Self-improving generative foundation model for synthetic medical image generation and clinical applications.

In many clinical and research settings, the scarcity of high-quality medical imaging datasets has hampered the potential of artificial intelligence (AI) clinical applications. This issue is particularly pronounced in less common conditions, underrepresented populations and emerging imaging modalities, where the availability of diverse and comprehensive datasets is often inadequate. To address this challenge, we introduce a unified medical image-text generative model called MINIM that is capable of synthesizing medical images of various organs across various imaging modalities based on textual instructions.

An explainable longitudinal multi-modal fusion model for predicting neoadjuvant therapy response in women with breast cancer.

Multi-modal image analysis using deep learning (DL) lays the foundation for neoadjuvant treatment (NAT) response monitoring. However, existing methods prioritize extracting multi-modal features to enhance predictive performance, with limited consideration on real-world clinical applicability, particularly in longitudinal NAT scenarios with multi-modal data. Here, we propose the Multi-modal Response Prediction (MRP) system, designed to mimic real-world physician assessments of NAT responses in breast cancer.

Enhancing representation in radiography-reports foundation model: a granular alignment algorithm using masked contrastive learning.

Recently, multi-modal vision-language foundation models have gained significant attention in the medical field. While these models offer great opportunities, they still face crucial challenges, such as the requirement for fine-grained knowledge understanding in computer-aided diagnosis and the capability of utilizing very limited or even no task-specific labeled data in real-world clinical applications. In this study, we present MaCo, a masked contrastive chest X-ray foundation model that tackles these challenges.

A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective.

Graph Neural Networks (GNNs) have gained momentum in graph representation learning and boosted the state of the art in a variety of areas, such as data mining (e.g., social network analysis and recommender systems), computer vision (e.

COVID-19 acts like a stress test, uncovering the vulnerable part of the human body: a retrospective study of 1640 cases in China.

Background: Since the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection exhibits multi-organ damage with diverse complications, the correlation between age, gender, medical history and clinical manifestations of novel coronavirus disease 2019 (COVID-19) patients was investigated.

Methods: 1640 patients who were infected with SARS-CoV-2 and hospitalized at the First Affiliated Hospital of Ningbo University from 22 December 2022 to 1 March 2023 were categorized and analysed. Normal distribution test and variance homogeneity test were performed.

Deubiquitinating PABPC1 by USP10 upregulates CLK2 translation to promote tumor progression in pancreatic ductal adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDAC) is extremely malignant with limited treatment options. Deubiquitinases (DUBs), which cleave ubiquitin on substrates, can regulate tumor progression and are appealing therapeutic targets, but there are few related studies in PDAC. In our study, we screened the expression levels and prognostic value of USP family members based on published databases and selected USP10 as the potential interventional target in PDAC.

nnFormer: Volumetric Medical Image Segmentation via a 3D Transformer.

Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional neural networks to learn more contextualized visual representations. However, most of recently proposed transformer-based segmentation approaches simply treated transformers as assisted modules to help encode global context into convolutional representations.

A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics.

During the diagnostic process, clinicians leverage multimodal information, such as the chief complaint, medical images and laboratory test results. Deep-learning models for aiding diagnosis have yet to meet this requirement of leveraging multimodal information. Here we report a transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner.

A Unified Visual Information Preservation Framework for Self-supervised Pre-Training in Medical Image Analysis.

Recent advances in self-supervised learning (SSL) in computer vision are primarily comparative, whose goal is to preserve invariant and discriminative semantics in latent representations by comparing siamese image views. However, the preserved high-level semantics do not contain enough local information, which is vital in medical image analysis (e.g.

Development and validation of an abnormality-derived deep-learning diagnostic system for major respiratory diseases.

Respiratory diseases impose a tremendous global health burden on large patient populations. In this study, we aimed to develop DeepMRD, a deep learning-based medical image interpretation system for the diagnosis of major respiratory diseases based on the automated identification of a wide range of radiological abnormalities through computed tomography (CT) and chest X-ray (CXR) from real-world, large-scale datasets. DeepMRD comprises four networks (two CT-Nets and two CXR-Nets) that exploit contrastive learning to generate pre-training parameters that are fine-tuned on the retrospective dataset collected from a single institution.

Virtual Reality in Treatment for Psychological Problems in First-Line Health Care Professionals Fighting COVID-19 Pandemic: A Case Series.

Virtual reality therapy (VRT) is a new psychotherapeutic approach integrating virtual reality technology and psychotherapy. This case series aimed to study effectiveness of VRT in treating psychological problems. We described four cases of first-line health care professionals with emerging clinically significant early psychological problems during the COVID-19 outbreak, and specifically received the VRT treatment.

