Fc-fused IL-7 provides broad antiviral effects against respiratory virus infections through IL-17A-producing pulmonary innate-like T cells.

Repeated pandemics caused by the influenza virus and severe acute respiratory syndrome coronavirus (SARS-CoV) have resulted in serious problems in global public health, emphasizing the need for broad-spectrum antiviral therapeutics against respiratory virus infections. Here, we show the protective effects of long-acting recombinant human interleukin-7 fused with hybrid Fc (rhIL-7-hyFc) against major respiratory viruses, including influenza virus, SARS-CoV-2, and respiratory syncytial virus. Administration of rhIL-7-hyFc in a therapeutic or prophylactic regimen induces substantial antiviral effects. During an influenza A virus (IAV) infection, rhIL-7-hyFc treatment increases pulmonary T cells composed of blood-derived interferon γ (IFNγ)+ conventional T cells and locally expanded IL-17A+ innate-like T cells. Single-cell RNA transcriptomics reveals that rhIL-7-hyFc upregulates antiviral genes in pulmonary T cells and induces clonal expansion of type 17 innate-like T cells. rhIL-7-hyFc-mediated disease prevention is dependent on IL-17A in both IAV- and SARS-CoV-2-infected mice. Collectively, we suggest that rhIL-7-hyFc can be used as a broadly active therapeutic for future respiratory virus pandemic.

Vaccine Strategy That Enhances the Protective Efficacy of Systemic Immunization by Establishing Lung-Resident Memory CD8 T Cells Against Influenza Infection.

Most influenza vaccines currently in use target the highly variable hemagglutinin protein to induce neutralizing antibodies and therefore require yearly reformulation. T cell-based universal influenza vaccines focus on eliciting broadly cross-reactive T-cell responses, especially the tissue-resident memory T cell (TRM) population in the respiratory tract, providing superior protection to circulating memory T cells. This study demonstrated that intramuscular (i.m.) administration of the adenovirus-based vaccine expressing influenza virus nucleoprotein (rAd/NP) elicited weak CD8 TRM responses in the lungs and airways, and yielded poor protection against lethal influenza virus challenge. However, a novel "prime-and-deploy" strategy that combines i.m. vaccination of rAd/NP with subsequent intranasal administration of an empty adenovector induced strong NP-specific CD8+ TRM cells and provided complete protection against influenza virus challenge. Overall, our results demonstrate that this "prime-and-deploy" vaccination strategy is potentially applicable to the development of universal influenza vaccines.

Translating AI to Clinical Practice: Overcoming Data Shift with Explainability.

To translate artificial intelligence (AI) algorithms into clinical practice requires generalizability of models to real-world data. One of the main obstacles to generalizability is data shift, a data distribution mismatch between model training and real environments. Explainable AI techniques offer tools to detect and mitigate the data shift problem and develop reliable AI for clinical practice. Most medical AI is trained with datasets gathered from limited environments, such as restricted disease populations and center-dependent acquisition conditions. The data shift that commonly exists in the limited training set often causes a significant performance decrease in the deployment environment. To develop a medical application, it is important to detect potential data shift and its impact on clinical translation. During AI training stages, from premodel analysis to in-model and post hoc explanations, explainability can play a key role in detecting model susceptibility to data shift, which is otherwise hidden because the test data have the same biased distribution as the training data. Performance-based model assessments cannot effectively distinguish the model overfitting to training data bias without enriched test sets from external environments. In the absence of such external data, explainability techniques can aid in translating AI to clinical practice as a tool to detect and mitigate potential failures due to data shift. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

SimpleMind: An open-source software environment that adds thinking to deep neural networks.

