Semi-supervised Learning Strategy Research Articles

Artificial intelligence and machine learning in optics: tutorial

Across the spectrum of scientific inquiry and practical applications, the emergence of artificial intelligence (AI) and machine learning (ML) has comprehensively revolutionized problem-solving methodologies. This tutorial explores key aspects of AI/ML and their remarkable role in augmenting the capabilities of optics and photonics technologies. Beginning with fundamental definitions and paradigms, the tutorial progresses to classical machine learning algorithms, with examples employing support vector machines and random forests. Extensive discussion of deep learning encompasses the backpropagation algorithm and artificial neural networks, with examples demonstrating the applications of dense and convolutional neural networks. Data augmentation and transfer learning are examined next as effective strategies for handling scenarios with limited datasets. Finally, the necessity of alleviating the burden of data collection and labeling is discussed, motivating the investigation of unsupervised and semi-supervised learning strategies as well as the utilization of reinforcement learning. By providing a structured exploration of AI/ML techniques, this tutorial equips researchers with the essential tools to begin leveraging AI’s transformative potential within the expansive realm of optics and photonics.

Wind turbine blade defect detection with a semi-supervised deep learning framework

To increase the economic efficiency of utilizing wind turbines, an enhanced object detection model based on the small version of the fifth generation of the You Look Only Once algorithm (YOLOv5s) is proposed in this paper, which can effectively detect cracks on the surface of wind turbine blades using images captured by unmanned aerial vehicles. To improve the extraction of light-colored and low-definition images, Omni-Dimensional Dynamic Convolution (ODConv) and Dynamic Head Module components (DyHead) are introduced in the proposed method, while a lightweight Group Shuffle convolution (GSConv) module is utilized to accelerate the model inference speed without sacrificing detection performance. Furthermore, a semi-supervised learning strategy is developed to reduce human labors in annotating images. Extensive experiments demonstrate that the proposed model outperforms the original YOLOv5s in terms of both detection accuracy and inference speed. Besides, the proposed model has good performance against state-of-the-art methods. Furthermore, the experiments validate the efficacy of the proposed semi-supervised learning strategy.

Real-time coronary artery segmentation in CAG images: A semi-supervised deep learning strategy

BackgroundWhen treating patients with coronary artery disease and concurrent renal concerns, we often encounter a conundrum: how to achieve a clearer view of vascular details while minimizing the contrast and radiation doses during percutaneous coronary intervention (PCI). Our goal is to use deep learning (DL) to create a real-time roadmap for guiding PCI. To this end, segmentation, a critical first step, paves the way for detailed vascular analysis. Unlike traditional supervised learning, which demands extensive labeling time and manpower, our strategy leans toward semi-supervised learning. This method not only economizes on labeling efforts but also aims at reducing contrast and radiation exposure. Methods and resultsCAG data sourced from eight tertiary centers in Taiwan, comprising 500 labeled and 8952 unlabeled images. Employing 400 labels for training and reserving 100 for validation, we built a U-Net based network within a teacher-student architecture. The initial teacher model was updated with 8952 unlabeled images inputted, employing a quality control strategy involving consistency regularization and RandAugment. The optimized teacher model produced pseudo-labels for label expansion, which were then utilized to train the final student model. We attained an average dice similarity coefficient of 0.9003 for segmentation, outperforming supervised learning methods with the same label count. Even with only 5 % labels for semi-supervised training, the results surpassed a supervised method with 100 % labels inputted. This semi-supervised approach's advantage extends beyond single-frame prediction, yielding consistently superior results in continuous angiography films. ConclusionsHigh labeling cost hinders DL training. Semi-supervised learning, quality control, and pseudo-label expansion can overcome this. DL-assisted segmentation potentially provides a real-time PCI roadmap and further diminishes radiation and contrast doses.

CABnet: A channel attention dual adversarial balancing network for multimodal image fusion

Infrared and visible image fusion aims to generate informative images by leveraging the distinctive strengths of infrared and visible modalities. These fused images play a crucial role in subsequent downstream tasks, including object detection, recognition, and segmentation. However, complementary information is often difficult to extract. Existing generative adversarial network-based methods generate fused images by modifying the distribution of source images' features to preserve instances and texture details in both infrared and visible images. Nevertheless, these approaches may result in a degradation of the fused image quality when the original image quality is low. Considering the balance of information from different modalities can improve the quality of the fused image. Hence, we introduce CABnet, a Channel Attention dual adversarial Balancing network. CABnet incorporates a channel attention mechanism to capture crucial channel features, thereby, enhancing complementary information. It also employs an adaptive factor to control the mixing distribution of infrared and visible images, which ensures the preservation of instances and texture details during the adversarial process. To enhance efficiency and reduce reliance on manual labeling, our training process adopts a semi-supervised learning strategy. Through qualitative and quantitative experiments across multiple datasets, CABnet surpasses existing state-of-the-art methods in fusion performance, notably achieving a 51.3% enhancement in signal to noise ratio and a 13.4% improvement in standard deviation.

