Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model using both labeled data from the source domain and unlabeled data from the target domain. Source-Free UDA (SFUDA) was recently proposed for UDA without requiring the source data during the adaptation, due to data privacy or data transmission issues, which normally adapts the pre-trained deep model in the testing stage. However, in real clinical scenarios of medical image segmentation, the trained model is normally frozen in the testing stage. In this paper, we propose Fourier Visual Prompting (FVP) for SFUDA of medical image segmentation. Inspired by prompting learning in natural language processing, FVP steers the frozen pre-trained model to perform well in the target domain by adding a visual prompt to the input target data. In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model. To our knowledge, FVP is the first work to apply visual prompts to SFUDA for medical image segmentation. The proposed FVP is validated using three public datasets, and experiments demonstrate that FVP yields better segmentation results, compared with various existing methods.

To facilitate the analysis and diagnosis of X-ray coronary angiography in interventional surgery, it is necessary to extract vessel from X-ray coronary angiography. However, vessel images of angiography suffer from low quality with large artefacts, which challenges the existing vascular technology. In this paper, we propose a ávessel framework to detect vessels and segment vessels in angiographic vessel data. In this framework, we develop a new matrix decomposition model with gradient sparse in the tensor representation. Then, the energy function with the input of the hierarchical vessel is used in vessel detection and vessel segmentation. Through experiments conducted on angiographic data, we have demonstrated the good performance of the proposed method in removing background structure. We evaluated our method for vessel detection and segmentation in different clinical settings, including LAO/RAO with cranial and caudal angulation, and showed its competitive results compared with eight state-of-the-art methods in terms of extensive qualitative and quantitative evaluation. Our method can remove a large number of background artefacts and obtain a better vascular structure, which has contributed to the clinical diagnosis of coronary artery diseases.

Purpose: To develop a practical approach to quantify the exposure to environmental risk factors of myopia. Methods: In total, 179 children (age, mean ± standard deviation [SD] 9.17 ± 0.52 years) were requested to wear Clouclip, designed to measure working distance (WD) and light intensity (LI), for a whole week. The spherical equivalent refraction (SER) was determined by cycloplegic autorefraction. The raw data of WD and LI were preprocessed through several steps, including data denoising, constructing a two-dimensional WD-LI space, and data sparseness disposing. Weighted linear regression was used to explore the relationship between WD/LI and SER. A novel parameter visual behaviour index (VBI) was developed to summarize the overall impact of WD/LI on SER. Results: The mean ± SD SER of 179 participants was 0.22 ± 1.18 D. WD and LI were positively associated with SER. However, their magnitude of effect on SER varied with the relative level between them. When WD and LI were split up, the detrimental threshold was approximately 40 cm for WD and 6300 lux for LI. VBI was significantly positively associated with SER (β = 0.0623, R² = 0.031, P < 0.05). Conclusions: The current study provides a novel approach to quantify environmental risk factors of myopia. Despite the complexity of the interaction between these risk factors and their impact on SER, this information can be summarized as one single-parameter VBI, which provides a useful tool to investigate the effect of environmental factors on myopia development and progression. Translational Relevance: We developed a novel approach to quantify environmental risk factors of myopia.

Fetal congenital heart disease (FCHD) is a common, serious birth defect affecting ∼1% of newborns annually. Fetal echocardiography is the most effective and important technique for prenatal FCHD diagnosis. The prerequisites for accurate ultrasound FCHD diagnosis are accurate view recognition and high-quality diagnostic view extraction. However, these manual clinical procedures have drawbacks such as, varying technical capabilities and inefficiency. Therefore, the automatic identification of high-quality multiview fetal heart scan images is highly desirable to improve prenatal diagnosis efficiency and accuracy of FCHD. Here, we present a framework for multiview fetal heart ultrasound image recognition and quality assessment that comprises two parts: a multiview classification and localization network (MCLN) and an improved contrastive learning network (ICLN). In the MCLN, a multihead enhanced self-attention mechanism is applied to construct the classification network and identify six accurate and interpretable views of the fetal heart. In the ICLN, anatomical structure standardization and image clarity are considered. With contrastive learning, the absolute loss, feature relative loss and predicted value relative loss are combined to achieve favorable quality assessment results. Experiments show that the MCLN outperforms other state-of-the-art networks by 1.52–13.61% when determining the F1 score in six standard view recognition tasks, and the ICLN is comparable to the performance of expert cardiologists in the quality assessment of fetal heart ultrasound images, reaching 97% on a test set within 2 points for the four-chamber view task. Thus, our architecture offers great potential in helping cardiologists improve quality control for fetal echocardiographic images in clinical practice.