Search

Background With the gradual increase of infertility in the world, among which male sperm problems are the main factor for infertility, more and more couples are using computer-assisted sperm analysis (CASA) to assist in the analysis and treatment of infertility. Meanwhile, the rapid development of deep learning (DL) has led to strong results in image classification tasks. However, the classification of sperm images has not been well studied in current deep learning methods, and the sperm images are often affected by noise in practical CASA applications. The purpose of this article is to investigate the anti-noise robustness of deep learning classification methods applied on sperm images.Methods The SVIA dataset is a publicly available large-scale sperm dataset containing three subsets. In this work, we used subset-C, which provides more than 125,000 independent images of sperms and impurities, including 121,401 sperm images and 4,479 impurity images. To investigate the anti-noise robustness of deep learning classification methods applied on sperm images, we conducted a comprehensive comparative study of sperm images using many convolutional neural network (CNN) and visual transformer (VT) deep learning methods to find the deep learning model with the most stable anti-noise robustness.Results This study proved that VT had strong robustness for the classification of tiny object (sperm and impurity) image datasets under some types of conventional noise and some adversarial attacks. In particular, under the influence of Poisson noise, accuracy changed from 91.45% to 91.08%, impurity precison changed from 92.7% to 91.3%, impurity recall changed from 88.8% to 89.5%, and impurity F1-score changed 90.7% to 90.4%. Meanwhile, sperm precision changed from 90.9% to 90.5%, sperm recall changed from 92.5% to 93.8%, and sperm F1-score changed from 92.1% to 90.4%.Conclusion Sperm image classification may be strongly affected by noise in current deep learning methods; the robustness with regard to noise of VT methods based on global information is greater than that of CNN methods based on local information, indicating that the robustness with regard to noise is reflected mainly in global information.

Hot compression experiment was conducted on Gleeble-3800 thermal simulation testing machine to investigate the hot deformation behavior of Cr5 die casting mold steel, with deformation temperatures of 1100–1300 °C and strain rates of 0.01−10s−1. The experimental results indicated that deformation temperature and strain rate have significant impacts on dynamic recrystallization(DRX) of Cr5 die casting mold steel, the critical strain of DRX decreased as deformation temperature increased and strain rate decreased. According to the Arrhenius model, the activation energy for deformation was 427.85 kJ/mol, and the constitutive equation of hot deformation was derived. Validation of high temperature flow stress model showed that the fitted model emerged appreciable accuracy and reliability. The processing map was constructed based on DMM theory, which was concluded that the unstable region is mainly concentrated around the deformation condition of 1300 °C/10s−1. Cr5 die casting mold steel exhibits the best hot processing performance under the deformation condition of 1250 °C/0.1s−1, with an excellent efficiency of power dissipation(η = 0.36) and a lower value of Kernel average misorientation(KAM average = 1.675°). Discontinuous dynamic recrystallization (DDRX) is the main mechanism for recrystallization nucleation and growth during hot deformation of Cr5 die casting mold steel.

Chinese herbal medicine (CHM) is integral to a traditional Chinese medicine (TCM) system. Accurately identifying Chinese herbal medicine is crucial for quality control and prescription compounding verification. However, with many Chinese herbal medicines and some with similar appearances but different therapeutic effects, achieving precise identification is a challenging task. Traditional manual identification methods have certain limitations, including labor-intensive, inefficient. Deep learning techniques for Chinese herbal medicine identification can enhance accuracy, improve efficiency and lower coats. However, few high-quality Chinese herbal medicine datasets are currently available for deep learning applications. To alleviate this problem, this study constructed a dataset (Dataset 1) containing 3,384 images of 20 common Chinese herbal medicine fruits through web crawling. All images are annotated by TCM experts, making them suitable for training and testing Chinese herbal medicine identification methods. Furthermore, this study establishes another dataset (Dataset 2) of 400 images by taking pictures using smartphones to provide materials for the practical efficacy evaluation of Chinese herbal medicine identification methods. The two datasets form a Ningbo Traditional Chinese Medicine Chinese Herb Medicine (NB-TCM-CHM) Dataset. In Dataset 1 and Dataset 2, each type of Chinese medicine herb is stored in a separate folder, with the folder named after its name. The dataset can be used to develop Chinese herbal medicine identification algorithms based on deep learning and evaluate the performance of Chinese herbal medicine identification methods.

Scoliosis refers to the abnormal curvature of human spine, which is one of the most common deformities in children and adolescents. The Cobb angle is the gold standard for quantifying the severity of scoliosis and is used to assess the severity of scoliosis. Often the accuracy of the Cobb angle measurement relies on the subjective experience of the doctor and the process is very time consuming. In this study, we propose a new deep neural network, ATT UNet 3+, based on UNet 3+. Our approach incorporates a novel hybrid attention mechanism in the network’s upsampling process. This mechanism allows for the appropriate reweighting of fused multi-scale information and facilitates effective supervision of the final output results. The proposed neural network is trained, tested and validated on 155 X-ray ortho-slices. The deep learning network is compared with the more effective neural networks commonly used today. ATT UNet 3+ achieves the best performance in the segmentation evaluation results. Regarding the final Cobb angle calculations, the absolute mean error between the longest distance ellipsoidal point (LDEP) method and expert measurements amounted to 1.6°. ATT UNet 3+ provides a potential tool for segmenting the spine in X-ray, which can improve the efficiency and accuracy of doctors in processing scoliosis pathological images.

Studying the structure and function of the heart through the left ventricle is one of the most common methods for diagnosing heart diseases. The automatic segmentation of the left ventricle can be achieved through deep learning techniques, and researchers have conducted a series of explorations in this field. Recently, the segment anything model (SAM) has achieved significant success in the field of natural images, sparking considerable interest among researchers. This has led them to investigate whether SAM can also be successfully applied in the medical imaging domain. The SAM model’s interactive interface enables zero-shot and few-shot learning in the natural image domain, achieving accurate segmentation tasks. However, there are certain limitations in the automatic segmentation of medical images, specifically in the context of natural image cues such as points, boxes, and text prompts. To address this issue, this paper explores the performance of a prompt-free SAM-related model with an attention module for automatic segmentation of the left ventricle in echocardiography, named as SAM-Att. The model employs a low-rank fine-tuning strategy in the upstream, introduces an attention mechanism in the downstream, and successfully accomplishes the automatic segmentation task of the left ventricle with the support of weight files pretrained on the SAM large model. The SAM-Att model achieves dice similarity coefficient (DSC) of 94.49% and hausdorff distance (HD) of 3.505 mm on the test set. The accuracy reaches 98.83%, with precision of 93.65% and recall of 94.77%. A performance comparison of SAM-Att with other SAM-related models (SAM-b, MSA, Sam-CNN, AutoSAM, SAMed) is conducted on the same echocardiography dataset. The results indicate that the left ventricle automatic segmentation achieved the best performance when using SAM-Att.

