Search

Medical image quality assessment (MIQA) is essential for reliable medical image analysis. While deep learning has shown promise in this field, current models could be misled by spurious correlations learned from data and struggle with out-of-distribution (OOD) scenarios. To that end, we propose an MIQA framework based on a concept from causal inference: Probability of Necessity and Sufficiency (PNS). PNS measures how likely a set of features is to be both necessary (always present for an outcome) and sufficient (capable of guaranteeing an outcome) for a particular result. Our approach leverages this concept by learning hidden features from medical images with high PNS values for quality prediction. This encourages models to capture more essential predictive information, enhancing their robustness to OOD scenarios. We evaluate our framework on an Anterior Segment Optical Coherence Tomography (AS-OCT) dataset for the MIQA task and experimental results demonstrate the effectiveness of our framework.

Anterior uveitis, a common form of eye inflammation, can lead to permanent vision loss if not promptly diagnosed. Monitoring this condition involves quantifying inflammatory cells in the anterior chamber (AC) of the eye, which can be captured using Anterior Segment Optical Coherence Tomography (AS-OCT). However, manually identifying cells in AS-OCT images is time-consuming and subjective. Moreover, existing automated approaches may have limitations in both the effectiveness of detecting cells and the reliability of their detection results. To address these challenges, we propose an automated framework to detect cells in the AS-OCT images. This framework consists of a zero-shot chamber segmentation module and a cell detection module. The first module segments the AC area in the image without requiring human-annotated training data. Subsequently, the second module identifies individual cells within the segmented AC region. Through experiments, our framework demonstrates superior performance compared to current state-of-the-art methods for both AC segmentation and cell detection tasks. Notably, we find that previous cell detection approaches could suffer from low recall, potentially overlooking a significant number of cells. In contrast, our framework offers an improved solution, which could benefit the diagnosis and study of anterior uveitis. Our code for cell detection is publicly available at: https://github.com/joeybyc/cell_detection.

Newly diagnosed Type 1 Diabetes (T1D) patients often struggle to obtain effective Blood Glucose (BG) prediction models due to the lack of sufficient BG data from Continuous Glucose Monitoring (CGM), presenting a significant "cold start" problem in patient care. Utilizing population models to address this challenge is a potential solution, but collecting patient data for training population models in a privacy-conscious manner is challenging, especially given that such data is often stored on personal devices. Considering the privacy protection and addressing the "cold start" problem in diabetes care, we propose "GluADFL", blood Glucose prediction by Asynchronous Decentralized Federated Learning. We compared GluADFL with eight baseline methods using four distinct T1D datasets, comprising 298 participants, which demonstrated its superior performance in accurately predicting BG levels for cross-patient analysis. Furthermore, patients' data might be stored and shared across various communication networks in GluADFL, ranging from highly interconnected (e.g., random, performs the best among others) to more structured topologies (e.g., cluster and ring), suitable for various social networks. The asynchronous training framework supports flexible participation. By adjusting the ratios of inactive participants, we found it remains stable if less than 70% are inactive. Our results confirm that GluADFL offers a practical, privacy-preserving solution for BG prediction in T1D, significantly enhancing the quality of diabetes management.

FMRI data are noisy, complicated to acquire, and typically go through many steps of processing before they are used in a study or clinical practice. Being able to visualize and understand the data from the start through the completion of processing, while being confident that each intermediate step was successful, is challenging. AFNI's afni_proc$.$py is a tool to create and run a processing pipeline for FMRI data. With its flexible features, afni_proc$.$py allows users to both control and evaluate their processing at a detailed level. It has been designed to keep users informed about all processing steps: it does not just process the data, but first outputs a fully commented processing script that the users can read, query, interpret and refer back to. Having this full provenance is important for being able to understand each step of processing; it also promotes transparency and reproducibility by keeping the record of individual-level processing and modeling specifics in a single, shareable place. Additionally, afni_proc$.$py creates pipelines that contain several automatic self-checks for potential problems during runtime. The output directory contains a dictionary of relevant quantities that can be programmatically queried for potential issues and a systematic, interactive quality control (QC) HTML. All of these features help users evaluate and understand their data and processing in detail. We describe these and other aspects of afni_proc$.$py here using a set of task-based and resting state FMRI example commands., Comment: 71 pages, 19 figures, 1 tables

