IEEE Transactions on Medical Imaging

Magnetic resonance imaging (MRI) exhibits substantial scanner and protocol dependent appearance variations, making harmonization challenging without distorting patient specific anatomy, particularly in abdominal imaging. We propose AC-Diff, an anatomy--contrast disentangled diffusion framework that formulates MRI harmonization as a factor-specific generative intervention. Using aligned multi-contrast supervision and cross-patient factor swapping, AC-Diff learns to separate anatomical structure from acquisition-dependent contrast. Unlike conventional image or latent diffusion, AC-Diff restricts stochastic generation to the contrast subspace while the source anatomy bypasses diffusion and is directly reused during reconstruction. Experiments on an in-house multi-vendor cohort and the external Duke Liver MRI dataset demonstrate improved target-domain alignment with strong structural preservation. In downstream liver segmentation, AC-Diff improves Dice from 0.942 for the original inputs to 0.954 for the harmonized images. These results support contrast-specific latent generation as a promising approach to anatomy-preserving MRI harmonization.

The Transport-of-Intensity Equation (TIE) and polarization differential phase contrast (pDPC) exhibit transfer characteristics that limit their use as standalone quantitative phase imaging modalities. TIE provides stable recovery of low spatial frequencies but attenuates fine structure, while pDPC enhances phase gradients but is intrinsically insensitive near zero frequency. We present a hybrid reconstruction framework that combines a single-shot pDPC measurement with an in-focus-defocused TIE image pair and fuses the resulting phase estimates in the Fourier domain using frequency-selective weighting. The illumination geometry is co-designed to enforce angular separation between modalities, enabling high-frequency phase-gradient acquisition in a single exposure while preserving low-frequency sensitivity through low-numerical-aperture symmetric illumination. The proposed method requires three intensity measurements without requiring interferometric stability or sequential asymmetric illumination. Experimental results demonstrate improved phase fidelity across spatial frequencies, reduced halo artifacts, and enhanced recovery of both smooth and fine structural features. This approach provides a compact and robust method that moves towards extended spatial-frequency phase imaging for dynamic and resource-constrained applications.

Vector flow mapping (VFM) reconstructs left-ventricular (LV) blood velocity from color-Doppler echocardiography by combining the measured beamwise component with physical and regularizing constraints. Analysis of the discrete VFM formulation shows that the inverse problem is intrinsically ill posed: the occurrence of singular modes can be predicted from the geometry of the segmented blood-pool domain, the imposed boundary conditions, and the degree of smoothing. These modes can propagate uncertainty along entire transverse bands of the reconstructed velocity field, yet conventional VFM neither quantifies this uncertainty nor allows for correcting the blood-pool segmentation. We introduce Bayesian VFM (B--VFM), a hierarchical framework that jointly infers radial and transverse velocities, a probabilistic blood-pool mask, their spatially resolved uncertainties, and hyperparameters weighting Doppler and segmentation fidelity, mass conservation, boundary conditions, and smoothness. The discretized posterior admits a closed-form gradient and exact Hessian, enabling computationally efficient, gradient-based MAP estimation, sampling, and direct analysis of ill-posed modes. Posterior inference combines Gibbs sampling of conjugate Gamma-distributed hyperparameters with conditional maximum-a-posteriori estimation and a Laplace approximation for the high-dimensional velocity and mask fields. To accommodate systematic departures from planar mass conservation, B-VFM can learn the covariance of the planar divergence residual from an ensemble of flows and incorporate it as a structured model-discrepancy prior. Independent chains converged reproducibly, while covariance priors learned from flow ensembles illustrated how model discrepancies can be incorporated into the inference. B--VFM was evaluated using Lamb-Chaplygin dipoles under ideal conditions and with Doppler corruption, Doppler voids, and segmentation defects, and using the Hicks-Moffatt family of spherical vortices to assess violations of planar mass conservation. The method produced smooth reconstructions, localized uncertainty near unreliable measurements and regions of model inconsistency, and used flow information to correct segmentation errors. Within the tested vortex family, the data-informed planar divergence prior reduced velocity bias and mask distortion. B--VFM thus provides an uncertainty-aware reconstruction method and a flexible foundation for future VFM formulations incorporating additional priors, observations, and physical models. Future work will evaluate the method using clinical data and more complex three-dimensional benchmark flows.