Diabetic retinopathy (DR) is a microvascular disease that is associated with diabetes mellitus. DR can cause irreversible vision loss and low vision. DR classification, that is, early DR diagnosis and accurate DR grading, is critical for vision protection and immediate treatment. Deep learning-based automated systems led to significant expectations for DR classification based on fundus images with several advantages. In the past several years, many outstanding studies in this area have been conducted and several review articles have been published. However, the new trends and the future directions are need to furtherly analyzed. Thus, we carefully included and read 94 related articles published from 2018 to 2023 through Web of Science, PubMed, Scopus, and IEEE Xplore. From this review, we found that transfer learning has been used as an outstanding strategy for overcoming the issue of the limited data resources to support DR analysis. CNN models of ResNet and VGGNet with layers of tens or even hundreds are the most popular frameworks used for DR classification. The APTOS 2019 and EyePACS are the most widely used datasets for DR classification. In addition, some lightweight DL architectures like SqueezeNet and MobileNet have been proposed for DR classification tasks, especially for limited data resources and computational capabilities. Although deep learning has achieved or surpassed human-level accuracy in DR classification, there is still a long way to go in real clinical workflows. Further improvements in model interpretability, trustworthiness from ophthalmologists, cost-effective and reliable DR screening systems are needed.

Abstract Coherent imaging techniques provide an unparalleled multi-scale view of materials across scientific and technological fields, from structural materials to quantum devices, from integrated circuits to biological cells. Driven by the construction of brighter sources and high-rate detectors, coherent imaging methods like ptychography are poised to revolutionize nanoscale materials characterization. However, these advancements are accompanied by significant increase in data and compute needs, which precludes real-time imaging, feedback and decision-making capabilities with conventional approaches. Here, we demonstrate a workflow that leverages artificial intelligence at the edge and high-performance computing to enable real-time inversion on X-ray ptychography data streamed directly from a detector at up to 2 kHz. The proposed AI-enabled workflow eliminates the oversampling constraints, allowing low-dose imaging using orders of magnitude less data than required by traditional methods.

Falls among the elderly are a common and serious health risk that can lead to physical injuries and other complications. To promptly detect and respond to fall events, radar-based fall detection systems have gained widespread attention. In this paper, a deep learning model is proposed based on the frequency spectrum of radar signals, called the convolutional bidirectional long short-term memory (CB-LSTM) model. The introduction of the CB-LSTM model enables the fall detection system to capture both temporal sequential and spatial features simultaneously, thereby enhancing the accuracy and reliability of the detection. Extensive comparison experiments demonstrate that our model achieves an accuracy of 98.83% in detecting falls, surpassing other relevant methods currently available. In summary, this study provides effective technical support using the frequency spectrum and deep learning methods to monitor falls among the elderly through the design and experimental validation of a radar-based fall detection system, which has great potential for improving quality of life for the elderly and providing timely rescue measures.

Abstract Noninvasive X-ray imaging of nanoscale three-dimensional objects, such as integrated circuits (ICs), generally requires two types of scanning: ptychographic, which is translational and returns estimates of the complex electromagnetic field through the IC; combined with a tomographic scan, which collects these complex field projections from multiple angles. Here, we present Attentional Ptycho-Tomography (APT), an approach to drastically reduce the amount of angular scanning, and thus the total acquisition time. APT is machine learning-based, utilizing axial self-Attention for Ptycho-Tomographic reconstruction. APT is trained to obtain accurate reconstructions of the ICs, despite the incompleteness of the measurements. The training process includes regularizing priors in the form of typical patterns found in IC interiors, and the physics of X-ray propagation through the IC. We show that APT with ×12 reduced angles achieves fidelity comparable to the gold standard Simultaneous Algebraic Reconstruction Technique (SART) with the original set of angles. When using the same set of reduced angles, then APT also outperforms Filtered Back Projection (FBP), Simultaneous Iterative Reconstruction Technique (SIRT) and SART. The time needed to compute the reconstruction is also reduced, because the trained neural network is a forward operation, unlike the iterative nature of these alternatives. Our experiments show that, without loss in quality, for a 4.48 × 93.2 × 3.92 µm3 IC (≃6 × 108 voxels), APT reduces the total data acquisition and computation time from 67.96 h to 38 min. We expect our physics-assisted and attention-utilizing machine learning framework to be applicable to other branches of nanoscale imaging, including materials science and biological imaging.

Previous studies on rub-impact faults have mainly focused on the rub-impact between rotors and stators, with less research on inter-rotor rub impact. The impact of inter-rotor rub impact on rotor nonlinear vibration is particularly significant. This study investigates the effects of inter-shaft rub impact on the vibration characteristics and whirl behavior of dual-rotor systems. Initially, a dual-rotor model with inter-shaft bearings is established using the finite element method, and inter-shaft rub-impact forces are derived based on contact mechanics. Next, the system response is solved using the Newmark method. Vibration characteristics are analyzed through Campbell diagrams, 3D waterfall plots, time-frequency domain plots, and steady-state rub-impact force plots. Finally, the influence of inter-shaft rub impact on the whirl behavior of the dual-rotor system is studied based on the theory of full-spectrum analysis. The study concludes that inter-shaft rub-impact faults shift the system’s resonance points backward, increase harmonic and combination frequency components, and significantly affect the system response under dual-rotor co-rotation. Excessive friction can lead to self-excited vibrations and sudden amplitude increases, particularly in the LP rotor frequency. Additionally, inter-shaft rub impact primarily affects the whirl behavior of the LP-compressor disk1, showing multiple cycles of forward and backward whirl alternation during acceleration due to combined unbalanced and rub-impact excitations.

Abstract The non-coding RNA secondary structure largely determines its function. Hence, accuracy in structure acquisition is of great importance. Currently, this acquisition primarily relies on various computational methods. The prediction of the structures of long RNA sequences with high precision and reasonable computational cost remains challenging. Here, we propose a deep learning model, RNA-par, which could partition an RNA sequence into several independent fragments (i-fragments) based on its exterior loops. Each i-fragment secondary structure predicted individually could be further assembled to acquire the complete RNA secondary structure. In the examination of our independent test set, the average length of the predicted i-fragments was 453 nt, which was considerably shorter than that of complete RNA sequences (848 nt). The accuracy of the assembled structures was higher than that of the structures predicted directly using the state-of-the-art RNA secondary structure prediction methods. This proposed model could serve as a preprocessing step for RNA secondary structure prediction for enhancing the predictive performance (especially for long RNA sequences) and reducing the computational cost. In the future, predicting the secondary structure of long-sequence RNA with high accuracy can be enabled by developing a framework combining RNA-par with various existing RNA secondary structure prediction algorithms. Our models, test codes and test data are provided at https://github.com/mianfei71/RNAPar .