ASSL-HGAT: Active semi-supervised learning empowered heterogeneous graph attention network

Recently, heterogeneous graph attention network (HGAT) has been widely applied to various machine learning tasks and achieved remarkable results with sufficient labeled data. However, it is noteworthy that in many tasks, labeled data is scarce and the data labeling process is expensive. To that end, this paper presents a novel framework for learning from data with limited labels by organically integrating active learning (AL) and semi-supervised learning (SSL) into heterogeneous graph network. Our framework consists of three components: heterogeneous information network (HIN), HGAT and active semi-supervised learning strategy (ASSL). The adjustable HIN is first constructed by fusing multi-modal features. Then the HGAT is used to encode HIN and the double-layer attention mechanism can mitigate noises during information fusion. The ASSL is further designed to enrich the high-quality labeled training data for model train. Samples selected by uncertainty-aware AL and samples labeled by pseudo-label selection based SSL are finally mixed to iteratively train the ASSL-HGAT framework. Experimental results prove that ASSL-HGAT surpasses the compared state-of-the-art methods on five representative semi-supervised benchmark datasets under the same experimental settings.

Deep learning for head and neck semi-supervised semantic segmentation

Objective. Radiation therapy (RT) represents a prevalent therapeutic modality for head and neck (H&N) cancer. A crucial phase in RT planning involves the precise delineation of organs-at-risks (OARs), employing computed tomography (CT) scans. Nevertheless, the manual delineation of OARs is a labor-intensive process, necessitating individual scrutiny of each CT image slice, not to mention that a standard CT scan comprises hundreds of such slices. Furthermore, there is a significant domain shift between different institutions’ H&N data, which makes traditional semi-supervised learning strategies susceptible to confirmation bias. Therefore, effectively using unlabeled datasets to support annotated datasets for model training has become a critical issue for preventing domain shift and confirmation bias. Approach. In this work, we proposed an innovative cross-domain orthogon-based-perspective consistency (CD-OPC) strategy within a two-branch collaborative training framework, which compels the two sub-networks to acquire valuable features from unrelated perspectives. More specifically, a novel generative pretext task cross-domain prediction (CDP) was designed for learning inherent properties of CT images. Then this prior knowledge was utilized to promote the independent learning of distinct features by the two sub-networks from identical inputs, thereby enhancing the perceptual capabilities of the sub-networks through orthogon-based pseudo-labeling knowledge transfer. Main results. Our CD-OPC model was trained on H&N datasets from nine different institutions, and validated on the four local intuitions’ H&N datasets. Among all datasets CD-OPC achieved more advanced performance than other semi-supervised semantic segmentation algorithms. Significance. The CD-OPC method successfully mitigates domain shift and prevents network collapse. In addition, it enhances the network’s perceptual abilities, and generates more reliable predictions, thereby further addressing the confirmation bias issue.

A review of research and development of semi-supervised learning strategies for medical image processing

Accurate and robust segmentation of organs or lesions from medical images plays a vital role in many clinical applications such as diagnosis and treatment planning. With the massive increase in labeled data, deep learning has achieved great success in image segmentation. However, for medical images, the acquisition of labeled data is usually expensive because generating accurate annotations requires expertise and time, especially in 3D images. To reduce the cost of labeling, many approaches have been proposed in recent years to develop a high-performance medical image segmentation model to reduce the labeling data. For example, combining user interaction with deep neural networks to interactively perform image segmentation can reduce the labeling effort. Self-supervised learning methods utilize unlabeled data to train the model in a supervised manner, learn the basics and then perform knowledge transfer. Semi-supervised learning frameworks learn directly from a limited amount of labeled data and a large amount of unlabeled data to get high quality segmentation results. Weakly supervised learning approaches learn image segmentation from borders, graffiti, or image-level labels instead of using pixel-level labeling, which reduces the burden of labeling. However, the performance of weakly supervised learning and self-supervised learning is still limited on medical image segmentation tasks, especially on 3D medical images. In addition to this, a small amount of labeled data and a large amount of unlabeled data are more in line with actual clinical scenarios. Therefore, semi-supervised learning strategies become very important in the field of medical image processing.

