Searcharxiv⌕ Search

arXiv subjects

Dorit Merhof

Publications and source records attributed to Dorit Merhof.

At least 19 recordsLinked to original sources

Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model

Automated segmentation in multi-view echocardiography is essential for comprehensive cardiac assessment, yet remains challenging due to substantial anatomical and appearance variability across standard acoustic windows. In this paper, we present P2Echo, a unified framework capable of segmenting diverse cardiac structures across multiple standard echocardiographic views using a single model controlled by structured view-aware text prompts. Unlike recent foundation model adaptations that rely on implicit latent priors, P2Echo explicitly conditions the segmentation process via a novel Dynamic Image-Text Alignment (DyITA) module. DyITA integrates a differentiable routing mechanism and token differential operators to dynamically modulate decoder features according to the requested view and target structure. This allows the network to adaptively switch its processing pathways for different views without architectural changes. Extensive experiments on a large-scale internal dataset (seen during training) and held-out evaluation on three external datasets demonstrate that P2Echo matches or exceeds both view-specific specialists and state-of-the-art universal models at a fraction of their computational cost, offering an efficient, controllable solution for multi-plane cardiac analysis. Code is available at: https://github.com/moeinheidari7829/P2Echo.

cs.CV↗

DEX: Digit-Level Early Exit for Energy-Efficient MSDF Neural Network Inference

U-Net inference for brain-tumor segmentation requires billions of multiply-accumulate operations, motivating hardware that can reduce computation dynamically rather than relying only on fixed precision or static model compression. Most-significant-digit-first (MSDF) arithmetic exposes the leading digits of a result during computation, enabling output-dependent decisions before the full value is generated. This paper presents an MSDF accelerator for quantized U-Net segmentation with a two-stage grouped processing element supporting signed INT8 operands and in-stream bias accumulation. Four runtime mechanisms operate directly on the output digit stream: exact early negative detection (END) in ReLU layers, exact sign-only decision making in the segmentation head, calibrated low-order-digit skipping, and calibrated pruning. The two approximate mechanisms are selected offline under an accuracy constraint, while execution requires only lightweight control and does not modify the stored weights. On a residual U-Net trained with nnU-Net for BraTS, the proposed mechanisms reduce digit cycles by 38.38\% while achieving a mean Dice score of 80.58\% on 73 held-out cases, compared with 81.20\% for the floating-point model; the exact mechanisms alone reduce cycles by 18.79\% without altering the quantized output. Synthesized in 45~nm, the processing element operates at 500~MHz, occupies 0.858~mm$^2$, and consumes 0.726~mJ per $192\times192$ patch under switching-activity-annotated power analysis. A projected eight-output accelerator with shared activation delivery achieves 16.6~ms latency and 1.67~mJ per patch.

cs.AR↗

PARIS: Parallel Arithmetic Reduction and Integrated Selection for MSDF Inner Products

Existing most-significant-digit-first (MSDF) accelerators serialize input-term processing, causing inner-product latency to increase with fan-in. This paper presents PARIS, an MSDF architecture that eliminates input-term serialization through parallel bit-plane reduction and shared carry-save residual selection. For $B$-bit operands, PARIS processes $B^2$ bit-position pairs, independent of fan-in within the supported tile, while generating exact MSDF outputs. Synthesized in 45\,nm at 100\,MHz, the 784-lane INT8 core occupies 0.008701\,mm$^2$ and completes an inner product in 88 cycles. Evaluation on two MNIST multilayer perceptrons demonstrates arithmetic-workload speedups of 240.44$\times$ and 180.47$\times$ over a matched reused-MSDF implementation, reducing arithmetic energy by 98.89\% and 98.58\%, respectively. A synthesized 16-engine accelerator occupies 0.90273\,mm$^2$ and meets the 100\,MHz timing constraint. Assuming immediate weight availability, it delivers a projected throughput of 24.33\,GOPS and an estimated energy efficiency of 1,581.14\,GOPS/W at unchanged mapped power. Bias-aware ReLU detection further reduces modeled arithmetic cycles by 5.52\% and 4.86\%. A separate 256-engine RTL implementation completes Model A in 259 cycles, demonstrating output-parallel scalability.

