OBJECTIVE: To explore the prenatal and postnatal phenotypes of 22q11.2 microdeletion syndrome (22q11.2DS) and enhance clinical understanding of this condition. METHODS: Data were collected from 86 fetuses diagnosed with 22q11.2DS at four prenatal diagnostic centers across China between January 2014 and August 2025. Prenatal imaging findings, pregnancy outcomes, and postnatal conditions were analyzed. RESULTS: Among the 86 fetuses, complete ultrasound data were available for 65 cases. Cardiovascular abnormalities were observed in 42 cases, thymic hypoplasia or aplasia in 7 cases, urinary system anomalies in 6 cases, nuchal translucency (NT) thickening in 7 cases, butterfly vertebrae, clubfoot, omphalocele and diaphragmatic hernia in 1 case each, cleft lip and palate in 2 cases, and ultrasound soft markers in 13 cases. The parents of 9 fetuses opted to continue with the pregnancy. Among these, 6 showed no significant ultrasound abnormalities and no related phenotypes postnatally, while the remaining 3 exhibited ultrasound anomalies with postnatal manifestations including developmental delay, immunodeficiency, and cardiac defects. CONCLUSION Fetuses with 22q11.2DS may exhibit various ultrasound abnormalities in multiple systems before and after birth. In addition to cardiovascular anomalies, they may also present with thymic hypoplasia or aplasia, thickened NT, and urinary abnormalities. Fetuses with thickened NT or thymic anomalies should be closely monitored, and thymic assessment should be included in routine prenatal imaging evaluations. For fetuses with 22q11.2DS who show no ultrasound abnormalities, the risk of developing severe phenotypes after birth is relatively low, but occult palate clefts and psychiatric disorders cannot be ruled out. Due to limitations in sample size and follow-up duration, above conclusions require further validation through large-scale prospective studies.
Humans ; Female ; Pregnancy ; Ultrasonography, Prenatal ; DiGeorge Syndrome/genetics* ; Adult ; Male ; Follow-Up Studies ; Fetus/diagnostic imaging* ; Phenotype ; Infant, Newborn

OBJECTIVE: To explore the genotype-phenotype correlation in a Chinese family with structural brain abnormalities due to variant of the TUBB gene. METHODS: A family undergoing prenatal diagnosis at Beijing Obstetrics and Gynecology Hospital in October 2024 was selected as the study subject. Clinical data were collected. Amniotic fluid sample was subjected to chromosomal copy number variation sequencing (CNV-seq). Trio whole-exome sequencing (Trio-WES) was carried out on the amniotic fluid and parental blood samples, and candidate variant was verified by Sanger sequencing. This study was approved by the Medical Ethics Committee of the hospital (Ethics No.: 2023-KY-076-01). RESULTS: Both prenatal ultrasound and fetal MRI showed deviation of brain midline, unilateral lateral ventriculomegaly, and bilateral gyral asymmetry. Trio-WES revealed that the fetus has harbored a maternally derived heterozygous missense variant of the TUBB gene [NM_178014.4: c.155A>G (p.N52S)]. Sanger sequencing confirmed that the woman and a previously terminated fetus both harbored the same variant. Both the proband and two fetuses exhibited similar neuroimaging abnormalities including midline deviation and asymmetrical gyri. Based on the guidelines from the American College of Medical Genetics and Genomics (ACMG), the variant was classified as likely pathogenic (PM2_Supporting+PS2_Moderate+PS3). CONCLUSION The heterozygous c.155A>G (p.N52S) variant was the TUBB gene probably underlay the pathogenesis of the structural brain abnormalities in this family. Above findings have expanded the phenotypic spectrum associated with the variant and facilitated the prenatal diagnosis for this family.
Humans ; Female ; Pregnancy ; Prenatal Diagnosis ; Tubulin/genetics* ; Adult ; Brain/diagnostic imaging* ; Male ; Pedigree ; DNA Copy Number Variations/genetics* ; Exome Sequencing ; Genetic Association Studies ; Magnetic Resonance Imaging

