GENERALIZING MEDICAL IMAGE SEGMENTATION TASK WITH EFFICIENT DEEP LEARNING MODELS

With the rapid development of science and technology, the application of artificial intelligence (AI) in various fields is constantly expanding, especially in the field of medical imaging [1]. AI technology is suitable to be applied to standardized digital medical image big data based on digital imaging and communications in medicine protocol and picture archiving and communication system. With the integration of AI technology, this field is undergoing profound transformation, not only improving the accuracy and efficiency of diagnosis, but also significantly reducing the workload of doctors [2]. At present, AI is widely used in medical imaging, including risk modeling and stratification, personalized screening, diagnosis (including classification of molecular pathologic subtypes), treatment response prediction, prognosis prediction, image segmentation, and image quality control. AI can help doctors identify and analyze lesions in various medical images, especially in diseases such as lung, breast, and prostate cancer. The research mainly focuses on the identification of benign and malignant, the measurement of risk factors, prognosis judgment and treatment guidance, and it is increasingly being used in the field of psychoradiology [3]. In addition, AI is also focused on reducing image acquisition time and improving data quality. Through deep learning algorithms, AI can optimize imaging parameters, improve imaging quality, and reduce noise and artifacts. This special issue of AI includes seven latest studies, which covers artificial intelligence of disease diagnosis and prediction, imaging technology model construction, image segmentation and quality control. Wang et al. [4] used systematic review to summarize the technical methods, clinical applications and existing problems of artificial intelligence in cerebrovascular diseases, they found that the availability of algorithms, reliability of validation, and consistency of evaluation metrics may facilitate better clinical applicability and acceptance. Zhu et al. [5] proposed a diffusion magnetic diffusion magnetic (dMRI) index reconstruction model based on deep learning methods-qIRR-Net and a training framework based on data enhancement and consistency loss, The reconstruction of dMRI index is realized without the influence of signal inhomogeneity, and the model validity is verified on simulated inhomogeneity data and real ultra-high field data, thus promoting the application of ultra-high field dMRI technology in medicine and clinic. Artificial intelligence-assisted compressed sensing is a deep learning technology based on convolutional neural networks which can reconstruct images with ultra-high resolution and reduce noise. On the premise of ensuring the quality of the image, the collection time of the sequence is greatly shortened. In this special issue, The application of assisted compressed sensing technology in 5T MRI by Zhou et al. [6] significantly reduced MRI scanning time, and ensured image quality and diagnostic accuracy. This innovative study can effectively improve clinical work efficiency. AI technology can play an important role in radiomics, through deep learning models, automatic extraction of a large number of quantitative image features, and combined with patient clinical data, gene expression information, to build high-precision diagnosis and prediction models [7]. Pawan et al. [8]reviewed the research on bone metastasis in prostate cancer from the fields of radiomics, machine learning, and deep learning. They present multiple strategies, including classification/prediction, detection, segmentation, and radiomic methods for evaluating prostate bone metastasis; it provides researchers with systematic learning opportunities for relevant research. The application of artificial intelligence in the field of medical imaging has shown great potential and advantages. From the optimization of intelligent imaging systems to the processing and analysis of complex images, AI technology is pushing medical imaging to new heights. In the future, AI technology will further promote the development of personalized medicine, remote diagnosis, and interdisciplinary integration. Bin Huang: Writing—original draft (equal). Bo Gao: Writing—review and editing (lead). artificial intelligence, deep learning, medical imaging None. Professor Bo Gao is a member of the iRADIOLOGY Editorial Board. To minimize bias, he was excluded from all editorial decision-making related to the acceptance of this article for publication. The remaining author declares no conflict of interest. National Natural Science Foundation of China, Grant/Award Numbers: 81871333, 82260340; Guizhou Province 7th Thousand Innovational and Enterprising Talents, Grant/Award Number: GZQ202007086; 2020 Innovation Group Project of Guizhou Province Educational Commission, Grant/Award Number: KY[2021]017; Guizhou Provincial Science & Technology Projects, Grant/Award Number: ZK[2024] General 194; Guizhou Province Science & Technology Project, Grant/Award Numbers: [2020]4Y159, [2021]430. Not applicable. Not applicable. Data sharing is not applicable to this article as no new data were created or analyzed.

