Wenqi Lu

U-Net style networks are commonly utilized in unsupervised image registration to predict dense displacement fields in the full-resolution spatial domain. For high-resolution volumetric image data, this process is, however, resource-intensive and time-consuming. To address this challenge, we propose Fourier-Net+, an image-domain deformable registration framework that operates on real-valued images for broad modality compatibility. Fourier-Net+ uses deterministic Fourier-domain band-limiting for efficient down- and up-sampling and employs a parameter-free, model-driven decoder to learn a band-limited, low-dimensional representation of the displacement field; all learnable network layers are real-valued. In addition, to enhance the registration performance and encourage diffeomorphism, we propose the cascaded and diffeomorphic versions of Fourier-Net+. We evaluate the proposed methods on five datasets, including two brain MRI, one 3-D cardiac MRI (3-D-CMR), one abdominal CT-MR dataset, and one noisy ultrasound cardiac dataset, comparing them against various state-of-the-art approaches. Our Fourier-Net+ and its variants achieve comparable results with these approaches while exhibiting faster training and inference speeds with a lower memory footprint and fewer multiply add operations (mult-adds). For example, on the 3-D-CMR dataset, our Diff-Fourier-Net+ significantly outperforms strong baselines such as TransMorph, TransMatch, and SACB-Net in Dice and HD, as well as in clinical metrics including end-diastolic (ED) volume and ejection fraction estimation, while using substantially less memory and computational cost. This efficiency enables large-scale 3-D registration training on low-VRAM GPUs.

Modern vision models increasingly rely on rich semantic representations that extend beyond class labels to include descriptive concepts and contextual attributes. However, existing datasets exhibit Semantic Coverage Imbalance (SCI), a previously overlooked bias arising from the long-tailed semantic representations. Unlike class imbalance, SCI occurs at the semantic level, affecting how models learn and reason about rare yet meaningful semantics. To mitigate SCI, we propose Semantic Coverage-Aware Network (SemCovNet), a novel model that explicitly learns to correct semantic coverage disparities. SemCovNet integrates a Semantic Descriptor Map (SDM) for learning semantic representations, a Descriptor Attention Modulation (DAM) module that dynamically weights visual and concept features, and a Descriptor-Visual Alignment (DVA) loss that aligns visual features with descriptor semantics. We quantify semantic fairness using a Coverage Disparity Index (CDI), which measures the alignment between coverage and error. Extensive experiments across multiple datasets demonstrate that SemCovNet enhances model reliability and substantially reduces CDI, achieving fairer and more equitable performance. This work establishes SCI as a measurable and correctable bias, providing a foundation for advancing semantic fairness and interpretable vision learning.

In unsupervised medical image registration, encoder-decoder architectures are widely used to predict dense, full-resolution displacement fields from paired images. Despite their popularity, we question the necessity of making both the encoder and decoder learnable. To address this, we propose LessNet, a simplified network architecture with only a learnable decoder, while completely omitting a learnable encoder. Instead, LessNet replaces the encoder with simple, handcrafted features, eliminating the need to optimize encoder parameters. This results in a compact, efficient, and decoder-only architecture for 3D medical image registration. We evaluate our decoder-only LessNet on five registration tasks: 1) inter-subject brain registration using the OASIS-1 dataset, 2) atlas-based brain registration using the IXI dataset, 3) cardiac ES-ED registration using the ACDC dataset, 4) inter-subject abdominal MR registration using the CHAOS dataset, and 5) multi-study, multi-site brain registration using images from 13 public datasets. Our results demonstrate that LessNet can effectively and efficiently learn both dense displacement and diffeomorphic deformation fields. Furthermore, our decoder-only LessNet can achieve comparable registration performance to benchmarking methods such as Voxel-Morph and TransMorph, while requiring significantly fewer computational resources. Our code and pre-trained models are available at https://github.com/xi-jia/LessNet.

Deep learning-based image registration methods have shown state-of-the-art performance and rapid inference speeds. Despite these advances, many existing approaches fall short in capturing spatially varying information in non-local regions of feature maps due to the reliance on spatially-shared convolution kernels. This limitation leads to suboptimal estimation of deformation fields. In this paper, we propose a 3D Spatial-Awareness Convolution Block (SACB) to enhance the spatial information within feature representations. Our SACB estimates the spatial clusters within feature maps by leveraging feature similarity and subsequently parameterizes the adaptive convolution kernels across diverse regions. This adaptive mechanism generates the convolution kernels (weights and biases) tailored to spatial variations, thereby enabling the network to effectively capture spatially varying information. Building on SACB, we introduce a pyramid flow estimator (named SACB-Net) that integrates SACBs to facilitate multi-scale flow composition, particularly addressing large deformations. Experimental results on the brain IXI and LPBA datasets as well as Abdomen CT datasets demonstrate the effectiveness of SACB and the superiority of SACB-Net over the state-of-the-art learning-based registration methods. The code is available at https://github.com/x-xc/SACB_Net .