OBJECTIVE: To investigate the genetic etiology of a fetus diagnosed with Mandibulofacial dysostosis with microcephaly (MFDM). METHODS: A fetus that underwent prenatal diagnosis at Beijing Obstetrics and Gynecology Hospital, Capital Medical University, on May 19, 2025 was selected for analysis. Results of fetal ultrasound findings, chromosomal karyotyping, copy number variation sequencing (CNV-seq), and whole-exome sequencing (WES) were collected. Sanger sequencing was performed for familial validation of the pathogenic variant. The Human Protein Atlas (HPA), STRING, and Simple ClinVar databases were queried to characterize the biological features of the candidate gene. Three-dimensional structures of the wild-type and variant proteins were modeled and analyzed, and the evolutionary conservation of the affected amino acid was assessed using UGENE. Prenatal phenotypes associated with EFTUD2 variants were summarized through a review of the literature. This study was approved by the Ethics Committee of Beijing Obstetrics and Gynecology Hospital, Capital Medical University (Ethics No.: 2025-KY-029-01). RESULTS: At 23⁺² weeks of gestation, ultrasound examination revealed bilateral microtia with low-set ears, mild micrognathia with a reduced mandibular-facial angle, a single umbilical artery, a slightly narrow aortic diameter, and trivial mitral regurgitation. Amniotic fluid karyotyping and CNV-seq showed no abnormalities. WES identified a de novo, previously unreported EFTUD2 variant, c.698dupA (p.V235Gfs*27), in the fetus. This frameshift variant is predicted to alter the structural integrity of the EFTUD2 protein. Literature review indicated that micrognathia and microtia or low-set ears are the most common sonographic features in fetuses with EFTUD2 variants, while secondary findings may include abnormal stomach bubble, cleft palate, single umbilical artery, gastrointestinal atresia, polyhydramnios, and reduced aortic diameter. CONCLUSION The EFTUD2: c.698dupA (p.V235Gfs*27) variant is likely the genetic cause underlying MFDM in this fetus.
Humans ; Mandibulofacial Dysostosis/diagnostic imaging* ; Microcephaly/diagnostic imaging* ; Female ; Pregnancy ; Ribonucleoprotein, U5 Small Nuclear/chemistry* ; Peptide Elongation Factors/chemistry* ; Fetus ; DNA Copy Number Variations/genetics* ; Adult ; Ultrasonography, Prenatal

With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence ; Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Deep Learning ; Diagnostic Imaging/methods*

Objective: To investigate the application effectiveness of the artificial intelligence(AI) based Generative Pre-treatment tool of Skeletal Pathology (GPTSP) in measuring functional lumbar radiographic examinations. Methods: This is a retrospective case series study,reviewing the clinical and imaging data of 34 patients who underwent lumbar dynamic X-ray radiography at Department of Orthopedics, the Second Hospital of Shandong University from September 2021 to June 2023. Among the patients, 13 were male and 21 were female, with an age of (68.0±8.0) years (range:55 to 88 years). The AI model of the GPTSP system was built upon a multi-dimensional constrained loss function constructed based on the YOLOv8 model, incorporating Kullback-Leibler divergence to quantify the anatomical distribution deviation of lumbar intervertebral space detection boxes, along with the introduction of a global dynamic attention mechanism. It can identify lumbar vertebral body edge points and measure lumbar intervertebral space. Furthermore, spondylolisthesis index, lumbar index, and lumbar intervertebral angles were measured using three methods: manual measurement by doctors, predefined annotated measurement, and AI-assisted measurement. The consistency between the doctors and the AI model was analyzed through intra-class correlation coefficient (ICC) and Kappa coefficient. Results: AI-assisted physician measurement time was (1.5±0.1) seconds (range: 1.3 to 1.7 seconds), which was shorter than the manual measurement time ((2 064.4±108.2) seconds,range: 1 768.3 to 2 217.6 seconds) and the pre-defined annotation measurement time ((602.0±48.9) seconds,range: 503.9 to 694.4 seconds). Kappa values between physicians' diagnoses and AI model's diagnoses (based on GPTSP platform) for the lumbar slip index, lumbar index, and intervertebral angles measured by three methods were 0.95, 0.92, and 0.82 (all P<0.01), with ICC values consistently exceeding 0.90, indicating high consistency. Based on the doctor's manual measurement, compared with the predefined label measurement, altering AI assistance, doctors measurement with average annotation errors reduced from 2.52 mm (range: 0.01 to 6.78 mm) to 1.47 mm(range: 0 to 5.03 mm). Conclusions: The GPTSP system enhanced efficiency in functional lumbar analysis. AI model demonstrated high consistency in annotation and measurement results, showing strong potential to serve as a reliable clinical auxiliary tool.
Humans ; Female ; Retrospective Studies ; Male ; Lumbar Vertebrae/diagnostic imaging* ; Middle Aged ; Aged ; Aged, 80 and over ; Artificial Intelligence ; Radiography ; Spondylolisthesis/diagnostic imaging*