Blocky Impedance Inversion of Seismic Data Based on Semi-Supervised Learning Scheme

Blocky Impedance Inversion of Seismic Data Based on Semi-Supervised Learning Scheme

Multi-Task Credible Pseudo-Label Learning for Semi-Supervised Crowd Counting.

As a widely used semi-supervised learning strategy, self-training generates pseudo-labels to alleviate the labor-intensive and time-consuming annotation problems in crowd counting while boosting the model performance with limited labeled data and massive unlabeled data. However, the noise in the pseudo-labels of the density maps greatly hinders the performance of semi-supervised crowd counting. Although auxiliary tasks, e.g., binary segmentation, are utilized to help improve the feature representation learning ability, they are isolated from the main task, i.e., density map regression and the multi-task relationships are totally ignored. To address the above issues, we develop a multi-task credible pseudo-label learning (MTCP) framework for crowd counting, consisting of three multi-task branches, i.e., density regression as the main task, and binary segmentation and confidence prediction as the auxiliary tasks. Multi-task learning is conducted on the labeled data by sharing the same feature extractor for all three tasks and taking multi-task relations into account. To reduce epistemic uncertainty, the labeled data are further expanded, by trimming the labeled data according to the predicted confidence map for low-confidence regions, which can be regarded as an effective data augmentation strategy. For unlabeled data, compared with the existing works that only use the pseudo-labels of binary segmentation, we generate credible pseudo-labels of density maps directly, which can reduce the noise in pseudo-labels and therefore decrease aleatoric uncertainty. Extensive comparisons on four crowd-counting datasets demonstrate the superiority of our proposed model over the competing methods. The code is available at: https://github.com/ljq2000/MTCP.

Retinal Vessel Segmentation by A Transformer-U-Net Hybrid Model with Dual-Path Decoder.

This paper introduces an effective and efficient framework for retinal vessel segmentation. First, we design a Transformer-CNN hybrid model in which a Transformer module is inserted inside the U-Net to capture long-range interactions. Second, we design a dual-path decoder in the U-Net framework, which contains two decoding paths for multi-task outputs. Specifically, we train the extra decoder to predict vessel skeletons as an auxiliary task which helps the model learn balanced features. The proposed framework, named as TSNet, not only achieves good performances in a fully supervised learning manner but also enables a rough skeleton annotation process. The annotators only need to roughly delineate vessel skeletons instead of giving precise pixel-wise vessel annotations. To learn with rough skeleton annotations plus a few precise vessel annotations, we propose a skeleton semi-supervised learning scheme. We adopt a mean teacher model to produce pseudo vessel annotations and conduct annotation correction for roughly labeled skeletons annotations. This learning scheme can achieve promising performance with fewer annotation efforts. We have evaluated TSNet through extensive experiments on five benchmarking datasets. Experimental results show that TSNet yields state-of-the-art performances on retinal vessel segmentation and provides an efficient training scheme in practice.

From Segmentation to Classification: A Deep Learning Scheme for Sintered Surface Images Processing

Effectively managing the quality of iron ore is critical to iron and steel metallurgy. Although quality inspection is crucial, the perspective of sintered surface identification remains largely unexplored. To bridge this gap, we propose a deep learning scheme for mining the necessary information in sintered images processing to replace manual labor and realize intelligent inspection, consisting of segmentation and classification. Specifically, we first employ a DeepLabv3+ semantic segmentation algorithm to extract the effective material surface features. Unlike the original model, which includes a high number of computational parameters, we use SqueezeNet as the backbone to improve model efficiency. Based on the initial annotation of the processed images, the sintered surface dataset is constructed. Then, considering the scarcity of labeled data, a semi-supervised deep learning scheme for sintered surface classification is developed, which is based on pseudo-labels. Experiments show that the improved semantic segmentation model can effectively segment the sintered surface, achieving 98.01% segmentation accuracy with only a 5.71 MB size. In addition, the effectiveness of the adopted semi-supervised learning classification method based on pseudo-labels is validated in six state-of-the-art models. Among them, the ResNet-101 model has the best classification performance, with 94.73% accuracy for the semi-supervised strategy while only using 30% labeled data, which is an improvement of 1.66% compared with the fully supervised strategy.

One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis.

