
ALT Deep joint source-channel coding (DeepJSCC) for image transmission must adapt to changes in the signal-to-noise ratio (SNR) and available transmission resources. However, some existing joint-adaptive methods condition the encoder on the requested rate, while others apply static masks after encoding. The former couples latent formation to the rate request, whereas the latter cannot adapt channel selection to image content. To address these limitations, we propose DecompJSCC, which decomposes joint adaptation into SNR-conditioned latent formation and post-encoding rate control within a single model. The encoder applies SNR-conditioned block attention residuals across all stages, aggregating intra-stage and cross-stage semantic representations. At the receiver, an adapter performs SNR-conditioned affine correction. We introduce a post-encoding rate-adaptive channel semantic budgeting (RCSB) module whose shared gate selects channels of the formed latent by image content, adjusts their gain

ALT Single-photon LiDAR (SPL) sensors offer exceptional temporal resolution and single-photon sensitivity for depth imaging. However, cost-effective SPL arrays typically suffer from extremely low spatial resolutions (e.g. 8Γ 8 pixels), limiting their real-world utility. In this paper, we propose a novel, one-step super-resolution framework, D2ToF, Distilled Diffusion for Time-of-Flight, that bridges the gap between high-fidelity generative modeling and real-time execution. Our approach uses an amortized variational distillation strategy that allows for a measurement-based data consistency term to be incorporated directly into the one-step training objective. This encourages that the synthesized high-resolution depth maps are consistent with the captured low-resolution Time-of-Flight (ToF) histograms. To overcome the severe ill-posedness of upsampling extremely degraded inputs, we introduce a multimodal guidance strategy. By leveraging a foundational monocular depth model to extract structu

ALT Conventional coherent X-ray tomography requires the phase of each projection to be reconstructed with high fidelity. However, individual reconstructed projections might be flawed, e.g. due to positioning errors, yielding inconsistent tomographic reconstructions. By directly coupling phase retrieval and tomography, consistency is enforced through a common object volume. But reconstructing a full volume demands substantial computational resources. To reduce this demand, we introduce Beta Splatted Tomography (BeST), which represents the common object volume using compactly supported beta primitives with closed-form analytical projections, enabling efficient reconstruction directly from coherent scattering images. This representation substantially reduces the number of optimizable parameters compared to a voxel grid. We demonstrate BeST on experimental datasets from hard X-ray near-field holography and far-field ptychography measurements. In both cases, the joint technique improves reconst

ALT Pixelwise classification of hyperspectral images (HSI) is a fundamental task in remote sensing, but its deployment in real-world applications is often limited by the scarcity of labeled data and the presence of unknown classes at inference time. In this work, we propose Few-shot Open-set hyperspectral recognition from Self-Supervised Learning training (FOSSeL), a unified framework for few-shot, open-set hyperspectral pixelwise classification that does not require supervised training. The proposed approach first leverages self-supervised learning to construct a discriminative feature space from unlabeled data. Then, given a small set of labeled seed pixels, class predictions are obtained through spatially-aware graph-based label propagation over superpixel representations, enabling the joint exploitation of spectral similarity and spatial consistency. To address the open-set scenario, we introduce simple yet effective strategies to identify pixels that do not belong to the known classes

ALT An X-ray angiogram sums every structure along a ray into one pixel. When vessels cross an aneurysm, they obscure part of it and mix their contrast into its filling curve. We present X-Strata, a network that separates a cine angiogram into three layers: the complete aneurysm sac, the vessels in front of it, and the vessels behind it. Contrast timing indicates how much each layer contributes to a pixel, and parallax between two views indicates their order, which a single view cannot determine. X-Strata first estimates the layers and their contrast curves, then uses the second view to assign vessels to the front or back layer, and lifts all layers into 3D. It learns from layer labels projected from same-session 3D rotational angiography, but needs only 2D cine runs and their acquisition geometry at inference. On 220 held-out patients from three centers (122 external), two-view X-Strata ranks first among 14 baselines, including VGGT and CΒ²RV, in recovering the sac where vessels overlap it