During transfer tasks, the dual-arm nursing-care robot require a human-robot mechanics model to determine the balance region to support the patient safely and stably. Previous studies utilized human-robot two-dimensional static equilibrium models, ignoring the human body volume and muscle torques, which decreased model accuracy and confined the robot ability to adjust the patient's posture in three-dimensional spatial. Therefore, this study proposes a three-dimensional spatial mechanics modeling method based on individualized human musculoskeletal multibody dynamics. Firstly, based on the mechanical features of dual-arm support, this study constructed a foundational three-dimensional human-robot mechanics model including body posture, contact position and body force. With the computed tomography data from subjects, a three-dimensional femur-pelvis-sacrum model was reconstructed, and the individualized musculoskeletal dynamics was analyzed using the ergonomics software, which derived the human joint forces and completed the mechanic model. Then, this study established a dual-arm robot transfer platform to conduct subject transfer experiments, showing that the constructed mechanics model possessed higher accuracy than previous methods. In summary, this study provides a three-dimensional human-robot mechanics model adapting to individual transfers, which has potential application in various scenarios such as nursing-care and rehabilitating robots.
Humans ; Robotics ; Biomechanical Phenomena ; Posture ; Imaging, Three-Dimensional ; Nursing Care

Synthetic CT (sCT) generated from CBCT has proven effective in artifact reduction and CT number correction, facilitating precise radiation dose calculation. However, the quality of different regions in sCT images is severely imbalanced, with soft tissue region exhibiting notably inferior quality compared to others. To address this imbalance, we proposed a Multi-Task Attention Network (MuTA-Net) based on VGG-16, specifically focusing the enhancement of image quality in soft tissue region of sCT. First, we introduced a multi-task learning strategy that divides the sCT generation task into three sub-tasks: global image generation, soft tissue region generation and bone region segmentation. This approach ensured the quality of overall sCT image while enhancing the network's focus on feature extraction and generation for soft tissues region. The result of bone region segmentation task guided the fusion of sub-tasks results. Then, we designed an attention module to further optimize feature extraction capabilities of the network. Finally, by employing a results fusion module, the results of three sub-tasks were integrated, generating a high-quality sCT image. Experimental results on head and neck CBCT demonstrated that the sCT images generated by the proposed MuTA-Net exhibited a 12.52% reduction in mean absolute error in soft tissue region, compared to the best performance among the three comparative methods, including ResNet, U-Net, and U-Net++. It can be seen that MuTA-Net is suitable for high-quality sCT image generation and has potential application value in the field of CBCT guided adaptive radiation therapy.
Cone-Beam Computed Tomography/methods* ; Humans ; Image Processing, Computer-Assisted/methods* ; Artifacts ; Algorithms ; Bone and Bones/diagnostic imaging* ; Neural Networks, Computer

