SMS Scam Detection Application Based on Optical Character Recognition for Image Data Using Unsupervised and Deep Semi-Supervised Learning.

The growing problem of unsolicited text messages (smishing) and data irregularities necessitates stronger spam detection solutions. This paper explores the development of a sophisticated model designed to identify smishing messages by understanding the complex relationships among words, images, and context-specific factors, areas that remain underexplored in existing research. To address this, we merge a UCI spam dataset of regular text messages with real-world spam data, leveraging OCR technology for comprehensive analysis. The study employs a combination of traditional machine learning models, including K-means, Non-Negative Matrix Factorization, and Gaussian Mixture Models, along with feature extraction techniques such as TF-IDF and PCA. Additionally, deep learning models like RNN-Flatten, LSTM, and Bi-LSTM are utilized. The selection of these models is driven by their complementary strengths in capturing both the linear and non-linear relationships inherent in smishing messages. Machine learning models are chosen for their efficiency in handling structured text data, while deep learning models are selected for their superior ability to capture sequential dependencies and contextual nuances. The performance of these models is rigorously evaluated using metrics like accuracy, precision, recall, and F1 score, enabling a comparative analysis between the machine learning and deep learning approaches. Notably, the K-means feature extraction with vectorizer achieved 91.01% accuracy, and the KNN-Flatten model reached 94.13% accuracy, emerging as the top performer. The rationale behind highlighting these models is their potential to significantly improve smishing detection rates. For instance, the high accuracy of the KNN-Flatten model suggests its applicability in real-time spam detection systems, but its computational complexity might limit scalability in large-scale deployments. Similarly, while K-means with vectorizer excels in accuracy, it may struggle with the dynamic and evolving nature of smishing attacks, necessitating continual retraining.

Application of the Semi-Supervised Learning Approach for Pavement Defect Detection.

Road surface quality is essential for driver comfort and safety, making it crucial to monitor pavement conditions and detect defects in real time. However, the diversity of defects and the complexity of ambient conditions make it challenging to develop an effective and robust classification and detection algorithm. In this study, we adopted a semi-supervised learning approach to train ResNet-18 for image feature retrieval and then classification and detection of pavement defects. The resulting feature embedding vectors from image patches were retrieved, concatenated, and randomly sampled to model a multivariate normal distribution based on the only one-class training pavement image dataset. The calibration pavement image dataset was used to determine the defect score threshold based on the receiver operating characteristic curve, with the Mahalanobis distance employed as a metric to evaluate differences between normal and defect pavement images. Finally, a heatmap derived from the defect score map for the testing dataset was overlaid on the original pavement images to provide insight into the network's decisions and guide measures to improve its performance. The results demonstrate that the model's classification accuracy improved from 0.868 to 0.887 using the expanded and augmented pavement image data based on the analysis of heatmaps.

Segmentation of supragranular and infragranular layers in ultra-high-resolution 7T ex vivo MRI of the human cerebral cortex.

Accurate labeling of specific layers in the human cerebral cortex is crucial for advancing our understanding of neurodevelopmental and neurodegenerative disorders. Building on recent advancements in ultra-high-resolution ex vivo MRI, we present a novel semi-supervised segmentation model capable of identifying supragranular and infragranular layers in ex vivo MRI with unprecedented precision. On a dataset consisting of 17 whole-hemisphere ex vivo scans at 120 $\mu $m, we propose a Multi-resolution U-Nets framework that integrates global and local structural information, achieving reliable segmentation maps of the entire hemisphere, with Dice scores over 0.8 for supra- and infragranular layers. This enables surface modeling, atlas construction, anomaly detection in disease states, and cross-modality validation while also paving the way for finer layer segmentation. Our approach offers a powerful tool for comprehensive neuroanatomical investigations and holds promise for advancing our mechanistic understanding of progression of neurodegenerative diseases.

Wi-Fi Fingerprint Indoor Localization by Semi-Supervised Generative Adversarial Network.