The quantification of cell numbers in microscopy images plays a vital role in biomedical research and medical diagnosis. Presently, deep regression networks are widely employed to generate cell density maps, and the number of cells is obtained by integrating the density maps. However, automating cell counting remains challenging due to the variability in cell morphology, the diversity of cell types, and the interference of image backgrounds. This paper aims to address the central question: ‘Can we design a robust and efficient deep learning model that can effectively count cells in microscopy images, regardless of these challenges?’ To tackle this issue, we propose a novel multi-scale convolutional attention UNet (MSCA-UNet) based on density regression. Compared with other advanced density regression methods, our method introduces two key innovations. Firstly, we employ an MSCA block with multi-scale interaction ability as an encoder component, which, when combined with spatial attention, enhances the extraction of cell details and spatial information. Secondly, the design of the asymmetric UNet allows the encoder to extract more global information and better understand the image. In the meantime, using smaller convolutional kernels and strides in the decoder helps to restore image details and edge information, resulting in improved network performance. Our method outperformed other advanced methods on three publicly available benchmark cell datasets, including the synthetic bacterial (VGG) dataset, the modified bone marrow (MBM) dataset, and the human subcutaneous adipose tissue (ADI) dataset.

The number of deaths from lung cancer reached 1.8 million in 2020, ranking first among all cancers. Early diagnosis has been found to improve the survival rate of lung cancer patients after treatment in clinical care. Computed tomography (CT) is a technique commonly used in the early detection of lung cancer to determine the benignity or malignancy of lung nodules. Manual analysis of CT results is less efficient and its accuracy is affected by physicians’ experience levels. Segmenting lung nodules in a computer-aided diagnosis (CAD) system can effectively improve the efficiency and accuracy of the diagnosis. In this paper, we evaluate several deep learning segmentation models (including UNet, SegNet, GCN, FCN, DeepLabV3+, PspNet TransUNet, SwinUNet) and examine the effects of different preprocessing methods on the models to explore the best preprocessing and training strategies for lung nodule segmentation. Specifically, we investigate the effects of two different data preprocessing methods (adding a lung mask and croping the region of interest) on the segmentation results, where better segmentation results are achieved by including the nodal data of the region of interest without the lung mask. Through a comprehensive comparison, TransUNet achieves the best segmentation accuracy, with DICE indices of 0.887, 0.871, 0.75, and 0.744 tested on four datasets, respectively.

The carotid artery is one of the most important blood vessels that supply blood to the brain. If thrombus occurs, it may cause cerebral ischemic stroke and endanger life. Carotid intima-media thickness and stability of carotid plaque are essential indicators for predicting stroke, which can be measured through medical image segmentation. Therefore, automatic and accurate carotid artery image segmentation and measurement of carotid intima-media thickness and the area and volume of carotid plaque are of great significance for stroke risk prediction and treatment. However, due to the complex shape of the carotid artery and the characteristics of carotid artery imaging, the traditional methods (such as threshold methods, region growth methods) can not segment the carotid artery very well. In recent years, researchers have taken artificial intelligence (traditional machine learning and deep learning) as a critical research method for carotid artery segmentation and extensive research has been performed with satisfactory results. In this paper, we present a comprehensive review of carotid artery segmentation using artificial intelligence methods. We first briefly introduce medical image processing methods and artificial intelligence methods. And then, review and summarize the application of artificial intelligence segmentation methods in carotid artery segmentation (including carotid lumen, media-adventitia, lumen-intima, and plaques). Finally, the challenges of current artificial intelligence methods in carotid artery segmentation are analyzed.

Abstract Background Major depressive disorder (MDD) is a common cause of disability and morbidity, affecting about 10% of the population worldwide. Subclinical depression (SD) can be understood as a precursor of MDD, and therefore provides an MDD risk indicator. The pathogenesis of MDD and SD in humans is still unclear, and the current diagnosis lacks accurate biomarkers and gold standards. Methods A total of 40 MDD, 34 SD, and 40 healthy control (HC) participants matched by age, gender, and education were included in this study. Resting-state functional magnetic resonance images (rs-fMRI) were used to analyze the functional connectivity (FC) of the posterior parietal thalamus (PPtha), which includes the lateral habenula, as the region of interest. Analysis of variance with the post hoc t-test test was performed to find significant differences in FC and clarify the variations in FC among the HC, SD, and MDD groups. Results Increased FC was observed between PPtha and the left inferior temporal gyrus (ITG) for MDD versus SD, and between PPtha and the right ITG for SD versus HC. Conversely, decreased FC was observed between PPtha and the right middle temporal gyrus (MTG) for MDD versus SD and MDD versus HC. The FC between PPtha and the middle frontal gyrus (MFG) in SD was higher than that in MDD and HC. Compared with the HC group, the FC of PPtha-ITG (left and right) increased in both the SD and MDD groups, PPtha-MTG (right) decreased in both the SD and MDD groups and PPtha-MFG (right) increased in the SD group and decreased in the MDD group. Conclusion Through analysis of FC measured by rs-fMRI, the altered FC between PPtha and several brain regions (right and left ITG, right MTG, and right MFG) has been identified in participants with SD and MDD. Different alterations in FC between PPtha and these regions were identified for patients with depression. These findings might provide insights into the potential pathophysiological mechanisms of SD and MDD, especially related to PPtha and the lateral habenula.

Image reconstruction is extremely important for computed tomography (CT) imaging, so it is significant to be continuously improved. The unfolding dynamics method combines a deep learning model with a traditional iterative algorithm. It is interpretable and has a fast reconstruction speed, but the essence of the algorithm is to replace the approximation operator in the optimization objective with a learning operator in the form of a convolutional neural network. In this paper, we firstly design a new iterator network (iNet), which is based on the universal approximation theorem and tries to simulate the functional relationship between the former and the latter in the maximum-likelihood expectation maximization (MLEM) algorithm. To evaluate the effectiveness of the method, we conduct experiments on a CT dataset, and the results show that our iNet method improves the quality of reconstructed images.

Presents corrections to the paper, (Corrections to “Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey”).

Abstract The survival rate of breast cancer patients is closely related to the pathological stage of cancer. The earlier the pathological stage, the higher the survival rate. Breast ultrasound is a commonly used breast cancer screening or diagnosis method, with simple operation, no ionizing radiation, and real-time imaging. However, ultrasound also has the disadvantages of high noise, strong artifacts, low contrast between tissue structures, which affect the effective screening of breast cancer. Therefore, we propose a deep learning based breast ultrasound detection system to assist doctors in the diagnosis of breast cancer. The system implements the automatic localization of breast cancer lesions and the diagnosis of benign and malignant lesions. The method consists of two steps: 1. Contrast enhancement of breast ultrasound images using segmentation-based enhancement methods. 2. An anchor-free network was used to detect and classify breast lesions. Our proposed method achieves a mean average precision (mAP) of 0.902 on the datasets used in our experiment. In detecting benign and malignant tumors, precision is 0.917 and 0.888, and recall is 0.980 and 0.963, respectively. Our proposed method outperforms other image enhancement methods and an anchor-based detection method. We propose a breast ultrasound image detection system for breast cancer detection. The system can locate and diagnose benign and malignant breast lesions. The test results on single dataset and mixed dataset show that the proposed method has good performance.