Alzheimer's disease (AD) classification models usually segment the entire brain image into voxel blocks and assign them labels consistent with the entire image, but not every voxel block is closely related to the disease. To this end, an AD auxiliary diagnosis framework based on weakly supervised multi-instance learning (MIL) and multi-scale feature fusion is proposed, and the framework is designed from three aspects: within the voxel block, between voxel blocks, and high-confidence voxel blocks. First, a three-dimensional convolutional neural network was used to extract deep features within the voxel block; then the spatial correlation information between voxel blocks was captured through position encoding and attention mechanism; finally, high-confidence voxel blocks were selected and combined with multi-scale information fusion strategy to integrate key features for classification decision. The performance of the model was evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies (OASIS) datasets. Experimental results showed that the proposed framework improved ACC and AUC by 3% and 4% on average compared with other mainstream frameworks in the two tasks of AD classification and mild cognitive impairment conversion classification, and could find the key voxel blocks that trigger the disease, providing an effective basis for AD auxiliary diagnosis.
Alzheimer Disease/diagnosis* ; Humans ; Neuroimaging/methods* ; Neural Networks, Computer ; Brain/diagnostic imaging* ; Magnetic Resonance Imaging ; Deep Learning ; Machine Learning

Due to its irregular shape and varying contour, pancreas segmentation is a recognized challenge in medical image segmentation. Convolutional neural network (CNN) and Transformer-based networks perform well but have limitations: CNN have constrained receptive fields, and Transformer underutilize image features. This work proposes an improved pancreas segmentation method by combining CNN and Transformer. Point-wise separable convolution was introduced in a stage-wise encoder to extract more features with fewer parameters. A densely connected ensemble decoder enabled multi-scale feature fusion, addressing the structural constraints of skip connections. Consistency terms and contrastive loss were integrated into deep supervision to ensure model accuracy. Extensive experiments on the Changhai and National Institute of Health (NIH) pancreas datasets achieved the highest Dice similarity coefficient (DSC) values of 76.32% and 86.78%, with superiority in other metrics. Ablation studies validated each component's contributions to performance and parameter reduction. Results demonstrate that the proposed loss function smooths training and optimizes performance. Overall, the method outperforms other advanced methods, enhances pancreas segmentation performance, supports physician diagnosis, and provides a reliable reference for future research.
Humans ; Neural Networks, Computer ; Pancreas/diagnostic imaging* ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Deep Learning

The accurate segmentation of breast ultrasound images is an important precondition for the lesion determination. The existing segmentation approaches embrace massive parameters, sluggish inference speed, and huge memory consumption. To tackle this problem, we propose T ²KD Attention U-Net (dual-Teacher Knowledge Distillation Attention U-Net), a lightweight semantic segmentation method combined double-path joint distillation in breast ultrasound images. Primarily, we designed two teacher models to learn the fine-grained features from each class of images according to different feature representation and semantic information of benign and malignant breast lesions. Then we leveraged the joint distillation to train a lightweight student model. Finally, we constructed a novel weight balance loss to focus on the semantic feature of small objection, solving the unbalance problem of tumor and background. Specifically, the extensive experiments conducted on Dataset BUSI and Dataset B demonstrated that the T ²KD Attention U-Net outperformed various knowledge distillation counterparts. Concretely, the accuracy, recall, precision, Dice, and mIoU of proposed method were 95.26%, 86.23%, 85.09%, 83.59%and 77.78% on Dataset BUSI, respectively. And these performance indexes were 97.95%, 92.80%, 88.33%, 88.40% and 82.42% on Dataset B, respectively. Compared with other models, the performance of this model was significantly improved. Meanwhile, compared with the teacher model, the number, size, and complexity of student model were significantly reduced (2.2×10 ⁶ vs. 106.1×10 ⁶, 8.4 MB vs. 414 MB, 16.59 GFLOPs vs. 205.98 GFLOPs, respectively). Indeedy, the proposed model guarantees the performances while greatly decreasing the amount of computation, which provides a new method for the deployment of clinical medical scenarios.
Humans ; Breast Neoplasms/diagnostic imaging* ; Female ; Ultrasonography, Mammary/methods* ; Image Processing, Computer-Assisted/methods* ; Algorithms ; Neural Networks, Computer ; Breast/diagnostic imaging*