Wi-Fi fingerprint indoor localization uses Wi-Fi signal strength measurements obtained from a number of access points. This method needs manual data collection across a positioning area and an annotation process to label locations to the measurement sets. To reduce the cost and effort, this paper proposes a Wi-Fi Semi-Supervised Generative Adversarial Network (SSGAN), which produces artificial but realistic trainable fingerprint data. The Wi-Fi SSGAN is based on a deep learning, which is extended from GAN in a semi-supervised learning manner. It is designed to create location-labeled Wi-Fi fingerprint data, which is different to unlabeled data generation by a normal GAN. Also, the proposed Wi-Fi SSGAN network includes a positioning model, so it does not need a external positioning method. When the Wi-Fi SSGAN is applied to a multi-story landmark localization, the experimental results demonstrate a 35% more accurate performance in comparison to a standard supervised deep neural network.

Optimizing Automated Optical Inspection: An Adaptive Fusion and Semi-Supervised Self-Learning Approach for Elevated Accuracy and Efficiency in Scenarios with Scarce Labeled Data.

In the field of automatic optical inspection (AOI), this study presents innovative strategies to enhance object detection accuracy while minimizing dependence on large annotated datasets. We initially developed a defect detection model using a dataset of 3579 images across 32 categories, created in collaboration with a major Taiwanese panel manufacturer. This model was evaluated using 12,000 ambiguously labeled images, with improvements achieved through data augmentation and annotation refinement. To address the challenges of limited labeled data, we proposed the Adaptive Fused Semi-Supervised Self-Learning (AFSL) method. This approach, designed for anchor-based object detection models, leverages a small set of labeled data alongside a larger pool of unlabeled data to enable continuous model optimization. Key components of AFSL include the Bounding Box Assigner, Adaptive Training Scheduler, and Data Allocator, which together facilitate dynamic threshold adjustments and balanced training, significantly enhancing the model's performance on AOI datasets. The AFSL method improved the mean average precision (mAP) from 43.5% to 57.1% on the COCO dataset and by 2.6% on the AOI dataset, demonstrating its effectiveness in achieving high levels of precision and efficiency in AOI with minimal labeled data.

A Comparative Analysis of U-Net and Vision Transformer Architectures in Semi-Supervised Prostate Zonal Segmentation.

The precise segmentation of different regions of the prostate is crucial in the diagnosis and treatment of prostate-related diseases. However, the scarcity of labeled prostate data poses a challenge for the accurate segmentation of its different regions. We perform the segmentation of different regions of the prostate using U-Net- and Vision Transformer (ViT)-based architectures. We use five semi-supervised learning methods, including entropy minimization, cross pseudo-supervision, mean teacher, uncertainty-aware mean teacher (UAMT), and interpolation consistency training (ICT) to compare the results with the state-of-the-art prostate semi-supervised segmentation network uncertainty-aware temporal self-learning (UATS). The UAMT method improves the prostate segmentation accuracy and provides stable prostate region segmentation results. ICT plays a more stable role in the prostate region segmentation results, which provides strong support for the medical image segmentation task, and demonstrates the robustness of U-Net for medical image segmentation. UATS is still more applicable to the U-Net backbone and has a very significant effect on a positive prediction rate. However, the performance of ViT in combination with semi-supervision still requires further optimization. This comparative analysis applies various semi-supervised learning methods to prostate zonal segmentation. It guides future prostate segmentation developments and offers insights into utilizing limited labeled data in medical imaging.

ABNet: AI-Empowered Abnormal Action Recognition Method for Laboratory Mouse Behavior.