Abstract The problem of phase retrieval underlies various imaging methods from astronomy to nanoscale imaging. Traditional phase retrieval methods are iterative and are therefore computationally expensive. Deep learning (DL) models have been developed to either provide learned priors or completely replace phase retrieval. However, such models require vast amounts of labeled data, which can only be obtained through simulation or performing computationally prohibitive phase retrieval on experimental datasets. Using 3D X-ray Bragg coherent diffraction imaging (BCDI) as a representative technique, we demonstrate AutoPhaseNN, a DL-based approach which learns to solve the phase problem without labeled data. By incorporating the imaging physics into the DL model during training, AutoPhaseNN learns to invert 3D BCDI data in a single shot without ever being shown real space images. Once trained, AutoPhaseNN can be effectively used in the 3D BCDI data inversion about 100× faster than iterative phase retrieval methods while providing comparable image quality.

Abstract Arterial stiffness, as measured by pulse wave velocity, for the early non-invasive screening of cardiovascular disease is becoming ever more widely used and is an independent prognostic indicator for a variety of pathologies including arteriosclerosis. Carotid-femoral pulse wave velocity (cfPWV) is regarded as the gold standard for aortic stiffness. Existing algorithms for cfPWV estimation have been shown to have good repeatability and accuracy, however, further assessment is needed, especially when signal quality is compromised. We propose a method for calculating cfPWV based on a simplified tube-load model, which allows for the propagation and reflection of the pulse wave. In-vivo cfPWV measurements from 57 subjects and numerical cfPWV data based on a one-dimensional model were used to assess the method and its performance was compared to three other existing approaches (waveform matching, intersecting tangent, and cross-correlation). The cfPWV calculated using the simplified tube-load model had better repeatability than the other methods (Intra-group Correlation Coefficient, ICC = 0.985). The model was also more accurate than other methods (deviation, 0.13 ms−1) and was more robust when dealing with noisy signals. We conclude that the determination of cfPWV based on the proposed model can accurately and robustly evaluate arterial stiffness.

Wounds not only harm the physical and mental health of patients, but also introduce huge medical costs. Meanwhile, there is a shortage of physicians in some areas, and clinical examinations are sometimes unreliable in wound diagnosis. Reliable wound analysis is of great importance in its diagnosis, treatment, and care. Currently, deep learning has developed rapidly in the field of computer vision and medical imaging and has become the most commonly used technique in wound image analysis. This paper studies the current research on deep learning in the field of wound image analysis, including classification, detection, and segmentation. We first review the publicly available datasets from various research, and study the preprocessing methods used in wound image analysis. Second, various models used in different deep learning tasks (classification, detection, and segmentation) and their applications in different types of wounds (e.g., burns, diabetic foot ulcers, pressure ulcers) are investigated. Finally, we discuss the challenges in the field of wound image analysis using deep learning, and provide an outlook on the research and development prospects.

Brachial plexus block is a common regional anesthesia method widely used in upper limb surgery. Nowadays, ultrasound-guided brachial plexus block has been extensively used in clinical anesthesia. However, accurate brachial plexus block is highly dependent on the physician’s experience, and a physician without extensive clinical experience may cause nerve injury when performing a nerve block. With the development of artificial intelligence technology, the deep learning method can automatically identify the brachial plexus in ultrasound images and assist doctors in completing the brachial plexus block accurately and quickly. In this paper, we aim to evaluate the performance of different deep learning models in identifying brachial plexus (i.e., segmentation of brachial plexus) from ultrasonic images to explore the best models and training strategies for this task. To this end, we use a new dataset containing 340 brachial plexus ultrasound images annotated by three experienced clinicians. Among the 12 deep learning models we evaluated, U-Net achieves the best segmentation accuracy, with an intersection over union (IoU) of 68.50%. However, the number of U-Net parameters is very large, and it can only process 15 images per second. Compared to U-Net, LinkNet can process 142 images per second and achieve the second-best segmentation accuracy with an IoU of 66.27%. It achieves the balance between segmentation accuracy and processing efficiency, which has a good potential for the brachial plexus’s real-time segmentation task.

BackgroundAs one of the most common diseases, major depressive disorder (MDD) has a significant adverse impact on the li of patients. As a mild form of depression, subclinical depression (SD) serves as an indicator of progression to MDD. This study analyzed the degree centrality (DC) for MDD, SD, and healthy control (HC) groups and identified the brain regions with DC alterations.MethodsThe experimental data were composed of resting-state functional magnetic resonance imaging (rs-fMRI) from 40 HCs, 40 MDD subjects, and 34 SD subjects. After conducting a one-way analysis of variance, two-sample t-tests were used for further analysis to explore the brain regions with changed DC. Receiver operating characteristic (ROC) curve analysis of single index and composite index features was performed to analyze the distinguishable ability of important brain regions.ResultsFor the comparison of MDD vs. HC, increased DC was found in the right superior temporal gyrus (STG) and right inferior parietal lobule (IPL) in the MDD group. For SD vs. HC, the SD group showed a higher DC in the right STG and the right middle temporal gyrus (MTG), and a smaller DC in the left IPL. For MDD vs. SD, increased DC in the right middle frontal gyrus (MFG), right IPL, and left IPL, and decreased DC in the right STG and right MTG was found in the MDD group. With an area under the ROC (AUC) of 0.779, the right STG could differentiate MDD patients from HCs and, with an AUC of 0.704, the right MTG could differentiate MDD patients from SD patients. The three composite indexes had good discriminative ability in each pairwise comparison, with AUCs of 0.803, 0.751, and 0.814 for MDD vs. HC, SD vs. HC, and MDD vs. SD, respectively.ConclusionAltered DC in the STG, MTG, IPL, and MFG were identified in depression groups. The DC values of these altered regions and their combinations presented good discriminative ability between HC, SD, and MDD. These findings could help to find effective biomarkers and reveal the potential mechanisms of depression.

In hydrogel-based tissue engineering, channel network is an efficient structure for transporting nutrients/oxygen to support cell survival and construct living tissues in vitro. 3D printing can create complex hydrogel-based tissue constructs, however, due to the weak mechanical properties of hydrogel bioinks, cell-laden hydrogel constructs with effective channel networks are difficult to be directly printed. Here, an easy sacrificial 3D printing method based on commercial desktop 3D printer and water-soluble polyvinyl alcohol (PVA) to construct effective hydrogel channel networks is introduced. Specifically, i) commercial PVA consumables are printed to be sacrificial templates; ii) gelatin methacryloyl (GelMA) solution is cast to encapsulate the sacrificial template; iii) the sacrificial template is dissolved to form channel networks. PVA is a water-soluble sacrificial material with sufficient dissolution time and high mechanical strength, which can avoid the disadvantages of classic sacrificial materials (sugar and Pluronic F127). High roundness of printed PVA filaments results in high roundness of the channel networks. The interconnected channel networks accelerate the supply of oxygen/nutrients and promote cell growth. And with a period of culture, the higher the channel networks density, the better the cell growth. Additionally, PVA sacrificial templates have high stability and long-term preservation, facilitating transportation, circulation and use, which is conducive to the manufacturing and promotion of hydrogel-based constructs with channel networks. Taken together, our easy strategy of manufacturing hydrogel constructs with channel networks has broad application prospects, such as 3D cell culture, construction of functional tissue in vitro or tissue repair in vivo etc.

