ObjectiveTo systematically summarize recent advancements in the application of artificial intelligence (AI) in key components of radiotherapy (RT), explore the integration of technical innovations with clinical practice, and identify current limitations in real-world implementation. MethodsA comprehensive analysis of representative studies from recent years was conducted, focusing on the technical implementation and clinical effectiveness of AI in image reconstruction, automatic delineation of target volumes and organs at risk, intelligent treatment planning, and prediction of RT-related toxicities. Particular attention was given to deep learning models, multimodal data integration, and their roles in enhancing decision-making processes. ResultsAI-based low-dose image enhancement techniques had significantly improved image quality. Automated segmentation methods had increased the efficiency and consistency of contouring. Both knowledge-driven and data-driven planning systems had addressed the limitations of traditional experience-dependent approaches, contributing to higher quality and reproducibility in treatment plans. Additionally, toxicity prediction models that incorporated multimodal data enabled more accurate, personalized risk assessment, supporting safer and more effective individualized RT. ConclusionsRT is a fundamental modality in cancer treatment. However, achieving precise tumor ablation while minimizing damage to surrounding healthy tissues remains a significant challenge. AI has demonstrated considerable value across multiple technical stages of RT, enhancing precision, efficiency, and personalization. Nevertheless, challenges such as limited model generalizability, lack of data standardization, and insufficient clinical validation persist. Future work should emphasize the alignment of algorithmic development with clinical demands to facilitate the standardized, reliable, and practical application of AI in RT.
The segmentation of dental models is a crucial step in computer-aided diagnosis and treatment systems for oral healthcare. To address the issues of poor universality and under-segmentation in tooth segmentation techniques, an intelligent tooth segmentation method combining multiple seed region growth and boundary extension is proposed. This method utilized the distribution characteristics of negative curvature meshes in teeth to obtain new seed points and effectively adapted to the structural differences between the top and sides of teeth through differential region growth. Additionally, the boundaries of the initial segmentation were extended based on geometric features, which was effectively compensated for under-segmentation issues in region growth. Ablation experiments and comparative experiments with current state-of-the-art algorithms demonstrated that the proposed method achieved better segmentation of crowded dental models and exhibited strong algorithm universality, thus possessing the capability to meet the practical segmentation needs in oral healthcare.
Accurate segmentation of pediatric echocardiograms is a challenging task, because significant heart-size changes with age and faster heart rate lead to more blurred boundaries on cardiac ultrasound images compared with adults. To address these problems, a dual decoder network model combining channel attention and scale attention is proposed in this paper. Firstly, an attention-guided decoder with deep supervision strategy is used to obtain attention maps for the ventricular regions. Then, the generated ventricular attention is fed back to multiple layers of the network through skip connections to adjust the feature weights generated by the encoder and highlight the left and right ventricular areas. Finally, a scale attention module and a channel attention module are utilized to enhance the edge features of the left and right ventricles. The experimental results demonstrate that the proposed method in this paper achieves an average Dice coefficient of 90.63% in acquired bilateral ventricular segmentation dataset, which is better than some conventional and state-of-the-art methods in the field of medical image segmentation. More importantly, the method has a more accurate effect in segmenting the edge of the ventricle. The results of this paper can provide a new solution for pediatric echocardiographic bilateral ventricular segmentation and subsequent auxiliary diagnosis of congenital heart disease.
Lung diseases such as lung cancer and COVID-19 seriously endanger human health and life safety, so early screening and diagnosis are particularly important. computed tomography (CT) technology is one of the important ways to screen lung diseases, among which lung parenchyma segmentation based on CT images is the key step in screening lung diseases, and high-quality lung parenchyma segmentation can effectively improve the level of early diagnosis and treatment of lung diseases. Automatic, fast and accurate segmentation of lung parenchyma based on CT images can effectively compensate for the shortcomings of low efficiency and strong subjectivity of manual segmentation, and has become one of the research hotspots in this field. In this paper, the research progress in lung parenchyma segmentation is reviewed based on the related literatures published at domestic and abroad in recent years. The traditional machine learning methods and deep learning methods are compared and analyzed, and the research progress of improving the network structure of deep learning model is emphatically introduced. Some unsolved problems in lung parenchyma segmentation were discussed, and the development prospect was prospected, providing reference for researchers in related fields.
There are some problems in positron emission tomography/ computed tomography (PET/CT) lung images, such as little information of feature pixels in lesion regions, complex and diverse shapes, and blurred boundaries between lesions and surrounding tissues, which lead to inadequate extraction of tumor lesion features by the model. To solve the above problems, this paper proposes a dense interactive feature fusion Mask RCNN (DIF-Mask RCNN) model. Firstly, a feature extraction network with cross-scale backbone and auxiliary structures was designed to extract the features of lesions at different scales. Then, a dense interactive feature enhancement network was designed to enhance the lesion detail information in the deep feature map by interactively fusing the shallowest lesion features with neighboring features and current features in the form of dense connections. Finally, a dense interactive feature fusion feature pyramid network (FPN) network was constructed, and the shallow information was added to the deep features one by one in the bottom-up path with dense connections to further enhance the model’s perception of weak features in the lesion region. The ablation and comparison experiments were conducted on the clinical PET/CT lung image dataset. The results showed that the APdet, APseg, APdet_s and APseg_s indexes of the proposed model were 67.16%, 68.12%, 34.97% and 37.68%, respectively. Compared with Mask RCNN (ResNet50), APdet and APseg indexes increased by 7.11% and 5.14%, respectively. DIF-Mask RCNN model can effectively detect and segment tumor lesions. It provides important reference value and evaluation basis for computer-aided diagnosis of lung cancer.