Deep neural networks (DNNs) detect patterns in data and have shown versatility and strong performance in many computer vision applications. However, DNNs alone are susceptible to obvious mistakes that violate simple, common sense concepts and are limited in their ability to use explicit knowledge to guide their search and decision making. While overall DNN performance metrics may be good, these obvious errors, coupled with a lack of explainability, have prevented widespread adoption for crucial tasks such as medical image analysis. The purpose of this paper is to introduce SimpleMind, an open-source software environment for Cognitive AI focused on medical image understanding. It allows creation of a knowledge base that describes expected characteristics and relationships between image objects in an intuitive human-readable form. The knowledge base can then be applied to an input image to recognize and understand its content. SimpleMind brings thinking to DNNs by: (1) providing methods for reasoning with the knowledge base about image content, such as spatial inferencing and conditional reasoning to check DNN outputs; (2) applying process knowledge, in the form of general-purpose software agents, that are dynamically chained together to accomplish image preprocessing, DNN prediction, and result post-processing, and (3) performing automatic co-optimization of all knowledge base parameters to adapt agents to specific problems. SimpleMind enables reasoning on multiple detected objects to ensure consistency, providing cross-checking between DNN outputs. This machine reasoning improves the reliability and trustworthiness of DNNs through an interpretable model and explainable decisions. Proof-of-principle example applications are provided that demonstrate how SimpleMind supports and improves deep neural networks by embedding them within a Cognitive AI environment.

Multi-scale, domain knowledge-guided attention + random forest: a two-stage deep learning-based multi-scale guided attention models to diagnose idiopathic pulmonary fibrosis from computed tomography images.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive, irreversible, and usually fatal lung disease of unknown reasons, generally affecting the elderly population. Early diagnosis of IPF is crucial for triaging patients' treatment planning into anti-fibrotic treatment or treatments for other causes of pulmonary fibrosis. However, current IPF diagnosis workflow is complicated and time-consuming, which involves collaborative efforts from radiologists, pathologists, and clinicians and it is largely subject to inter-observer variability. PURPOSE: The purpose of this work is to develop a deep learning-based automated system that can diagnose subjects with IPF among subjects with interstitial lung disease (ILD) using an axial chest computed tomography (CT) scan. This work can potentially enable timely diagnosis decisions and reduce inter-observer variability. METHODS: Our dataset contains CT scans from 349 IPF patients and 529 non-IPF ILD patients. We used 80% of the dataset for training and validation purposes and 20% as the holdout test set. We proposed a two-stage model: at stage one, we built a multi-scale, domain knowledge-guided attention model (MSGA) that encouraged the model to focus on specific areas of interest to enhance model explainability, including both high- and medium-resolution attentions; at stage two, we collected the output from MSGA and constructed a random forest (RF) classifier for patient-level diagnosis, to further boost model accuracy. RF classifier is utilized as a final decision stage since it is interpretable, computationally fast, and can handle correlated variables. Model utility was examined by (1) accuracy, represented by the area under the receiver operating characteristic curve (AUC) with standard deviation (SD), and (2) explainability, illustrated by the visual examination of the estimated attention maps which showed the important areas for model diagnostics. RESULTS: During the training and validation stage, we observe that when we provide no guidance from domain knowledge, the IPF diagnosis model reaches acceptable performance (AUC±SD = 0.93±0.07), but lacks explainability; when including only guided high- or medium-resolution attention, the learned attention maps are not satisfactory; when including both high- and medium-resolution attention, under certain hyperparameter settings, the model reaches the highest AUC among all experiments (AUC±SD = 0.99±0.01) and the estimated attention maps concentrate on the regions of interests for this task. Three best-performing hyperparameter selections according to MSGA were applied to the holdout test set and reached comparable model performance to that of the validation set. CONCLUSIONS: Our results suggest that, for a task with only scan-level labels available, MSGA+RF can utilize the population-level domain knowledge to guide the training of the network, which increases both model accuracy and explainability.

Density Functional Theory Description of Paramagnetic Hexagonal Close-Packed Iron.

The hexagonal close-packed (hcp) phase of iron is unstable under ambient conditions. The limited amount of existing experimental data for this system has been obtained by extrapolating the parameters of hcp Fe-Mn alloys to pure Fe. On the theory side, most density functional theory (DFT) studies on hcp Fe have considered non-magnetic or ferromagnetic states, both having limited relevance in view of the current understanding of the system. Here, we investigate the equilibrium properties of paramagnetic hcp Fe using DFT modelling in combination with alloy theory. We show that the theoretical equilibrium c/a and the equation of state of hcp Fe become consistent with the experimental values when the magnetic disorder is properly accounted for. Longitudinal spin fluctuation effects further improve the theoretical description. The present study provides useful data on hcp Fe at ambient and hydrostatic pressure conditions, contributing largely to the development of accurate thermodynamic modelling of Fe-based alloys.

FBXW7-mediated ERK3 degradation regulates the proliferation of lung cancer cells.