The rapid advancements in medical imaging technologies have significantly enhanced diagnostic accuracy and clinical decision-making in modern healthcare. Image segmentation and deep learning have emerged as transformative tools among these advancements. This article explores the pivotal role of image segmentation and deep learning in medical imaging, detailing their methodologies, applications, challenges, and future directions. Deep learning, particularly Convolutional Neural Networks (CNNs), has revolutionized medical imaging by automating the analysis of complex datasets and improving diagnostic precision. Image segmentation, a fundamental component of medical imaging, allows for delineating specific structures such as organs, tissues, and pathological regions. Together, these technologies have been applied in diverse fields, including oncology, cardiology, neurology, and ophthalmology, enabling applications such as tumor detection, organ segmentation, disease progression monitoring, and treatment planning. However, despite its transformative potential, the integration of deep learning into medical imaging faces several challenges. These include data scarcity, privacy concerns, interpretability issues, and regulatory hurdles. The article discusses various strategies to address these challenges, such as data augmentation, transfer learning, and the development of explainable AI models to ensure transparency and trustworthiness. Evaluation metrics, such as accuracy, sensitivity, specificity, and Dice Similarity Coefficient (DSC), are essential for assessing model performance. Rigorous clinical validation and regulatory approval are crucial to integrating deep learning systems into clinical workflows effectively. Looking ahead, the future of deep learning in medical imaging holds immense promise. Innovations like multimodal imaging, personalized medicine, and AI-driven automation are set to further revolutionize the field, enhancing the efficiency and accuracy of diagnostics. Collaborative efforts between clinicians, researchers, and AI developers will play a vital role in overcoming current limitations and driving progress. This article concludes by emphasizing the transformative potential of deep learning and image segmentation in medical imaging, highlighting their ability to improve diagnostic accuracy, streamline clinical workflows, and ultimately, enhance patient care. By addressing current challenges and continuing to innovate, these technologies are poised to redefine the landscape of medical diagnostics and treatment in the years to come.

In medical images, lesion segmentation is used to locate and isolate abnormal structures. It is an essential part of medical image analysis for precise diagnosis and care. However, obstacles exist in medical image lesion segmentation owing to things like image noise, shape and size fluctuation, and poor image quality. Automated lesion segmentation methods include conventional image processing techniques, deep learning (DL) models and machine learning (ML) algorithms to name a few. Thresholding, region growth, and active contour models are examples of conventional methods, while decision trees, random forests, and support vector machines are examples of ML techniques. DL models particularly convolutional neural networks (CNNs), have shown extraordinary performance in lesion segmentation because to their innate potential to autonomously collect high-level characteristics. The objective of the research is to study lesion segmentation in medical images and explore different methods for accurate and precise diagnosis and care.The research focuses on the obstacles faced in lesion segmentation in medical images, such as image noise, shape and size fluctuation, and poor image quality. The research also highlights the need for evaluation metrics, such as sensitivity, specificity, Dice coefficient, and Hausdorff distance, to assess the performance of lesion segmentation algorithms. Additionally, the research emphasizes the importance of annotated datasets for training and evaluating the performance of segmentation algorithms.

Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning

Focus issue: Artificial intelligence in medical physics.

Deep learning has achieved great success in the field of computer vision, and the precision in image classification and image detection has surpassed humans. Therefore, this paper combines deep learning and medical image segmentation, focusing on how to improve the accuracy and speed of segmentation algorithm of medical exercise rehabilitation image. Aiming at the shortcomings of traditional medical image recognition methods, a medical exercise rehabilitation image segmentation algorithm based on hierarchical features of convolutional neural networks is proposed, this paper calls it as hierarchical features of convolutional neural networks (HFCNN). The algorithm firstly samples the convolution output of multiple layers in the convolutional neural network to a unified scale and combines them to construct a hierarchical feature. This hierarchical feature combines the structural information of objects contained in the shallow layer of the network with the semantic information of objects contained in the deep layers of the network, so it has a strong ability to express. Secondly, the image can be segmented into multiple super pixels by the super pixel segmentation algorithm. The classifier is trained using the hierarchical features of the super pixel, and then the classification result is mapped back to the pixel. Finally, a fully connected conditional random field algorithm including one-potential potential energy and paired potential energy is constructed. The corresponding energy function is used to smooth the classification result of the pixel, and the regional consistency and continuity of the pixel mark are improved. Compared with many classical convolutional neural network algorithms, this algorithm not only accelerates the network convergence speed, shortens the training time, but also significantly improves the accuracy of segmentation algorithm of medical exercise rehabilitation image, showing good practical value.