Flutter flight test involves the evaluation of the airframes aeroelastic stability by applying artificial excitation on the aircraft lifting surfaces. The subsequent responses are captured and analyzed to extract the frequencies and damping characteristics of the system. However, noise contamination, turbulence, non-optimal excitation of modes, and sensor malfunction in one or more sensors make it time-consuming and corrupt the extraction process. In order to expedite the process of identifying and analyzing aeroelastic modes, this study implements a time-delay embedded Dynamic Mode Decomposition technique. This approach is complemented by Robust Principal Component Analysis methodology, and a sparsity promoting criterion which enables the automatic and optimal selection of sparse modes. The anonymized flutter flight test data, provided by the fifth author of this research paper, is utilized in this implementation. The methodology assumes no knowledge of the input excitation, only deals with the responses captured by accelerometer channels, and rapidly identifies the aeroelastic modes. By incorporating a compressed sensing algorithm, the methodology gains the ability to identify aeroelastic modes, even when the number of available sensors is limited. This augmentation greatly enhances the methodology's robustness and effectiveness, making it an excellent choice for real-time implementation during flutter test campaigns., Comment: 31 pages, 12 figures, submitted in 'Mechanical Systems and Signal processing' journal

Accurate prediction of future blood glucose (BG) levels can effectively improve BG management for people living with diabetes, thereby reducing complications and improving quality of life. The state of the art of BG prediction has been achieved by leveraging advanced deep learning methods to model multi-modal data, i.e., sensor data and self-reported event data, organised as multi-variate time series (MTS). However, these methods are mostly regarded as ``black boxes'' and not entirely trusted by clinicians and patients. In this paper, we propose interpretable graph attentive recurrent neural networks (GARNNs) to model MTS, explaining variable contributions via summarizing variable importance and generating feature maps by graph attention mechanisms instead of post-hoc analysis. We evaluate GARNNs on four datasets, representing diverse clinical scenarios. Upon comparison with twelve well-established baseline methods, GARNNs not only achieve the best prediction accuracy but also provide high-quality temporal interpretability, in particular for postprandial glucose levels as a result of corresponding meal intake and insulin injection. These findings underline the potential of GARNN as a robust tool for improving diabetes care, bridging the gap between deep learning technology and real-world healthcare solutions.

False discovery rate (FDR) is commonly used for correction for multiple testing in neuroimaging studies. However, when using two-tailed tests, making directional inferences about the results can lead to vastly inflated error rate, even approaching 100\% in some cases. This happens because FDR only provides weak control over the error rate, meaning that the proportion of error is guaranteed only globally over all tests, not within subsets, such as among those in only one or another direction. Here we consider and evaluate different strategies for FDR control with two-tailed tests, using both synthetic and real imaging data. Approaches that separate the tests by direction of the hypothesis test, or by the direction of the resulting test statistic, more properly control the directional error rate and preserve FDR benefits, albeit with a doubled risk of errors under complete absence of signal. Strategies that combine tests in both directions, or that use simple two-tailed p-values, can lead to invalid directional conclusions, even if these tests remain globally valid. To enable valid thresholding for directional inference, we suggest that imaging software should allow the possibility that the user sets asymmetrical thresholds for the two sides of the statistical map. While FDR continues to be a valid, powerful procedure for multiple testing correction, care is needed when making directional inferences for two-tailed tests, or more broadly, when making any localized inference., Comment: 27 pages, 3 figures, 2 tables, 39 references

