Major depressive disorder (MDD) is one of the most common mental disorders, with significant impacts on many daily activities and quality of life. It stands as one of the most common mental disorders globally and ranks as the second leading cause of disability. The current diagnostic approach for MDD primarily relies on clinical observations and patient-reported symptoms, overlooking the diverse underlying causes and pathophysiological factors contributing to depression. Therefore, scientific researchers and clinicians must gain a deeper understanding of the pathophysiological mechanisms involved in MDD. There is growing evidence in neuroscience that depression is a brain network disorder, and the use of neuroimaging, such as magnetic resonance imaging (MRI), plays a significant role in identifying and treating MDD. Rest-state functional MRI (rs-fMRI) is among the most popular neuroimaging techniques used to study MDD. Deep learning techniques have been widely applied to neuroimaging data to help with early mental health disorder detection. Recent years have seen a rise in interest in graph neural networks (GNNs), which are deep neural architectures specifically designed to handle graph-structured data like rs-fMRI. This research aimed to develop an ensemble-based GNN model capable of detecting discriminative features from rs-fMRI images for the purpose of diagnosing MDD. Specifically, we constructed an ensemble model by combining features from multiple brain region segmentation atlases to capture brain complexity and detect distinct features more accurately than single atlas-based models. Further, the effectiveness of our model is demonstrated by assessing its performance on a large multi-site MDD dataset. The best performing model among all folds achieved an accuracy of 75.80%, a sensitivity of 88.89%, a specificity of 61.84%, a precision of 71.29%, and an F1-score of 79.12%.
Foundation models have revolutionized the paradigm of digital pathology, as they leverage general-purpose features to emulate real-world pathological practices, enabling the quantitative analysis of critical histological patterns and the dissection of cancer-specific signals. However, these static general features constrain the flexibility and pathological relevance in the ever-evolving needs of clinical applications, hindering the broad use of the current models. Here we introduce PathFiT, a dynamic feature learning method that can be effortlessly plugged into various pathology foundation models to unlock their adaptability. Meanwhile, PathFiT performs seamless implementation across diverse pathology applications regardless of downstream specificity. To validate PathFiT, we construct a digital pathology benchmark with over 20 terabytes of Internet and real-world data comprising 28 H\&E-stained tasks and 7 specialized imaging tasks including Masson's Trichrome staining and immunofluorescence images. By applying PathFiT to the representative pathology foundation models, we demonstrate state-of-the-art performance on 34 out of 35 tasks, with significant improvements on 23 tasks and outperforming by 10.20% on specialized imaging tasks. The superior performance and versatility of PathFiT open up new avenues in computational pathology.
This paper explores and enhances the application of Transfer Learning (TL) for multilabel image classification in medical imaging, focusing on brain tumor class and diabetic retinopathy stage detection. The effectiveness of TL-using pre-trained models on the ImageNet dataset-varies due to domain-specific challenges. We evaluate five pre-trained models-MobileNet, Xception, InceptionV3, ResNet50, and DenseNet201-on two datasets: Brain Tumor MRI and APTOS 2019. Our results show that TL models excel in brain tumor classification, achieving near-optimal metrics. However, performance in diabetic retinopathy detection is hindered by class imbalance. To mitigate this, we integrate the Synthetic Minority Over-sampling Technique (SMOTE) with TL and traditional machine learning(ML) methods, which improves accuracy by 1.97%, recall (sensitivity) by 5.43%, and specificity by 0.72%. These findings underscore the need for combining TL with resampling techniques and ML methods to address data imbalance and enhance classification performance, offering a pathway to more accurate and reliable medical image analysis and improved patient outcomes with minimal extra computation powers.