ALT Accurate prediction of isocitrate dehydrogenase (IDH) mutation status is essential for glioma diagnosis, prognosis, and treatment planning. Although recent deep learning approaches have demonstrated promising performance, many rely on whole-brain feature extraction and provide limited interpretability. This study proposes a tumour-aware multimodal framework for explainable, non-invasive prediction of IDH mutation status from multiparametric magnetic resonance imaging (MRI). The proposed framework integrates four MRI sequences (T1, T1CE, T2, and FLAIR), tumour subregion segmentation, quantitative radiomic descriptors, and clinical information within a unified deep learning architecture. An ablation study was conducted to evaluate the contribution of tumour-aware learning, radiomic features, and clinical variables. Model performance was assessed using multiple complementary evaluation metrics, including accuracy, precision, recall, F1-score, balanced accuracy, receiver operating characte

ALT 2D-to-3D image registration is a key component for several medical imaging purposes such as intraoperative guidance, enabling the alignment between preoperative 3D volumes and real-time 2D images. While conventional optimisation-based methods often struggle with non-convex objectives, sensitivity to initialisation, and high computational demands, deep learning (DL) has emerged as a promising alternative, offering improved alignment robustness and the potential for real-time performance. This review provides a comprehensive analysis of DL frameworks developed to address the challenges inherent in 2D-to-3D registration. We first outline how core concepts of DL are adapted to the registration problem. We then examine recent methodological advancements from multiple perspectives, including pipeline design, architectural innovations, and domain adaptation strategies. Particular attention is given to quantitative metrics, highlighting how performance is defined and measured across studies. A

ALT This document describes open Electrical Impedance Tomography (EIT) measurement data that were collected from biomedical imaging inspired phantoms with moderate conductivity contrasts. The data were collected with the KIT4 and KIT5 EIT measurement devices at the University of Eastern Finland, and are intended for EIT image reconstruction algorithm development and testing. The data from thoracic imaging inspired cylindrical and chest-shaped phantoms are suitable for 2D algorithms, and the data from an intracerebral hemorrhage imaging inspired head-shaped phantom with resistive skull are suitable for 3D algorithms. In addition to the measurement data, computational meshes and example reconstruction codes are provided and sample reconstructions included.

ALT Harmful algal blooms dominated by Microcystis spp. threaten freshwater systems through proliferation and microcystin (MC) production. Conventional measurements of cyanobacterial abundance and MC concentration commonly require laboratory processing, specialized instrumentation, or assay reagents. Because MC concentration cannot always be reliably inferred from cell abundance, complementary optical approaches for estimating both quantities are of interest. This study proposes and evaluates a transmission mode multispectral imaging (MSI) framework for estimating Microcystis spp. cell concentration and ELISA-equivalent MC concentration from culture derived dilution samples. A custom built MSI system acquiring twelve spectral bands from near-ultraviolet to near-infrared wavelengths measured transmitted light spectral responses. Following principal component analysis based dimensionality reduction, spectral variation was quantified using an aggregated Wasserstein distance descriptor for regr

ALT Multitemporal multispectral surface reflectance imagery exhibits radiometric and spectral variability due to atmospheric effects, sensor differences, and actual surface changes, complicating the identification of pseudoinvariant features (PIFs). The SOTA DeepMGCCA captures nonlinear dependencies across acquisition dates, but similarity in its learned feature space does not directly establish consistency in the original reflectance domain. Meanwhile, we believe that the PIFs extracted by DeepMGCCA preserve essential structural characteristics, providing an effective prior to guide subsequent refinement. Therefore, we propose the CODE-PIF architecture, an unsupervised convex/deep (CODE) framework that refines the coarse PIF from DeepMGCCA using convex optimization. Specifically, CODE-PIF uses the data-fitting term to integrate reflectance deviations, correlation-weighted spectral angles, and temporal reference change information to promote radiometric and spectral consistency between pre

ALT Deep learning (DL) has achieved remarkable success in medical image segmentation by learning data-driven representations from large-scale annotated datasets. However, medical images are often collected independently across clinical sites, resulting in substantial domain shifts due to differences in imaging modalities, acquisition protocols, and intensity distributions. Meanwhile, segmentation classes may vary across sites due to differences in annotation standards, leading to class shifts. These evolving domains and class definitions can substantially degrade segmentation performance on newly encountered data, while sequential adaptation may cause catastrophic forgetting of knowledge acquired from previously encountered domains and classes. Existing incremental learning methods for medical image segmentation primarily address either domain shifts or class shifts, with these two settings largely investigated independently. This separation leaves a critical gap in developing a unified ap