Text-driven medical image segmentation demands unified models based on multi-modal learning, capable of processing diverse imaging modalities while providing spatially reliable prediction estimates for clinical practice. Nevertheless, existing vision-language model solutions suffer from poor domain generalization and exhibit limited capability for uncertainty estimation to model the cumulative unreliability of cross-modal alignment across network layers. In this paper, we propose UniMedSeg, a unified vision-language framework for multi-modal medical image segmentation built upon frozen pre-trained vision-language backbones. Our framework incorporates modality-aware adaptation, cross-layer uncertainty-guided encoding, and a frequency-spatial dual-prompt decoder, wherein the progressive uncertainty propagation mechanism of the encoder suppresses misleading cross-modal features, whereas the decoder disentangles anatomical structure and boundary details in the frequency domain under dual textual prompts. Auxiliary losses further sharpen boundary representations and calibrate pixel-wise uncertainty maps. Extensive experiments demonstrate that UniMedSeg preserves competitive in-domain segmentation performance, improves domain generalization, and yields clinically useful spatial risk estimation.

Optical coherence tomography angiography (OCTA) has been extensively explored for the detection of pathological retinal changes arising in various ophthalmological diseases. Due to phase instability of conventional systems, most OCTA signal processing methods to date have relied on intensity-based averaging, despite the resulting lower contrast and dynamic range compared to coherent averaging approaches. In this work, we (1) present a novel computation pipeline that enables fully-coherent processing in any phase-stable or phase-unstable system, and (2) demonstrate the first angiography metric with integrated signal-to-noise ratio (SNR) correction and coherent spatiotemporal ensemble averaging effective in any OCT system. Our method does not rely on 2D en face projections or binarization to produce high-contrast en face views and it significantly enhances the contrast-to-noise ratio of computed OCTA volumes, particularly in regions with reduced SNR levels. Our OCTA volumes also have high cross-sectional quality, enabling the use of single-depth en face views and the localization of capillary paths in the axial dimension. We can now identify capillaries below the retinal pigment epithelium, near the lamina cribrosa in the optic cup, which was not previously possible due to low SNR. We also conducted an analysis of strategies for bias reduction in OCTA and developed the optimal method utilizing coherent spatiotemporal ensemble averaging. Because our method leverages coherent averaging across all dimensions, it provides flexibility in shaping the averaging kernel to target specific workflows. The value of this additional degree of freedom is illustrated in our vessel tracing investigations, in which the depth resolution was maximized by limiting coherent ensemble averaging to the two lateral dimensions even in presence of strong phase noise, enabling the identification of 3D features such as overlapping capillary paths.

Synthetic medical data are commonly generated from manually chosen prompts, inverse frequency sampling, or fixed subgroup balancing rules. These strategies increase sample count but do not answer a more consequential question: which missing observations would most improve the current model? We introduce GAP DREAM, a closed-loop framework that treats a medical image generator as a queryable source of candidate evidence rather than an unlimited source of augmentation. At each round, GAP DREAM maps model failures into an evidence gap score that combines scarcity, predictive uncertainty, local representation density, and gradient novelty. A query policy translates high-value gaps into structured clinical requests, a modality specific generator proposes candidate imagetext pairs, and an independent selector retains only diagnostically consistent, diverse, non-duplicative candidates. The downstream model is then updated and the gap map recomputed. The central objective is therefore not image realism in isolation, but reduction of measurable evidence gaps under a fixed synthetic budget. Across a multi-modality protocol spanning long-tailed chest radiography, dermoscopy, clinical dermatology, and histopathology, GAPDREAM reaches stronger held-out real-data performance with substantially fewer generated samples than random,class-balanced, uncertainty-only, and static targeted augmentation. Results show gains in CXRLT tail mAP, HAM10000 macroAUROC, Came lyon17 out-of-domain accuracy, and worst group dermatology accuracy while reducing redundant synthetic samples. GAPDREAM reframes medical generation as active evidence acquisition: generate the examples the learner needs, not simply more examples of what is rare.

