{"title":"Personalized Video-Based Hand Taxonomy Using Egocentric Video in the Wild.","authors":"Mehdy Dousty, David J Fleet, Jose Zariffa","doi":"10.1109/JBHI.2024.3495699","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3495699","url":null,"abstract":"<p><strong>Objective: </strong>Hand function is central to inter- actions with our environment. Developing a comprehen- sive model of hand grasps in naturalistic environments is crucial across various disciplines, including robotics, ergonomics, and rehabilitation. Creating such a taxonomy poses challenges due to the significant variation in grasp- ing strategies that individuals may employ. For instance, individuals with impaired hands, such as those with spinal cord injuries (SCI), may develop unique grasps not used by unimpaired individuals. These grasping techniques may differ from person to person, influenced by variable senso- rimotor impairment, creating a need for personalized meth- ods of analysis.</p><p><strong>Method: </strong>This study aimed to automatically identify the dominant distinct hand grasps for each indi- vidual without reliance on a priori taxonomies, by applying semantic clustering to egocentric video. Egocentric video recordings collected in the homes of 19 individual with cervical SCI were used to cluster grasping actions with semantic significance. A deep learning model integrating posture and appearance data was employed to create a per- sonalized hand taxonomy.</p><p><strong>Results: </strong>Quantitative analysis reveals a cluster purity of 67.6% ± 24.2% with 18.0% ± 21.8% redundancy. Qualitative assessment revealed meaningful clusters in video content.</p><p><strong>Discussion: </strong>This methodology provides a flexible and effective strategy to analyze hand function in the wild, with applications in clinical assess- ment and in-depth characterization of human-environment interactions in a variety of contexts.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":6.7,"publicationDate":"2024-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142619325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Konstantinos Vilouras, Pedro Sanchez, Alison Q O'Neil, Sotirios A Tsaftaris
{"title":"Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Models.","authors":"Konstantinos Vilouras, Pedro Sanchez, Alison Q O'Neil, Sotirios A Tsaftaris","doi":"10.1109/JBHI.2024.3494246","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3494246","url":null,"abstract":"<p><p>Localizing the exact pathological regions in a given medical scan is an important imaging problem that traditionally requires a large amount of bounding box ground truth annotations to be accurately solved. However, there exist alternative, potentially weaker, forms of supervision, such as accompanying free-text reports, which are readily available. The task of performing localization with textual guidance is commonly referred to as phrase grounding. In this work, we use a publicly available Foundation Model, namely the Latent Diffusion Model, to perform this challenging task. This choice is supported by the fact that the Latent Diffusion Model, despite being generative in nature, contains cross-attention mechanisms that implicitly align visual and textual features, thus leading to intermediate representations that are suitable for the task at hand. In addition, we aim to perform this task in a zero-shot manner, i.e., without any training on the target task, meaning that the model's weights remain frozen. To this end, we devise strategies to select features and also refine them via post-processing without extra learnable parameters. We compare our proposed method with state-of-the-art approaches which explicitly enforce image-text alignment in a joint embedding space via contrastive learning. Results on a popular chest X-ray benchmark indicate that our method is competitive with SOTA on different types of pathology, and even outperforms them on average in terms of two metrics (mean IoU and AUC-ROC). Source code will be released upon acceptance at https://github.com/vios-s.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":6.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142603814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Georgia Karanasiou, Elazer Edelman, Francois-Henri Boissel, Robert Byrne, Luca Emili, Martin Fawdry, Nenad Filipovic, David Flynn, Liesbet Geris, Alfons Hoekstra, Maria Cristina Jori, Ali Kiapour, Dejan Krsmanovic, Thierry Marchal, Flora Musuamba, Francesco Pappalardo, Lorenza Petrini, Markus Reiterer, Marco Viceconti, Klaus Zeier, Lampros K Michalis, Dimitrios I Fotiadis
{"title":"Advancing In Silico Clinical Trials for Regulatory Adoption and Innovation.","authors":"Georgia Karanasiou, Elazer Edelman, Francois-Henri Boissel, Robert Byrne, Luca Emili, Martin Fawdry, Nenad Filipovic, David Flynn, Liesbet Geris, Alfons Hoekstra, Maria Cristina Jori, Ali Kiapour, Dejan Krsmanovic, Thierry Marchal, Flora Musuamba, Francesco Pappalardo, Lorenza Petrini, Markus Reiterer, Marco Viceconti, Klaus Zeier, Lampros K Michalis, Dimitrios I Fotiadis","doi":"10.1109/JBHI.2024.3486538","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3486538","url":null,"abstract":"<p><p>The evolution of information and communication technologies has affected all fields of science, including health sciences. However, the rate of technological innovation adoption by the healthcare sector has been historically slow, compared to other industrial sectors. Innovation in computer modeling and simulation approaches has changed the landscape in biomedical applications and biomedicine, paving the way for their potential contribution in reducing, refining, and partially replacing animal and human clinical trials. In Silico Clinical Trials (ISCT) allow the development of virtual populations used in the safety and efficacy testing of new drugs and medical devices. This White Paper presents the current framework for ISCT, the role of in silico medicine research communities, the different perspectives (research, scientific, clinical, regulatory, standardization, data quality, legal and ethical), the barriers, challenges, and opportunities for ISCT adoption. In addition, an overview of successful ISCT projects, market-available platforms, and FDA- approved paradigms, along with their vision, mission and outcomes are presented.