Extracellular signal-regulated kinase 3 (ERK3) is an atypical member of the mitogen-activated protein kinase (MAPK) family, members of which play essential roles in diverse cellular processes during carcinogenesis, including cell proliferation, differentiation, migration, and invasion. Unlike other MAPKs, ERK3 is an unstable protein with a short half-life. Although deubiquitination of ERK3 has been suggested to regulate the activity, its ubiquitination has not been described in the literature. Here, we report that FBXW7 (F-box and WD repeat domain-containing 7) acts as a ubiquitination E3 ligase for ERK3. Mammalian two-hybrid assay and immunoprecipitation results demonstrated that ERK3 is a novel binding partner of FBXW7. Furthermore, complex formation between ERK3 and the S-phase kinase-associated protein 1 (SKP1)-cullin 1-F-box protein (SCF) E3 ligase resulted in the destabilization of ERK3 via a ubiquitination-mediated proteasomal degradation pathway, and FBXW7 depletion restored ERK3 protein levels by inhibiting this ubiquitination. The interaction between ERK3 and FBXW7 was driven by binding between the C34D of ERK3, especially at Thr417 and Thr421, and the WD40 domain of FBXW7. A double mutant of ERK3 (Thr417 and Thr421 to alanine) abrogated FBXW7-mediated ubiquitination. Importantly, ERK3 knockdown inhibited the proliferation of lung cancer cells by regulating the G1/S-phase transition of the cell cycle. These results show that FBXW7-mediated ERK3 destabilization suppresses lung cancer cell proliferation in vitro.

MGA-NET: MULTI-SCALE GUIDED ATTENTION MODELS FOR AN AUTOMATED DIAGNOSIS OF IDIOPATHIC PULMONARY FIBROSIS (IPF).

We propose a Multi-scale, domain knowledge-Guided Attention model (MGA-Net) for a weakly supervised problem - disease diagnosis with only coarse scan-level labels. The use of guided attention models encourages the deep learning-based diagnosis model to focus on the area of interests (in our case, lung parenchyma), at different resolutions, in an end-to-end manner. The research interest is to diagnose subjects with idiopathic pulmonary fibrosis (IPF) among subjects with interstitial lung disease (ILD) using an axial chest high resolution computed tomography (HRCT) scan. Our dataset contains 279 IPF patients and 423 non-IPF ILD patients. The network's performance was evaluated by the area under the receiver operating characteristic curve (AUC) with standard errors (SE) using stratified five-fold cross validation. We observe that without attention modules, the IPF diagnosis model performs unsatisfactorily (AUC±SE =0.690 ± 0.194); by including unguided attention module, the IPF diagnosis model reaches satisfactory performance (AUC±SE =0.956±0.040), but lack explainability; when including only guided high- or medium- resolution attention, the learned attention maps highlight the lung areas but the AUC decreases; when including both high- and medium- resolution attention, the model reaches the highest AUC among all experiments (AUC± SE =0.971 ±0.021) and the estimated attention maps concentrate on the regions of interests for this task. Our results suggest that, for a weakly supervised task, MGA-Net can utilize the population-level domain knowledge to guide the training of the network in an end-to-end manner, which increases both model accuracy and explainability.

ISLES 2016 and 2017-Benchmarking Ischemic Stroke Lesion Outcome Prediction Based on Multispectral MRI.

Performance of models highly depend not only on the used algorithm but also the data set it was applied to. This makes the comparison of newly developed tools to previously published approaches difficult. Either researchers need to implement others' algorithms first, to establish an adequate benchmark on their data, or a direct comparison of new and old techniques is infeasible. The Ischemic Stroke Lesion Segmentation (ISLES) challenge, which has ran now consecutively for 3 years, aims to address this problem of comparability. ISLES 2016 and 2017 focused on lesion outcome prediction after ischemic stroke: By providing a uniformly pre-processed data set, researchers from all over the world could apply their algorithm directly. A total of nine teams participated in ISLES 2015, and 15 teams participated in ISLES 2016. Their performance was evaluated in a fair and transparent way to identify the state-of-the-art among all submissions. Top ranked teams almost always employed deep learning tools, which were predominately convolutional neural networks (CNNs). Despite the great efforts, lesion outcome prediction persists challenging. The annotated data set remains publicly available and new approaches can be compared directly via the online evaluation system, serving as a continuing benchmark (www.isles-challenge.org).