Linear semantic transformation for semi-supervised medical image segmentation.

Medical image segmentation is a focus research and foundation in developing intelligent medical systems. Recently, deep learning for medical image segmentation has become a standard process and succeeded significantly, promoting the development of reconstruction, and surgical planning of disease diagnosis. However, semantic learning is often inefficient owing to the lack of supervision of feature maps, resulting in that high-quality segmentation models always rely on numerous and accurate data annotations. Learning robust semantic representation in latent spaces remains a challenge. In this paper, we propose a novel semi-supervised learning framework to learn vital attributes in medical images, which constructs generalized representation from diverse semantics to realize medical image segmentation. We first build a self-supervised learning part that achieves context recovery by reconstructing space and intensity of medical images, which conduct semantic representation for feature maps. Subsequently, we combine semantic-rich feature maps and utilize simple linear semantic transformation to convert them into image segmentation. The proposed framework was tested using five medical segmentation datasets. Quantitative assessments indicate the highest scores of our method on IXI (73.78%), ScaF (47.50%), COVID-19-Seg (50.72%), PC-Seg (65.06%), and Brain-MR (72.63%) datasets. Finally, we compared our method with the latest semi-supervised learning methods and obtained 77.15% and 75.22% DSC values, respectively, ranking first on two representative datasets. The experimental results not only proved that the proposed linear semantic transformation was effectively applied to medical image segmentation, but also presented its simplicity and ease-of-use to pursue robust segmentation in semi-supervised learning. Our code is now open at: https://github.com/QingYunA/Linear-Semantic-Transformation-for-Semi-Supervised-Medical-Image-Segmentation.

Skin Conductance-Based Acupoint and Non-Acupoint Recognition Using Machine Learning.

Acupoints (APs) prove to have positive effects on disease diagnosis and treatment, while intelligent techniques for the automatic detection of APs are not yet mature, making them more dependent on manual positioning. In this paper, we realize the skin conductance-based APs and non-APs recognition with machine learning, which could assist in APs detection and localization in clinical practice. Firstly, we collect skin conductance of traditional Five-Shu Point and their corresponding non-APs with wearable sensors, establishing a dataset containing over 36000 samples of 12 different AP types. Then, electrical features are extracted from the time domain, frequency domain, and nonlinear perspective respectively, following which typical machine learning algorithms (SVM, RF, KNN, NB, and XGBoost) are demonstrated to recognize APs and non-APs. The results demonstrate XGBoost with the best precision of 66.38%. Moreover, we also quantify the impacts of the differences among AP types and individuals, and propose a pairwise feature generation method to weaken the impacts on recognition precision. By using generated pairwise features, the recognition precision could be improved by 7.17%. The research systematically realizes the automatic recognition of APs and non-APs, and is conducive to pushing forward the intelligent development of APs and Traditional Chinese Medicine theories.

A learnable Gabor Convolution kernel for vessel segmentation.

Vessel segmentation is significant for characterizing vascular diseases, receiving wide attention of researchers. The common vessel segmentation methods are mainly based on convolutional neural networks (CNNs), which have excellent feature learning capabilities. Owing to inability to predict learning direction, CNNs generate large channels or sufficient depth to obtain sufficient features. It may engender redundant parameters. Drawing on performance ability of Gabor filters in vessel enhancement, we built Gabor convolution kernel and designed its optimization. Unlike traditional filter using and common modulation, its parameters are automatically updated using gradients in the back propagation. Since the structural shape of Gabor convolution kernels is the same as that of regular convolution kernels, it can be integrated into any CNNs architecture. We built Gabor ConvNet using Gabor convolution kernels and tested it using three vessel datasets. It scored 85.06%, 70.52% and 67.11%, respectively, ranking first on three datasets. Results shows that our method outperforms advanced models in vessel segmentation. Ablations also proved that Gabor kernel has better vessel extraction ability than the regular convolution kernel.

All answers are in the images: A review of deep learning for cerebrovascular segmentation.