Deep learning techniques are recently exploited for segmentation of medical images. These deep learning techniques have accomplished state-of-art conduct for automatic medical image segmentation. Image segmentation helps in quantitative and qualitative analysis of the medical images, which leads to diagnosis of various diseases. Manual segmentation of medical images is a laborious task that prevents early diagnosis of diseases. For these particular reasons, automated techniques play a major role in medical image segmentation. The recent research is focused on deep learning algorithms for efficient automatic medical image segmentation. Deep learning algorithms are classified as supervised as well as unsupervised learning. Supervised learning consists of convolutional neural networks (CNNs) and unsupervised learning consists of stacked auto-encoder, restricted Boltzmann’s machine (RBM), and deep belief networks. CNNs comprise convolutional layer, pooling layer, dropout layer, and fully connected layer. The convolutional layer carries out the convolution operation with a set of kernels along with weights and added biases individually creating a new feature map on the input image at each layer. Stacked auto-encoder models are designed by insertion of different layers termed to be auto-encoder layers in the form of stack. These layers take image as an input and extracts different features in the form of feature maps in an unsupervised mode lacking labeled data. It is a model that takes input data, gathers feature representations from this, and then uses these feature representations to restructure output data. According to the literature survey, auto-encoder layers are trained independently after which the full network is used to make a prediction by fine-tuning it using supervised training. The neurons present in deep belief nets are densely connected which helps in rapid and accurate learning of a good set of parameters. RBMs are a type of Markov random fields, consisting of input layer or visible layer and a hidden layer that brings hidden feature representation. There are bidirectional connections between the nodes, so latent feature representation extracted from an input vector and vice versa. This chapter provides an outline on the state of deep learning algorithms for medical image segmentation, highlighting those facets that are frequently useful for brain tumor segmentation. In addition, comparative analysis of the deep learning algorithms is discussed. This concludes that with the different algorithms for segmentation tumor regions from brain MRI images, deep learning has proven to be the most effective in the recent trends.

Medical image segmentation (MIS) and 3D reconstruction are crucial research directions in the field of medical imaging, which is of great significance for disease diagnosis, treatment planning and surgical navigation. In recent years, with the rapid development of Deep Learning (DL) technology, DL has made remarkable progress in the field of medical image processing and has become one of the important methods of MIS and 3D reconstruction. In this paper, the application of DL technologies in MIS and 3D reconstruction is systematically studied and discussed. Firstly, the paper introduces the basic concepts and technical challenges of MIS and 3D reconstruction, including image quality, noise interference and edge detection. Secondly, the paper introduces the data acquisition process in detail, including the medical image data set and data preprocessing method. Then, the paper puts forward the DL model framework based on self-attention mechanism, as well as the loss function and optimizer used in the training process. Then, the model is verified by experiments, and the performance of different models in MIS and 3D reconstruction is analyzed. Finally, the experimental results are comprehensively analyzed, and the application prospect and future development direction of DL in MIS and 3D reconstruction are discussed. The research results of this paper provide important theoretical and practical guidance for improving medical image processing technology and promoting the development and clinical application of medical imaging.

Medical image segmentation is a key technology for image guidance. Therefore, the advantages and disadvantages of image segmentation play an important role in image-guided surgery. Traditional machine learning methods have achieved certain beneficial effects in medical image segmentation, but they have problems such as low classification accuracy and poor robustness. Deep learning theory has good generalizability and feature extraction ability, which provides a new idea for solving medical image segmentation problems. However, deep learning has problems in terms of its application to medical image segmentation: one is that the deep learning network structure cannot be constructed according to medical image characteristics; the other is that the generalizability y of the deep learning model is weak. To address these issues, this paper first adapts a neural network to medical image features by adding cross-layer connections to a traditional convolutional neural network. In addition, an optimized convolutional neural network model is established. The optimized convolutional neural network model can segment medical images using the features of two scales simultaneously. At the same time, to solve the generalizability problem of the deep learning model, an adaptive distribution function is designed according to the position of the hidden layer, and then the activation probability of each layer of neurons is set. This enhances the generalizability of the dropout model, and an adaptive dropout model is proposed. This model better addresses the problem of the weak generalizability of deep learning models. Based on the above ideas, this paper proposes a medical image segmentation algorithm based on an optimized convolutional neural network with adaptive dropout depth calculation. An ultrasonic tomographic image and lumbar CT medical image were separately segmented by the method of this paper. The experimental results show that not only are the segmentation effects of the proposed method improved compared with those of the traditional machine learning and other deep learning methods but also the method has a high adaptive segmentation ability for various medical images. The research work in this paper provides a new perspective for research on medical image segmentation.

