The rapid development of multimodal generative vision models has drawn scientific curiosity. Notable advancements, such as OpenAI’s ChatGPT and Stable Diffusion, demonstrate the potential of combining multimodal data for generative content. Nonetheless, customising these models to specific domains or tasks is challenging due to computational costs and data requirements. Conventional fine-tuning methods take redundant processing resources, motivating the development of parameter-efficient fine-tuning technologies such as adapter module, low-rank factorization and orthogonal fine-tuning. These solutions selectively change a subset of model parameters, reducing learning needs while maintaining high-quality results. Orthogonal fine-tuning, regarded as a reliable technique, preserves semantic linkages in weight space but has limitations in its expressive powers. To better overcome these constraints, we provide a simple but innovative and effective transformation method inspired by Möbius geometry, which replaces conventional orthogonal transformations in parameter-efficient fine-tuning. This strategy improved fine-tuning’s adaptability and expressiveness, allowing it to capture more data patterns. Our strategy, which is supported by theoretical understanding and empirical validation, outperforms existing approaches, demonstrating competitive improvements in generation quality for key generative tasks.

Precise segmentation of brain tumors, particularly contrast-enhancing regions visible in post-contrast MRI (areas highlighted by contrast agent injection), is crucial for accurate clinical diagnosis and treatment planning but remains challenging. However, current methods exhibit notable performance degradation in segmenting these enhancing brain tumor areas, largely due to insufficient consideration of MRI-specific tumor features such as complex textures and directional variations. To address this, we propose the Harmonized Frequency Fusion Network (HFF-Net), which rethinks brain tumor segmentation from a frequency-domain perspective. To comprehensively characterize tumor regions, we develop a Frequency Domain Decomposition (FDD) module that separates MRI images into low-frequency components, capturing smooth tumor contours and high-frequency components, highlighting detailed textures and directional edges. To further enhance sensitivity to tumor boundaries, we introduce an Adaptive Laplacian Convolution (ALC) module that adaptively emphasizes critical high-frequency details using dynamically updated convolution kernels. To effectively fuse tumor features across multiple scales, we design a Frequency Domain Cross-Attention (FDCA) integrating semantic, positional, and slice-specific information. We further validate and interpret frequency-domain improvements through visualization, theoretical reasoning, and experimental analyses. Extensive experiments on four public datasets demonstrate that HFF-Net achieves an average relative improvement of 4.48% (ranging from 2.39% to 7.72%) in the mean Dice scores across the three major subregions, and an average relative improvement of 7.33% (ranging from 5.96% to 8.64%) in the segmentation of contrast-enhancing tumor regions, while maintaining favorable computational efficiency and clinical applicability. Our code is available at: https://github.com/VinyehShaw/HFF.

Human activity recognition (HAR) is one of the core research themes in ubiquitous and wearable computing. With the shift to deep learning (DL) based analysis approaches, it has become possible to extract high-level features and perform classification in an end-to-end manner. Despite their promising overall capabilities, DL-based HAR may suffer from overfitting due to the notoriously small, often inadequate, amounts of labeled sample data that are available for typical HAR applications. In response to such challenges, we propose ConvBoost -- a novel, three-layer, structured model architecture and boosting framework for convolutional network based HAR. Our framework generates additional training data from three different perspectives for improved HAR, aiming to alleviate the shortness of labeled training data in the field. Specifically, with the introduction of three conceptual layers--Sampling Layer, Data Augmentation Layer, and Resilient Layer--we develop three "boosters"--R-Frame, Mix-up, and C-Drop--to enrich the per-epoch training data by dense-sampling, synthesizing, and simulating, respectively. These new conceptual layers and boosters, that are universally applicable for any kind of convolutional network, have been designed based on the characteristics of the sensor data and the concept of frame-wise HAR. In our experimental evaluation on three standard benchmarks (Opportunity, PAMAP2, GOTOV) we demonstrate the effectiveness of our ConvBoost framework for HAR applications based on variants of convolutional networks: vanilla CNN, ConvLSTM, and Attention Models. We achieved substantial performance gains for all of them, which suggests that the proposed approach is generic and can serve as a practical solution for boosting the performance of existing ConvNet-based HAR models. This is an open-source project, and the code can be found at https://github.com/sshao2013/ConvBoost

