Segmentation Algorithm of Medical Exercise Rehabilitation Image Based on HFCNN and IoT

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.

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.

The challenges of rotation, occlusion, and scale change in visual object tracking have been an urgent problem to be solved. In recent years, the online learning ability and discriminative power of convolutional neural network (CNN) features have gained great attention in many computer vision tasks. Previous studies have shown that individual layer CNN features can be used for dealing with specific tracking challenges, such as target accurate positioning, rotation, and deformation. However, tracking with single CNN features is not enough to deal with serious challenges, such as the above-mentioned. To handle this problem, we evaluate the contribution of specific CNN layers features in tracking tasks and present a complementary CNN features tracking framework, which treats tracking procedure as a deep CNN features optimizing. Our tracker does not merely fuse the CNN features but is a semantic level method, which adds a competition mechanism to optimize the target appearance encoding of CNN layers. Therefore, the proposed tracker is robust not only to target location but also to rotation and deformation. We also embed hard negative mining to enhance the discriminative power of the tracking model and use bounding box regression to refine the tracking result. Having compared our tracker performance with other state-of-the-art trackers, the obtained experimental results in a large-scale dataset demonstrate that the effectiveness of our proposed tracker outperforms state-of-the-art ones.

Automated tumor characterization has a prominent role in the computer-aided diagnosis (CAD) system for the human brain. Despite being a well-studied topic, CAD of brain tumors poses severe challenges in some specific aspects. One such challenging problem is the category-based classification of brain tumors among glioma, meningioma, and pituitary tumors using magnetic resonance imaging (MRI) images. The emergence of deep learning and machine learning algorithms have addressed image classification tasks with promising results. But an associated limitation with the medical image classification is the small sizes of medical image databases. This limitation, in turn, limits the availability of medical images for training deep neural networks. To mitigate this challenge, we adopt a combination of convolutional neural network (CNN) features with support vector machine (SVM) for classification of the medical images. The fully automated system is evaluated using Figshare open dataset containing MRI images for the three types of brain tumors. CNN is designed to extract features from brain MRI images. For enhanced performance, a multiclass SVM is used with CNN features. Testing and evaluation of the integrated system followed a fivefold cross-validation procedure. The proposed model attained an overall classification accuracy of 95.82%, better than the state-of-the-art method. Extensive experiments are performed on other MRI datasets for the brain to ascertain the improved performance of the proposed system. When the amount of available training data is small, the SVM classifier is observed to perform better than the softmax classifier for the CNN features. Compared to transfer learning-based classification, the adopted strategy of CNN-SVM has lesser computations and memory requirements.

ObjectiveTo systematically examine the design, reporting standards, risk of bias, and claims of studies comparing the performance of diagnostic deep learning algorithms for medical imaging with that of expert clinicians.DesignSystematic...

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.

Medical image classification plays a key role in computer-aided detection and diagnosis systems. Conventional machine learning, neural network-based approaches strongly depends on the type of features i.e. texture, edge, shape, and/or blob along with their amalgamations, extracted from the medical image. Since most of the feature extraction algorithms are specific to the modalities and problem. The machine learning or neural network-based model built using these features lack- of generalization and high-level problem representation ability. Deep Learning (DL) methods based on deep features deliver an active way to build an edge-to-edge model which has the ability to reckon the classification labels with the input raw pixels of medical domain images. Due to the unavailability of massive medical data, high noise rate, and resolution of medical images, DL approaches grieve in terms of classification rate. To improve the classification rate, we propose to fuse the contemporary features (high-level features) extracted from a deep convolution neural network (DCNN) and conventional texture features. The building of the planned model comprises the subsequent steps. Firstly, DCNNs (MobileNet, GoogelNet, and Resnet.) are trained as feature extractors, and the feature vectors are extracted. Second, we extract the traditional texture features of medical images. Lastly, we fuse the deep features and texture features which represent robust high-level features for medical image classification. We assess the proposed method on standard medical image benchmark datasets: MEDMNIST We attain classification accuracy of 99.1%,experimental results confirm that fusing texture features and deep learning features results in the increase of accuracy of medical image classification.

Medical image segmentation is crucial for healthcare, yet convolution-based methods like U-Net face limitations in modeling long-range dependencies. To address this, Transformers designed for sequence-to-sequence predictions have been integrated into medical image segmentation. However, a comprehensive understanding of Transformers’ self-attention in U-Net components is lacking. TransUNet, first introduced in 2021, is widely recognized as one of the first models to integrate Transformer into medical image analysis. In this study, we present the versatile framework of TransUNet that encapsulates Transformers’ self-attention into two key modules: (1) a Transformer encoder tokenizing image patches from a convolution neural network (CNN) feature map, facilitating global context extraction, and (2) a Transformer decoder refining candidate regions through cross-attention between proposals and U-Net features. These modules can be flexibly inserted into the U-Net backbone, resulting in three configurations: Encoder-only, Decoder-only, and Encoder+Decoder. TransUNet provides a library encompassing both 2D and 3D implementations, enabling users to easily tailor the chosen architecture. Our findings highlight the encoder’s efficacy in modeling interactions among multiple abdominal organs and the decoder’s strength in handling small targets like tumors. It excels in diverse medical applications, such as multi-organ segmentation, pancreatic tumor segmentation, and hepatic vessel segmentation. Notably, our TransUNet achieves a significant average Dice improvement of 1.06% and 4.30% for multi-organ segmentation and pancreatic tumor segmentation, respectively, when compared to the highly competitive nn-UNet, and surpasses the top-1 solution in the BrasTS2021 challenge. 2D/3D Code and models are available at https://github.com/Beckschen/TransUNet and https://github.com/Beckschen/TransUNet-3D, respectively.