The automatic recognition and quantitative analysis of abnormal behavior in mice play a crucial role in behavioral observation experiments in neuroscience, pharmacology, and toxicology. Due to the challenging definition of abnormal behavior and difficulty in collecting training samples, directly applying behavior recognition methods to identify abnormal behavior is often infeasible. This paper proposes ABNet, an AI-empowered abnormal action recognition approach for mice. ABNet utilizes an enhanced Spatio-Temporal Graph Convolutional Network (ST-GCN) as an encoder; ST-GCN combines graph convolution and temporal convolution to efficiently capture and analyze spatio-temporal dynamic features in graph-structured data, making it suitable for complex tasks such as action recognition and traffic prediction. ABNet trains the encoding network with normal behavior samples, then employs unsupervised clustering to identify abnormal behavior in mice. Compared to the original ST-GCN network, the method significantly enhances the capabilities of feature extraction and encoding. We conduct comprehensive experiments on the Kinetics-Skeleton dataset and the mouse behavior dataset to evaluate and validate the performance of ABNet in behavior recognition and abnormal motion detection. In the behavior recognition experiments conducted on the Kinetics-Skeleton dataset, ABNet achieves an accuracy of 32.7% for the top one and 55.2% for the top five. Moreover, in the abnormal behavior analysis experiments conducted on the mouse behavior dataset, ABNet achieves an average accuracy of 83.1%.

Dimma: Semi-Supervised Low-Light Image Enhancement with Adaptive Dimming.

Enhancing low-light images with natural colors poses a challenge due to camera processing variations and limited access to ground-truth lighting conditions. To address this, we propose Dimma, a semi-supervised approach that aligns with any camera using a small set of image pairs captured under extreme lighting conditions. Our method employs a convolutional mixture density network to replicate camera-specific noise present in dark images. We enhance results further by introducing a conditional UNet architecture based on user-provided lightness values. Trained on just a few real image pairs, Dimma achieves competitive results compared to fully supervised state-of-the-art methods trained on large datasets.

Efficient and accurate semi-supervised semantic segmentation for industrial surface defects.

Deep learning-based defect detection methods have gained widespread application in industrial quality inspection. However, limitations such as insufficient sample sizes, low data utilization, and issues with accuracy and speed persist. This paper proposes a semi-supervised semantic segmentation framework that addresses these challenges through perturbation invariance at both the image and feature space. The framework employs diverse perturbation cross-pseudo-supervision to reduce dependency on extensive labeled datasets. Our lightweight method incorporates edge pixel-level semantic information and shallow feature fusion to enhance real-time performance and improve the accuracy of defect edge detection and small target segmentation in industrial inspection. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art (SOTA) semi-supervised semantic segmentation methods across various industrial scenarios. Specifically, our method achieves a mean Intersection over Union (mIoU) 3.11% higher than the SOTA method on our dataset and 4.39% higher on the public KolektorSDD dataset. Additionally, our semantic segmentation network matches the speed of the fastest network, U-net, while achieving a mIoU 2.99% higher than DeepLabv3Plus.

Semi-supervised CT image segmentation via contrastive learning based on entropy constraints.

Deep learning-based methods for fast target segmentation of computed tomography (CT) imaging have become increasingly popular. The success of current deep learning methods usually depends on a large amount of labeled data. Labeling medical data is a time-consuming and laborious task. Therefore, this paper aims to enhance the segmentation of CT images by using a semi-supervised learning method. In order to utilize the valid information in unlabeled data, we design a semi-supervised network model for contrastive learning based on entropy constraints. We use CNN and Transformer to capture the image's local and global feature information, respectively. In addition, the pseudo-labels generated by the teacher networks are unreliable and will lead to degradation of the model performance if they are directly added to the training. Therefore, unreliable samples with high entropy values are discarded to avoid the model extracting the wrong features. In the student network, we also introduce the residual squeeze and excitation module to learn the connection between different channels of each layer feature to obtain better segmentation performance. We demonstrate the effectiveness of the proposed method on the COVID-19 CT public dataset. We mainly considered three evaluation metrics: DSC, HD95, and JC. Compared with several existing state-of-the-art semi-supervised methods, our method improves DSC by 2.3%, JC by 2.5%, and reduces HD95 by 1.9 mm. In this paper, a semi-supervised medical image segmentation method is designed by fusing CNN and Transformer and utilizing entropy-constrained contrastive learning loss, which improves the utilization of unlabeled medical images.