This study proposes a novel lightweight neural network model leveraging features extracted from electrocardiogram (ECG) and respiratory signals for early OSA screening. ECG signals are used to generate feature spectrograms to predict sleep stages, while respiratory signals are employed to detect sleep-related breathing abnormalities. By integrating these predictions, the method calculates the apnea-hypopnea index (AHI) with enhanced accuracy, facilitating precise OSA diagnosis. The method was validated on three publicly available sleep apnea databases: the Apnea-ECG database, the UCDDB dataset, and the MIT-BIH Polysomnographic database. Results showed an overall OSA detection accuracy of 0.978, highlighting the model's robustness. Respiratory event classification achieved an accuracy of 0.969 and an area under the receiver operating characteristic curve (ROC-AUC) of 0.98. For sleep stage classification, in UCDDB dataset, the ROC-AUC exceeded 0.85 across all stages, with recall for Sleep reaching 0.906 and specificity for REM and Wake states at 0.956 and 0.937, respectively. This study underscores the potential of integrating lightweight neural networks with multi-signal analysis for accurate, portable, and cost-effective OSA screening, paving the way for broader adoption in home-based and wearable health monitoring systems.
Bacteriophages are promising alternative antimicrobial agents due to their high specificity for host bacteria and minimal immunogenicity in humans. However, their therapeutic application is limited by their nature as biological entities, which can lead to unintended evolutionary consequences such as horizontal gene transfer. In this study, we address these challenges by repurposing only the structural components of bacteriophages as vesicles to deliver antibiotics directly into the cytoplasm of bacterial hosts. This approach is based on two key hypotheses: first, antibiotics such as beta-lactams remain effective against resistant bacteria if injected directly into the cytoplasm, bypassing resistance mechanisms; second, phage structures can be synthesized and self-assembled in vitro using modular genomes and cell-free protein expression systems to carry small molecules such as antibiotics as cargo. To test these hypotheses, we utilized T7 phages and penicillin-resistant Escherichia coli as a model system. First, we designed the T7 phage genome into a modular format containing only the genes encoding structural components and synthesized the gene fragments via de novo gene synthesis. These phage structures were then rebooted in vitro using a cell-free protein expression system in the presence of penicillin G, allowing the antibiotics to be incorporated as cargo during the self-assembly process. Finally, we tested the antimicrobial activity of these antibiotic-loaded phage syringes against penicillin-resistant E. coli. The results demonstrate that phage syringes effectively reduce the population of penicillin-resistant E. coli compared to negative controls, including free penicillin and water. This study highlights the potential of using phage structures as antibiotic delivery vehicles, offering a novel strategy to overcome both antibiotic resistance and the limitations of phage therapy.
While large language models, such as GPT and BERT, have already demonstrated unprecedented skills in everything from natural language processing to domain-specific applications, there came an unexplored phenomenon we term the Rosetta Paradox. The Rosetta Paradox characterizes the counterintuitive performance inversions across domains of knowledge. This paradox captures how such LLMs can excel in highly specialized fields but do poorly on tasks which require general, everyday knowledge. This paper formalizes the definition of the Rosetta Paradox and introduces a panoramic analysis framework that includes both a Domain Specificity Index (DSI) and a Performance Inversion Metric (PIM) for consistent quantification of domain-specific behavior in LLMs. We adopt this paradox and conduct a series of investigations through extensive experiments across diverse models and knowledge domains, ranging from rich technical areas to common-sense reasoning. Our findings indicate that the Rosetta Paradox is likely not a mere artifact of data distribution but an intrinsic architectural and emergent property of deep neural networks. We present comparative analyses across different model architectures, sizes, and training methodologies that shed light into the peculiar ways this paradox manifests itself and challenge the standard evaluation metrics.