Euler’s elastica energy regularizer, initially employed in mathematical and physical systems, has recently garnered much attention in image processing and computer vision tasks. Due to the non-convexity, non-smoothness, and high order of its derivative, however, the term has yet to be effectively applied in 3D reconstruction. To this day, the industry is still searching for 3D reconstruction systems that are robust, accurate, efficient, and easy to use. While implicit surface reconstruction methods generally demonstrate superior robustness and flexibility, the traditional methods rely on initialization and can easily become trapped in local minima. Some low-order variational models are able to overcome these issues, but they still struggle with the reconstruction of object details. Euler’s elastica term, on the other hand, has been found to share the advantages of both the TV regularization term and the curvature regularization term. In this paper, we aim to address the problems of missing details and complex computation in implicit 3D reconstruction by efficiently using Euler’s elastica term. The main contributions of this article can be outlined in three aspects. Firstly, Euler’s elastica is introduced as a regularization term in 3D point cloud reconstruction. Secondly, a new dual algorithm is devised for the proposed model, significantly improving solution efficiency compared to the commonly used TV model. Lastly, numerical experiments conducted in 2D and 3D demonstrate the remarkable performance of Euler’s elastica in enhancing features of curved surfaces during point cloud reconstruction. The reconstructed point cloud surface adheres more closely to the initial point cloud surface when compared to the classical TV model. However, it is worth noting that Euler’s elastica exhibits a lesser capability in handling local extrema compared to the TV model.

Early‐stage estrogen receptor positive and human epidermal growth factor receptor negative (ER+/HER2−) luminal breast cancer (BC) is quite heterogeneous and accounts for about 70% of all BCs. Ki67 is a proliferation marker that has a significant prognostic value in luminal BC despite the challenges in its assessment. There is increasing evidence that spatial colocalization, which measures the evenness of different types of cells, is clinically important in several types of cancer. However, reproducible quantification of intra‐tumor spatial heterogeneity remains largely unexplored. We propose an automated pipeline for prognostication of luminal BC based on the analysis of spatial distribution of Ki67 expression in tumor cells using a large well‐characterized cohort (n = 2,081). The proposed Ki67 colocalization (Ki67CL) score can stratify ER+/HER2− BC patients with high significance in terms of BC‐specific survival (p < 0.00001) and distant metastasis‐free survival (p = 0.0048). Ki67CL score is shown to be highly significant compared with the standard Ki67 index. In addition, we show that the proposed Ki67CL score can help identify luminal BC patients who can potentially benefit from adjuvant chemotherapy.

Objective To develop an interpretable artificial intelligence algorithm to rule out normal large bowel endoscopic biopsies, saving pathologist resources and helping with early diagnosis. Design A graph neural network was developed incorporating pathologist domain knowledge to classify 6591 whole-slides images (WSIs) of endoscopic large bowel biopsies from 3291 patients (approximately 54% female, 46% male) as normal or abnormal (non-neoplastic and neoplastic) using clinically driven interpretable features. One UK National Health Service (NHS) site was used for model training and internal validation. External validation was conducted on data from two other NHS sites and one Portuguese site. Results Model training and internal validation were performed on 5054 WSIs of 2080 patients resulting in an area under the curve-receiver operating characteristic (AUC-ROC) of 0.98 (SD=0.004) and AUC-precision-recall (PR) of 0.98 (SD=0.003). The performance of the model, named Interpretable Gland-Graphs using a Neural Aggregator (IGUANA), was consistent in testing over 1537 WSIs of 1211 patients from three independent external datasets with mean AUC-ROC=0.97 (SD=0.007) and AUC-PR=0.97 (SD=0.005). At a high sensitivity threshold of 99%, the proposed model can reduce the number of normal slides to be reviewed by a pathologist by approximately 55%. IGUANA also provides an explainable output highlighting potential abnormalities in a WSI in the form of a heatmap as well as numerical values associating the model prediction with various histological features. Conclusion The model achieved consistently high accuracy showing its potential in optimising increasingly scarce pathologist resources. Explainable predictions can guide pathologists in their diagnostic decision-making and help boost their confidence in the algorithm, paving the way for its future clinical adoption.