced to ≈4 μm and cure-induced overgrowth eliminated. Cure depth tuning effectively confined light penetration, improving interlayer bonding and dimensional precision. A full-scale silica-based ceramic core printed with the optimized formulation preserved intricate features and achieved dimensional accuracy within ±0.5 mm after sintering. These findings demonstrate that, within the studied silica-based system, pigment-modified photopolymer formulations enable high-resolution, low-defect DLP ceramic printing, offering a scalable and reliable route for precision components in aerospace, investment casting, and high-temperature tooling. • Black pigment tuned light absorption in DLP ceramic printing, improving cure uniformity and resolution. • At 2 wt.% BP, peeling force dropped ~40%, recoating became resistance-free, and conversion rose to ~76%. • Green and sintered flexural strengths reached ~36 and ~12 MPa, respectively. • Porosity decreased, surface roughness reached ~4 µm Sa, and shrinkage anisotropy was reduced to ~0.12%. • A full-scale silica-based core achieved ±0.5 mm post-sintering accuracy in complex geometries.

Hypoxic Ischemic Encephalopathy (HIE) represents a brain dysfunction, affecting approximately 1 to 5 per 1000 full-term neonates. The precise delineation and segmentation of HIE-related lesions in neonatal brain Magnetic Resonance Images (MRI) are pivotal in advancing outcome predictions, identifying patients at high risk, elucidating neurological manifestations, and assessing treatment efficacies. Despite its importance, the development of algorithms for segmenting HIE lesions from MRI volumes has been impeded by data scarcity. Addressing this critical gap, we organized the first BONBID-HIE challenge with diffusion MRI data (Apparent Diffusion Coefficient (ADC) maps) for HIE lesion segmentation, in conjunction with the MICCAI 2023. Totally 14 algorithms were submitted, employing a gamut of cutting-edge automatic machine-learning-based segmentation algorithms. Our comprehensive analysis of HIE lesion segmentation and submitted algorithms facilitates an in-depth evaluation of the current technological zenith, outlines directions for future advancements, and highlights persistent hurdles. To foster ongoing research and benchmarking, the annotated HIE dataset, developed algorithm dockers, and unified evaluation codes are accessible through a dedicated online platform (https://bonbid-hie2023.grand-challenge.org).

Visual object counting has recently shifted towards class-agnostic counting (CAC), which addresses the challenge of counting objects across arbitrary categories—a crucial capability for flexible and generalizable counting systems. Unlike humans, who effortlessly identify and count objects from diverse categories without prior knowledge, most existing counting methods are restricted to enumerating instances of known classes, requiring extensive labeled datasets for training and struggling in open-vocabulary settings. In contrast, CAC aims to count objects belonging to classes never seen during training, operating in a few-shot setting. In this paper, we present the first comprehensive review of CAC methodologies. We propose a taxonomy to categorize CAC approaches into three paradigms based on how target object classes can be specified: reference-based, reference-less, and open-world text-guided. Reference-based approaches achieve state-of-the-art performance by relying on exemplar-guided mechanisms. Reference-less methods eliminate exemplar dependency by leveraging inherent image patterns. Finally, open-world text-guided methods use vision-language models, enabling object class descriptions via textual prompts, offering a flexible and promising solution. Based on this taxonomy, we provide an overview of 30 CAC architectures and report their performance on gold-standard benchmarks, discussing key strengths and limitations. Specifically, we present results on the FSC-147 dataset, setting a leaderboard using gold-standard metrics, and on the CARPK dataset to assess generalization capabilities. Finally, we offer a critical discussion of persistent challenges, such as annotation dependency and generalization, alongside future directions. We believe this survey offers a valuable resource for researchers, capturing the evolution of CAC and providing insights to guide future developments in the field. • Provides the first comprehensive survey on class-agnostic object counting (CAC). • Proposes a taxonomy: reference-based, reference-less, and open-world text-guided. • Benchmarks 30 CAC methods on FSC-147 and CARPK, setting a leaderboard. • Discusses trade-offs between accuracy, flexibility, and annotation requirements. • Identifies open challenges and future directions for generalizable counting.