Coarse to fine segmentation is a natural strategy for three dimensional lesion delineation becausefull resolution processing of an entire scan is expensive while only a small fraction of the volume contains pathology. Its main failure mode, however, is structural: a lesion missed by the coarse stage is usually absent from the region of interest and therefore cannot be recovered by the fine stage. This problem is most severe for small, low contrast, and multifocal lesions. We introduce RECALLREFINE, a coverage constrained coarse to fine framework that treats candidate-region selection as a recall critical learning problem rather than a deterministic crop around the coarse mask.A full-volume network first predicts coarse lesion probabilities and multi-scale features. A candidate score network then combines coarse probability, predictive uncertainty, feature novelty, and spatial context to score overlapping 3D blocks. During training, a differentiable selector is optimized with a component-wise coverage objective that requires every annotated lesion instance to remain covered by at least one selected block under a fixed refinement budget. Selected blocks are processed at native resolution by a local refiner with a context-ring branch, and overlapping predictions are merged back into the full volume. Across four public 3D lesion benchmarks, RECALLREFINE improves mean tumor Dice from 76.5% for the strongest matched coarse-to-fine baseline to 78.4%, while increasing sensitivity for lesions below 10 mm from 60.9% to 70.8%.At a 20% candidate budget, the selector covers 94.4% of lesion instances, substantially reducing irreversible coarse-stage misses. The results suggest that the central problem in cascaded lesion segmentation is not only how to refine a detected lesion, but how to guarantee that difficult lesions are still represented in the refinement set.

Purpose: To evaluate, within a synthetic pulmonary-artery benchmark, whether biomarker-aware super-resolution improves hemodynamic endpoint fidelity in 4D flow MRI. Methods: A 3D residual channel attention network (RCAN) was trained on 22 CFD simulations from 11 pulmonary-artery geometries with 2x spatial degradation. The original primary comparison evaluated full biomarker-aware training against a combined divergence-temporal-regularization control across 14 matched seeds on a fixed six-case test set. Additional matched analyses subsequently separated divergence and adjacent-frame temporal-difference regularization and evaluated biomarker supervision in a controlled 2x2 design with a common reconstruction schedule. Results: In the original primary comparison, biomarker-aware training reduced PI error relative to the matched combined-regularization control (12.76 +/- 2.34% vs. 17.12 +/- 1.23%; paired difference -4.35 percentage points [95% CI -5.58, -3.09]; p = 0.0015). In the matched factorial analysis, biomarker supervision reduced PI error without (-2.235 percentage points [95% CI -3.514, -0.849]) and with (-4.125 percentage points [95% CI -5.392, -2.732]) combined regularization. PI improvement was not mirrored by uniformly improved reconstruction metrics: PSNR changed by -0.058 (p = 0.50) and +0.144 dB (p = 0.28), while SSIM decreased by 0.009 (p = 0.004) and 0.007 (p = 0.009), respectively. Divergence alone changed PI by +0.034 percentage points [95% CI -0.705, 0.809] while reducing DivRMS by 1.869 percentage points; temporal-difference regularization increased PI error by 1.562 percentage points [95% CI 0.594, 2.439]. Conclusion: Within this synthetic, fixed-case RCAN benchmark, biomarker supervision improved PI under both regularization conditions. PI improvement was not mirrored by uniformly improved reconstruction metrics. Temporal-difference - not divergence - regularization was the only isolated component associated with reproducible PI deterioration. These findings are configuration-specific and require geometry-independent and in vivo validation.