A Semi-Supervised Transformer-Based Deep Learning Framework for Automated Tooth Segmentation and Identification on Panoramic Radiographs.

Automated tooth segmentation and identification on dental radiographs are crucial steps in establishing digital dental workflows. While deep learning networks have been developed for these tasks, their performance has been inferior in partially edentulous individuals. This study proposes a novel semi-supervised Transformer-based framework (SemiTNet), specifically designed to improve tooth segmentation and identification performance on panoramic radiographs, particularly in partially edentulous cases, and establish an open-source dataset to serve as a unified benchmark. A total of 16,317 panoramic radiographs (1589 labeled and 14,728 unlabeled images) were collected from various datasets to create a large-scale dataset (TSI15k). The labeled images were divided into training and test sets at a 7:1 ratio, while the unlabeled images were used for semi-supervised learning. The SemiTNet was developed using a semi-supervised learning method with a label-guided teacher-student knowledge distillation strategy, incorporating a Transformer-based architecture. The performance of SemiTNet was evaluated on the test set using the intersection over union (IoU), Dice coefficient, precision, recall, and F1 score, and compared with five state-of-the-art networks. Paired t-tests were performed to compare the evaluation metrics between SemiTNet and the other networks. SemiTNet outperformed other networks, achieving the highest accuracy for tooth segmentation and identification, while requiring minimal model size. SemiTNet's performance was near-perfect for fully dentate individuals (all metrics over 99.69%) and excellent for partially edentulous individuals (all metrics over 93%). In edentulous cases, SemiTNet obtained statistically significantly higher tooth identification performance than all other networks. The proposed SemiTNet outperformed previous high-complexity, state-of-the-art networks, particularly in partially edentulous cases. The established open-source TSI15k dataset could serve as a unified benchmark for future studies.

Structural tensor and frequency guided semi-supervised segmentation for medical images.

BACKGROUND: The method of semi-supervised semantic segmentation entails training with a limited number of labeled samples alongside many unlabeled samples, aiming to reduce dependence on pixel-level annotations. Most semi-supervised semantic segmentation methods primarily focus on sample augmentation in spatial dimensions to reduce the shortage of labeled samples. These methods tend to ignore the structural information of objects. In addition, frequency-domain information also supplies another perspective to evaluate information from images, which includes different properties compared to the spatial domain. PURPOSE: In this study, we attempt to answer these two questions: (1) is it helpful to provide structural information of objects in semi-supervised semantic segmentation tasks for medical images? (2) is it more effective to evaluate the segmentation performance in the frequency domain compared to the spatial domain for semi-supervised medical image segmentation? Therefore, we seek to introduce structural and frequency information to improve the performance of semi-supervised semantic segmentation for medical images. METHODS: We present a novel structural tensor loss (STL) to guide feature learning on the spatial domain for semi-supervised semantic segmentation. Specifically, STL utilizes the structural information encoded in the tensors to enforce the consistency of objects across spatial regions, thereby promoting more robust and accurate feature extraction. Additionally, we proposed a frequency-domain alignment loss (FAL) to enable the neural networks to learn frequency-domain information across different augmented samples. It leverages the inherent patterns present in frequency-domain representations to guide the network in capturing and aligning features across diverse augmentation variations, thereby enhancing the model's robustness for the inputting variations. RESULTS: We conduct our experiments on three benchmark datasets, which include MRI (ACDC) for cardiac, CT (Synapse) for abdomen organs, and ultrasound image (BUSI) for breast lesion segmentation. The experimental results demonstrate that our method outperforms state-of-the-art semi-supervised approaches regarding the Dice similarity coefficient. CONCLUSIONS: We find the proposed approach could improve the final performance of the semi-supervised medical image segmentation task. It will help reduce the need for medical image labels. Our code will are available at https://github.com/apple1986/STLFAL.