Cerebrovascular imaging is a common examination. Its accurate cerebrovascular segmentation become an important auxiliary method for the diagnosis and treatment of cerebrovascular diseases, which has received extensive attention from researchers. Deep learning is a heuristic method that encourages researchers to derive answers from the images by driving datasets. With the continuous development of datasets and deep learning theory, it has achieved important success for cerebrovascular segmentation. Detailed survey is an important reference for researchers. To comprehensively analyze the newest cerebrovascular segmentation, we have organized and discussed researches centered on deep learning. This survey comprehensively reviews deep learning for cerebrovascular segmentation since 2015, it mainly includes sliding window based models, U-Net based models, other CNNs based models, small-sample based models, semi-supervised or unsupervised models, fusion based models, Transformer based models, and graphics based models. We organize the structures, improvement, and important parameters of these models, as well as analyze development trends and quantitative assessment. Finally, we have discussed the challenges and opportunities of possible research directions, hoping that our survey can provide researchers with convenient reference.

Integration- and separation-aware adversarial model for cerebrovascular segmentation from TOF-MRA.

PURPOSE: Cerebrovascular segmentation from time-of-flight magnetic resonance angiography (TOF-MRA) is important but challenging for the simulation and measurement of cerebrovascular diseases. Recently, deep learning has promoted the rapid development of cerebrovascular segmentation. However, model optimization relies on voxel or regional punishment and lacks global awareness and interpretation from the texture and edge. To overcome the limitations of the existing methods, we propose a new cerebrovascular segmentation method to obtain more refined structures. METHODS: In this paper, we propose a new adversarial model that achieves segmentation using segmentation model and filters the results using discriminator. Considering the sample imbalance in cerebrovascular imaging, we separated the TOF-MRA images and utilized high- and low-frequency images to enhance the texture and edge representation. The encoder weight sharing from the segmentation model not only saves the model parameters, but also strengthens the integration and separation correlation. Diversified discrimination enhances the robustness and regularization of the model. RESULTS: The adversarial model was tested using two cerebrovascular datasets. It scored 82.26% and 73.38%, respectively, ranking first on both datasets. The results show that our method not only outperforms the recent cerebrovascular segmentation model, but also surpasses the common adversarial models. CONCLUSION: Our adversarial model focuses on improving the extraction ability of the model on texture and edge, thereby achieving awareness of the global cerebrovascular topology. Therefore, we obtained an accurate and robust cerebrovascular segmentation. This framework has potential applications in many imaging fields, particularly in the application of sample imbalance. Our code is available at the website https://github.com/MontaEllis/ISA-model.

Pairwise attention-enhanced adversarial model for automatic bone segmentation in CT images.

Objective. Bone segmentation is a critical step in screw placement navigation. Although the deep learning methods have promoted the rapid development for bone segmentation, the local bone separation is still challenging due to irregular shapes and similar representational features.Approach. In this paper, we proposed the pairwise attention-enhanced adversarial model (Pair-SegAM) for automatic bone segmentation in computed tomography images, which includes the two parts of the segmentation model and discriminator. Considering that the distributions of the predictions from the segmentation model contains complicated semantics, we improve the discriminator to strengthen the awareness ability of the target region, improving the parsing of semantic information features. The Pair-SegAM has a pairwise structure, which uses two calculation mechanics to set up pairwise attention maps, then we utilize the semantic fusion to filter unstable regions. Therefore, the improved discriminator provides more refinement information to capture the bone outline, thus effectively enhancing the segmentation models for bone segmentation.Main results. To test the Pair-SegAM, we selected the two bone datasets for assessment. We evaluated our method against several bone segmentation models and latest adversarial models on the both datasets. The experimental results prove that our method not only exhibits superior bone segmentation performance, but also states effective generalization.Significance. Our method provides a more efficient segmentation of specific bones and has the potential to be extended to other semantic segmentation domains.

FDE-net: Frequency-domain enhancement network using dynamic-scale dilated convolution for thyroid nodule segmentation.