Quantitative analysis of biological shape is central to understanding how form encodes function. Despite rapid advances in volumetric imaging and segmentation, analysis and of three-dimensional morphology remains challenging due to complex geometries and topologies found in biology. Existing approaches either rely on handcrafted metrics that lack generalizability or employ data-driven neural models that sacrifice interpretability and robustness. Here, we introduce Minkowski Tensors (MT), a family of integral-geometric shape descriptors that extend classical scalar measures of volume, surface area, and curvature into tensor-valued quantities encoding direction and anisotropy. MT form a provably complete yet compact and interpretable feature set that captures volumetric and curvature-based information in a transformation- and scale-covariant, topology-aware manner. We benchmark MT on diverse segmented 3D biomedical images spanning vascular and adrenal structures from magnetic resonance angiography (MRA) and computed tomography (CT), and dividing cell nuclei imaged by confocal microscopy, demonstrating competitive or superior classification performance relative to classical geometric descriptors and neural baselines while retaining direct biological interpretability. Our results establish Minkowski tensors as a concise yet powerful framework for discriminative analysis of complex 3D biological morphology.

Accurate breast lesion segmentation in ultrasound is difficult because speckle noise, heterogeneous lesion appearance, and poorly defined margins can obscure clinically relevant boundaries. This work presents UGB-SegNet, an uncertainty-guided breast ultrasound segmentation network that combines four components: multi-scale convolutional block attention (CBAM) at three EfficientNet-B0 encoder stages, a learnable feature pyramid network for adaptive multi-scale fusion, an entropy-guided decoder that routes fine-grained encoder information toward uncertain regions, and a boundary-aware composite loss with deep supervision. The model was evaluated on the public BUSI dataset (647 annotated lesion images) using a stratified 454/64/129 train/validation/test split. On the held-out test set, UGB-SegNet achieved 81.30% Dice, 68.49% IoU, 81.71% sensitivity, 98.14% specificity, and 15.63-pixel HD95. Under identical training conditions it outperformed five directly trained baselines: U-Net, Attention U-Net, SegNet, DeepLabV3+, and TransUNet. A five-fold resampling experiment over the development set with the held-out test set fixed yielded a mean Dice of 76.36% +/- 1.66% (95% CI 74.90-77.81). Reported ablations attribute gains of +2.06 Dice points to multi-scale CBAM, +1.52 to learnable FPN fusion, +1.22 to the uncertainty-guided decoder, and +1.24 to boundary-aware training. UGB-SegNet contains 14.00M parameters and runs at 62.4 FPS at 224 x 224 resolution on the tested NVIDIA GPU, providing a compact accuracy-efficiency trade-off for future prospective clinical validation.

Brain foundation models have shown promising advances in learning generalizable representations from functional magnetic resonance imaging (fMRI) data. However, existing models are typically tied to specific brain atlases and cannot be applied to fMRI data represented using different atlases without full retraining, thereby severely limiting their broader utility across neuroimaging studies. To address this bottleneck, we introduce AREION, atlas-agnostic representation learning of brain connectomes. AREION overcomes atlas dependency through two integrated innovations. First, a Brain Region Contextualizing technique maps brain regions and connectivity entries from diverse atlases into a unified representation space based on their spatial, functional, and morphological characteristics. Second, a Hierarchical Brain Transformer Encoder processes region-specific connectivity profiles as variable-length token sequences and jointly captures local functional structure and global brain functional organization, conditioned on brain regional context, without assuming a fixed number of regions. Together, these two techniques enable the learning of generalizable representations across brain atlases with different parcellation resolutions and connectivity dimensions. AREION is pretrained on a large-scale multi-atlas cohort of fMRI data via self-supervised modeling and evaluated across diverse downstream tasks. Extensive experiments show that it outperforms strong supervised baselines and fMRI foundation models while using substantially fewer parameters, demonstrating strong transferability to atlases unseen during pretraining, generalization to external datasets, and excellent interpretability at the brain regional level.