Bidirectional consistency with temporal-aware for semi-supervised time series classification.

Semi-supervised learning (SSL) has achieved significant success due to its capacity to alleviate annotation dependencies. Most existing SSL methods utilize pseudo-labeling to propagate useful supervised information for training unlabeled data. However, these methods ignore learning temporal representations, making it challenging to obtain a well-separable feature space for modeling explicit class boundaries. In this work, we propose a semi-supervised Time Series classification framework via Bidirectional Consistency with Temporal-aware (TS-BCT), which regularizes the feature space distribution by learning temporal representations through pseudo-label-guided contrastive learning. Specifically, TS-BCT utilizes time-specific augmentation to transform the entire raw time series into two distinct views, avoiding sampling bias. The pseudo-labels for each view, generated through confidence estimation in the feature space, are then employed to propagate class-related information into unlabeled samples. Subsequently, we introduce a temporal-aware contrastive learning module that learns discriminative temporal-invariant representations. Finally, we design a bidirectional consistency strategy by incorporating pseudo-labels from two distinct views into temporal-aware contrastive learning to construct a class-related contrastive pattern. This strategy enables the model to learn well-separated feature spaces, making class boundaries more discriminative. Extensive experimental results on real-world datasets demonstrate the effectiveness of TS-BCT compared to baselines.

A home-based hand rehabilitation platform for hemiplegic patients after stroke: A feasibility study.

Background: Patients with stroke often experience weakened upper limbs, making daily tasks difficult to perform. Although rehabilitation devices are available, patients often relapse post-discharge due to insufficient practice. We present a home-based hand telerehabilitation intervention using the iManus™ platform comprising a sensorized glove, a mobile app for the patients, and a therapist portal for monitoring patient progress. Objectives: This research aimed to examine the feasibility, safety, and effectiveness of a home-based telerehabilitation intervention in improving hand function for individuals with mild stroke. A qualitative approach was also used to explore users' experiences, perceived benefits, and challenges associated with using the platform in a home setting. Methods: In this single-case study, we delivered a hand telerehabilitation intervention to a chronic stroke patient with impaired hand function using the iManus™ platform. The intervention consisted of 40 home sessions over eight weeks. We assessed feasibility through user adherence and feedback obtained using a System Usability Scale (SUS) and a semi-structured interview with the participant and their informal caregiver. Safety was evaluated by monitoring pain levels using the Visual Analog Scale (VAS), and efficacy was determined by observing the changes in the fingers' range of motion using the iManus™ platform and clinical outcomes measures, namely the Fugl-Meyer Assessment (FMA) and Jebsen Taylor Hand Function Test (JTHFT). Results: Our participant completed all the assigned sessions, with each averaging 20 min. Usability scored 77.5 out of 100 on the SUS. User feedback from the interviews revealed improved mobility and control over therapy as benefits, indicating room for improvement in the intervention's adaptability and functionality. During the intervention, the participant noted no pain increase, and the telerehabilitation platform recorded range of motion improvements for all finger and wrist joints, excluding wrist extension. The FMA scores were 43 at T0, 53 at T1, and 56 at T2, while the JTHFT scores were 223 at T0, 188 at T1, and 240 at T2. Conclusions: This single case study demonstrated the preliminary feasibility, safety, and efficacy of a novel home-based hand intervention for stroke survivors. The participant showed improved hand functions, good adherence to the program, and reported satisfaction with the intervention. However, these results are based on a single-case study, and further large-scale studies are needed before any generalization is recommended.

Improved region proposal network for enhanced few-shot object detection.