The respiratory rate (RR) serves as a critical physiological parameter in the context of both diagnostic and prognostic evaluations. Due to the challenges of direct measurement, RR is still predominantly measured through the traditional manual counting-breaths method in clinic practice. Numerous algorithms and machine learning models have been developed to predict RR using physiological signals, such as electrocardiogram (ECG) or/and photoplethysmogram (PPG) signals. Yet, the accuracy of these existing methods on available datasets remains limited, and their prediction on new data is also unsatisfactory for actual clinical applications. In this paper, we proposed an enhanced Transformer model with inception blocks for predicting RR based on both ECG and PPG signals. To evaluate the generalization capability on new data, our model was trained and tested using subject-level ten-fold cross-validation using data from both BIDMC and CapnoBase datasets. On the test set, our model achieved superior performance over five popular deep-learning-based methods with mean absolute error (1.2) decreased by 36.5% and correlation coefficient (0.85) increased by 84.8% compared to the best results of these models. In addition, we also proposed a new pipeline to preprocess ECG and PPG signals to improve model performance. We believe that the development of the TransRR model is expected to further expedite the clinical implementation of automatic RR estimation.

ObjectiveDiffusion tensor imaging (DTI) studies have investigated white matter (WM) integrity abnormalities in Parkinson’s disease (PD). However, little is known about the topological changes in the brain network. This study aims to reveal these changes by comparing PD without freezing of gait (FOG) (PD FOG–), PD with FOG (PD FOG+), and healthy control (HC).Methods21 PD FOG+, 34 PD FOG-, and 23 HC were recruited, and DTI images were acquired. The graph theoretical analysis and network-based statistical method were used to calculate the topological parameters and assess connections.ResultsPD FOG+ showed a decreased normalized clustering coefficient, small-worldness, clustering coefficient, and increased local network efficiency compared with HCs. PD FOG+ showed decreased centrality, degree centrality, and nodal efficiency in the striatum, frontal gyrus, and supplementary motor area (SMA). PD FOG+ showed decreased connections in the frontal gyrus, cingulate gyrus, and caudate nucleus (CAU). The between centrality of the left SMA and left CAU was negatively correlated with FOG questionnaire scores.ConclusionThis study demonstrates that PD FOG+ exhibits disruption of global and local topological organization in structural brain networks, and the disrupted topological organization can be potential biomarkers in PD FOG+. These new findings may provide increasing insight into the pathophysiological mechanism of PD FOG+.

Modulation recognition is one of the fundamental tasks for communications systems, which can be widely applied in various fields, such as cognitive radio, intelligent communications, radio surveillance, electronic warfare, etc.In recent years, deep learning (DL) based modulation recognition has attracted great attention due to its superiority in feature extraction and recognition performance.The techniques of DL based modulation recognition were systematically summarized.Firstly, some knowledge relevant to DL based modulation recognition was introduced.Then, the system architecture, data pre-processing methods, deep neural network structures, prevalent datasets and performance metrics of DL based modulation recognition were illustrated.Finally, the future directions of DL based modulation recognition were also discussed.

Ultrasound (US) is one of the most widely used imaging modalities in medical diagnosis. It has the advantages of real-time, low cost, noninvasive nature, and easy to operate. However, it also has the unique disadvantages of strong artifacts and noise and high dependence on the experience of doctors. In order to overcome the shortcomings of ultrasound diagnosis and help doctor improve the accuracy and efficiency of diagnosis, many computer aided diagnosis (CAD) systems have been developed. In recent years, deep learning has achieved great success in computer vision with its unique advantages. In the aspect of medical US image analysis, deep learning has also been exploited for its great potential and more and more researchers apply it to CAD systems. In this paper, we first introduce the deep learning models commonly used in medical US image analysis; Second, we review the data preprocessing methods of medical US images, including data augmentation, denoising, and enhancement; Finally, we analyze the applications of deep learning in medical US imaging tasks (such as image classification, object detection, and image reconstruction).

The arterial pulse wave is a physiological signal which can reflect the function of the human cardiovascular system. Owing to the measurement being convenient and safe, radial pulse waves have been often used in noninvasive monitoring of human health, which can further reflect the health status of the cardiovascular system, including information of the aorta and peripheral arteries. Moreover, radial pulse waves can assist clinical diagnosis in the prevention and treatment of cardiovascular disease. This paper systematically reviews the progress in analysis of pulse wave analysis, including pulse wave acquisition, waveform processing, pattern classification, parameter estimation, and clinical applications. In terms of waveform acquisition, this paper reviews a variety of methods to obtain radial pulse waves, including tonometry, photoplethysmography, ultrasound manometry, and flexible tactile pressure sensors. In the aspect of waveform processing, this paper summarizes the methods of radial pulse waves preprocessing and feature extraction. With the rapid development of machine learning and deep learning algorithms, radial pulse waves can be used to identify the status of human cardiovascular systems and to estimate parameters related to cardiovascular function. This paper also discusses the applications of radial pulse waves in clinical practice, including cardiovascular function evaluation and pulse diagnosis in traditional Chinese medicine. Some open-source databases and analysis software are also listed. The current development trend, challenges, and future directions of analysis of radial pulse waves are also offered.

Performance improvement of cathode materials represents one of the most critical technological challenges for lithium-ion batteries. Here the authors show a close correlation between surface chemistry and phase distribution from homogeneity to heterogeneity, and its impact on the cyclic performance.

This article develops a quantum bacterial foraging optimization (QBFO) algorithm, a quantum intelligence algorithm based on quantum computing and bacterial foraging optimization (BFO), with application in MIMO system optimization designs. In QBFO, a multiqubit is used to represent a bacterium, and a quantum rotation gate is used to mimic chemotaxis. Because the quantum bacterium with multiqubit has the advantage that it can represent a linear superposition of states (binary solutions) in search space probabilistically, the proposed QBFO algorithms shows better performance on solving combinatorial optimization problems than its classical counterpart BFO and Quantum Genetic Algorithm (QGA), especially for parallel non-gradient optimization. A sparse channel estimation scheme based on QBFO with adaptive phase rotation (AQBFO) in 3D MIMO system is proposed, and simulation results show that AQBFO achieved a better performance than existing algorithms including least squares (LS), iteratively reweighted least squares (IRLS), matching pursuit (MP), and orthogonal matching pursuit (OMP). We further improve some critical aspects such as reproduction and dispersal processes of AQBFO, propose an improved IQBFO algorithm, and apply it for interference coordination in 3D multi-cell multi-user MIMO systems, aiming to maximize the spectral efficiency. It considers user fairness and jointly optimizes cell-center and cell-edge user specific antenna downtilts and power to maximize each user's sum rate. This problem is a combinatorial non-convex optimization problem that cannot be solved by the traditional Karush-Kuhn-Tucker Lagrangian algorithm whereas the IQBFO algorithm solves it effectively.