Gene silencing via small interfering RNA (siRNA) represents a transformative tool in cancer therapy, offering specificity and reduced off-target effects compared to conventional treatments. A crucial step in siRNA-based therapies is endosomal escape, the release of siRNA from endosomes into the cytoplasm. Quantifying endosomal escape is challenging due to the dynamic nature of the process and limitations in imaging and analytical techniques. Traditional methods often rely on fluorescence intensity measurements or manual image processing, which are time-intensive and fail to capture continuous dynamics. This paper presents a novel computational framework that integrates automated image processing to analyze time-lapse fluorescent microscopy data of endosomal escape, hierarchical Bayesian inference, and stochastic simulations. Our method employs image segmentation techniques such as binary masks, Gaussian filters, and multichannel color quantification to extract precise spatial and temporal data from microscopy images. Using a hierarchical Bayesian approach, we estimate the parameters of a compartmental model that describes endosomal escape dynamics, accounting for variability over time. These parameters inform a Gillespie stochastic simulation algorithm, ensuring realistic simulations of siRNA release events over time. Our framework provides a scalable and reproducible method for quantifying endosomal escape. The model captures uncertainty and variability in parameter estimation, and endosomal escape dynamics. Additionally, synthetic data generation allows researchers to validate experimental findings and explore alternative conditions without extensive laboratory work. This integrated approach not only improves the accuracy of endosomal escape quantification but also provides predictive insights for optimizing siRNA delivery systems and advancing gene therapy research.
Cases of laryngeal cancer are predicted to rise significantly in the coming years. Current diagnostic pathways are inefficient, putting undue stress on both patients and the medical system. Artificial intelligence offers a promising solution by enabling non-invasive detection of laryngeal cancer from patient voice, which could help prioritise referrals more effectively. A major barrier in this field is the lack of reproducible methods. Our work addresses this challenge by introducing a benchmark suite comprising 36 models trained and evaluated on open-source datasets. These models classify patients with benign and malignant voice pathologies. All models are accessible in a public repository, providing a foundation for future research. We evaluate three algorithms and three audio feature sets, including both audio-only inputs and multimodal inputs incorporating demographic and symptom data. Our best model achieves a balanced accuracy of 83.7%, sensitivity of 84.0%, specificity of 83.3%, and AUROC of 91.8%.
Flow-based generative models (FMs) have rapidly advanced as a method for mapping noise to data, its efficient training and sampling process makes it widely applicable in various fields. FMs can be viewed as a variant of diffusion models (DMs). At the same time, previous studies have shown that DMs are vulnerable to Trojan/Backdoor attacks, a type of output manipulation attack triggered by a maliciously embedded pattern at model input. We found that Trojan attacks on generative models are essentially equivalent to image transfer tasks from the backdoor distribution to the target distribution, the unique ability of FMs to fit any two arbitrary distributions significantly simplifies the training and sampling setups for attacking FMs, making them inherently natural targets for backdoor attacks. In this paper, we propose TrojFlow, exploring the vulnerabilities of FMs through Trojan attacks. In particular, we consider various attack settings and their combinations and thoroughly explore whether existing defense methods for DMs can effectively defend against our proposed attack scenarios. We evaluate TrojFlow on CIFAR-10 and CelebA datasets, our experiments show that our method can compromise FMs with high utility and specificity, and can easily break through existing defense mechanisms.
Systematic reviews (SRs) are essential for evidence-based guidelines but are often limited by the time-consuming nature of literature screening. We propose and evaluate an in-house system based on Large Language Models (LLMs) for automating both title/abstract and full-text screening, addressing a critical gap in the literature. Using a completed SR on Vitamin D and falls (14,439 articles), the LLM-based system employed prompt engineering for title/abstract screening and Retrieval-Augmented Generation (RAG) for full-text screening. The system achieved an article exclusion rate (AER) of 99.5%, specificity of 99.6%, a false negative rate (FNR) of 0%, and a negative predictive value (NPV) of 100%. After screening, only 78 articles required manual review, including all 20 identified by traditional methods, reducing manual screening time by 95.5%. For comparison, Rayyan, a commercial tool for title/abstract screening, achieved an AER of 72.1% and FNR of 5% when including articles Rayyan considered as undecided or likely to include. Lowering Rayyan's inclusion thresholds improved FNR to 0% but increased screening time. By addressing both screening phases, the LLM-based system significantly outperformed Rayyan and traditional methods, reducing total screening time to 25.5 hours while maintaining high accuracy. These findings highlight the transformative potential of LLMs in SR workflows by offering a scalable, efficient, and accurate solution, particularly for the full-text screening phase, which has lacked automation tools.