cs.AR↗

Echo-E$^3$Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimation

Left ventricular ejection fraction (LVEF) is a primary marker of cardiac function. However, routine estimation from endocardial measurements requires manual delineation at end-diastole (ED) and end-systole (ES), a process that is time-consuming and subject to inter-observer variability. Reliable automation is especially valuable for point-of-care ultrasound (POCUS), where computational resources are limited and acquisition quality varies. We propose Echo-E$^3$Net, an anatomy-guided spatio-temporal network that explicitly embeds cardiac anatomy into LVEF prediction. A dual-phase Endocardial Border Detector (E$^2$CBD) uses phase-specific cross-attention to localize ED/ES endocardial landmarks and produce phase-aware landmark embeddings, while an Endocardial Feature Aggregator (E$^2$FA) fuses these embeddings with global statistical descriptors of deep feature maps to refine EF regression. Training is guided by a lightweight geometric loss that uses ED and ES endocardial landmarks to regularize EF prediction. On EchoNet-Dynamic and a PSAX subset of EchoNet-Pediatric, Echo-E$^3$Net attains competitive performance using only 1.55M parameters and 8.05 GFLOPs, an order-of-magnitude compute reduction versus recent baselines, supporting real-time deployment. Our code is publicly available at https://github.com/moeinheidari7829/Echo-E3Net.

eess.IV↗

HemaHier: Chain-Conditioned Ordinal Hierarchies for Lineage-Aware Bone-Marrow Cytology

Bone-marrow cytology is inherently structured: each cell belongs to a hematopoietic lineage, and many cell types lie on ordered maturation trajectories. Standard flat classifiers ignore this structure, treating a mild same-lineage confusion the same as a severe cross-lineage mistake and predicting only discrete labels. We propose HemaHier, an ordinal-hierarchical prediction head for a frozen or lightly adapted cytology foundation model. Its central component is a chain-conditioned maturity score that reads a single maturity value under a per-chain query, supervised only on biologically valid healthy chains, while dysplastic and off-chain cell types remain classes but are excluded from maturity supervision. Fine and lineage predictions are coupled through a shared posterior that guarantees hierarchical consistency, and a staged objective first stabilizes recognition, then adds lineage and maturity supervision. On three bone-marrow datasets under a shared ontology, HemaHier achieves competitive recognition while reducing biologically severe errors and adding a within-lineage maturity ordering that flat classifiers lack. Code is available at https://github.com/xmindflow/HemaHier.

cs.CV↗

Fast and Accurate Monomodal 3D High Resolution Deep Registration of Drosophila Larval Brain Volumes

The larval stage of Drosophila melanogaster is a compact model system for neuroscience whose genetic toolkit allows fluorescent markers to be expressed in defined neural populations, and comparing the resulting expression patterns across animals requires every brain to be registered into a shared anatomical reference space. Existing pipelines for this task are predominantly based on classical registration methods, which perform a new optimization for each volume, often require per-case parameter tuning, and can take minutes per brain, limiting their use as a routine preprocessing step. We present a trained deep registration pipeline that deformably aligns a larval brain to a reference template in a single forward pass at high spatial resolution, on volumes that hold several times more voxels than those learned 3D registration is normally reported on, together with the preprocessing and anatomy-anchored evaluation pipeline required to apply it. Against eleven classical and seven further learned baselines on a held-out collection acquired with different acquisition and quality strata, the proposed pipeline is the most accurate, improving on the strongest classical baseline by 23 percentage points of anatomical landmark-local mutual information. It registers a volume one to two orders of magnitude faster than the classical deformable pipelines, and it retains more of its accuracy than any other method as acquisition quality degrades. The network, its trained weights and the full pipeline are released as the open-source deep larval brain registration framework: https://github.com/agentdr1/deep-larval-brain-reg

cs.CV↗

TRIUNE-Net: Harmonizing Scale, Shape, and Efficiency in Pancreatic Tumor Segmentation