A behavior description helps analyze tiny objects, similar objects, objects with weak visual information, and objects with similar visual information. It plays a fundamental role in the identification and classification of dynamic objects in microscopic videos. To this end, we propose foldover features to describe the behavior of dynamic objects. Foldover is defined as: Each frame of an object's motion is superimposed on the same spatial plane in the spacetime order of the motion, the result of the superposition is the foldover of the object's motion. Foldover of an object contains temporal information, spatial information, behavior features and static features. Therefore, the features extracted based on the foldover of the object are the foldover features. In this work, we first generate foldover for each object in microscopic videos in X, Y and Z directions, respectively. Then, we extract foldover features from the X, Y and Z directions with statistical methods, respectively. The core content of this paper is to construct the foldovers and extract the foldover features. Through these two steps, the temporal information, spatial information, behavior features and static features of the object are enhanced and included in the foldover features. Furthermore, the description of the behavior of dynamic objects by the foldover features is strengthened. Finally, we use four different classifiers to test the effectiveness of the proposed foldover features. In the experiment, we use a microscopic sperm video dataset to evaluate the proposed foldover features, including three types of 1374 sperms, and obtain the highest classification accuracy of 96.5%.

Breast cancer is one of the most common and deadliest cancers among women. Since histopathological images contain sufficient phenotypic information, they play an indispensable role in the diagnosis and treatment of breast cancers. To improve the accuracy and objectivity of Breast Histopathological Image Analysis (BHIA), Artificial Neural Network (ANN) approaches are widely used in the segmentation and classification tasks of breast histopathological images. In this review, we present a comprehensive overview of the BHIA techniques based on ANNs. First of all, we categorize the BHIA systems into classical and deep neural networks for in-depth investigation. Then, the relevant studies based on BHIA systems are presented. After that, we analyze the existing models to discover the most suitable algorithms. Finally, publicly accessible datasets, along with their download links, are provided for the convenience of future researchers.

In recent years, researches are concentrating on the effectiveness of Transfer Learning (TL) and Ensemble Learning (EL) techniques in cervical histopathology image analysis. However, there have been very few investigations that have described the stages of differentiation of cervical histopathological images. Therefore, in this article, we propose an Ensembled Transfer Learning (ETL) framework to classify well, moderate and poorly differentiated cervical histopathological images. First of all, we have developed Inception-V3, Xception, VGG-16, and Resnet-50 based TL structures. Then, to enhance the classification performance, a weighted voting based EL strategy is introduced. After that, to evaluate the proposed algorithm, a dataset consisting of 307 images, stained by three immunohistochemistry methods (AQP, HIF, and VEGF) is considered. In the experiment, we obtain the highest overall accuracy of 97.03% and 98.61% on AQP staining images and poor differentiation of VEGF staining images, individually. Finally, an additional experiment for classifying the benign cells from the malignant ones is carried out on the Herlev dataset and obtains an overall accuracy of 98.37%.

Cervical cancer is one of the most common and deadliest cancers among women. Despite that, this cancer is entirely treatable if it is detected at a precancerous stage. Pap smear test is the most extensively performed screening method for early detection of cervical cancer. However, this hand-operated screening approach suffers from a high false-positive result because of human errors. To improve the accuracy and manual screening practice, computer-aided diagnosis methods based on deep learning is developed widely to segment and classify the cervical cytology images automatically. In this survey, we provide a comprehensive study of the state of the art approaches based on deep learning for the analysis of cervical cytology images. Firstly, we introduce deep learning and its simplified architectures that have been used in this field. Secondly, we discuss the publicly available cervical cytopathology datasets and evaluation metrics for segmentation and classification tasks. Then, a thorough review of the recent development of deep learning for the segmentation and classification of cervical cytology images is presented. Finally, we investigate the existing methodology along with the most suitable techniques for the analysis of pap smear cells.

Computer-Aided Diagnosis (CAD) can improve the accuracy of diagnosis effectively, reduce the rate of misdiagnosis, and provide the support for the valid decision. In clinical applications, high requirements are often imposed on the execution speed and accuracy of CAD systems. The classifier is regarded as the core of the CAD system, that is, the performance of the classifier will have a decisive influence on the operating affection of the CAD system. Extreme Learning Machine (ELM) is a fast learning algorithm using Single Hidden Layer Feedforward Neural Network (SLFN) structure. With its advantages in training speed, generalization performance and accuracy, ELM has draw attention in many research fields, including the development of CAD system. The applications of ELM in CAD are reviewed in this research. First, the mathematical model of ELM and framework of CAD system are briefly introduced. Then, the application of ELM in CAD is reviewed in detail, including the feature modeling method combined with ELM in CAD and the specific application of ELM. Finally, we summarized the current research status of CAD systems based on ELM, and the future work is prospected.

The main obstacle to image augmentation with Generative Adversarial Networks (GANs) is the need for a large amount of training data, but this is difficult for small datasets like Environmental Microorganisms (EMs). EM image analysis plays a vital role in environmental monitoring and protection, but it is often encountered with small datasets due to the difficulty of EM image collection. To this end, we propose an Enhanced Framework of GANs (EF-GANs) that combines geometric transformation methods and GANs for EM image augmentation. First of all, the color of an EM image has an insignificant impact on its class label, based on this fact, we perform color space augmentation to the original EM images. Secondly, we train EF-GANs with augmented EM images to generate utterly new EM images. Finally, we rotate the generated samples in various directions to obtain a more natural performance. In this study, we use VGG16 and ResNet50 networks to evaluate the proposed EF-GANs on 21 different types of EMs (420 EM images). It is observed that the average precision (AP) of VGG16 increases between 4.5% and 84.1% in 20 EM classes and one class remains unchanged. The AP of Resnet50 rises between 8.7% and 38.7% in 12 EM classes and reaches 100% in two EM classes. Furthermore, to reflect the generalization performance of EF-GANs, we employ an utterly new EM image dataset (630 EM images) to test the previous VGG16 networks. We select the VGG16 networks with original and optimal settings for all the EM classes, and for testing, optimal settings for a single EM class is considered. In the 20 of 21 one-vs-rest EM image classification tasks, the AP of VGG16 increases between 1.66% and 88.1%. The results demonstrate that the proposed EF-GANs can achieve outstanding performance in augmenting single EM images with high quality and resolution, thus, to improve the APs of EM image classification.

Extreme learning machine (ELM) is characterized by good generalization performance, fast training speed and less human intervention. With the explosion of large amount of data generated on the Internet, the learning algorithm in the single-machine environment cannot meet the huge memory consumption of matrix computing, so the implement of distributed ELM algorithm has gradually become one of the research focuses. In view of the research significance and implementation value of distributed ELM, this paper first introduced the research background of ELM and improved ELM. Secondly, this paper elaborated the implementation method of distributed ELM from the two directions: ensemble and matrix operation. Finally, we summarized the development status of distributed ELM and discussed the future research direction.