Fluorescence microscopy is a central tool in biomedical image analysis, but its practical use is often constrained by incomplete and heterogeneous data. This is especially true in rare disease research, where patient cohorts are small, biological material is limited, and complex study designs frequently yield images with missing, degraded, or low-quality channels. We introduce Reliability-Mask-Conditioned DDPM (RM-DDPM), a conditional diffusion model that formulates multichannel image generation, missing-channel imputation, and degraded-channel restoration as a single reliability-guided inference problem. The model is trained on a curated subset of complete, high-quality multichannel images using a self-supervised masking objective to learn rich cross-channel dependencies from the available channels. At inference time, reliable observations condition the reverse diffusion process, allowing the same trained model to solve multiple reconstruction tasks without task-specific retraining. We evaluate RM-DDPM against task-specific baselines on one public and two in-house fluorescence microscopy datasets, comprising a rare-disease preclinical model study and a clinical patient cohort. Across these settings, RM-DDPM matches the specialized baselines in reconstruction quality, hallucinates fewer false structures, and remains more robust as degradation severity increases, while repeated sampling provides per-pixel uncertainty maps that flag unreliable reconstructions.

Three-dimensional medical image segmentation is unusually heterogeneous in its computational needs: large homogeneous organ interiors are often resolved at coarse scale, whereas small organs, lesions, thin vessels, and ambiguous boundaries benefit from native-resolution processing. Yet modern 3D segmentation networks allocate nearly uniform computation across the entire volume. Existing dynamic-resolution or coarse-to fine methods reduce cost, but typically route regions using hand-crafted image complexity, prediction confidence, or a fixed crop, none of which directly estimates whether spending additional computation on a region will improve the segmentation. We introduce ERRORROUTE, a budgeted inference framework that learns the marginal refinement utility of candidate 3D blocks. A coarse branch first predicts global low-resolution semantics. During training, we estimate for each candidate block the loss reduction achievable by native resolution refinement and supervise a utility estimator to predict this gain before refinement. A differentiable budgeted selector then allocates a fixed compute budget to blocks with the highest expected utility per unit cost, while unselected regions remain on the efficient global path. Selected blocks are refined locally and merged through residual cross-scale fusion. Across six 3D CT/MRI benchmarks, ERRORROUTE achieves a mean Dice of 90.5% at 128 GFLOPs, improving the accuracy-compute frontier over dense 3D baselines and fixed coarse-to-fine systems. At a 30% routing budget, the learned utility estimator recovers 83% of the blocks selected by an oracle router, with the largest allocation concentrated on lesions, small structures, and complex boundaries. These results suggest that efficient medical segmentation benefits from learning where additional computation is useful, rather than merely where the model is uncertain.

Submillimeter functional magnetic resonance imaging (fMRI) based on blood-oxygenation-level-dependent (BOLD) signal enables the study of brain function at the submillimeter level, uncovering insights into fine-scale organisations like cortical layers and columns. However, its inherently low contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR) often limit its reliability and applicability. Noise Reduction with Distribution Corrected Principal Components Analysis (NORDIC PCA) is a locally low-rank denoising algorithm that reduces thermal noise levels in BOLD fMRI in a local patch manner. However, local patches often contain a mixture of signals from multiple tissues that negatively affects the low-rank structure of the patches, which limits the denoising capabilities of the algorithm. We propose an alternative approach for patch formation by gathering similar non-local voxels, dubbed voxel-matching (VM) NORDIC. The results on submillimeter-resolution BOLD fMRI data indicate that VM-NORDIC effectively promotes the low rank of the patches by boosting signal redundancy, allowing for more efficient noise attenuation. Moreover, the method barely affects spatial smoothness due to the non-local voxel selection based on time-series similarity. In particular, VM-NORDIC outperforms standard NORDIC with default local patching (Standard-NORDIC) in terms of temporal SNR (tSNR) (~9-90% larger than Standard-NORDIC; ~23-250% larger than the original) and spatial smoothness estimates (~20% of the smoothness induced by Standard-NORDIC). These improvements are fundamental to improving the validity and precision of fMRI studies at submillimeter resolutions.