Brain Tumor Detection (BTD) using Artificial Intelligence (AI) has gained major attention in the field of medical imaging and diagnostics. AI-based systems, particularly Machine Learning (ML) and Deep Learning (DL) algorithms, offer an advanced and efficient approach to identifying Brain Tumors (BTs) in medical images such as Magnetic Resonance Imaging (MRI) scans. These systems can automatically process and analyze large volumes of imaging data, detecting abnormalities with high accuracy and speed. In this study, the authors proposed 4 ML models (SVM, RF, MLP, and XG-Boost) and 4 DL (Bi-LSTM, Res-Net50, VGG-16, and Inception V3) models. This proposed approach involves data preprocessing step, feature selection, model optimization in a timely manner to improve and maximize prediction of BT. By training AI models on vast datasets, these technologies learn to recognize patterns associated with different types of BTs, including gliomas, meningiomas, and pituitary tumors. By leveraging these algorithms, the research evaluates their performance in terms of accuracy ( ), precision ( ), recall ( ), Specificity ( ) and F1-score ( ). After comparison between the ML and DL model, the proposed DL methods, including Inception V3 achieved highest accuracy (99.04%), precision (98.23%), recall (98.53), (96.73%), and F1-score (97.95%) than the suggested ML models.

Medical image segmentation is a fundamental task in the field of medical imaging, enabling the accurate identification and delineation of structures such as organs, tissues, and lesions within medical images. These segmented regions are essential for diagnostic purposes, treatment planning, and disease monitoring. Over the years, medical image segmentation has evolved significantly, driven by advances in imaging technologies and computational techniques. Traditional methods, such as thresholding, region-growing, and active contours, have been supplemented and, in some cases, replaced by more sophisticated machine learning (ML) and deep learning (DL) approaches. Convolutional neural networks (CNNs) and their variants, including U-Net and Transformer-based models, have shown remarkable success in automating and improving segmentation tasks. This survey paper provides a comprehensive review of the various segmentation techniques, categorizing them into classical and deep learning-based methods. It discusses the strengths, limitations, and challenges of each approach, including issues related to data quality, class imbalance, and the generalizability of models. Furthermore, the paper highlights recent advancements in the field, emerging trends, and future directions for further enhancing segmentation accuracy, robustness, and efficiency in clinical applications. This work aims to serve as a valuable resource for researchers and clinicians looking to understand the current state of medical image segmentation and its potential future developments.

Nowadays, computer-aided decision support systems (CADs) for the analysis of images have been a perennial technique in the medical imaging field. In CADs, deep learning algorithms are widely used to perform tasks like classification, identification of patterns, detection, etc. Deep learning models learn feature representations from images rather than handcrafted features. Hence, deep learning models are quickly becoming the state-of-the-art method to achieve good performances in different computer-aided decision-support systems in medical applications. Similarly, deep learning-based generative models called Generative Adversarial Networks (GANs) have recently been developed as a novel method to produce realistic-looking synthetic data. GANs are used in different domains, including medical imaging generation. The common problems, like class imbalance and a small dataset, in healthcare are well addressed by GANs, and it is a leading area of research. Segmentation, reconstruction, detection, denoising, registration, etc. are the important applications of GANs. So in this work, the successes of deep learning methods in segmentation, classification, cell structure and fracture detection, computer-aided identification, and GANs in synthetic medical image generation, segmentation, reconstruction, detection, denoising, and registration in recent times are reviewed. Lately, the review article concludes by raising research directions for DL models and GANs in medical applications.

In the field of computer vision and medical imaging, the classification is one of the common approaches apply to solve different problems. There are several Deep Learning (DL) models have been proposed in the last few years and applied for classification tasks and shown significantly better performance compared to existing methods. In particular, the DL methods have been applied and achieved state-of-the-art performance for classification, segmentation, and detection tasks in the field of medical imaging. In the field of digital pathology, very large dimensional images are captured with microscopes which are significantly higher in dimension and different (texture, color, etc.) compared to the images are used for analysis in computer vision tasks. As the computational pathology becomes very promising area of research, it is very important to study the impact of different color spaces for pathological image classification problems. In this paper, we have considered six different color spaces including RGB, CIE, HSV, YCbCr, Lab, and HSL for histopathology tissue classification tasks where the Inception Residual Recurrent Convolutional Neural Network (IRRCNN) model is applied. The KIMIA Path960 database is used for evaluating the model in this implementation. The RGB color space shows the highest testing performance for tissue classification task which is around 0. 73% and 1.13% better compared to the performance of Lab and CIE color spaces respectively and this performance is significantly higher than the testing accuracy of the model in others color spaces. In addition, the highest performance for the proposed model is around 0.5 percent better compared to existing methods. This study will provide a clear guidance in advance for implementing classification tasks in digital pathology.I n the field of computer vision and medical imaging, the classification is one of the common approaches apply to solve different problems. There are several Deep Learning (DL) models have been proposed in the last few years and applied for classification tasks and shown significantly better performance compared to existing methods. In particular, the DL methods have been applied and achieved state-of-the-art performance for classification, segmentation, and detection tasks in the field of medical imaging. In the field of digital pathology, very large dimensional images are captured with microscopes which are significantly higher in dimension and different (texture, color, etc.) compared to the images are used for analysis in computer vision tasks. As the computational pathology becomes very promising area of research, it is very important to study the impact of different color spaces for pathological image classification problems. In this paper, we have considered six different color spaces including RGB, CIE, HSV, YCbCr, Lab, and HSL for histopathology tissue classification tasks where the Inception Residual Recurrent Convolutional Neural Network (IRRCNN) model is applied. The KIMIA Path960 database is used for evaluating the model in this implementation. The RGB color space shows the highest testing performance for tissue classification task which is around 0. 73% and 1.13% better compared to the performance of Lab and CIE color spaces respectively and this performance is significantly higher than the testing accuracy of the model in others color spaces. In addition, the highest performance for the proposed model is around 0.5 percent better compared to existing methods. This study will provide a clear guidance in advance for implementing classification tasks in digital pathology.