Current research focus on the perovskites solar cells (PSCs) is mainly limited to the lead-based ones with bandgaps above 1.5 eV. Here Hu et al. report efficient and stable inorganic tin-containing PSCs, opening doors to exploring abundant perovskite materials with bandgaps lower than 1.4 eV.

Freezing of gait (FOG) in Parkinson's disease (PD) leads to devastating consequences; however, little is known about its functional brain network. We explored the differences in degree centrality (DC) of functional networks among PD with FOG (PD FOG+), PD without FOG (PD FOG–), and healthy control (HC) groups. In all, 24 PD FOG+, 37 PD FOG–, and 22 HCs were recruited and their resting-state functional magnetic imaging images were acquired. The whole brain network was analyzed using graph theory analysis. DC was compared among groups using the two-sample t-test. The DC values of disrupted brain regions were correlated with the FOG Questionnaire (FOGQ) scores. Receiver operating characteristic curve analysis was performed. We found significant differences in DC among groups. Compared with HCs, PD FOG+ patients showed decreased DC in the middle frontal gyrus (MFG), superior temporal gyrus (STG), parahippocampal gyrus (PhG), inferior temporal gyrus (ITG), and middle temporal gyrus (MTG). Compared with HC, PD FOG– presented with decreased DC in the MFG, STG, PhG, and ITG. Compared with PD FOG–, PD FOG+ showed decreased DC in the MFG and ITG. A negative correlation existed between the DC of ITG and FOGQ scores; the DC in ITG could distinguish PD FOG+ from PD FOG– and HC. The calculated AUCs were 81.3, 89.5, and 77.7% for PD FOG+ vs. HC, PD FOG– vs. HC, and PD FOG+ vs. PD FOG–, respectively. In conclusion, decreased DC of ITG in PD FOG+ patients compared to PD FOG– patients and HCs may be a unique feature for PD FOG+ and can likely distinguish PD FOG+ from PD FOG– and HC groups.

Secondary structure plays an important role in determining the function of noncoding RNAs. Hence, identifying RNA secondary structures is of great value to research. Computational prediction is a mainstream approach for predicting RNA secondary structure. Unfortunately, even though new methods have been proposed over the past 40 years, the performance of computational prediction methods has stagnated in the last decade. Recently, with the increasing availability of RNA structure data, new methods based on machine learning (ML) technologies, especially deep learning, have alleviated the issue. In this review, we provide a comprehensive overview of RNA secondary structure prediction methods based on ML technologies and a tabularized summary of the most important methods in this field. The current pending challenges in the field of RNA secondary structure prediction and future trends are also discussed.

Abstract The physiological processes and mechanisms of an arterial system are complex and subtle. Physics-based models have been proven to be a very useful tool to simulate actual physiological behavior of the arteries. The current physics-based models include high-dimensional models (2D and 3D models) and low-dimensional models (0D, 1D and tube-load models). High-dimensional models can describe the local hemodynamic information of arteries in detail. With regard to an exact model of the whole arterial system, a high-dimensional model is computationally impracticable since the complex geometry, viscosity or elastic properties and complex vectorial output need to be provided. For low-dimensional models, the structure, centerline and viscosity or elastic properties only need to be provided. Therefore, low-dimensional modeling with lower computational costs might be a more applicable approach to represent hemodynamic properties of the entire arterial system and these three types of low-dimensional models have been extensively used in the study of cardiovascular dynamics. In recent decades, application of physics-based models to estimate central aortic pressure has attracted increasing interest. However, to our best knowledge, there has been few review paper about reconstruction of central aortic pressure using these physics-based models. In this paper, three types of low-dimensional physical models (0D, 1D and tube-load models) of systemic arteries are reviewed, the application of three types of models on estimation of central aortic pressure is taken as an example to discuss their advantages and disadvantages, and the proper choice of models for specific researches and applications are advised.

Since the Internet of Things (IoT) applications today employ many different sensors to provide information, a large number of the Bluetooth low energy (BLE) devices will be developed as part of the IoT systems. The low-power and low-cost requirements of all BLE nodes are among the most challenging issues when supporting the neighbor discovery process (NDP) for such a large number of devices. Since the parameter settings are essential to achieve the required performance for the NDP, a parameter configuration method for neighbor discovery in BLE can be beneficial for determining some critical parameter metrics, such as the AdvInterval, ScanInterval, and ScanWindow. In this paper, we propose a parameter configuration scheme to balance the tradeoff between discovery latency and energy consumption. In the proposed scheme, the neighbor discovery latency and average energy consumption are expressed based on the Chinese Remainder Theory (CRT). With the expected primary performance, the parameters are configured accordingly using the parameter configuration algorithm. The experimental results show that the performance of the neighbor discovery varies with the parameter settings. Furthermore, two typical IoT applications are assessed in this paper. Compared with the simulation results, the proposed parameter configuration scheme can achieve high accuracy.

CT screening has been proven to be effective for diagnosing lung cancer at its early manifestation in the form of pulmonary nodules, thus decreasing the mortality. However, the exponential increase of image data makes their accurate assessment a very challenging task given that the number of radiologists is limited and they have been overworked. Recently, numerous methods, especially ones based on deep learning with convolutional neural network (CNN), have been developed to automatically detect and classify pulmonary nodules in medical images. In this paper, we present a comprehensive analysis of these methods and their performances. First, we briefly introduce the fundamental knowledge of CNN as well as the reasons for their suitability to medical images analysis. Then, a brief description of various medical images datasets, as well as the environmental setup essential for facilitating lung nodule investigations with CNNs, is presented. Furthermore, comprehensive overviews of recent progress in pulmonary nodule analysis using CNNs are provided. Finally, existing challenges and promising directions for further improving the application of CNN to medical images analysis and pulmonary nodule assessment, in particular, are discussed. It is shown that CNNs have transformed greatly the early diagnosis and management of lung cancer. We believe that this review will provide all the medical research communities with the necessary knowledge to master the concept of CNN so as to utilize it for improving the overall human healthcare system.

Spectral reconstruction method based on narrow-band measurements has been demonstrated to achieve ultrafast spectroscopic imaging with high spatial and spectral resolution, in which multiple narrow-band images are collected by using several specific filters. Although commercially available filters can be employed in such method, filters with complex transmittance that are difficult to be fabricated typically show significant improvement in spectral reconstruction accuracy. In this study, a two dimensional programmable optical filter based on digital micromirror device (DMD) is proposed, in which its transmittance spectrum can be arbitrarily and quickly switched to realize complex transmittance. Furthermore, its flexible transmittance enables directly hardware-based spectral data post-processing, which can perform data acquisition and analysis simultaneously. Those have been evaluated by the diffuse reflectance spectra from normal and occluded skin flaps, as well as Raman spectra from live, apoptosis and necrosis leukemia cells. Our simulation results show that much higher spectral reconstruction accuracies can be achieved by the optimized filters with complex transmittance. Furthermore, the classification accuracy by using the proposed method is comparable to those achieved by conventional numerical methods. Therefore, based on the proposed programmable optical filter, fast spectroscopic imaging with high spatial and spectral resolution can be achieved for observing fast changing phenomena and even real-time target identification.