Fast optic disk localization and boundary segmentation is an important research topic in computer aided diagnosis. This paper proposes a novel method to effectively segment optic disk by using human visual characteristics in analyzing and processing fundus image. After a general analysis of optic disk features in fundus images, the target of interest could be located quickly, and intensity, color and spatial distribution of the disc are used to generate saliency map based on pixel distance. Then the adaptive threshold is used to segment optic disk. Moreover, to reduce the influence of vascular, a rotary scanning method is devised to achieve complete and continuous contour of optic disk boundary. Tests in the public fundus images database Drishti-GS have good performances, which mean that the proposed method is simple and rapid, and it meets the standard of the eye specialists. It is hoped that the method could be conducive to the computer aided diagnosis of eye diseases in the future.
The PET/CT imaging technology combining positron emission tomography (PET) and computed tomography (CT) is the most advanced imaging examination method currently, and is mainly used for tumor screening, differential diagnosis of benign and malignant tumors, staging and grading. This paper proposes a method for breast cancer lesion segmentation based on PET/CT bimodal images, and designs a dual-path U-Net framework, which mainly includes three modules: encoder module, feature fusion module and decoder module. Among them, the encoder module uses traditional convolution for feature extraction of single mode image; The feature fusion module adopts collaborative learning feature fusion technology and uses Transformer to extract the global features of the fusion image; The decoder module mainly uses multi-layer perceptron to achieve lesion segmentation. This experiment uses actual clinical PET/CT data to evaluate the effectiveness of the algorithm. The experimental results show that the accuracy, recall and accuracy of breast cancer lesion segmentation are 95.67%, 97.58% and 96.16%, respectively, which are better than the baseline algorithm. Therefore, it proves the rationality of the single and bimodal feature extraction method combining convolution and Transformer in the experimental design of this article, and provides reference for feature extraction methods for tasks such as multimodal medical image segmentation or classification.
The existing retinal vessels segmentation algorithms have various problems that the end of main vessels are easy to break, and the central macula and the optic disc boundary are likely to be mistakenly segmented. To solve the above problems, a novel retinal vessels segmentation algorithm is proposed in this paper. The algorithm merged together vessels contour information and conditional generative adversarial nets. Firstly, non-uniform light removal and principal component analysis were used to process the fundus images. Therefore, it enhanced the contrast between the blood vessels and the background, and obtained the single-scale gray images with rich feature information. Secondly, the dense blocks integrated with the deep separable convolution with offset and squeeze-and-exception (SE) block were applied to the encoder and decoder to alleviate the gradient disappearance or explosion. Simultaneously, the network focused on the feature information of the learning target. Thirdly, the contour loss function was added to improve the identification ability of the blood vessels information and contour information of the network. Finally, experiments were carried out on the DRIVE and STARE datasets respectively. The value of area under the receiver operating characteristic reached 0.982 5 and 0.987 4, respectively, and the accuracy reached 0.967 7 and 0.975 6, respectively. Experimental results show that the algorithm can accurately distinguish contours and blood vessels, and reduce blood vessel rupture. The algorithm has certain application value in the diagnosis of clinical ophthalmic diseases.
In this paper, we propose a new active contour algorithm, i.e. hierarchical contextual active contour (HCAC), and apply it to automatic liver segmentation from three-dimensional CT (3D-CT) images. HCAC is a learning-based method and can be divided into two stages. At the first stage, i.e. the training stage, given a set of abdominal 3D-CT training images and the corresponding manual liver labels, we tried to establish a mapping between automatic segmentations (in each round) and manual reference segmentations via context features, and obtained a series of self-correcting classifiers. At the second stage, i.e. the segmentation stage, we firstly used the basic active contour to segment the image and subsequently used the contextual active contour (CAC) iteratively, which combines the image information and the current shape model, to improve the segmentation result. The current shape model is produced by the corresponding self-correcting classifier (the input is the previous automatic segmentation result). The proposed method was evaluated on the datasets of MICCAI 2007 liver segmentation challenge. The experimental results showed that we would get more and more accurate segmentation results by the iterative steps and the satisfied results would be obtained after about six rounds of iterations.
The three-dimensional (3D) liver and tumor segmentation of liver computed tomography (CT) has very important clinical value for assisting doctors in diagnosis and prognosis. This paper proposes a tumor 3D conditional generation confrontation segmentation network (T3scGAN) based on conditional generation confrontation network (cGAN), and at the same time, a coarse-to-fine 3D automatic segmentation framework is used to accurately segment liver and tumor area. This paper uses 130 cases in the 2017 Liver and Tumor Segmentation Challenge (LiTS) public data set to train, verify and test the T3scGAN model. Finally, the average Dice coefficients of the validation set and test set segmented in the 3D liver regions were 0.963 and 0.961, respectively, while the average Dice coefficients of the validation set and test set segmented in the 3D tumor regions were 0.819 and 0.796, respectively. Experimental results show that the proposed T3scGAN model can effectively segment the 3D liver and its tumor regions, so it can better assist doctors in the accurate diagnosis and treatment of liver cancer.