Convolutional neural networks (CNNs) are a promising technique for automated glaucoma diagnosis from images of the fundus, and these images are routinely acquired as part of an ophthalmic exam. Nevertheless, CNNs typically require a large amount of well-labeled data for training, which may not be available in many biomedical image classification applications, especially when diseases are rare and where labeling by experts is costly. This article makes two contributions to address this issue: 1) It extends the conventional Siamese network and introduces a training method for low-shot learning when labeled data are limited and imbalanced, and 2) it introduces a novel semi-supervised learning strategy that uses additional unlabeled training data to achieve greater accuracy. Our proposed multi-task Siamese network (MTSN) can employ any backbone CNN, and we demonstrate with four backbone CNNs that its accuracy with limited training data approaches the accuracy of backbone CNNs trained with a dataset that is 50 times larger. We also introduce One-Vote Veto (OVV) self-training, a semi-supervised learning strategy that is designed specifically for MTSNs. By taking both self-predictions and contrastive predictions of the unlabeled training data into account, OVV self-training provides additional pseudo labels for fine-tuning a pre-trained MTSN. Using a large (imbalanced) dataset with 66,715 fundus photographs acquired over 15 years, extensive experimental results demonstrate the effectiveness of low-shot learning with MTSN and semi-supervised learning with OVV self-training. Three additional, smaller clinical datasets of fundus images acquired under different conditions (cameras, instruments, locations, populations) are used to demonstrate the generalizability of the proposed methods.

Joint localization and classification of breast masses on ultrasound images using an auxiliary attention-based framework.

Multi-task learning (MTL) methods have been extensively employed for joint localization and classification of breast lesions on ultrasound images to assist in cancer diagnosis and personalized treatment. One typical paradigm in MTL is a shared trunk network architecture. However, such a model design may suffer information-sharing conflicts and only achieve suboptimal performance for individual tasks. Additionally, the model relies on fully-supervised learning methodologies, imposing heavy burdens on data annotation. In this study, we propose a novel joint localization and classification model based on attention mechanisms and a sequential semi-supervised learning strategy to address these challenges. Our proposed framework offers three primary advantages. First, a lesion-aware network with multiple attention modules is designed to improve model performance on lesion localization. An attention-based classifier explicitly establishes correlations between the two tasks, alleviating information-sharing conflicts while leveraging location information to assist in classification. Second, a two-stage sequential semi-supervised learning strategy is designed for model training to achieve optimal performance on both tasks and substantially reduces the need for data annotation. Third, the asymmetric and modular model architecture allows for the flexible interchangeability of individual components, rendering the model adaptable to various applications. Experimental results from two different breast ultrasound image datasets under varied conditions have demonstrated the effectiveness of the proposed method. Furthermore, we conduct comprehensive investigations into the impacts of various factors on model performance, gaining in-depth insights into the mechanism of our proposed framework. The code is available at https://github.com/comp-imaging-sci/lanet-bus.git.

Cost-effective identification of the field maturity of tobacco leaves based on deep semi-supervised active learning and smartphone photograph

As a key technology for tobacco leaf harvesting, automatic identification of the field maturity of tobacco leaves is an important issue in the tobacco industry. For years, researchers have been exploring machine learning methods to perform the identification task, with traditional supervised learning (SL) schemes being studied in depth. However, the actual use of an SL algorithm is always costly and cumbersome, as it requires a large amount of labor and time to collect and label enough tobacco leaf samples. Therefore, a cost-effective algorithm solution is desired by the industry. To this end, we investigate the efficacy and efficiency of semi-supervised learning (SSL) scheme for this task, attempting to significantly reduce the labeling cost and provide a flexible way to control the cost. Considering the advantages of smartphones in terms of availability and economy, we use smartphone photography as an image acquisition tool, thereby building a tobacco leaf maturity dataset containing more than 7000 tobacco leaf images of three field maturity categories (unripe, ripe and overripe) of three stem positions (bottom, middle and top). According to the fact that the maturity of the unripe, ripe and overripe leaves increases sequentially, we propose a maturity structure constraint (MSC) to make the identification model converge to a confident space and be generalizable. Furthermore, we propose a sample selection method based on self-supervised representation learning, which can effectively select high-quality samples for the identification network. Finally, we design an SSL algorithm framework called maturity structure constraint based semi-supervised learning (MSC-SSL) for the identification task. Experimental results show that our SSL framework is capable to significantly reduce the sample usage and improve the identification accuracy. It achieves the accuracies of 91.92% (bottom position/with 33.16% training samples), 87.06% (middle position/with 27.57% training samples) and 87.64% (top position/with 28.02% training samples) when auto stopped, as compared to the SSL benchmarks of 87.37% and 90.40%, 83.53% and 85.10%, 81.65% and 84.64%, respectively. Furthermore, our method can match or exceed the accuracy of the SL scheme using only about 25% of the labeled samples required by the SL scheme.