ALT Deep-learning-based magnetic resonance imaging (MRI) reconstruction holds great promise for accelerating acquisitions, yet its clinical translation remains bottlenecked by poor generalizability across unseen scanners, populations, anatomies, and protocols. Gathering sufficiently diverse clinical datasets to overcome this bottleneck is hindered by high acquisition costs, privacy restrictions, and institutional biases. Here, we introduce Scalable Inverse Model (SIM), a framework that systematically co-designs physics-simulated training data, model architecture, and learning paradigms around scalabilityβleveraging compute scaling to overcome historical data bottlenecks and achieve robust zero-shot MRI reconstruction. Across 14 public and in-house datasetsβspanning seven international centers, five vendors, field strengths of 0.3-7 T, over ten anatomical regions, more than ten acquisition protocols, downstream quantitative and molecular tasks, and a 150-scan blinded radiologist studyβSIM d

ALT Ultra-high-resolution neural video coding (NVC) remains challenging because temporal correspondence becomes increasingly unreliable as spatial resolution increases. Although recent neural B-frame codecs have improved bi-directional temporal prediction, complex motion and fine-grained structures still lead to unreliable temporal references, while spatial information of the current frame remains underexploited. In this work, we propose HR-NVC++, a unified ultra-high-resolution NVC approach that supports both fidelity-oriented and perceptual-quality-oriented compression with a shared spatial-temporal context. The context integrates bi-directional temporal cues with complementary spatial information: confidence-guided fusion adaptively balances the forward and backward temporal cues according to their estimated correspondence reliability, while a spatial complement branch enriches regions that temporal references fail to explain. The resulting context serves as a common basis for two compr
![Radiotherapy contour ranking can support quality assurance, but vision-language model (VLM) gains may reflect supervision, score construction, available inputs, or representation access. We evaluated frozen MedGemma 1.5 in a single-institution study, a 12-patient held-out HaN-Seg test, five-fold cross-fitting on 30 non-test HaN-Seg patients, and transfer without refitting to 120 SegRap2023 patients. On held-out HaN-Seg, a supervised readout of the final prompt state exceeded a supervised readout of the model's yes/no output probabilities by +0.3047 pooled average precision (AP; 95% patient-bootstrap interval [+0.2822, +0.3269]); the advantage persisted against a parameter-count-matched nonlinear control. A readout of projected visual tokens exceeded the final-state readout in cross-fitting and transfer (+0.0706 AP averaged equally across patients on SegRap; 95% interval [+0.0607, +0.0804]), while a structured panel-feature readout remained competitive with visual tokens. The anatomy-co](https://pbs.twimg.com/media/HXAr_-ZX0AA9IYI.png?name=small&format=webp)
ALT Radiotherapy contour ranking can support quality assurance, but vision-language model (VLM) gains may reflect supervision, score construction, available inputs, or representation access. We evaluated frozen MedGemma 1.5 in a single-institution study, a 12-patient held-out HaN-Seg test, five-fold cross-fitting on 30 non-test HaN-Seg patients, and transfer without refitting to 120 SegRap2023 patients. On held-out HaN-Seg, a supervised readout of the final prompt state exceeded a supervised readout of the model's yes/no output probabilities by +0.3047 pooled average precision (AP; 95% patient-bootstrap interval [+0.2822, +0.3269]); the advantage persisted against a parameter-count-matched nonlinear control. A readout of projected visual tokens exceeded the final-state readout in cross-fitting and transfer (+0.0706 AP averaged equally across patients on SegRap; 95% interval [+0.0607, +0.0804]), while a structured panel-feature readout remained competitive with visual tokens. The anatomy-co

ALT Selective-review systems aim to reduce human review by passing candidates predicted to be low risk. However, coverage (the fraction passed) can be misleading when measurements needed to interpret risk are unavailable. We separate structural evaluability (a nonempty mask with all required measurements available), computational-endpoint status, and pass-or-review decisions using archived Mayo records and controlled OpenKBP analyses. In 3,968 Mayo records, all 1,167 recorded empty predictions (predicted target-organ masks containing zero voxels despite nonempty reference masks) were endpoint-negative and passed both modules, accounting for approximately 76% of each pass set. In a held-out OpenKBP test, a logistic-regression router achieved an area under the receiver operating characteristic curve of 0.833 and average precision of 0.449 but passed all 544 non-evaluable candidates, including 542 prespecified empty-mask controls and 2 erosions that became empty. A structural gate removed tho