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":6.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142603507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"PointCHD: A Point Cloud Benchmark for Congenital Heart Disease Classification and Segmentation.","authors":"Dinghao Yang, Wei Gao","doi":"10.1109/JBHI.2024.3495035","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3495035","url":null,"abstract":"<p><p>Congenital heart disease (CHD) is one of the most common birth defects. With the development of medical imaging analysis technology, medical image analysis for CHD has become an important research direction. Due to the lack of data and the difficulty of labeling, CHD datasets are scarce. Previous studies focused on CT and other medical image modes, while point cloud is still unstudied. As a representative type of 3D data, point cloud can intuitively model organ shapes, which has obvious advantages in medical analysis and can assist doctors in diagnosis. However, the production of a medical point cloud dataset is more complex than that of an image dataset, and the 3D modeling of internal organs needs to be reconstructed after scanning by high-precision instruments. We propose PointCHD, the first point cloud dataset for CHD diagnosis, with a large number of high precision-annotated and wide-categorized data. PointCHD includes different types of three-dimensional data with varying degrees of distortion, and supports multiple analysis tasks, i.e. classification, segmentation, reconstruction, etc. We also construct a benchmark on PointCHD with the goal of medical diagnosis, we design the analysis process and compare the performances of the mainstream point cloud analysis methods. In view of the complex internal and external structure of the heart point cloud, we propose a point cloud representation learning method based on manifold learning. By introducing normal lines to consider the continuity of the surface to construct a manifold learning method of the adaptive projection plane, fully extracted the structural features of the heart, and achieved the best performance on each task of the PointCHD benchmark. Finally, we summarize the existing problems in the analysis of the CHD point cloud and prospects for potential research directions in the future. The benchmark will be released soon.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":6.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142603813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marta Gomez, Jesus Carro, Esther Pueyo, Alba Perez, Aida Olivan, Violeta Monasterio
{"title":"In Silico Modeling and Validation of the Effect of Calcium-Activated Potassium Current on Ventricular Repolarization in Failing Myocytes.","authors":"Marta Gomez, Jesus Carro, Esther Pueyo, Alba Perez, Aida Olivan, Violeta Monasterio","doi":"10.1109/JBHI.2024.3495027","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3495027","url":null,"abstract":"<p><strong>Objective: </strong>The pathophysiological role of the small conductance calcium-activated potassium (SK) channels in human ventricular myocytes remains unclear. Experimental studies have reported upregulation of in pathological states, potentially contributing to ventricular arrhythmias. In heart failure (HF) patients, the upregulation of SK channels could be an adaptive physiological response to shorten the action potential duration (APD) under conditions of reduced repolarization reserve. In this work, we aimed at uncovering the contribution of SK channels to ventricular repolarization in failing myocytes.</p><p><strong>Methods: </strong>We extended an in silico electrophysiological model of human ventricular failing myocytes by including a representation of the SK channel activity. To calibrate the maximal SK current conductance (G <sub>SK</sub>), we simulated action potentials (APs) at different pacing frequencies and matched the changes in AP duration induced by SK channel inhibition or activation to available experimental data.</p><p><strong>Results: </strong>The optimal value obtained for G<sub>SK</sub> was 4.288 μ S/ μF in mid-myocardial cells, and 6.4 μS/ μF for endocardial and epicardial cells. The simulated SK block-induced effects were consistent with experimental evidence. 1-D simulations of a transmural ventricular fiber indicated that SK channel block may prolong the QT interval and increase the transmural dispersion of repolarization, potentially increasing the risk of arrhythmia in HF.</p><p><strong>Conclusion: </strong>Our results highlight the importance of considering the SK channels to improve the characterization of HF-induced ventricular remodeling. Simulations across various scenarios in 0-D and 1-D scales suggest that pharmacological SK channel inhibition could lead to adverse effects in failing ventricles.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":6.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142603719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"M-NET: Transforming Single Nucleotide Variations into Patient Feature Images for the Prediction of Prostate Cancer Metastasis and Identification of Significant Pathways.","authors":"Li Zhou, Jie Li, Weilong Tan","doi":"10.1109/JBHI.2024.3493618","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3493618","url":null,"abstract":"<p><p>High-performance prediction of prostate cancer metastasis based on single nucleotide variations remains a challenge. Therefore, we developed a novel biologically informed deep learning framework, named M-NET, for the prediction of prostate cancer metastasis. Within the framework, we transformed single nucleotide variations into patient feature images that are optimal for fitting convolutional neural networks. Moreover, we identified significant pathways associated with the metastatic status. The experimental results showed that M-NET significantly outperformed other comparison methods based on single nucleotide variations, achieving improvements in accuracy, precision, recall, F1-score, area under the receiver operating characteristics curve, and area under the precision-recall curve by 6.3%, 8.4%, 5.1%, 0.070, 0.041, and 0.026, respectively. Furthermore, M-NET identified some important pathways associated with the metastatic status, such as signaling by the hedgehog pathway. In summary, compared with other comparative methods, M-NET exhibited a better performance in the prediction of prostate cancer metastasis.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":6.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142603794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dongxu Liu, Qichuan Ding, Chenyu Tong, Jinshuo Ai, Fei Wang