Sudden Cardiac Arrest (SCA) is the leading cause of death among athletes of all age levels worldwide. Current prescreening methods for cardiac risk factors are largely ineffective, and implementing the International Olympic Committee recommendation for 12-lead ECG screening remains prohibitively expensive. To address these challenges, a preliminary comprehensive screening system (CSS) was developed to efficiently and economically screen large populations for risk factors to SCA. A protocol was established to measure a 4-lead ECG using an Apple Watch. Additionally, two key advances were introduced and validated: 1) A decomposition regression model to upscale 4-lead data to 12 leads, reducing ECG cost and usage complexity. 2) A deep learning model, the Transformer Auto-Encoder System (TAES), was designed to extract spatial and temporal features from the data for beat-based classification. TAES demonstrated an average sensitivity of 95.3% and specificity of 99.1% respectively in the testing dataset, outperforming human physicians in the same dataset (Se: 94%, Sp: 93%). Human subject trials (n = 30) validated the smartwatch protocol, with Bland-Altman analysis showing no statistical difference between the smartwatch vs. ECG protocol. Further validation of the complete CSS on a 20-subject cohort (10 affected, 10 controls) did not result in any misidentifications. This paper presents a mass screening system with the potential to achieve superior accuracy in high-throughput cardiac pre-participation evaluation compared to the clinical gold standard.
Electroencephalogram (EEG) signals are critical for detecting abnormal brain activity, but their high dimensionality and complexity pose significant challenges for effective analysis. In this paper, we propose CwA-T, a novel framework that combines a channelwise CNN-based autoencoder with a single-head transformer classifier for efficient EEG abnormality detection. The channelwise autoencoder compresses raw EEG signals while preserving channel independence, reducing computational costs and retaining biologically meaningful features. The compressed representations are then fed into the transformer-based classifier, which efficiently models long-term dependencies to distinguish between normal and abnormal signals. Evaluated on the TUH Abnormal EEG Corpus, the proposed model achieves 85.0% accuracy, 76.2% sensitivity, and 91.2% specificity at the per-case level, outperforming baseline models such as EEGNet, Deep4Conv, and FusionCNN. Furthermore, CwA-T requires only 202M FLOPs and 2.9M parameters, making it significantly more efficient than transformer-based alternatives. The framework retains interpretability through its channelwise design, demonstrating great potential for future applications in neuroscience research and clinical practice. The source code is available at https://github.com/YossiZhao/CAE-T.
Current ophthalmology clinical workflows are plagued by over-referrals, long waits, and complex and heterogeneous medical records. Large language models (LLMs) present a promising solution to automate various procedures such as triaging, preliminary tests like visual acuity assessment, and report summaries. However, LLMs have demonstrated significantly varied performance across different languages in natural language question-answering tasks, potentially exacerbating healthcare disparities in Low and Middle-Income Countries (LMICs). This study introduces the first multilingual ophthalmological question-answering benchmark with manually curated questions parallel across languages, allowing for direct cross-lingual comparisons. Our evaluation of 6 popular LLMs across 7 different languages reveals substantial bias across different languages, highlighting risks for clinical deployment of LLMs in LMICs. Existing debiasing methods such as Translation Chain-of-Thought or Retrieval-augmented generation (RAG) by themselves fall short of closing this performance gap, often failing to improve performance across all languages and lacking specificity for the medical domain. To address this issue, We propose CLARA (Cross-Lingual Reflective Agentic system), a novel inference time de-biasing method leveraging retrieval augmented generation and self-verification. Our approach not only improves performance across all languages but also significantly reduces the multilingual bias gap, facilitating equitable LLM application across the globe.