Brain structural and functional connectivity alterations are associated with fatigue in neuromyelitis optica spectrum disorder.

Background: Many patients with neurological disorders experience chronic fatigue, but the neural mechanisms involved are unclear.

Objective: Here we investigated whether the brain structural and functional connectivity alterations were involved in fatigue related to neuromyelitis optica spectrum disorder (NMOSD).

Methods: This prospective pilot study used structural and resting-state functional brain magnetic resonance imaging to compare total cortical thickness, cortical surface area, deep gray matter volume and functional connectivity (FC) between 33 patients with NMOSD and 20 healthy controls (HCs).

MASS: Modality-collaborative semi-supervised segmentation by exploiting cross-modal consistency from unpaired CT and MRI images.

Training deep segmentation models for medical images often requires a large amount of labeled data. To tackle this issue, semi-supervised segmentation has been employed to produce satisfactory delineation results with affordable labeling cost. However, traditional semi-supervised segmentation methods fail to exploit unpaired multi-modal data, which are widely adopted in today's clinical routine.

Relation Matters: Foreground-Aware Graph-Based Relational Reasoning for Domain Adaptive Object Detection.

Domain Adaptive Object Detection (DAOD) focuses on improving the generalization ability of object detectors via knowledge transfer. Recent advances in DAOD strive to change the emphasis of the adaptation process from global to local in virtue of fine-grained feature alignment methods. However, both the global and local alignment approaches fail to capture the topological relations among different foreground objects as the explicit dependencies and interactions between and within domains are neglected.

An enriched environment reduces hippocampal inflammatory response and improves cognitive function in a mouse model of stroke.

An enriched environment is used as a behavioral intervention therapy that applies sensory, motor, and social stimulation, and has been used in basic and clinical research of various neurological diseases. In this study, we established mouse models of photothrombotic stroke and, 24 hours later, raised them in a standard, enriched, or isolated environment for 4 weeks. Compared with the mice raised in a standard environment, the cognitive function of mice raised in an enriched environment was better and the pathological damage in the hippocampal CA1 region was remarkably alleviated.

[Effect and Mechanism of Treating Experimental Autoimmune Encephalomyelitis in Mice with Butylphthalide Combined with Bone Marrow Mesenchymal Stem Cells].

Objective: To explore the efficacy and mechanism of using 3-n-butylphthalide (NBP) in combination with bone marrow mesenchymal stem cells (BMSCs) in the treatment of experimental autoimmune encephalomyelitis (EAE) in mice.

Methods: Myelin oligodendrocyte glycoprotein (MOG35-55) was used for the induction and establishment of the EAE model in C57BL/6 mice. The mice were randomly assigned to the EAE group, which received intraperitoneal injection of phosphate-buffered saline (PBS), the NBP-treated EAE group, or the NBP group, which received intraperitoneal injection of NBP, the BMSCs transplantion EAE group, or the BMSCs group, which received BMSCs injected into the lateral ventricle and intraperitoneal injection of PBS, and the BMSCs and NBP combination treatment EAE group, or the BMSCs+NBP group, which received BMSCs injected into the lateral ventricle and intraperitoneal injection of NBP.

Anesthetic technique for awake artery malformation clipping with motor evoked potential and somatosensory evoked potential: A case report.

Background: Awake craniotomy has been widely used for tumor resection, epilepsy surgery, deep brain stimulation, and carotid endarterectomy. The report on awake artery malformation clipping is rare, especially for anesthesia management.

Case Summary: A 62-year-old female diagnosed with malformation of anterior cerebral artery at the right side.

Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition.

Multi-label image recognition is a practical and challenging task compared to single-label image classification. However, previous works may be suboptimal because of a great number of object proposals or complex attentional region generation modules. In this paper, we propose a simple but efficient two-stream framework to recognize multi-category objects from global image to local regions, similar to how human beings perceive objects.

SSMD: Semi-Supervised medical image detection with adaptive consistency and heterogeneous perturbation.

Semi-Supervised classification and segmentation methods have been widely investigated in medical image analysis. Both approaches can improve the performance of fully-supervised methods with additional unlabeled data. However, as a fundamental task, semi-supervised object detection has not gained enough attention in the field of medical image analysis.

Evaluation and comparison of accurate automated spinal curvature estimation algorithms with spinal anterior-posterior X-Ray images: The AASCE2019 challenge.

Scoliosis is a common medical condition, which occurs most often during the growth spurt just before puberty. Untreated Scoliosis may cause long-term sequelae. Therefore, accurate automated quantitative estimation of spinal curvature is an important task for the clinical evaluation and treatment planning of Scoliosis.