Severe aortic stenosis detection by deep learning applied to echocardiography.

BACKGROUND AND AIMS: Early diagnosis of aortic stenosis (AS) is critical to prevent morbidity and mortality but requires skilled examination with Doppler imaging. This study reports the development and validation of a novel deep learning model that relies on two-dimensional (2D) parasternal long axis videos from transthoracic echocardiography without Doppler imaging to identify severe AS, suitable for point-of-care ultrasonography. METHODS AND RESULTS: In a training set of 5257 studies (17 570 videos) from 2016 to 2020 [Yale-New Haven Hospital (YNHH), Connecticut], an ensemble of three-dimensional convolutional neural networks was developed to detect severe AS, leveraging self-supervised contrastive pretraining for label-efficient model development. This deep learning model was validated in a temporally distinct set of 2040 consecutive studies from 2021 from YNHH as well as two geographically distinct cohorts of 4226 and 3072 studies, from California and other hospitals in New England, respectively. The deep learning model achieved an area under the receiver operating characteristic curve (AUROC) of 0.978 (95% CI: 0.966, 0.988) for detecting severe AS in the temporally distinct test set, maintaining its diagnostic performance in geographically distinct cohorts [0.952 AUROC (95% CI: 0.941, 0.963) in California and 0.942 AUROC (95% CI: 0.909, 0.966) in New England]. The model was interpretable with saliency maps identifying the aortic valve, mitral annulus, and left atrium as the predictive regions. Among non-severe AS cases, predicted probabilities were associated with worse quantitative metrics of AS suggesting an association with various stages of AS severity. CONCLUSION: This study developed and externally validated an automated approach for severe AS detection using single-view 2D echocardiography, with potential utility for point-of-care screening.

Conditional knockout of ASK1 in microglia/macrophages attenuates epileptic seizures and long-term neurobehavioural comorbidities by modulating the inflammatory responses of microglia/macrophages.

BACKGROUND: Apoptosis signal-regulating kinase 1 (ASK1) not only causes neuronal programmed cell death via the mitochondrial pathway but also is an essential component of the signalling cascade during microglial activation. We hypothesize that ASK1 selective deletion modulates inflammatory responses in microglia/macrophages(Mi/Mϕ) and attenuates seizure severity and long-term cognitive impairments in an epileptic mouse model. METHODS: Mi/Mϕ-specific ASK1 conditional knockout (ASK1 cKO) mice were obtained for experiments by mating ASK1flox/flox mice with CX3CR1creER mice with tamoxifen induction. Epileptic seizures were induced by intrahippocampal injection of kainic acid (KA). ASK1 expression and distribution were detected by western blotting and immunofluorescence staining. Seizures were monitored for 24 h per day with video recordings. Cognition, social and stress related activities were assessed with the Y maze test and the three-chamber social novelty preference test. The heterogeneous Mi/Mϕ status and inflammatory profiles were assessed with immunofluorescence staining and real-time polymerase chain reaction (q-PCR). Immunofluorescence staining was used to detect the proportion of Mi/Mϕ in contact with apoptotic neurons, as well as neuronal damage. RESULTS: ASK1 was highly expressed in Mi/Mϕ during the acute phase of epilepsy. Conditional knockout of ASK1 in Mi/Mϕ markedly reduced the frequency of seizures in the acute phase and the frequency of spontaneous recurrent seizures (SRSs) in the chronic phase. In addition, ASK1 conditional knockout mice displayed long-term neurobehavioral improvements during the Y maze test and the three-chamber social novelty preference test. ASK1 selective knockout mitigated neuroinflammation, as evidenced by lower levels of Iba1+/CD16+ proinflammatory Mi/Mϕ. Conditional knockout of ASK1 increased Mi/Mϕ proportion in contact with apoptotic neurons. Neuronal loss was partially restored by ASK1 selective knockout. CONCLUSION: Conditional knockout of ASK1 in Mi/Mϕ reduced seizure severity, neurobehavioral impairments, and histological damage, at least via inhibiting proinflammatory microglia/macrophages responses. ASK1 in microglia/macrophages is a potential therapeutic target for inflammatory responses in epilepsy.

Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts.