ALT Deep-learning-based 3D MRI reconstruction is limited in practice by the GPU memory and compute cost of full-volume training; 3D acquisitions are thus most often reconstructed by 2D models applied slice-by-slice and then stacked, which ignores through-plane (stacking-axis) structure. We reconstruct in full 3D and ask whether a model can be trained at low resolution (fast and memory-feasible) yet deployed at higher resolution. This coarse-to-fine strategy needs reliable cross-resolution performance, but standard networks are resolution-specific and degrade substantially when evaluated outside the training setting. We therefore use resolution-agnostic neural operators (NOs) and propose KIR-NO (k-space-to-Image Reconstruction Neural Operator), a discretization-agnostic framework for accelerated 3D MRI reconstruction. KIR-NO is trained with full backpropagation on low-resolution volumes and applied zero-shot to higher-resolution volumes at inference. Its core building block is a 3D neural o

ALT Medical vision-language models (VLMs) are compared mainly by accuracy averaged across findings, a summary that can hide complete failure on a single diagnosis. We audit five open medical VLMs (MedGemma-4B, Lingshu-7B, HuatuoGPT-Vision-7B, Qwen2.5-VL-7B, and MedVLM-R1) on 6,048 ChestX-ray14 questions balanced by sex, age, finding, and label. On the 432 pneumothorax-positive X-rays, HuatuoGPT-Vision and Qwen2.5-VL detect zero cases while MedGemma and Lingshu detect 38% and 67% of the same images. The two failing models answer "no" to all 864 pneumothorax cases (balanced accuracy 0.500, chance), yet produce fluent, anatomically specific explanations that name the signs of a collapsed lung and then deny them, with no hedge or abstention. This failure is not an artifact of prompting, image resolution, label ambiguity, or model scale. It persists across four prompt formats, at native resolution, and on single-label cases. A within-model control shows the same forced prompt gives HuatuoGPT 79

ALT Deep-learning unrolled networks are the leading approach to accelerated MRI reconstruction. State-of-the-art models such as PromptMR+ learn a distinct block for every cascade, so their size grows with the number of cascades. Sharing one block across iterations avoids adding parameters, but earlier shared-weight models typically used a tiny block and produced worse images than models with distinct weights. Therefore, it remained unclear whether weight sharing itself or the choice of block was the problem. Recent advances in looped transformers, which reuse the same block across layers, show that they can match or outperform their distinct-weight counterparts on several tasks. Motivated by this, we propose LoopMR, which reuses a single Restormer block at every iteration as its core. Besides the current image estimate, the block receives data-consistency inputs and latent images. On four datasets covering the brain (CC359), knee (fastMRI), heart (CMRxRecon2023) and carotid (in-house), Loo

ALT Background blur and background replacement are now normal parts of a video call. Many open models and open source pipelines can do this, but it is hard to know which one to pick. Speed, edge quality and license all matter, and they are often reported on different hardware, or not reported at all. In this work we ran 20 setups on the same laptop CPU, with the same 640x480 frames and the same output view. The setups are 15 open models and 5 complete open source pipelines. We measured frames per second on a test clip and on a live webcam, compared the masks on a public domain portrait and on three video call photos with a raised hand, one of them a close front camera view, and recorded the license of every model. The fastest setups reach more than 40 frames per second on a laptop CPU, while the slowest, a high detail model for still images, needs several seconds per frame. A few setups give clean edges and still run in real time. We also found that the runtime library and the steps around

ALT Intraoperative scene perception in ophthalmic microsurgery is limited by instrument occlusion: when a tool enters the high-magnification field, it conceals tissue from both the surgeon and the perception components of robot-assisted systems that process the video. Generative inpainting can remove the occluder but replaces the missing image content with synthesis, which is unsuitable when visual provenance matters. Many video inpainters also depend on future frames and cannot operate online. We present TransGHOST, a causal reference-guided reconstruction pipeline whose non-generative safe mode operates in real time. Every restored value is obtained by resampling a recorded frame using geometric transforms fitted only to visible regions. The system provides per-pixel confidence and provenance and marks unsupported pixels as abstentions. We evaluate TransGHOST on a new veterinary clinical corpus of canine cataract surgery with pixel-level instrument and anatomy labels. Only the occluded r