Pancreatic tumor segmentation in 3D CT volumes is challenged by extreme scale variability across both the pancreas and tumor, and highly irregular tumor morphology. While recent advances have pushed segmentation performance, existing methods do not explicitly address these challenges and come at the cost of excessive computational complexity, limiting their practicality in resource-constrained clinical environments. We propose TRIUNE-Net, a lightweight unified architecture that harmonizes scale, shape, and efficiency through three synergistic innovations. A multi-scale context aggregation module with stage-adaptive dilated convolutions enables the model to reason across the broad range of anatomical scales present in both organs. A serial linear-deformable attention mechanism combines large effective receptive fields with shapeadaptive deformable convolutions to capture irregular, non-convex tumor morphologies. Finally, an information-preserving downsampling module replaces conventional max pooling entirely, retaining all spatial information while adding negligible parameters, preventing small tumors from being discarded before they can be recognized. On both the MSD Pancreas and NVD Pancreas datasets, TRIUNE-Net achieves state-of-theart results with only 5.86 M parameters and no external pre-training, outperforming all baselines across all key tumor metrics. Specifically, it surpasses the next-best model by 0.45% in tumor Dice, 6.0 points in F1 score, 6.6 points in sensitivity, and 3.4 points in precision, simultaneously reflecting its ability to suppress both missed tumors and false alarms in clinically realistic conditions. Our code is available at: https://github.com/abdora-ai/TRIUNE-Net

cs.CV↗

MaLViL: Multi-axis Low-rank Vision-LSTM for Medical Image Segmentation

Vision-LSTM (ViL) enables efficient global modeling, but its cost still scales with the number of spatial tokens, so existing segmenters confine ViL to a coarse bottleneck and lose fine anatomical detail. Rasterizing 2D features into a 1D sequence further breaks adjacency across the orthogonal scan axis. We propose MaLViL, a Multi-axis Low-rank Vision-LSTM network that extends ViL across decoder resolutions. Bidirectional low-rank ViL (Bi-LRViL) reasons on a compact orthonormal subspace and preserves detail through an orthogonal residual; scale-aware SaLViL restores cross-axis neighbors before serialization; and a Cross-Directional Mixer (CDM) fuses orthogonal horizontal and vertical traversal paths. Statistics-Guided Skip Modulation (SGSM) further retains boundary cues in encoder skips. On skin-lesion, ultrasound, and multi-organ CT benchmarks, MaLViL achieves competitive or state-of-the-art segmentation accuracy, while reducing ViL operator memory by up to $83\times$ at fine decoder resolutions. Code is available at: https://github.com/xmindflow/malvil.

cs.CV↗

Spatial Masked-Set Learning for Sparse Multi-Shell Diffusion MRI Signal Synthesis

Dense multi-shell diffusion MRI provides rich q-space information but requires long acquisition times. We propose a spatial masked-set framework for sparse multi-shell diffusion MRI signal synthesis. The model treats observed measurements as an unordered set, uses a local $3 \times 3 \times 3$ neighborhood for spatial context, and predicts radial-order-6 SHORE coefficients for the center voxel. The coefficients can then be decoded analytically to synthesize signals at arbitrary q-space locations. Training combines shell-wise gradient dropping, dense signal supervision, and rotation-consistent SHORE targets so that sparse input signals remain aligned with their coefficient supervision under augmentation. We evaluate on held-out HCP100 white-matter voxels by retaining limited subsets of measured diffusion-weighted signals from the reference acquisition. The proposed method achieves lower signal NMSE than both analytical q-space models and a state-of-the-art continuous dMRI signal synthesis model designed for arbitrary input and output q-space sampling. In the $b=1000$ setting with 10 input gradients, it achieves $2.70\%$ NMSE, a $22.4\%$ relative reduction over this continuous model. Fractional anisotropy on reconstructed $b=1000$ signals provides a complementary tensor-derived endpoint, with analytical models remaining competitive for FA despite higher dense-signal NMSE across the evaluated q-space. The implementation is available on \href{https://github.com/xmindflow/SHOREPred}{https://github.com/xmindflow/SHOREPred}.

eess.IV↗

Approximate Attention Weighting for Sustainable FPGA-Based Vision Transformer Inference