Predicting compound-protein affinity is beneficial for accelerating drug discovery. Doing so without the often-unavailable structure data is gaining interest. However, recent progress in structure-free affinity prediction, made by machine learning, focuses on accuracy but leaves much to be desired for interpretability. Defining intermolecular contacts underlying affinities as a vehicle for interpretability; our large-scale interpretability assessment finds previously used attention mechanisms inadequate. We thus formulate a hierarchical multiobjective learning problem, where predicted contacts form the basis for predicted affinities. We solve the problem by embedding protein sequences (by hierarchical recurrent neural networks) and compound graphs (by graph neural networks) with joint attentions between protein residues and compound atoms. We further introduce three methodological advances to enhance interpretability: (1) structure-aware regularization of attentions using protein sequence-predicted solvent exposure and residue-residue contact maps; (2) supervision of attentions using known intermolecular contacts in training data; and (3) an intrinsically explainable architecture where atomic-level contacts or "relations" lead to molecular-level affinity prediction. The first two and all three advances result in DeepAffinity+ and DeepRelations, respectively. Our methods show generalizability in affinity prediction for molecules that are new and dissimilar to training examples. Moreover, they show superior interpretability compared to state-of-the-art interpretable methods: with similar or better affinity prediction, they boost the AUPRC of contact prediction by around 33-, 35-, 10-, and 9-fold for the default test, new-compound, new-protein, and both-new sets, respectively. We further demonstrate their potential utilities in contact-assisted docking, structure-free binding site prediction, and structure-activity relationship studies without docking. Our study represents the first model development and systematic model assessment dedicated to interpretable machine learning for structure-free compound-protein affinity prediction.

DeepAffinity: interpretable deep learning of compound-protein affinity through unified recurrent and convolutional neural networks.

MOTIVATION: Drug discovery demands rapid quantification of compound-protein interaction (CPI). However, there is a lack of methods that can predict compound-protein affinity from sequences alone with high applicability, accuracy and interpretability. RESULTS: We present a seamless integration of domain knowledges and learning-based approaches. Under novel representations of structurally annotated protein sequences, a semi-supervised deep learning model that unifies recurrent and convolutional neural networks has been proposed to exploit both unlabeled and labeled data, for jointly encoding molecular representations and predicting affinities. Our representations and models outperform conventional options in achieving relative error in IC50 within 5-fold for test cases and 20-fold for protein classes not included for training. Performances for new protein classes with few labeled data are further improved by transfer learning. Furthermore, separate and joint attention mechanisms are developed and embedded to our model to add to its interpretability, as illustrated in case studies for predicting and explaining selective drug-target interactions. Lastly, alternative representations using protein sequences or compound graphs and a unified RNN/GCNN-CNN model using graph CNN (GCNN) are also explored to reveal algorithmic challenges ahead. AVAILABILITY AND IMPLEMENTATION: Data and source codes are available at https://github.com/Shen-Lab/DeepAffinity. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Therapeutic and Immunoregulatory Effects of Tacrolimus in Patients with Refractory Generalized Myasthenia Gravis.

OBJECTIVES: The aim of this study wasto investigate the efficacy of tacrolimus treatment in patients with refractory generalized myasthenia gravis (MG) and explore its impact on lymphocytic phenotypes and related cytokines mRNA expression. METHODS: A total of 24 refractory generalized MG patients were enrolled. Before treatment and at 2, 6, and 12 months after tacrolimus treatment, the therapeutic effect was evaluated by the quantitative MG score of the Myasthenia Gravis Foundation of America (QMG), Manual Muscle Test (MMT), MG-specific Activities of Daily Living (MG-ADL), 15-item Myasthenia Gravis Quality-of-Life Scale (MG-QOL15), and changes of prednisone dosage. Also, we used the flow cytometer for the lymphocytic immunophenotyping and real-time PCR for the qualification of cytokine mRNA in peripheral blood mononuclear cells (PBMCs) at different time points during the treatment. RESULTS: Significantly decreased QMG, MMT, MG-ADL, and MG-QOL15 were observed at all time points during the tacrolimus treatment. The dosage of prednisone also reduced at the end of the observation period with only 6 adverse events reported. The immunological impact of tacrolimus was revealed by reduced percentages of Tfh, Breg, CD19+BAFF-R+ B cells, and increased percentages of Treg cells as well as down-regulated expression of IL-2, IL-4, IL-10, and IL-13 mRNA levels in PBMCs during the treatment. CONCLUSION: Our study indicated the clinical efficacy of tacrolimus in patients with refractory generalized MG. The underlying immunoregulatory mechanism of tacrolimus may involve alterations in the phenotypes of peripheral blood lymphocytes and Th1/Th2-related cytokine expression of PBMCs.