Accurate segmentation of bi-ventricle from cardiac magnetic resonance images (MRI) is a critical step in cardiac function analysis and disease diagnosis. Due to the morphological diversification of the heart and the factors of MRI itself, fully automated and concurrent bi-ventricle segmentation is a well-known challenge. In this paper, we propose cascaded conditional generative adversarial networks (C-cGANs) to divide the problem into two segmentation subtasks: binary segmentation for region of interest (ROI) extraction and bi-ventricle segmentation. In both subtasks, we adopt adversarial training that makes discriminator network to discriminate segmentation maps either from generator network or ground-truth which aims to detect and correct pixel-wise inconsistency between the sources of segmentation maps. For capturing more spatial information with multi-scale semantic features, in the generator network, we insert a multi-scale attention fusion (MSAF) module between the encoder and decoder paths. The experiment on ACDC 2017 dataset shows that the proposed model outperforms other state-of-the-art methods in most metrics. Moreover, we validate the generalization capability of this model on MS-CMRSeg 2019 and RVSC 2012 datasets without fine-tuning, and the results demonstrate the effectiveness and robustness of the proposed method for bi-ventricle segmentation.

A computer-aided diagnosis (CAD) system based on mammograms enables early breast cancer detection, diagnosis, and treatment. However, the accuracy of the existing CAD systems remains unsatisfactory. This paper explores a breast CAD method based on feature fusion with convolutional neural network (CNN) deep features. First, we propose a mass detection method based on CNN deep features and unsupervised extreme learning machine (ELM) clustering. Second, we build a feature set fusing deep features, morphological features, texture features, and density features. Third, an ELM classifier is developed using the fused feature set to classify benign and malignant breast masses. Extensive experiments demonstrate the accuracy and efficiency of our proposed mass detection and breast cancer classification method.

Abstract Background Lung segmentation constitutes a critical procedure for any clinical-decision supporting system aimed to improve the early diagnosis and treatment of lung diseases. Abnormal lungs mainly include lung parenchyma with commonalities on CT images across subjects, diseases and CT scanners, and lung lesions presenting various appearances. Segmentation of lung parenchyma can help locate and analyze the neighboring lesions, but is not well studied in the framework of machine learning. Methods We proposed to segment lung parenchyma using a convolutional neural network (CNN) model. To reduce the workload of manually preparing the dataset for training the CNN, one clustering algorithm based method is proposed firstly. Specifically, after splitting CT slices into image patches, the k-means clustering algorithm with two categories is performed twice using the mean and minimum intensity of image patch, respectively. A cross-shaped verification, a volume intersection, a connected component analysis and a patch expansion are followed to generate final dataset. Secondly, we design a CNN architecture consisting of only one convolutional layer with six kernels, followed by one maximum pooling layer and two fully connected layers. Using the generated dataset, a variety of CNN models are trained and optimized, and their performances are evaluated by eightfold cross-validation. A separate validation experiment is further conducted using a dataset of 201 subjects (4.62 billion patches) with lung cancer or chronic obstructive pulmonary disease, scanned by CT or PET/CT. The segmentation results by our method are compared with those yielded by manual segmentation and some available methods. Results A total of 121,728 patches are generated to train and validate the CNN models. After the parameter optimization, our CNN model achieves an average F-score of 0.9917 and an area of curve up to 0.9991 for classification of lung parenchyma and non-lung-parenchyma. The obtain model can segment the lung parenchyma accurately for 201 subjects with heterogeneous lung diseases and CT scanners. The overlap ratio between the manual segmentation and the one by our method reaches 0.96. Conclusions The results demonstrated that the proposed clustering algorithm based method can generate the training dataset for CNN models. The obtained CNN model can segment lung parenchyma with very satisfactory performance and have the potential to locate and analyze lung lesions.

This paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy. The PID-Net is an end-to-end convolutional neural network (CNN) model with an encoder–decoder architecture. The pixel interval down-sampling operations are concatenated with max-pooling operations to combine the sparse and dense features. This addresses the limitation of contour conglutination of dense objects while counting. The evaluation was conducted using classical segmentation metrics (the Dice, Jaccard and Hausdorff distance) as well as counting metrics. The experimental results show that the proposed PID-Net had the best performance and potential for dense tiny object counting tasks, which achieved 96.97% counting accuracy on the dataset with 2448 yeast cell images. By comparing with the state-of-the-art approaches, such as Attention U-Net, Swin U-Net and Trans U-Net, the proposed PID-Net can segment dense tiny objects with clearer boundaries and fewer incorrect debris, which shows the great potential of PID-Net in the task of accurate counting.

Freezing of gait (FOG) has devastating consequences for patients with Parkinson's disease (PD), but the underlying pathophysiological mechanism is unclear. This was investigated in the present study by integrated structural and functional connectivity analyses of PD patients with or without FOG (PD FOG+ and PD FOG–, respectively) and healthy control (HC) subjects. We performed resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging of 24 PD FOG+ patients, 37 PD FOG– patients, and 24 HCs. Tract-based spatial statistics was applied to identify white matter (WM) abnormalities across the whole brain. Fractional anisotropy (FA) and mean diffusivity (MD) of abnormal WM areas were compared among groups, and correlations between these parameters and clinical severity as determined by FOG Questionnaire (FOGQ) score were analyzed. Voxel-mirrored homotopic connectivity (VMHC) was calculated to identify brain regions with abnormal interhemispheric connectivity. Structural and functional measures were integrated by calculating correlations between VMHC and FOGQ score and between FA, MD, and VMHC. The results showed that PD FOG+ and PD FOG– patients had decreased FA in the corpus callosum (CC), cingulum (hippocampus), and superior longitudinal fasciculus and increased MD in the CC, internal capsule, corona radiata, superior longitudinal fasciculus, and thalamus. PD FOG+ patients had more WM abnormalities than PD FOG– patients. FA and MD differed significantly among the splenium, body, and genu of the CC in all three groups (P < 0.05). The decreased FA in the CC was positively correlated with FOGQ score. PD FOG+ patients showed decreased VMHC in the post-central gyrus (PCG), pre-central gyrus, and parietal inferior margin. In PD FOG+ patients, VMHC in the PCG was negatively correlated with FOGQ score but positively correlated with FA in CC. Thus, FOG is associated with impaired interhemispheric brain connectivity measured by FA, MD, and VMHC, which are related to clinical FOG severity. These results demonstrate that integrating structural and functional MRI data can provide new insight into the pathophysiological mechanism of FOG in PD.