Despite significant success of deep learning in object detection tasks, the standard training of deep neural networks requires access to a substantial quantity of annotated images across all classes. Data annotation is an arduous and time-consuming endeavor, particularly when dealing with infrequent objects. Few-shot object detection (FSOD) methods have emerged as a solution to the limitations of classic object detection approaches based on deep learning. FSOD methods demonstrate remarkable performance by achieving robust object detection using a significantly smaller amount of training data. A challenge for FSOD is that instances from novel classes that do not belong to the fixed set of training classes appear in the background and the base model may pick them up as potential objects. These objects behave similarly to label noise because they are classified as one of the training dataset classes, leading to FSOD performance degradation. We develop a semi-supervised algorithm to detect and then utilize these unlabeled novel objects as positive samples during the FSOD training stage to improve FSOD performance. Specifically, we develop a hierarchical ternary classification region proposal network (HTRPN) to localize the potential unlabeled novel objects and assign them new objectness labels to distinguish these objects from the base training dataset classes. Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception ability of the object detection model for large objects. We test our approach and COCO and PASCAL VOC baselines that are commonly used in FSOD literature. Our experimental results indicate that our method is effective and outperforms the existing state-of-the-art (SOTA) FSOD methods. Our implementation is provided as a supplement to support reproducibility of the results https://github.com/zshanggu/HTRPN.1.

Semi-supervised machine learning method for predicting homogeneous ancestry groups to assess Hardy-Weinberg equilibrium in diverse whole-genome sequencing studies.

Large-scale, multi-ethnic whole-genome sequencing (WGS) studies, such as the National Human Genome Research Institute Genome Sequencing Program's Centers for Common Disease Genomics (CCDG), play an important role in increasing diversity for genetic research. Before performing association analyses, assessing Hardy-Weinberg equilibrium (HWE) is a crucial step in quality control procedures to remove low quality variants and ensure valid downstream analyses. Diverse WGS studies contain ancestrally heterogeneous samples; however, commonly used HWE methods assume that the samples are homogeneous. Therefore, directly applying these to the whole dataset can yield statistically invalid results. To account for this heterogeneity, HWE can be tested on subsets of samples that have genetically homogeneous ancestries and the results aggregated at each variant. To facilitate valid HWE subset testing, we developed a semi-supervised learning approach that predicts homogeneous ancestries based on the genotype. This method provides a convenient tool for estimating HWE in the presence of population structure and missing self-reported race and ethnicities in diverse WGS studies. In addition, assessing HWE within the homogeneous ancestries provides reliable HWE estimates that will directly benefit downstream analyses, including association analyses in WGS studies. We applied our proposed method on the CCDG dataset, predicting homogeneous genetic ancestry groups for 60,545 multi-ethnic WGS samples to assess HWE within each group.

Dual-consistency guidance semi-supervised medical image segmentation with low-level detail feature augmentation.

In deep-learning-based medical image segmentation tasks, semi-supervised learning can greatly reduce the dependence of the model on labeled data. However, existing semi-supervised medical image segmentation methods face the challenges of object boundary ambiguity and a small amount of available data, which limit the application of segmentation models in clinical practice. To solve these problems, we propose a novel semi-supervised medical image segmentation network based on dual-consistency guidance, which can extract reliable semantic information from unlabeled data over a large spatial and dimensional range in a simple and effective manner. This serves to improve the contribution of unlabeled data to the model accuracy. Specifically, we construct a split weak and strong consistency constraint strategy to capture data-level and feature-level consistencies from unlabeled data to improve the learning efficiency of the model. Furthermore, we design a simple multi-scale low-level detail feature enhancement module to improve the extraction of low-level detail contextual information, which is crucial to accurately locate object contours and avoid omitting small objects in semi-supervised medical image dense prediction tasks. Quantitative and qualitative evaluations on six challenging datasets demonstrate that our model outperforms other semi-supervised segmentation models in terms of segmentation accuracy and presents advantages in terms of generalizability. Code is available at https://github.com/0Jmyy0/SSMIS-DC.