Simultaneous Pulmonary Embolism and Ischemic Stroke in a Patient with Cor Biloculare after Glenn Anastomosis.

BACKGROUND: Cor biloculare, two-chambered heart due to the absence of atrial and ventricular septa, is a rare congenital heart anomaly. For Cor biloculare and other cardiac defects with single ventricle physiology, Glenn anastomosis has been developed as a palliative procedure. Thrombosis secondary to Glenn anastomosis in the patient with Cor biloculare could pose a serious threat to the survival, and has never been reported before. CASE REPORT: We report the case of a 27-year-old patient, with past history of Glenn anastomosis that was performed 7 years ago for the palliation of Cor biloculare. She presented with pulmonary embolism and ischemic stroke simultaneously at 7 days after Cesarean section. Due to her critical status, systemic anticoagulation with low-molecular-weight heparin was started immediately, followed by lifelong warfarin therapy. Pulmonary embolism regressed and neurological symptoms were considerably diminished after the anticoagulation treatment. CONCLUSION: This case illuminates the potential risk of thrombotic events in this patient cohort and demonstrates that anticoagulation therapy is an effective, secure, and appropriate for the management of this disease.

Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning.

BACKGROUND: Advances in self-supervised learning (SSL) have enabled state-of-the-art automated medical image diagnosis from small, labeled datasets. This label efficiency is often desirable, given the difficulty of obtaining expert labels for medical image recognition tasks. However, most efforts toward SSL in medical imaging are not adapted to video-based modalities, such as echocardiography. METHODS: We developed a self-supervised contrastive learning approach, EchoCLR, for echocardiogram videos with the goal of learning strong representations for efficient fine-tuning on downstream cardiac disease diagnosis. EchoCLR pretraining involves (i) contrastive learning, where the model is trained to identify distinct videos of the same patient, and (ii) frame reordering, where the model is trained to predict the correct of video frames after being randomly shuffled. RESULTS: When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improves classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) over other transfer learning and SSL approaches across internal and external test sets. When fine-tuning on 10% of available training data (519 studies), an EchoCLR-pretrained model achieves 0.72 AUROC (95% CI: [0.69, 0.75]) on LVH classification, compared to 0.61 AUROC (95% CI: [0.57, 0.64]) with a standard transfer learning approach. Similarly, using 1% of available training data (53 studies), EchoCLR pretraining achieves 0.82 AUROC (95% CI: [0.79, 0.84]) on severe AS classification, compared to 0.61 AUROC (95% CI: [0.58, 0.65]) with transfer learning. CONCLUSIONS: EchoCLR is unique in its ability to learn representations of echocardiogram videos and demonstrates that SSL can enable label-efficient disease classification from small amounts of labeled data.

Artificial intelligence (AI) has been used to develop software that can automatically diagnose diseases from medical images. However, these AI models require thousands or millions of examples to properly learn from, which can be very expensive, as diagnosis is often time-consuming and requires clinical expertise. Using a technique called self-supervised learning (SSL), we develop an AI method to effectively diagnose heart disease from as few as 50 instances. Our method, EchoCLR, is designed for echocardiography, a key imaging technique to monitor heart health, and outperforms other methods on disease diagnosis from small amounts of data. This method can advance AI for echocardiography and enable researchers with limited resources to create disease diagnosis models from small medical imaging datasets.

Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities.

Recently, zero-shot (or training-free) Neural Architecture Search (NAS) approaches have been proposed to liberate NAS from the expensive training process. The key idea behind zero-shot NAS approaches is to design proxies that can predict the accuracy of some given networks without training the network parameters. The proxies proposed so far are usually inspired by recent progress in theoretical understanding of deep learning and have shown great potential on several datasets and NAS benchmarks. This paper aims to comprehensively review and compare the state-of-the-art (SOTA) zero-shot NAS approaches, with an emphasis on their hardware awareness. To this end, we first review the mainstream zero-shot proxies and discuss their theoretical underpinnings. We then compare these zero-shot proxies through large-scale experiments and demonstrate their effectiveness in both hardware-aware and hardware-oblivious NAS scenarios. Finally, we point out several promising ideas to design better proxies. Our source code and the list of related papers are available on https://github.com/SLDGroup/survey-zero-shot-nas.

Biometric contrastive learning for data-efficient deep learning from electrocardiographic images.