The biophysical interactions between the T cell receptor (TCR) and its ligands determine the specificity of the cellular immune response. However, the immense diversity of receptors and ligands has made it challenging to discover generalizable rules across the distinct binding affinity landscapes created by different ligands. Here, we present an optimization framework for discovering biophysical rules that predict whether TCRs share specificity to a ligand. Applying this framework to TCRs associated with a collection of SARS-CoV-2 peptides we systematically characterize how co-specificity depends on the type and position of amino-acid differences between receptors. We also demonstrate that the inferred rules generalize to ligands highly dissimilar to any seen during training. Our analysis reveals that matching of steric properties between substituted amino acids is more important for receptor co-specificity than the hydrophobic properties that prominently determine evolutionary substitutability. Our analysis also quantifies the substantial importance of positions not in direct contact with the peptide for specificity. These findings highlight the potential for data-driven approaches to uncover the molecular mechanisms underpinning the specificity of adaptive immune responses.
Log-based anomaly detection (LogAD) is the main component of Artificial Intelligence for IT Operations (AIOps), which can detect anomalous that occur during the system on-the-fly. Existing methods commonly extract log sequence features using classical machine learning techniques to identify whether a new sequence is an anomaly or not. However, these classical approaches often require trade-offs between efficiency and accuracy. The advent of quantum machine learning (QML) offers a promising alternative. By transforming parts of classical machine learning computations into parameterized quantum circuits (PQCs), QML can significantly reduce the number of trainable parameters while maintaining accuracy comparable to classical counterparts. In this work, we introduce a unified framework, \ourframework{}, for evaluating QML models in the context of LogAD. This framework incorporates diverse log data, integrated QML models, and comprehensive evaluation metrics. State-of-the-art methods such as DeepLog, LogAnomaly, and LogRobust, along with their quantum-transformed counterparts, are included in our framework.Beyond standard metrics like F1 score, precision, and recall, our evaluation extends to factors critical to QML performance, such as specificity, the number of circuits, circuit design, and quantum state encoding. Using \ourframework{}, we conduct extensive experiments to assess the performance of these models and their quantum counterparts, uncovering valuable insights and paving the way for future research in QML model selection and design for LogAD.
Purpose: This work addresses the detection of Helicobacter pylori (H. pylori) in histological images with immunohistochemical staining. This analysis is a time demanding task, currently done by an expert pathologist that visually inspects the samples. Given the effort required to localise the pathogen in images, a limited number of annotations might be available in an initial setting. Our goal is to design an approach that, using a limited set of annotations, is capable of obtaining results good enough to be used as a support tool. Methods: We propose to use autoencoders to learn the latent patterns of healthy patches and formulate a specific measure of the reconstruction error of the image in HSV space. ROC analysis is used to set the optimal threshold of this measure and the percentage of positive patches in a sample that determines the presence of H. pylori. Results: Our method has been tested on an own database of 245 Whole Slide Images (WSI) having 117 cases without H. pylori and different density of the bacteria in the remaining ones. The database has 1211 annotated patches, with only 163 positive patches. This dataset of positive annotations was used to train a baseline thresholding and an SVM using the features of a pre-trained RedNet18 and ViT models. A 10-fold cross-validation shows that our method has better performance with 91% accuracy, 86% sensitivity, 96% specificity and 0.97 AUC in the diagnosis of H. pylori. Conclusion: Unlike classification approaches, our shallow autoencoder with threshold adaptation for the detection of anomalous staining is able to achieve competitive results with a limited set of annotated data. This initial approach is good enough to be used as a guide for fast annotation of infected patches.