Blind source separation (BSS) recovers latent sources from observed mixtures. In brain imaging, sources occur in two domains, spatial and temporal, so a criterion applied in one leaves the other unconstrained. Independent component analysis, the most used BSS tool, exploits diversity such as non-Gaussianity and sample dependence, but in one domain at a time. Methods that use both domains apply the same criterion to each and weight them against each other. We propose spatio-dynamical decomposition (SDD), scoring maps by non-Gaussianity and timecourses by dynamical independence: how much each source's dynamics depend on the others. We normalize each score by how much it can improve on the data, eliminating the need for a weight. Across simulations and 130 naturalistic fMRI runs, SDD recovers sources distinguished by either maps or dynamics and reproduces both across disjoint episodes, while baselines trade off the two; map and timescale together also better predict stimulus tracking, with the largest gain for SDD. Together, these results show that separation is strongest when spatial and temporal domains each carry their own criterion.

Background and purpose: Accurate identification of cardiac MRI volume orientations is essential for reliable image interpretation and for enabling downstream automated analysis pipelines. However, orientation labels and commonly assigned manually, making the process time-consuming and prone to variability. Recent advances in vision-language models offers new opportunities for automated label generation by jointly modeling visual and semantic information. Methods: In this study, we systematically compare a conventional end-to-end transformer-based captioning model with a CLIPCap architecture for automated cardiac MRI view labelling. Both models were evaluated on a dataset of 1184 de-identified cardiac MR images spanning across six clinically relevant orientations: short axis, two-, three-, four-chamber views, left and right ventricular outflow tract views. The caption transformer was trained from scratch, whereas CLIPCap leveraged pretrained CLIP image embeddings combined with lightweight mapping network and a frozen language model. Results: Experimental results demonstrate a substantial performance advantage from CLIPCap, which achieved an overall accuracy of 98% compared to 68% for the caption transformer. CLIPCap consistently delivered high precision and recall across all orientation classes, including those of high clinical importance, while the end to end transformer exhibited unstable performance and complete failure in certain views. Conclusion: These findings highlight the benefits of leveraging large scale multimodal pretrained model for medical image labeling tasks, particularly in data limited settings. The study suggests that CLIPCap provides a more robust and clinically reliable solution for automated cardiac MRI orientation labeling, supporting its integration into efficient and scalable clinical workflows.

Purpose: Magnetic Resonance Acoustic Radiation Force Imaging (MR-ARFI) encodes focused ultrasound (FUS)-induced tissue displacements to MR phase shifts. Because these phase shifts are small, optimizing displacement sensitivity and minimizing motion artifacts requires characterization of the temporal dynamics of acoustic radiation force (ARF). Beyond sequence design, such characterization enables MR-ARFI to serve as a probe of brain viscoelastic behavior and can inform the design of therapeutic ultrasound pulsing schemes by quantifying how rapidly tissue deforms and relaxes. Methods: We developed a dynamic model assuming a gamma-variate impulse response for ARF(t), with time constant ({tau}) to be estimated. A single-shot spin echo ARFI acquisition with a bipolar motion encoding gradient (MEG) was implemented, incorporating retrospective corrections for head motion and physiological noise. A 500 kHz FUS pulse was applied in on/off blocks while systematically varying the timing between the MEG and sonication. The resulting phase time series were fit to the model to estimate time constant in five human participants. To assess sensitivity to tissue stiffness, {tau} was additionally measured in two customized gelatin phantoms of differing stiffness, characterized independently by MR elastography (MRE). Results: The average measured time constant in human participants was {tau} 3.7 {+/-} 0.27 ms. Comparing the two phantoms, the stiffer phantom exhibited a shorter {tau} (3.0-3.5 ms) than the softer phantom (4.0-4.5 ms), which tracked the MRE-derived Kelvin-Voigt viscoelastic time constants. In addition, the peak ARFI displacement was lower in the stiffer phantom (0.17 vs 0.74 m for the less stiff phantom), and a broader displacement focal spot size (FWHM 22 mm vs 15 mm). Conclusion: This time series approach with motion and physiological noise corrections validates an MR-based technique capable of characterizing the brain's temporal response to sonication-induced mechanical forces, providing a foundation for optimizing the design of ultrasound pulsing schemes for ARFI, as well as for future studies of brain biomechanics.