OBJECTIVE: Artificial intelligence (AI) detects heart disease from images of electrocardiograms (ECGs). However, traditional supervised learning is limited by the need for large amounts of labeled data. We report the development of Biometric Contrastive Learning (BCL), a self-supervised pretraining approach for label-efficient deep learning on ECG images. MATERIALS AND METHODS: Using pairs of ECGs from 78 288 individuals from Yale (2000-2015), we trained a convolutional neural network to identify temporally separated ECG pairs that varied in layouts from the same patient. We fine-tuned BCL-pretrained models to detect atrial fibrillation (AF), gender, and LVEF < 40%, using ECGs from 2015 to 2021. We externally tested the models in cohorts from Germany and the United States. We compared BCL with ImageNet initialization and general-purpose self-supervised contrastive learning for images (simCLR). RESULTS: While with 100% labeled training data, BCL performed similarly to other approaches for detecting AF/Gender/LVEF < 40% with an AUROC of 0.98/0.90/0.90 in the held-out test sets, it consistently outperformed other methods with smaller proportions of labeled data, reaching equivalent performance at 50% of data. With 0.1% data, BCL achieved AUROC of 0.88/0.79/0.75, compared with 0.51/0.52/0.60 (ImageNet) and 0.61/0.53/0.49 (simCLR). In external validation, BCL outperformed other methods even at 100% labeled training data, with an AUROC of 0.88/0.88 for Gender and LVEF < 40% compared with 0.83/0.83 (ImageNet) and 0.84/0.83 (simCLR). DISCUSSION AND CONCLUSION: A pretraining strategy that leverages biometric signatures of different ECGs from the same patient enhances the efficiency of developing AI models for ECG images. This represents a major advance in detecting disorders from ECG images with limited labeled data.

De Novo Synthesis of α-Ketoamides via Pd/TBD Synergistic Catalysis.

Precisely controlling the product selectivity of a reaction is an important objective in organic synthesis. α-Ketoamides are vital intermediates in chemical transformations and privileged motifs in numerous drugs, natural products, and biologically active molecules. The selective synthesis of α-ketoamides from feedstock chemicals in a safe and operationally simple manner under mild conditions is a long-standing catalysis challenge. Herein, an unprecedented TBD-switched Pd-catalyzed double isocyanide insertion reaction for assembling ketoamides in aqueous DMSO from (hetero)aryl halides and pseudohalides under mild conditions is reported. The effectiveness and utility of this protocol are demonstrated by its diverse substrate scope (93 examples), the ability to late-stage modify pharmaceuticals, scalability to large-scale synthesis, and the synthesis of pharmaceutically active molecules. Mechanistic studies indicate that TBD is a key ligand that modulates the Pd-catalyzed double isocyanide insertion process, thereby selectively providing the desired α-ketoamides in a unique manner. In addition, the imidoylpalladium(II) complex and α-ketoimine amide are successfully isolated and determined by X-ray analysis, confirming that they are probable intermediates in the catalytic pathway.

Saccharide mapping as an extraordinary method on characterization and identification of plant and fungi polysaccharides: A review.

Saccharide mapping was a promising scheme to unveil the mystery of polysaccharide structure by analysis of the fragments generated from polysaccharide decomposition process. However, saccharide mapping was not widely applied in the polysaccharide analysis for lacking of systematic introduction. In this review, a detailed description of the establishment process of saccharide mapping, the pros and cons of downstream technologies, an overview of the application of saccharide mapping, and practical strategies were summarized. With the updating of the available downstream technologies, saccharide mapping had been expanding its scope of application to various kinds of polysaccharides. The process of saccharide mapping analysis included polysaccharides degradation and hydrolysates analysis, and the degradation process was no longer limited to acid hydrolysis. Some downstream technologies were convenient for rapid qualitative analysis, while others could achieve quantitative analysis. For the more detailed structure information could be provided by saccharide mapping, it was possible to improve the quality control of polysaccharides during preparation and application. This review filled the blank of basic information about saccharide mapping and was helpful for the establishment of a professional workflow for the saccharide mapping application to promote the deep study of polysaccharide structure.

Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound: a multi-center study.