Automating brain tumor segmentation using deep learning methods is an ongoing challenge in medical imaging. Multiple lingering issues exist including domain-shift and applications in low-resource settings which brings a unique set of challenges including scarcity of data. As a step towards solving these specific problems, we propose Convolutional adapter-inspired Parameter-efficient Fine-tuning (PEFT) of MedNeXt architecture. To validate our idea, we show our method performs comparable to full fine-tuning with the added benefit of reduced training compute using BraTS-2021 as pre-training dataset and BraTS-Africa as the fine-tuning dataset. BraTS-Africa consists of a small dataset (60 train / 35 validation) from the Sub-Saharan African population with marked shift in the MRI quality compared to BraTS-2021 (1251 train samples). We first show that models trained on BraTS-2021 dataset do not generalize well to BraTS-Africa as shown by 20% reduction in mean dice on BraTS-Africa validation samples. Then, we show that PEFT can leverage both the BraTS-2021 and BraTS-Africa dataset to obtain mean dice of 0.8 compared to 0.72 when trained only on BraTS-Africa. Finally, We show that PEFT (0.80 mean dice) results in comparable performance to full fine-tuning (0.77 mean dice) which may show PEFT to be better on average but the boxplots show that full finetuning results is much lesser variance in performance. Nevertheless, on disaggregation of the dice metrics, we find that the model has tendency to oversegment as shown by high specificity (0.99) compared to relatively low sensitivity(0.75). The source code is available at https://github.com/CAMERA-MRI/SPARK2024/tree/main/PEFT_MedNeXt
Query suggestion, a technique widely adopted in information retrieval, enhances system interactivity and the browsing experience of document collections. In cross-modal retrieval, many works have focused on retrieving relevant items from natural language queries, while few have explored query suggestion solutions. In this work, we address query suggestion in cross-modal retrieval, introducing a novel task that focuses on suggesting minimal textual modifications needed to explore visually consistent subsets of the collection, following the premise of ''Maybe you are looking for''. To facilitate the evaluation and development of methods, we present a tailored benchmark named CroQS. This dataset comprises initial queries, grouped result sets, and human-defined suggested queries for each group. We establish dedicated metrics to rigorously evaluate the performance of various methods on this task, measuring representativeness, cluster specificity, and similarity of the suggested queries to the original ones. Baseline methods from related fields, such as image captioning and content summarization, are adapted for this task to provide reference performance scores. Although relatively far from human performance, our experiments reveal that both LLM-based and captioning-based methods achieve competitive results on CroQS, improving the recall on cluster specificity by more than 115% and representativeness mAP by more than 52% with respect to the initial query. The dataset, the implementation of the baseline methods and the notebooks containing our experiments are available here: https://paciosoft.com/CroQS-benchmark/
Topic modeling is widely used for uncovering thematic structures within text corpora, yet traditional models often struggle with specificity and coherence in domain-focused applications. Guided approaches, such as SeededLDA and CorEx, incorporate user-provided seed words to improve relevance but remain labor-intensive and static. Large language models (LLMs) offer potential for dynamic topic refinement and discovery, yet their application often incurs high API costs. To address these challenges, we propose the LLM-assisted Iterative Topic Augmentation framework (LITA), an LLM-assisted approach that integrates user-provided seeds with embedding-based clustering and iterative refinement. LITA identifies a small number of ambiguous documents and employs an LLM to reassign them to existing or new topics, minimizing API costs while enhancing topic quality. Experiments on two datasets across topic quality and clustering performance metrics demonstrate that LITA outperforms five baseline models, including LDA, SeededLDA, CorEx, BERTopic, and PromptTopic. Our work offers an efficient and adaptable framework for advancing topic modeling and text clustering.
Since high resolution remote sensing image classification often requires a relatively high computation complexity, lightweight models tend to be practical and efficient. Model pruning is an effective method for model compression. However, existing methods rarely take into account the specificity of remote sensing images, resulting in significant accuracy loss after pruning. To this end, we propose an effective structural pruning approach for remote sensing image classification. Specifically, a pruning strategy that amplifies the differences in channel importance of the model is introduced. Then an adaptive mining loss function is designed for the fine-tuning process of the pruned model. Finally, we conducted experiments on two remote sensing classification datasets. The experimental results demonstrate that our method achieves minimal accuracy loss after compressing remote sensing classification models, achieving state-of-the-art (SoTA) performance.