Vision Transformers have reshaped computer vision by using self-attention to capture global context across image regions. This makes them attractive for edge visual inspection and monitoring in applications such as renewable-energy infrastructure, industrial quality control, medical imaging, and autonomous-system sensing. However, deploying ViTs on small FPGAs remains challenging because the softmax stage in self-attention requires exponential evaluation and normalization, which are costly in hardware. Existing implementations often rely on CORDIC pipelines or BRAM-based look-up tables, increasing area and power consumption. This paper presents a BRAM-free approximate attention-weighting unit for FPGA-based ViT inference. The proposed design approximates the natural exponential in softmax using a 16-segment piecewise-linear function implemented entirely with distributed LUT fabric. Unlike base-2 approximations, the natural-exponential formulation preserves the pre-trained attention temperature and avoids model-specific recalibration. Implemented on a Xilinx Zynq-7020, the complete attention-row core uses 1444 LUTs, 77 DSPs, and no BRAM, while hardware-accurate emulation shows accuracy within a \(0.20\%\) absolute top-1 difference from the exact-softmax reference on ViT-family models. These results demonstrate the potential of the proposed core for energy-efficient ViT inference on resource-constrained edge-AI platforms.

cs.AR↗

Dynamic Ultrasound Beamforming Using Left-to-Right Arithmetic Adders on FPGA

Adder trees are the computational backbone of delay-and-sum (DAS) ultrasound beamforming, where their implementation directly determines the energy, throughput, and area of a real-time imaging pipeline. Conventional parallel adder trees perform full-precision combinational reduction on every sample, leading to wide critical paths, high LUT consumption, and timing failures on small FPGA devices. This paper presents an alternative adder tree architecture based on \emph{left-to-right (LR)} or \emph{most significant digit first (MSDF) arithmetic}. We implement the proposed and conventional adder trees on a Xilinx Zynq XC7Z010 FPGA and evaluate them for DAS beamforming of a 64-channel ultrasound dataset. The proposed design uses 2.5$\times$ fewer LUTs than the smallest conventional tree, successfully meets the timing constraint, and consumes 23\% less dynamic power than the most efficient conventional baseline. A key advantage of the proposed MSDF adder tree is that it can generate high-quality beamformed images without waiting for full-precision completion. This naturally enables dynamic precision at runtime with negligible control overhead, since precision selection is achieved simply by stopping the computation clock after the desired number of cycles. Such quality--energy scalability is fundamentally unavailable in conventional fixed-cycle adder trees. Iso-area replication enables up to 15 parallel instances on the XC7Z010, achieving 67 FPS, which is 80\% higher throughput than the best conventional design.

cs.AR↗

MINT: Dynamic-Precision CNN Inference with MSDF Digit-Serial Arithmetic on FPGA

We present MINT, a dynamic-precision CNN inference accelerator based on left-to-right (LR) arithmetic. LR arithmetic computes in most-significant-digit-first manner and exposes useful partial results early so that the computation can be terminated once the desired precision is achieved. At the core, there is a MSDF serial-parallel inner-product unit, which uses redundant signed-digit representation to compute each convolution window. A budget-constrained greedy search profiles all convolution layers from INT2 to INT7 and selects the lowest precision per layer while constraining total accuracy loss to within 2\% of the INT8 baseline for VGG-16 and ResNet-18 networks. The design is synthesized on a Xilinx Zynq-7020 at \SI{200}{\mega\hertz}, and uses 5.64 average bits for VGG-16 and 6.04 for ResNet-18, while achieving 19.86 GOPS and 29.51 GOPS/W on VGG-16, and 18.86 GOPS and 26.40 GOPS/W on ResNet-18. This corresponds to 32.6\% and 26.0\% higher throughput and 82.10\% and 62.90\% higher energy efficiency than INT8 with only 1.81\% and 1.96\% drops relative to the INT8 baseline. Compared with representative prior FPGA CNN accelerators considered in this study, MINT delivers the highest energy efficiency among the listed VGG-16 and ResNet-18 designs on Zynq-7020 platform.