In this paper, we introduce Nagini3D, a 3D biological image segmentation method that hybridizes two high-performing yet highly complementary segmentation paradigms: deep learning-based approaches and snake-based methods. Our approach leverages both the high efficiency of data-driven techniques and the convenient shape representation provided by active surfaces, which proves highly practical for incorporating a priori knowledge as well as for the post-analysis of segmented objects. By considering a complete 3D volume, our method ensures segmentation consistency across all three dimensions, unlike many approaches that handle volumes in a slice-by-slice manner. Additionally, it theoretically enables the representation of any object with spherical topology, overcoming the limitations of common 3D methods that rely on object convexity assumptions. Furthermore, the continuous representation of objects allows for a resolution-independent description, facilitating the extraction of various geometric features of interest (e.g., local curvature, principal deformations). We demonstrate both the quality of the segmentation produced by our method and the richness of the accessible geometric features through an extensive set of experiments conducted on multiple real and simulated datasets, including objects with challenging geometries.

Background. Automated segmentation of glioma subregions on multiparametric MRI can be improved by changing either the network architecture or the information presented to the network. These two design levers are usually studied together, which makes their individual contributions difficult to see. We present an integrated analysis of two completed, independent studies, each of which isolates one lever. Methods. In the architecture-level study (Slice), SIBA-UNet - a 2D U-Net combining depthwise separable convolution, inverted-bottleneck blocks and attention-guided skip fusion - was trained on 128 x 128 multimodal slices from BraTS 2020 with a patient-level split, and a sigmoid decision threshold was selected on validation data. In the representation-level study (Subtract), CMSR-3D augmented the four standard MRI sequences with four voxel-wise cross-modal subtraction maps (T1-T1CE, T2-FLAIR, FLAIR-T1CE, T2-T1CE) and evaluated 4-, 6- and 8-channel inputs with an identical 3D U-Net on 1,251 BraTS-GLI 2023 cases (1,001/125/125 split). Results. SIBA-UNet reached an overall validation Dice of 0.8601 at a validation-selected threshold of 0.51, with reported subregion Dice of 0.8795 (necrotic core), 0.8501 (edema) and 0.9125 (enhancing tumor); the source ablation was only partially reported. With the architecture held fixed, the 8-channel CMSR-3D configuration gave the highest mean Dice among the evaluated inputs (0.8699 vs. 0.8534 for the 4-channel baseline) and the lowest mean HD95 (5.9859 vs. 8.2308), whereas either two-map subset alone changed mean Dice by at most 0.0037. Conclusions. Architecture design and input-representation design are separable levers for brain tumor segmentation. The controlled representation ablation indicates that the complete set of subtraction maps was more informative than either subset under a fixed 3D U-Net. Both studies were evaluated internally on their respective datasets, and their numerical results are not directly compared because the datasets, dimensionality and evaluation protocols differ.

The -Bonacci weighted sequence space {ell}(,) is introduced for [&ge;] 2, 1 [&le;] < {infty}, and > 0). It is proved to be a Banach space which is isometrically isomorphic to {ell}, with an unconditional Schauder basis. The space is also reflexive and uniformly convex. Its strict inclusion chain, continuous dual, and asymptotic truncation estimate of order - / are also established. Based on this framework, Scaled &#119898-BonacciNet is proposed as a lightweight CNN that rescales Fibonacci-Net channels using the dominant &#119898-Bonacci root and employs depth wise separable convolutions. Tribonacci-Net achieved 96.09% accuracy and a 0.9581 macro F1-score on the 15-class Brain MRI dataset using 0.85 million parameters and 0.366 GFLOPs. Pentanacci-Net attained 95.87% accuracy on the 44-class dataset while reducing parameters and FLOPs by 47.10% and 44.48%, respectively. On the CKD ultrasound dataset, Hexanacci-Net achieved 83.75% accuracy and a 0.7941 macro F1-score, with corresponding reductions of 50.37% and 45.10%. These findings support dominant-root scaling as a structured approach to lightweight CNN design.