Background: Point-of-care ultrasonography (POCUS) enables cardiac imaging at the bedside and in communities but is limited by abbreviated protocols and variation in quality. We developed and tested artificial intelligence (AI) models to automate the detection of underdiagnosed cardiomyopathies from cardiac POCUS. Methods: In a development set of 290,245 transthoracic echocardiographic videos across the Yale-New Haven Health System (YNHHS), we used augmentation approaches and a customized loss function weighted for view quality to derive a POCUS-adapted, multi-label, video-based convolutional neural network (CNN) that discriminates HCM (hypertrophic cardiomyopathy) and ATTR-CM (transthyretin amyloid cardiomyopathy) from controls without known disease. We evaluated the final model across independent, internal and external, retrospective cohorts of individuals who underwent cardiac POCUS across YNHHS and Mount Sinai Health System (MSHS) emergency departments (EDs) (2011-2024) to prioritize key views and validate the diagnostic and prognostic performance of single-view screening protocols. Findings: We identified 33,127 patients (median age 61 [IQR: 45-75] years, n=17,276 [52·2%] female) at YNHHS and 5,624 (57 [IQR: 39-71] years, n=1,953 [34·7%] female) at MSHS with 78,054 and 13,796 eligible cardiac POCUS videos, respectively. An AI-enabled single-view screening approach successfully discriminated HCM (AUROC of 0·90 [YNHHS] & 0·89 [MSHS]) and ATTR-CM (YNHHS: AUROC of 0·92 [YNHHS] & 0·99 [MSHS]). In YNHHS, 40 (58·0%) HCM and 23 (47·9%) ATTR-CM cases had a positive screen at median of 2·1 [IQR: 0·9-4·5] and 1·9 [IQR: 1·0-3·4] years before clinical diagnosis. Moreover, among 24,448 participants without known cardiomyopathy followed over 2·2 [IQR: 1·1-5·8] years, AI-POCUS probabilities in the highest (vs lowest) quintile for HCM and ATTR-CM conferred a 15% (adj.HR 1·15 [95%CI: 1·02-1·29]) and 39% (adj.HR 1·39 [95%CI: 1·22-1·59]) higher age- and sex-adjusted mortality risk, respectively. Interpretation: We developed and validated an AI framework that enables scalable, opportunistic screening of treatable cardiomyopathies wherever POCUS is used. Funding: National Heart, Lung and Blood Institute, Doris Duke Charitable Foundation, BridgeBio.

A Multimodality Video-Based AI Biomarker For Aortic Stenosis Development And Progression.

Importance: Aortic stenosis (AS) is a major public health challenge with a growing therapeutic landscape, but current biomarkers do not inform personalized screening and follow-up. Objective: A video-based artificial intelligence (AI) biomarker (Digital AS Severity index [DASSi]) can detect severe AS using single-view long-axis echocardiography without Doppler. Here, we deploy DASSi to patients with no or mild/moderate AS at baseline to identify AS development and progression. Design Setting and Participants: We defined two cohorts of patients without severe AS undergoing echocardiography in the Yale-New Haven Health System (YNHHS) (2015-2021, 4.1[IQR:2.4-5.4] follow-up years) and Cedars-Sinai Medical Center (CSMC) (2018-2019, 3.4[IQR:2.8-3.9] follow-up years). We further developed a novel computational pipeline for the cross-modality translation of DASSi into cardiac magnetic resonance (CMR) imaging in the UK Biobank (2.5[IQR:1.6-3.9] follow-up years). Analyses were performed between August 2023-February 2024. Exposure: DASSi (range: 0-1) derived from AI applied to echocardiography and CMR videos. Main Outcomes and Measures: Annualized change in peak aortic valve velocity (AV-Vmax) and late (>6 months) aortic valve replacement (AVR). Results: A total of 12,599 participants were included in the echocardiographic study (YNHHS: n=8,798, median age of 71 [IQR (interquartile range):60-80] years, 4250 [48.3%] women, and CSMC: n=3,801, 67 [IQR:54-78] years, 1685 [44.3%] women). Higher baseline DASSi was associated with faster progression in AV-Vmax (per 0.1 DASSi increments: YNHHS: +0.033 m/s/year [95%CI:0.028-0.038], n=5,483, and CSMC: +0.082 m/s/year [0.053-0.111], n=1,292), with levels ≥ vs <0.2 linked to a 4-to-5-fold higher AVR risk (715 events in YNHHS; adj.HR 4.97 [95%CI: 2.71-5.82], 56 events in CSMC: 4.04 [0.92-17.7]), independent of age, sex, ethnicity/race, ejection fraction and AV-Vmax. This was reproduced across 45,474 participants (median age 65 [IQR:59-71] years, 23,559 [51.8%] women) undergoing CMR in the UK Biobank (adj.HR 11.4 [95%CI:2.56-50.60] for DASSi ≥vs<0.2). Saliency maps and phenome-wide association studies supported links with traditional cardiovascular risk factors and diastolic dysfunction. Conclusions and Relevance: In this cohort study of patients without severe AS undergoing echocardiography or CMR imaging, a new AI-based video biomarker is independently associated with AS development and progression, enabling opportunistic risk stratification across cardiovascular imaging modalities as well as potential application on handheld devices.