Background: Although electronic health records (EHR) provide useful insights into disease patterns and patient treatment optimisation, their reliance on unstructured data presents a difficulty. Echocardiography reports, which provide extensive pathology information for cardiovascular patients, are particularly challenging to extract and analyse, because of their narrative structure. Although natural language processing (NLP) has been utilised successfully in a variety of medical fields, it is not commonly used in echocardiography analysis. Objectives: To develop an NLP-based approach for extracting and categorising data from echocardiography reports by accurately converting continuous (e.g., LVOT VTI, AV VTI and TR Vmax) and discrete (e.g., regurgitation severity) outcomes in a semi-structured narrative format into a structured and categorised format, allowing for future research or clinical use. Methods: 135,062 Trans-Thoracic Echocardiogram (TTE) reports were derived from 146967 baseline echocardiogram reports and split into three cohorts: Training and Validation (n = 1075), Test Dataset (n = 98) and Application Dataset (n = 133,889). The NLP system was developed and was iteratively refined using medical expert knowledge. The system was used to curate a moderate-fidelity database from extractions of 133,889 reports. A hold-out validation set of 98 reports was blindly annotated and extracted by two clinicians for comparison with the NLP extraction. Agreement, discrimination, accuracy and calibration of outcome measure extractions were evaluated. Results: Continuous outcomes including LVOT VTI, AV VTI and TR Vmax exhibited perfect inter-rater reliability using intra-class correlation scores (ICC = 1.00, p < 0.05) alongside high R² values, demonstrating an ideal alignment between the NLP system and clinicians. A good level (ICC = 0.75–0.9, p < 0.05) of inter-rater reliability was observed for outcomes such as LVOT Diam, Lateral MAPSE, Peak E Velocity, Lateral E’ Velocity, PV Vmax, Sinuses of Valsalva and Ascending Aorta diameters. Furthermore, the accuracy rate for discrete outcome measures was 91.38% in the confusion matrix analysis, indicating effective performance. Conclusions: The NLP-based technique yielded good results when it came to extracting and categorising data from echocardiography reports. The system demonstrated a high degree of agreement and concordance with clinician extractions. This study contributes to the effective use of semi-structured data by providing a useful tool for converting semi-structured text to a structured echo report that can be used for data management. Additional validation and implementation in healthcare settings can improve data availability and support research and clinical decision-making.

Background: Ensemble tree-based models such as Xgboost are highly prognostic in cardiovascular medicine, as measured by the Clinical Effectiveness Metric (CEM). However, their ability to handle correlated data, such as hospital-level effects, is limited. Objectives: The aim of this work is to develop a binary-outcome mixed-effects Xgboost (BME) model that integrates random effects at the hospital level. To ascertain how well the model handles correlated data in cardiovascular outcomes, we aim to assess its performance and compare it to fixed-effects Xgboost and traditional logistic regression models. Methods: A total of 227,087 patients over 17 years of age, undergoing cardiac surgery from 42 UK hospitals between 1 January 2012 and 31 March 2019, were included. The dataset was split into two cohorts: training/validation (n = 157,196; 2012–2016) and holdout (n = 69,891; 2017–2019). The outcome variable was 30-day mortality with hospitals considered as the clustering variable. The logistic regression, mixed-effects logistic regression, Xgboost and binary-outcome mixed-effects Xgboost (BME) were fitted to both standardized and unstandardized datasets across a range of sample sizes and the estimated prediction power metrics were compared to identify the best approach. Results: The exploratory study found high variability in hospital-related mortality across datasets, which supported the adoption of the mixed-effects models. Unstandardized Xgboost BME demonstrated marked improvements in prediction power over the Xgboost model at small sample size ranges, but performance differences decreased as dataset sizes increased. Generalized linear models (glms) and generalized linear mixed-effects models (glmers) followed similar results, with the Xgboost models also excelling at greater sample sizes. Conclusions: These findings suggest that integrating mixed effects into machine learning models can enhance their performance on datasets where the sample size is small.

Introduction: The heterogeneity in tumours poses significant challenges to the accurate prediction of cancer stages, necessitating the expertise of highly trained medical professionals for diagnosis. Over the past decade, the integration of deep learning into medical diagnostics, particularly for predicting cancer stages, has been hindered by the black-box nature of these algorithms, which complicates the interpretation of their decision-making processes. Methods: This study seeks to mitigate these issues by leveraging the complementary attributes found within functional genomics datasets (including mRNA, miRNA, and DNA methylation) and stained histopathology images. We introduced the Extended Squeeze- and-Excitation Multiheaded Attention (ESEMA) model, designed to harness these modalities. This model efficiently integrates and enhances the multimodal features, capturing biologically pertinent patterns that improve both the accuracy and interpretability of cancer stage predictions. Results: Our findings demonstrate that the explainable classifier utilised the salient features of the multimodal data to achieve an area under the curve (AUC) of 0.9985, significantly surpassing the baseline AUCs of 0.8676 for images and 0.995 for genomic data. Conclusion: Furthermore, the extracted genomics features were the most relevant for cancer stage prediction, suggesting that these identified genes are promising targets for further clinical investigation.