cs.AR↗

Energy-Efficient CNN Acceleration with MSDF Digit-Serial Arithmetic on FPGA

This paper presents an energy-efficient hardware acceleration of the convolutional layers in the U-Net architecture for image segmentation, implemented on FPGA. While digit-serial arithmetic, particularly most-significant-digit-first (MSDF) techniques, offers a compact hardware footprint, it suffers from initial latency before producing the first output digit. This delay accumulates in cascaded operations like multiplication followed by addition, where each unit introduces its own startup overhead. To overcome this, we propose a merged multiply-add (MMA) architecture that fuses these operations into a unified pipeline. Instead of incurring separate delays, the MMA introduces a single streamlined latency per iteration, shorter than the combined latency of conventional cascaded units, resulting in enhanced throughput and efficiency. The MMA units are designed to process spatial input depths in parallel, achieving significantly higher performance than both standalone MSDF-based and conventional designs. We evaluate the proposed design using U-Net as a target application. Despite operating at a lower frequency than a CPU, the FPGA-based accelerator achieves up to an order of magnitude higher energy efficiency, delivering up to $15.14$ GOPS/W compared to $1.93$ GOPS/W for CPU-based inference. The design also shows approximately $9\times$ reduction in energy consumption compared to MSDF-based FPGA implementations. These results highlight the efficacy of the merged arithmetic approach for resource-constrained, latency-sensitive edge applications in medical imaging and computer vision.

cs.AR↗

Harmonized Feature Conditioning and Frequency-Prompt Personalization for Multi-Rater Medical Segmentation

Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and imaging devices. Existing approaches often reduce this diversity to consensus labels or treat rater differences as noise, resulting in overconfident and poorly calibrated models. We propose a harmonized probabilistic framework that disentangles acquisition artifacts from genuine annotator variability through adaptive feature conditioning and frequency-domain personalization. A lightweight Harmonizer Network implicitly models scanner-specific artifacts and performs dynamic feature modulation to standardize latent representations, ensuring that uncertainty reflects anatomy rather than noise. To represent rater-specific styles, we introduce a novel High-Frequency Prompt Modules that operate in the spectral domain to encode annotator-dependent boundary precision and textural sensitivity. These prompts adaptively modulate harmonized features to produce personalized yet anatomically consistent segmentations. Furthermore, a Generalized Energy Distance based regularization aligns the generative distribution with empirical annotation variability, promoting diversity where experts disagree and consensus where they converge. Experiments on LIDC-IDRI and NPC-170 show SOTA aggregated and individualized segmentation, with notable GED reductions and improved Dice scores, especially on noisy cases. Beyond accuracy, the model exhibits clinically meaningful uncertainty. Confidence rises in agreement regions and declines in ambiguous areas, supporting its use as a reliable and interpretable tool for multi-expert clinical workflows.

cs.CV↗

Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation

Medical image segmentation requires models that preserve fine anatomical boundaries while remaining practical for clinical deployment. Transformers capture long-range dependencies but incur quadratic attention cost, whereas CNNs are efficient but less effective at global reasoning. Linear attention offers \(\mathcal{O}(N)\) scaling, but often produces diffuse feature aggregation that weakens boundary-sensitive prediction. We introduce a gated differential linear-attention mixer for medical image segmentation. Its global path, Gated Differential Linear Attention (GDLA), performs differential subtraction between two kernelized attention branches over complementary query/key subspaces to suppress redundant responses, and employs a data-dependent gate for token refinement. A parallel local token-mixing branch with depthwise convolution strengthens neighborhood interactions for better refinement, and the two branches are fused while preserving \(\mathcal{O}(N)\) complexity. When instantiated in a pretrained Pyramid Vision Transformer (PVT)-based encoder--decoder model, \name achieves state-of-the-art results on the evaluated 2D medical segmentation benchmarks spanning CT, MRI, ultrasound, and dermoscopy, with a favorable accuracy--efficiency trade-off over closely related baselines. The code is publicly available at \href{https://github.com/xmindflow/gdla}{https://github.com/xmindflow/gdla}.