A Client-Cloud-Chain Data Annotation System of Internet of Things for Semi-Supervised Missing Data

With continuous progress in science and technology, a large amount of data are produced in all fields of the world at anytime and anywhere. These data are unmarked and lack marking information, while manual marking is time-consuming and laborious. Herein, this paper introduces a distributed semi-supervised labeling framework. This framework addresses the issue of missing data by proposing an attribute-filling method based on subspace learning. Furthermore, this paper presents a distributed semi-supervised learning strategy that trains sub-models (private models) within each sub-system. Finally, this paper develops a distributed graph convolutional neural network fusion technique with enhanced interpretability grounded on the attention mechanism. This paper assigns weights of importance to the edges of each layer in the graph neural network based on sub-models and public data, thereby enabling distributed and interpretable graph convolutional attention. Extensive experimentation using public datasets demonstrates the superiority of the proposed scheme over other state-of-the-art baselines, achieving a reduction in loss of 50% compared to the original approach.

CISO: Co-iteration semi-supervised learning for visual object detection

Semi-supervised learning offers a solution to the high cost and limited availability of manually labeled samples in supervised learning. In semi-supervised visual object detection, the use of unlabeled data can significantly enhance the performance of deep learning models. In this paper, we introduce an end-to-end framework, named CISO (Co-Iteration Semi-Supervised Learning for Object Detection), which integrates a knowledge distillation approach and a collaborative, iterative semi-supervised learning strategy. To maximize the utilization of pseudo-label data and address the scarcity of pseudo-label data due to high threshold settings, we propose a mean iteration approach where all unlabeled data is applied to each training iteration. Pseudo-label data with high confidence is extracted based on an ever-changing threshold (average intersection over union of all pseudo-labeled data). This strategy not only ensures the accuracy of the pseudo-label but also optimizes the use of unlabeled data. Subsequently, we apply a weak-strong data augmentation strategy to update the model. Lastly, we evaluate CISO using Swin Transformer model and conduct comprehensive experiments on MS-COCO. Our framework showcases impressive results, outperforms the state-of-the-art methods by 2.16 mAP and 1.54 mAP with 10% and 5% labeled data, respectively.

Semisupervised Boundary Detection for Aluminum Grains Combined With Transfer Learning and Region Growing.

In the manufacturing process of aluminum alloy, the size, distribution, and shape of microscopic grains indicate the mechanical characteristics and product quality. However, for metallographic images that can reveal microstructures, the cost of expert labeling at pixel level is high. To solve the problem, we propose a semisupervised learning strategy for grain boundary detection with a few labeled images and abundant unlabeled samples. To expand the helpful information, transfer learning and rule-based region growing are considered. Specifically, a deep network used for extracting multiscale features is designed. With constant training, through a few labeled metallographic images and abundant transferred natural images, pseudo annotations are generated gradually for unlabeled metallographic images iteratively by feature similarity and boundary region growing. The increased unlabeled samples with their pseudo annotations would be involved in the following training process in semisupervised self-training mode to improve the generalization ability of model, together with the domain adaptation block. In experiments, the proposed two methods named semiricher convolutional features-generative adversarial networks (SemiRCF-GAN) and semiricher convolutional features-maximum mean discrepancy (SemiRCF-MMD) can effectively detect grain boundaries with only one labeled metallographic image, and achieve F1 scores of 0.73 and 0.72, respectively, which surpass typical methods.

Online semi-supervised learning for motor imagery EEG classification

ObjectiveTime-consuming data labeling in brain-computer interfaces (BCIs) raises many problems such as mental fatigue and is one key factor that hinders the real-world adoption of motor imagery (MI)-based BCIs. An alternative approach is to integrate readily available, as well as informative, unlabeled data online, whereas this approach is less investigated. ApproachWe proposed an online semi-supervised learning scheme to improve the classification performance of MI-based BCI. This scheme uses regularized weighted online sequential extreme learning machine (RWOS-ELM) as the base classifier and updates its model parameters with incoming balanced data chunk-by-chunk. In the initial stage, we designed a technique that combines the synthetic minority oversampling with the edited nearest neighbor rule for data augmentation to construct more discriminative initial classifiers. When used online, the incoming chunk of data is first pseudo-labeled by RWOS-ELM as well as an auxiliary classifier, and then balanced again by the above-mentioned technique. Initial classifiers are further updated based on these class-balanced data. Main resultsOffline experimental results on two publicly available MI datasets demonstrate the superiority of the proposed scheme over its counterparts. Further online experiments on six subjects show that their BCI performance gradually improved by learning from incoming unlabeled data. SignificanceOur proposed online semi-supervised learning scheme has higher computation and memory usage efficiency, which is promising for online MI-based BCIs, especially in the case of insufficient labeled training data.