A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression.

Importance: Aortic stenosis (AS) is a major public health challenge with a growing therapeutic landscape, but current biomarkers do not inform personalized screening and follow-up. A video-based artificial intelligence (AI) biomarker (Digital AS Severity index [DASSi]) can detect severe AS using single-view long-axis echocardiography without Doppler characterization. Objective: To deploy DASSi to patients with no AS or with mild or moderate AS at baseline to identify AS development and progression. Design, Setting, and Participants: This is a cohort study that examined 2 cohorts of patients without severe AS undergoing echocardiography in the Yale New Haven Health System (YNHHS; 2015-2021) and Cedars-Sinai Medical Center (CSMC; 2018-2019). A novel computational pipeline for the cross-modal translation of DASSi into cardiac magnetic resonance (CMR) imaging was further developed in the UK Biobank. Analyses were performed between August 2023 and February 2024. Exposure: DASSi (range, 0-1) derived from AI applied to echocardiography and CMR videos. Main Outcomes and Measures: Annualized change in peak aortic valve velocity (AV-Vmax) and late (>6 months) aortic valve replacement (AVR). Results: A total of 12 599 participants were included in the echocardiographic study (YNHHS: n = 8798; median [IQR] age, 71 [60-80] years; 4250 [48.3%] women; median [IQR] follow-up, 4.1 [2.4-5.4] years; and CSMC: n = 3801; median [IQR] age, 67 [54-78] years; 1685 [44.3%] women; median [IQR] follow-up, 3.4 [2.8-3.9] years). Higher baseline DASSi was associated with faster progression in AV-Vmax (per 0.1 DASSi increment: YNHHS, 0.033 m/s per year [95% CI, 0.028-0.038] among 5483 participants; CSMC, 0.082 m/s per year [95% CI, 0.053-0.111] among 1292 participants), with values of 0.2 or greater associated with a 4- to 5-fold higher AVR risk than values less than 0.2 (YNHHS: 715 events; adjusted hazard ratio [HR], 4.97 [95% CI, 2.71-5.82]; CSMC: 56 events; adjusted HR, 4.04 [95% CI, 0.92-17.70]), independent of age, sex, race, ethnicity, ejection fraction, and AV-Vmax. This was reproduced across 45 474 participants (median [IQR] age, 65 [59-71] years; 23 559 [51.8%] women; median [IQR] follow-up, 2.5 [1.6-3.9] years) undergoing CMR imaging in the UK Biobank (for participants with DASSi ≥0.2 vs those with DASSi <.02, adjusted HR, 11.38 [95% CI, 2.56-50.57]). Saliency maps and phenome-wide association studies supported associations with cardiac structure and function and traditional cardiovascular risk factors. Conclusions and Relevance: In this cohort study of patients without severe AS undergoing echocardiography or CMR imaging, a new AI-based video biomarker was independently associated with AS development and progression, enabling opportunistic risk stratification across cardiovascular imaging modalities as well as potential application on handheld devices.

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge.

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" - there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification.

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge.

Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" - there are a few common findings followed by many more relatively rare conditions. In chest radiography, diagnosis is both a long-tailed and multi-label problem, as patients often present with multiple findings simultaneously. While researchers have begun to study the problem of long-tailed learning in medical image recognition, few have studied the interaction of label imbalance and label co-occurrence posed by long-tailed, multi-label disease classification. To engage with the research community on this emerging topic, we conducted an open challenge, CXR-LT, on long-tailed, multi-label thorax disease classification from chest X-rays (CXRs). We publicly release a large-scale benchmark dataset of over 350,000 CXRs, each labeled with at least one of 26 clinical findings following a long-tailed distribution. We synthesize common themes of top-performing solutions, providing practical recommendations for long-tailed, multi-label medical image classification. Finally, we use these insights to propose a path forward involving vision-language foundation models for few- and zero-shot disease classification.

Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning.

Federated learning (FL) emerges as a popular distributed learning schema that learns a model from a set of participating users without sharing raw data. One major challenge of FL comes with heterogeneous users, who may have distributionally different (or non-iid) data and varying computation resources. As federated users would use the model for prediction, they often demand the trained model to be robust against malicious attackers at test time. Whereas adversarial training (AT) provides a sound solution for centralized learning, extending its usage for federated users has imposed significant challenges, as many users may have very limited training data and tight computational budgets, to afford the data-hungry and costly AT. In this paper, we study a novel FL strategy: propagating adversarial robustness from rich-resource users that can afford AT, to those with poor resources that cannot afford it, during federated learning. We show that existing FL techniques cannot be effectively integrated with the strategy to propagate robustness among non-iid users and propose an efficient propagation approach by the proper use of batch-normalization. We demonstrate the rationality and effectiveness of our method through extensive experiments. Especially, the proposed method is shown to grant federated models remarkable robustness even when only a small portion of users afford AT during learning. Source code will be released.

How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts.

Increasing concerns have been raised on deep learning fairness in recent years. Existing fairness-aware machine learning methods mainly focus on the fairness of in-distribution data. However, in real-world applications, it is common to have distribution shift between the training and test data. In this paper, we first show that the fairness achieved by existing methods can be easily broken by slight distribution shifts. To solve this problem, we propose a novel fairness learning method termed CUrvature MAtching (CUMA), which can achieve robust fairness generalizable to unseen domains with unknown distributional shifts. Specifically, CUMA enforces the model to have similar generalization ability on the majority and minority groups, by matching the loss curvature distributions of the two groups. We evaluate our method on three popular fairness datasets. Compared with existing methods, CUMA achieves superior fairness under unseen distribution shifts, without sacrificing either the overall accuracy or the in-distribution fairness.

Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays.

Before the recent success of deep learning methods for automated medical image analysis, practitioners used handcrafted radiomic features to quantitatively describe local patches of medical images. However, extracting discriminative radiomic features relies on accurate pathology localization, which is difficult to acquire in real-world settings. Despite advances in disease classification and localization from chest X-rays, many approaches fail to incorporate clinically-informed domainspecific radiomic features. For these reasons, we propose a Radiomics-Guided Transformer (RGT) that fuses global image information with local radiomics-guided auxiliary information to provide accurate cardiopulmonary pathology localization and classification without any bounding box annotations. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomics information. Using the learned self-attention of its image branch, RGT extracts a bounding box for which to compute radiomic features, which are further processed by the radiomics branch; learned image and radiomic features are then fused and mutually interact via cross-attention layers. Thus, RGT utilizes a novel end-to-end feedback loop that can bootstrap accurate pathology localization only using image-level disease labels. Experiments on the NIH ChestXRay dataset demonstrate that RGT outperforms prior works in weakly supervised disease localization (by an average margin of 3.6% over various intersection-over-union thresholds) and classification (by 1.1% in average area under the receiver operating characteristic curve). We publicly release our codes and pre-trained models at https://github.com/VITAGroup/chext.

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study.

Training deep graph neural networks (GNNs) is notoriously hard. Besides the standard plights in training deep architectures such as vanishing gradients and overfitting, it also uniquely suffers from over-smoothing, information squashing, and so on, which limits their potential power for encoding the high-order neighbor structure in large-scale graphs. Although numerous efforts are proposed to address these limitations, such as various forms of skip connections, graph normalization, and random dropping, it is difficult to disentangle the advantages brought by a deep GNN architecture from those "tricks" necessary to train such an architecture. Moreover, the lack of a standardized benchmark with fair and consistent experimental settings poses an almost insurmountable obstacle to gauge the effectiveness of new mechanisms. In view of those, we present the first fair and reproducible benchmark dedicated to assessing the "tricks" of training deep GNNs. We categorize existing approaches, investigate their hyperparameter sensitivity, and unify the basic configuration. Comprehensive evaluations are then conducted on tens of representative graph datasets including the recent large-scale Open Graph Benchmark, with diverse deep GNN backbones. We demonstrate that an organic combo of initial connection, identity mapping, group and batch normalization attains the new state-of-the-art results for deep GNNs on large datasets. Codes are available: https://github.com/VITA-Group/Deep_GCN_Benchmarking.