Medical images are information carriers that visually reflect and record the anatomical structure of the human body, and play an important role in clinical diagnosis, teaching and research, etc. Modern medicine has become increasingly inseparable from the intelligent processing of medical images. In recent years, there have been more and more attempts to apply deep learning theory to medical image segmentation tasks, and it is imperative to explore a simple and efficient deep learning algorithm for medical image segmentation. In this paper, we investigate the segmentation of lung nodule images. We address the above-mentioned problems of medical image segmentation algorithms and conduct research on medical image fusion algorithms based on a hybrid channel-space attention mechanism and medical image segmentation algorithms with a hybrid architecture of Convolutional Neural Networks (CNN) and Visual Transformer. To the problem that medical image segmentation algorithms are difficult to capture long-range feature dependencies, this paper proposes a medical image segmentation model SW-UNet based on a hybrid CNN and Vision Transformer (ViT) framework. Self-attention mechanism and sliding window design of Visual Transformer are used to capture global feature associations and break the perceptual field limitation of convolutional operations due to inductive bias. At the same time, a widened self-attentive vector is used to streamline the number of modules and compress the model size so as to fit the characteristics of a small amount of medical data, which makes the model easy to be overfitted. Experiments on the LUNA16 lung nodule image dataset validate the algorithm and show that the proposed network can achieve efficient medical image segmentation on a lightweight scale. In addition, to validate the migratability of the model, we performed additional validation on other tumor datasets with desirable results. Our research addresses the crucial need for improved medical image segmentation algorithms. By introducing the SW-UNet model, which combines CNN and ViT, we successfully capture long-range feature dependencies and break the perceptual field limitations of traditional convolutional operations. This approach not only enhances the efficiency of medical image segmentation but also maintains model scalability and adaptability to small medical datasets. The positive outcomes on various tumor datasets emphasize the potential migratability and broad applicability of our proposed model in the field of medical image analysis.

Traditional medical image segmentation methods have problems such as low segmentation accuracy and low adaptive ability. Therefore, many scholars have proposed a medical image segmentation method based on deep learning, which has achieved good results in the field of medical image segmentation. However, this type of method has the following problems in the application process: (1) Medical image segmentation target boundary positioning problem. Constrained by factors such as medical image contrast, heterogeneity, and boundary resolution, existing convolution models still cannot accurately locate boundaries. (2) Deep adaptability of deep learning network structure to medical images. Because medical images have more distinct and different feature information than natural images, the current deep learning-based medical segmentation methods have not fully considered this feature. In view of this, this paper proposes a multi-level boundary-aware RUNet segmentation model. The network structure consists of a U-Net-based segmentation network and a multi-level boundary detection network. It can solve the problem of boundary positioning. At the same time, in order to solve the problem of poor adaptability of deep learning network structures to medical images, this paper proposes to introduce a new interactive self-attention module into deep learning models. It can make the feature map get global information, and realize the effective extraction of medical image feature information. It solves the problem of weak matching between the deep learning network structure and medical images. Based on the above ideas, this paper proposes an image segmentation algorithm based on a multi-layer boundary perception-self-attention mechanism deep learning model. This method and other mainstream segmentation algorithms are used to perform experiments on related medical databases. The results show that the proposed method not only improves the segmentation effect significantly compared with traditional machine learning methods, but also improves it to a certain extent compared with other deep learning methods.