{"title":"Incremental Classification for High-Dimensional EEG Manifold Representation Using Bidirectional Dimensionality Reduction and Prototype Learning.","authors":"Dongxu Liu, Qichuan Ding, Chenyu Tong, Jinshuo Ai, Fei Wang","doi":"10.1109/JBHI.2024.3491096","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3491096","url":null,"abstract":"<p><p>In brain-computer interface (BCI) systems, symmetric positive definite (SPD) manifold within Riemannian space has been frequently utilized to extract spatial features from electroencephalogram (EEG) signals. However, the intrinsic high dimensionality of SPD matrices introduces too much computational burden to hinder the real-time applications of such BCI, especially in handling dynamic tasks, like incremental learning. Directly reducing the dimensionality of SPD matrices with conventional dimensionality reduction (DR) methods will alter the fundamental properties of SPD matrices. Moreover, current DR methods for incremental learning always necessitate retaining old data to update their representations under new mapping. To this end, a bidirectional two-dimensional principal component analysis for SPD manifold (B2DPCA-SPD) is proposed to reduce the dimensionality of SPD matrices, in such way that the reduced matrices remain on SPD manifold. Afterwards, the B2DPCA-SPD is extended to adapt to incremental learning tasks without saving old data. The incremental B2DPCA-SPD can be seamlessly integrated with the matrix-formed growing neural gas network (MF-GNG) to achieve an incremental EEG classification, where the new low-dimensional representations of the prototypes in old classifiers can be easily recalculated with the updated projection matrix. Extensive experiments are conducted on two public datasets to perform the EEG classification. The results demonstrate that our method significantly reduces computation time by 38.53% and 35.96%, and outperforms conventional methods in classification accuracy by 4.21% to 19.59%.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":6.7,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142603671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Katarzyna Kobylińska;Mateusz Krzyziński;Rafał Machowicz;Mariusz Adamek;Przemysław Biecek
{"title":"Exploration of the Rashomon Set Assists Trustworthy Explanations for Medical Data","authors":"Katarzyna Kobylińska;Mateusz Krzyziński;Rafał Machowicz;Mariusz Adamek;Przemysław Biecek","doi":"10.1109/JBHI.2024.3443069","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3443069","url":null,"abstract":"The machine learning modeling process conventionally results in selecting a single model that maximizes a selected performance metric. However, this approach leads to abandoning a more profound analysis of slightly inferior models. Particularly in medical and healthcare studies, where the objective extends beyond predictions to generation of valuable insights, relying solely on a single model can result in misleading or incomplete conclusions. This problem is particularly pertinent when dealing with a set of models known as \u0000<italic>Rashomon set</i>\u0000, with performance close to maximum one. Such a set can be numerous and may contain models describing the data in a different way, which calls for comprehensive analysis. This paper introduces a novel method to explore models in the Rashomon set, extending the conventional modeling approach. We propose the \u0000<monospace>Rashomon_DETECT</monospace>\u0000 algorithm to detect models with different behavior. It is based on recent developments in the eXplainable Artificial Intelligence (XAI) field. To quantify differences in variable effects among models, we introduce the Profile Disparity Index (PDI) based on measures from functional data analysis. To illustrate the effectiveness of our approach, we showcase its application on real-world medical problem: predicting survival among hemophagocytic lymphohistiocytosis (HLH) patients – a foundational case study. Additionally, we benchmark our approach on other medical data sets, demonstrating its versatility and utility in various contexts. If differently behaving models are detected in the Rashomon set, their combined analysis leads to more trustworthy conclusions, which is of vital importance for high-stakes applications such as medical applications.","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"28 11","pages":"6454-6465"},"PeriodicalIF":6.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"IEEE Journal of Biomedical and Health Informatics Publication Information","authors":"","doi":"10.1109/JBHI.2024.3472131","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3472131","url":null,"abstract":"","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"28 11","pages":"C2-C2"},"PeriodicalIF":6.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10745945","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Guest Editorial: Trustworthy Machine Learning for Health Informatics","authors":"Luyang Luo;Daguang Xu;Jing Qin;Yueming Jin;Hao Chen","doi":"10.1109/JBHI.2024.3472368","DOIUrl":"https://doi.org/10.1109/JBHI.2024.3472368","url":null,"abstract":"Machine learning (ML), the stem of today's artificial intelligence, has shown significant growth in the field of biomedical and health informatics. On the one hand, ML techniques are becoming more complex in order to deal with real-world data. On the other hand, ML is also more and more accessible to broader users. For example, automated machine learning products are enabling users to build their own ML models without writing code [1].","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"28 11","pages":"6370-6372"},"PeriodicalIF":6.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10745914","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}