cs.CV↗

Footprint-Guided Exemplar-Free Continual Histopathology Report Generation

Rapid progress in vision-language modeling has enabled pathology report generation from gigapixel whole-slide images, but most approaches assume static training with simultaneous access to all data. In clinical deployment, however, new organs, institutions, and reporting conventions emerge over time, and sequential fine-tuning can cause catastrophic forgetting. We introduce an exemplar-free continual learning framework for WSI-to-report generation that avoids storing raw slides or patch exemplars. The core idea is a compact domain footprint built in a frozen patch-embedding space: a small codebook of representative morphology tokens together with slide-level co-occurrence summaries and lightweight patch-count priors. These footprints support generative replay by synthesizing pseudo-WSI representations that reflect domain-specific morphological mixtures, while a teacher snapshot provides pseudo-reports to supervise the updated model without retaining past data. To address shifting reporting conventions, we distill domain-specific linguistic characteristics into a compact style descriptor and use it to steer generation. At inference, the model identifies the most compatible descriptor directly from the slide signal, enabling domain-agnostic setup without requiring explicit domain identifiers. Evaluated across multiple public continual learning benchmarks, our approach outperforms exemplar-free and limited-buffer rehearsal baselines, highlighting footprint-based generative replay as a practical solution for deployment in evolving clinical settings.

cs.CV↗

Towards Modality-Agnostic Continual Domain-Incremental Brain Lesion Segmentation

Brain lesion segmentation from multi-modal MRI often assumes fixed modality sets or predefined pathologies, making existing models difficult to adapt across cohorts and imaging protocols. Continual learning (CL) offers a natural solution but current approaches either impose a maximum modality configuration or suffer from severe forgetting in buffer-free settings. We introduce CLMU-Net, a replay-based CL framework for 3D brain lesion segmentation that supports arbitrary and variable modality combinations without requiring prior knowledge of the maximum set. A conceptually simple yet effective channel-inflation strategy maps any modality subset into a unified multi-channel representation, enabling a single model to operate across diverse datasets. To enrich inherently local 3D patch features, we incorporate lightweight domain-conditioned textual embeddings that provide global modality-disease context for each training case. Forgetting is further reduced through principled replay using a compact buffer composed of both prototypical and challenging samples. Experiments on five heterogeneous MRI brain datasets demonstrate that CLMU-Net consistently outperforms popular CL baselines. Notably, our method yields an average Dice score improvement of $\geq$ 18\% while remaining robust under heterogeneous-modality conditions. These findings underscore the value of flexible modality handling, targeted replay, and global contextual cues for continual medical image segmentation. Our implementation is available at https://github.com/xmindflow/CLMU-Net.

eess.IV↗

Tissue Classification and Whole-Slide Images Analysis via Modeling of the Tumor Microenvironment and Biological Pathways

Automatic integration of whole slide images (WSIs) and gene expression profiles has demonstrated substantial potential in precision clinical diagnosis and cancer progression studies. However, most existing studies focus on individual gene sequences and slide level classification tasks, with limited attention to spatial transcriptomics and patch level applications. To address this limitation, we propose a multimodal network, BioMorphNet, which automatically integrates tissue morphological features and spatial gene expression to support tissue classification and differential gene analysis. For considering morphological features, BioMorphNet constructs a graph to model the relationships between target patches and their neighbors, and adjusts the response strength based on morphological and molecular level similarity, to better characterize the tumor microenvironment. In terms of multimodal interactions, BioMorphNet derives clinical pathway features from spatial transcriptomic data based on a predefined pathway database, serving as a bridge between tissue morphology and gene expression. In addition, a novel learnable pathway module is designed to automatically simulate the biological pathway formation process, providing a complementary representation to existing clinical pathways. Compared with the latest morphology gene multimodal methods, BioMorphNet's average classification metrics improve by 2.67%, 5.48%, and 6.29% for prostate cancer, colorectal cancer, and breast cancer datasets, respectively. BioMorphNet not only classifies tissue categories within WSIs accurately to support tumor localization, but also analyzes differential gene expression between tissue categories based on prediction confidence, contributing to the discovery of potential tumor biomarkers.

cs.CV↗