JOSA: Joint surface-based registration and atlas construction of brain geometry and function.

Surface-based cortical registration is an important topic in medical image analysis and facilitates many downstream applications. Current approaches for cortical registration are mainly driven by geometric features, such as sulcal depth and curvature, and often assume that registration of folding patterns leads to alignment of brain function. However, functional variability of anatomically corresponding areas across subjects has been widely reported, particularly in higher-order cognitive areas. In this work, we present JOSA, a novel cortical registration framework that jointly models the mismatch between geometry and function while simultaneously learning an unbiased population-specific atlas. Using a semi-supervised training strategy, JOSA achieves superior registration performance in both geometry and function to the state-of-the-art methods but without requiring functional data at inference. This learning framework can be extended to any auxiliary data to guide spherical registration that is available during training but is difficult or impossible to obtain during inference, such as parcellations, architectonic identity, transcriptomic information, and molecular profiles. By recognizing the mismatch between geometry and function, JOSA provides new insights into the future development of registration methods using joint analysis of brain structure and function.

Semi-Supervised Semantic Image Segmentation by Deep Diffusion Models and Generative Adversarial Networks.

Typically, deep learning models for image segmentation tasks are trained using large datasets of images annotated at the pixel level, which can be expensive and highly time-consuming. A way to reduce the amount of annotated images required for training is to adopt a semi-supervised approach. In this regard, generative deep learning models, concretely Generative Adversarial Networks (GANs), have been adapted to semi-supervised training of segmentation tasks. This work proposes MaskGDM, a deep learning architecture combining some ideas from EditGAN, a GAN that jointly models images and their segmentations, together with a generative diffusion model. With careful integration, we find that using a generative diffusion model can improve EditGAN performance results in multiple segmentation datasets, both multi-class and with binary labels. According to the quantitative results obtained, the proposed model improves multi-class image segmentation when compared to the EditGAN and DatasetGAN models, respectively, by [Formula: see text] and [Formula: see text]. Moreover, using the ISIC dataset, our proposal improves the results from other models by up to [Formula: see text] for the binary image segmentation approach.

Dual-branch Transformer for semi-supervised medical image segmentation.

PURPOSE: In recent years, the use of deep learning for medical image segmentation has become a popular trend, but its development also faces some challenges. Firstly, due to the specialized nature of medical data, precise annotation is time-consuming and labor-intensive. Training neural networks effectively with limited labeled data is a significant challenge in medical image analysis. Secondly, convolutional neural networks commonly used for medical image segmentation research often focus on local features in images. However, the recognition of complex anatomical structures or irregular lesions often requires the assistance of both local and global information, which has led to a bottleneck in its development. Addressing these two issues, in this paper, we propose a novel network architecture. METHODS: We integrate a shift window mechanism to learn more comprehensive semantic information and employ a semi-supervised learning strategy by incorporating a flexible amount of unlabeled data. Specifically, a typical U-shaped encoder-decoder structure is applied to obtain rich feature maps. Each encoder is designed as a dual-branch structure, containing Swin modules equipped with windows of different size to capture features of multiple scales. To effectively utilize unlabeled data, a level set function is introduced to establish consistency between the function regression and pixel classification. RESULTS: We conducted experiments on the COVID-19 CT dataset and DRIVE dataset and compared our approach with various semi-supervised and fully supervised learning models. On the COVID-19 CT dataset, we achieved a segmentation accuracy of up to 74.56%. Our segmentation accuracy on the DRIVE dataset was 79.79%. CONCLUSIONS: The results demonstrate the outstanding performance of our method on several commonly used evaluation metrics. The high segmentation accuracy of our model demonstrates that utilizing Swin modules with different window sizes can enhance the feature extraction capability of the model, and the level set function can enable semi-supervised models to more effectively utilize unlabeled data. This provides meaningful insights for the application of deep learning in medical image segmentation. Our code will be released once the manuscript is accepted for publication.