Convolutional Neural Networks (CNNs) have demonstrated immense application potential in medical image processing due to their powerful feature learning capabilities, playing an increasingly vital role in disease diagnosis and treatment planning. However, when processing complex medical image data, CNNs still face challenges such as high computational resource consumption, limited model generalization ability, and high demand for labeled data. In recent years, to overcome these limitations, numerous researchers have focused on innovative structural improvements for CNNs, with enhancing model efficiency emerging as a central research priority. This review will focus on analyzing the contributions and significant effects of these improvement strategies in enhancing medical image classification and segmentation accuracy, accelerating model inference speed, and strengthening model robustness. Based on an in-depth synthesis of existing research, we draw the core conclusion: improved CNN architectures are an effective approach to enhancing the accuracy and efficiency of medical image segmentation, and specific improvement strategies demonstrate significant advantages across different tasks and various medical image modalities.

With the development of computer vision and image segmentation technology, medical image segmentation and recognition technology has become an important part of computer-aided diagnosis. The traditional image segmentation method relies on artificial means to extract and select information such as edges, colors, and textures in the image. It not only consumes considerable energy resources and people's time but also requires certain expertise to obtain useful feature information, which no longer meets the practical application requirements of medical image segmentation and recognition. As an efficient image segmentation method, convolutional neural networks (CNNs) have been widely promoted and applied in the field of medical image segmentation. However, CNNs that rely on simple feedforward methods have not met the actual needs of the rapid development of the medical field. Thus, this paper is inspired by the feedback mechanism of the human visual cortex, and an effective feedback mechanism calculation model and operation framework is proposed, and the feedback optimization problem is presented. A new feedback convolutional neural network algorithm based on neuron screening and neuron visual information recovery is constructed. So, a medical image segmentation algorithm based on a feedback mechanism convolutional neural network is proposed. The basic idea is as follows: The model for obtaining an initial region with the segmented medical image classifies the pixel block samples in the segmented image. Then, the initial results are optimized by threshold segmentation and morphological methods to obtain accurate medical image segmentation results. Experiments show that the proposed segmentation method has not only high segmentation accuracy but also extremely high adaptive segmentation ability for various medical images. The research in this paper provides a new perspective for medical image segmentation research. It is a new attempt to explore more advanced intelligent medical image segmentation methods. It also provides technical approaches and methods for further development and improvement of adaptive medical image segmentation technology.

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.

Convolutional Neural Network (CNN) features have demonstrated outstanding performance as global representations for image classification, but they lack invariance to scale transformation, which makes it difficult to adapt to various complex tasks such as scene classification. To strengthen the scale invariance of CNN features and meanwhile retain their powerful discrimination in scene classification, we propose a framework where cross-level Locality-constrained Linear Coding and cascaded fine-tuned CNN features are combined, which is shorted as cross-level LLC-CNN. Specifically, this framework first fine-tunes multi-level CNNs in a cascaded way, then extracts multi-level CNN features to learn a cross-level universal codebook, and finally performs locality-constrained linear coding (LLC) and max-pooling on the patches of all levels to form the final representation. It is experimentally verified that the LLC responses on the universal codebook outperform the CNN features and achieve the state-of-the-art performance on the two currently largest scene classification benchmarks, MIT Indoor Scenes and SUN 397.

To predict lung nodule malignancy with a high sensitivity and specificity for low dose CT (LDCT) lung cancer screening, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine HF, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM). We then trained 3D CNNs modified from three 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract the CNN features learned at the output layer. For each 3D CNN, the CNN features combined with the 29 HF were used as the input for the support vector machine (SVM) coupled with the sequential forward feature selection (SFS) method to select the optimal feature subset and construct the classifiers. The fusion algorithm takes full advantage of the HF and the highest level CNN features learned at the output layer. It can overcome the disadvantage of the HF that may not fully reflect the unique characteristics of a particular lesion by combining the intrinsic CNN features. Meanwhile, it also alleviates the requirement of a large scale annotated dataset for the CNNs based on the complementary of HF. The patient cohort includes 431 malignant nodules and 795 benign nodules extracted from the LIDC/IDRI database. For each investigated CNN architecture, the proposed fusion algorithm achieved the highest AUC, accuracy, sensitivity, and specificity scores among all competitive classification models.

A review of medical ocular image segmentation

The accurate and quick derivation of the distribution of damaged building must be considered essential for the emergency response. With the success of deep learning, there is an increasing interest to apply it for earthquake-induced building damage mapping, and its performance has not been compared with conventional methods in detecting building damage after the earthquake. In the present study, the performance of grey-level co-occurrence matrix texture and convolutional neural network (CNN) features were comparatively evaluated with the random forest classifier. Pre- and post-event very high-resolution (VHR) remote sensing imagery were considered to identify collapsed buildings after the 2010 Haiti earthquake. Overall accuracy (OA), allocation disagreement (AD), quantity disagreement (QD), Kappa, user accuracy (UA), and producer accuracy (PA) were used as the evaluation metrics. The results showed that the CNN feature with random forest method had the best performance, achieving an OA of 87.6% and a total disagreement of 12.4%. CNNs have the potential to extract deep features for identifying collapsed buildings compared to the texture feature with random forest method by increasing Kappa from 61.7% to 69.5% and reducing the total disagreement from 16.6% to 14.1%. The accuracy for identifying buildings was improved by combining CNN features with random forest compared with the CNN approach. OA increased from 85.9% to 87.6%, and the total disagreement reduced from 14.1% to 12.4%. The results indicate that the learnt CNN features can outperform texture features for identifying collapsed buildings using VHR remotely sensed space imagery.