This paper proposes one of the first clinical applications of multimodal large language models (LLMs) as an assistant for radiologists to check errors in their reports. We created an evaluation dataset from real-world radiology datasets (including X-rays and CT scans). A subset of original reports was modified to contain synthetic errors by introducing three types of mistakes: "insert", "remove", and "substitute". The evaluation contained two difficulty levels: SIMPLE for binary error-checking and COMPLEX for identifying error types. At the SIMPLE level, our fine-tuned model significantly enhanced performance by 47.4% and 25.4% on MIMIC-CXR and IU X-ray data, respectively. This performance boost is also observed in unseen modality, CT scans, as the model performed 19.46% better than the baseline model. The model also surpassed the domain expert's accuracy in the MIMIC-CXR dataset by 1.67%. Notably, among the subsets (N=21) of the test set where a clinician did not achieve the correct conclusion, the LLaVA ensemble mode correctly identified 71.4% of these cases. However, all models performed poorly in identifying mistake types, underscoring the difficulty of the COMPLEX level. This study marks a promising step toward utilizing multimodal LLMs to enhance diagnostic accuracy in radiology. The ensemble model demonstrated comparable performance to clinicians, even capturing errors overlooked by humans.

An apparent giant wave event having a maximum trough-to-crest height of 21 metres and a maximum zero-upcrossing period of 27 seconds was recorded by a wave buoy at a nearshore location off the southwestern coast of Australia. It appears as a group of waves which are significantly larger both in height and period than the waves preceding and following them. This paper reports a multifaceted analysis into the plausibility of the event. We first examine the statistics of the event in relation to the rest of the record, where we look at quantities such as maximum-to-significant wave height ratios, ordered crest-trough statistics, and average wave profiles. We then investigate the kinematics of the buoy, where we look at the relationship between the horizontal and vertical displacements of the buoy, and also attempt to numerically reconstruct the giant event using Boussinesq and nonlinear shallow water equations. Additional analyses are performed on other sea states where at least one of the buoy's accelerometers reached its maximum limit. Our analysis reveals incompatibilities of the event with known behaviour of real waves, leading us to conclude that it was not a real wave event. Wave events similar to the one reported in our study have been reported elsewhere and have sometimes been accepted as real occurrences. Our methods of forensically analysing the giant wave event should be potentially useful for identifying false rogue wave events in these cases.

Since intermittent and highly variable power supply is undesirable, quantifying power yield fluctuations of wave energy converters (WECs) aids with assessment of potential deployment sites. This paper presents analysis of 3-hourly, monthly, seasonal, and inter-annual variability of power output of the M4 WEC. We compare expected performance from deployment at two wave energy hotspots: off Albany on the south-western coast of Australia and off the European Marine Energy Centre (EMEC) at Orkney, UK. We use multi-decadal wave hindcast data to predict the power that would have been generated by M4 WEC machines. The M4 machine, as a floating articulated device which extracts energy from flexing motion about a hinge, is sized according to a characteristic wavelength of the local wave climate. Using probability distributions, production duration curves, and coefficients of variation we demonstrate larger variability of the 3-hourly power yield at Orkney compared to Albany. At longer timescales, seasonal trends are highlighted through average monthly power values. From a continuity of supply perspective, we investigate occurrences of low production at three different threshold levels and calculate duration and likelihood of such events. Orkney is found to suffer from more persistent lows, causing a more intermittent power output. We also consider the effect of machine size on its power performance. Smaller machines are found to more effectively smooth out the stochastic nature of the underlying wave resource.

During the COVID-19 pandemic, the sheer volume of imaging performed in an emergency setting for COVID-19 diagnosis has resulted in a wide variability of clinical CXR acquisitions. This variation is seen in the CXR projections used, image annotations added and in the inspiratory effort and degree of rotation of clinical images. The image analysis community has attempted to ease the burden on overstretched radiology departments during the pandemic by developing automated COVID-19 diagnostic algorithms, the input for which has been CXR imaging. Large publicly available CXR datasets have been leveraged to improve deep learning algorithms for COVID-19 diagnosis. Yet the variable quality of clinically-acquired CXRs within publicly available datasets could have a profound effect on algorithm performance. COVID-19 diagnosis may be inferred by an algorithm from non-anatomical features on an image such as image labels. These imaging shortcuts may be dataset-specific and limit the generalisability of AI systems. Understanding and correcting key potential biases in CXR images is therefore an essential first step prior to CXR image analysis. In this study, we propose a simple and effective step-wise approach to pre-processing a COVID-19 chest X-ray dataset to remove undesired biases. We perform ablation studies to show the impact of each individual step. The results suggest that using our proposed pipeline could increase accuracy of the baseline COVID-19 detection algorithm by up to 13%.