Can Glaucoma Suspect Data Help to Improve the Performance of Glaucoma Diagnosis?

The presence of imbalanced datasets in medical applications can negatively affect deep learning methods. This study aims to investigate how the performance of convolutional neural networks (CNNs) for glaucoma diagnosis can be improved by addressing imbalanced learning issues through utilizing glaucoma suspect samples, which are often excluded from studies because they are a mixture of healthy and preperimetric glaucomatous eyes, in a semi-supervised learning approach. A baseline 3D CNN was developed and trained on a real-world glaucoma dataset, which is naturally imbalanced (like many other real-world medical datasets). Then, three methods, including reweighting samples, data resampling to form balanced batches, and semi-supervised learning on glaucoma suspect data were applied to practically assess their impacts on the performances of the trained methods. The proposed method achieved a mean accuracy of 95.24%, an F1 score of 97.42%, and an area under the curve of receiver operating characteristic (AUC ROC) of 95.64%, whereas the corresponding results for the traditional supervised training using weighted cross-entropy loss were 92.88%, 96.12%, and 92.72%, respectively. The obtained results show statistically significant improvements in all metrics. Exploiting glaucoma suspect eyes in a semi-supervised learning method coupled with resampling can improve glaucoma diagnosis performance by mitigating imbalanced learning issues. Clinical imbalanced datasets may negatively affect medical applications of deep learning. Utilizing data with uncertain diagnosis, such as glaucoma suspects, through a combination of semi-supervised learning and class-imbalanced learning strategies can partially address the problems of having limited data and learning on imbalanced datasets.

A semi-supervised learning-based quality evaluation system for digital chest radiographs.

Digital radiography is the most commonly utilized medical imaging technique worldwide, and the quality of radiographs plays a crucial role in accurate disease diagnosis. Therefore, evaluating the quality of radiographs is an essential step in medical examinations. However, manual evaluation can be time-consuming, labor-intensive, and prone to interobserver differences, making it less reliable. To alleviate the workload of radiographic technologists and enhance the efficiency of radiograph quality evaluation, it is crucial to develop rapid and reliable quality evaluation methods and establish a set of quantitative evaluation standards. To address this, we have proposed a quality evaluation system for digital radiographs that utilizes deep learning techniques to achieve fast and precise evaluation. The evaluation of frontal chest radiograph quality involves assessing patient positioning through semantic segmentation and foreign body detection. For lung, scapula, and clavicle segmentation in digital chest radiographs, a residual connection-based convolutional neural network π-ResUNet, was proposed. Criteria for patient positioning evaluation were established based on the segmentation and manual evaluation results. A convolutional neural network, FasterRCNN, was utilized to detect and localize foreign bodies in digital chest radiographs. To enhance the performance of both neural networks, a semi-supervised learning (SSL) strategy was implemented by incorporating a consistency loss that leverages a large number of unlabeled digital radiographs. We also trained the network using the fully supervised learning (FSL) strategy and compared their performance on the test set. The ChestXRay-14 and object-CXR datasets were used throughout the process. By comparing with the manual annotation, the proposed network, trained using the SSL method, achieved a high Dice similarity coefficient (DSC) of 0.96, 0.88, and 0.88 for lung, scapula, and clavicle segmentation, respectively, outperforming the network trained with the FSL method. In addition, for foreign body detection, the proposed SSL method was superior to the FSL method, achieving an AUC (Area under receiver operating characteristic curve, Area under ROC curve) of 0.90 and an FROC (Free-response ROC) of 0.77 on the test dataset. The experimental results show that our proposed system is well-suited for radiograph quality evaluation, with the semi-supervised learning method further improving the network's performance. The proposed method can evaluate the quality of a chest radiograph from two aspects-patient positioning and foreign body detection-within 1 s, offering a promising tool in radiograph quality evaluation.