Thyroid nodules, a common disease of endocrine system, have a probability of nearly 10% to turn into malignant nodules and thus pose a serious threat to health. Automatic segmentation of thyroid nodules is of great importance for clinicopathological diagnosis. This work proposes FDE-Net, a combined segmental frequency domain enhancement and dynamic scale cavity convolutional network for thyroid nodule segmentation. In FDE-Net, traditional image omics method is introduced to enhance the feature image in the segmented frequency domain. Such an approach reduces the influence of noise and strengthens the detail and contour information of the image. The proposed method introduces a cascade cross-scale attention module, which addresses the insensitivity of the network to the change in target scale by fusing the features of different receptive fields and improves the ability of the network to identify multiscale target regions. It repeatedly uses the high-dimensional feature image to improve segmentation accuracy in accordance with the simple structure of thyroid nodules. In this study, 1355 ultrasound images are used for training and testing. Quantitative evaluation results showed that the Dice coefficient of FDE-Net in thyroid nodule segmentation was 83.54%, which is better than other methods. Therefore, FDE-Net can enable the accurate and rapid segmentation of thyroid nodules.

Generative Consistency for Semi-Supervised Cerebrovascular Segmentation From TOF-MRA.

Cerebrovascular segmentation from Time-of-flight magnetic resonance angiography (TOF-MRA) is a critical step in computer-aided diagnosis. In recent years, deep learning models have proved its powerful feature extraction for cerebrovascular segmentation. However, they require many labeled datasets to implement effective driving, which are expensive and professional. In this paper, we propose a generative consistency for semi-supervised (GCS) model. Considering the rich information contained in the feature map, the GCS model utilizes the generation results to constrain the segmentation model. The generated data comes from labeled data, unlabeled data, and unlabeled data after perturbation, respectively. The GCS model also calculates the consistency of the perturbed data to improve the feature mining ability. Subsequently, we propose a new model as the backbone of the GSC model. It transfers TOF-MRA into graph space and establishes correlation using Transformer. We demonstrated the effectiveness of the proposed model on TOF-MRA representations, and tested the GCS model with state-of-the-art semi-supervised methods using the proposed model as backbone. The experiments prove the important role of the GCS model in cerebrovascular segmentation. Code is available at https://github.com/MontaEllis/SSL-For-Medical-Segmentation.

Cerebrovascular segmentation in phase-contrast magnetic resonance angiography by multi-feature fusion and vessel completion.

Phase-Contrast Magnetic Resonance Angiography (PC-MRA) is a potential way of cerebrovascular imaging, which can suppress non-vascular tissue while presenting vessels. But PC-MRA will bring much noise and is easy to result in partially broken vessels. Usually, deep learning is an effective way to quantify vessels. However, how to choose an appropriate deep learning model is an important and difficult issue. In this work, we adopted the Dempster-Shafer (DS) evidence theory to fuse multi-feature from different models. Also, the vessel thinning and completion method were proposed to fill in information of broken cerebrovascular in PC-MRA images. For quantitative analysis, we chose Precision (PRE), Recall (REC), and Dice Similarity Coefficient (DSC) as assessment metrics, and established U-Net, V-Net, and Dense-Net. The 22 subjects tested this method. Comparison with different fusion strategies and common deep learning models have confirmed the effectiveness of the proposed method. In addition, we scanned Contrast-Enhanced MRA (CE-MRA) for 12 patients to verify reliability of vessel completion. Experiments show that the completion vessel can improve the matching ratio with CE-MRA, which has clinical potential.

TMSF-Net: Multi-series fusion network with treeconnect for colorectal tumor segmentation.

PURPOSE: Colorectal tumors are common clinical diseases. Automatic segmentation of colorectal tumors captured in computed tomography (CT) images can provide numerous possibilities for computer-assisted treatment. Obtaining large datasets is expensive, and completing labeling is time- and manpower-consuming. To solve the challenge using a limited pathological dataset, this paper proposes a multi-series fusion network with treeconnect (TMSF-Net), which can automatically achieve colorectal tumor segmentation using CT images. METHODS: To drive the TMSF-Net, three-series enhanced CT images were collected from all patients to improve the data characteristics. In the TMSF-Net, the coding path was designed as a three-branch structure to realize the feature extraction of the different series. Subsequently, the three branches were merged to start the feature analysis in the decoding path. To achieve the objective of feature fusion, different layers in the decoding path fused feature maps from the upper layer in the encoding path to achieve a cross-scale fusion. In addition, to reduce the problem of parameter redundancy, this study adopted a three-dimensional treeconnect to complete data connection on three branches. RESULTS: A total of 22 cases were conducted by ablation and comparative experiments to test the TMSF-Net. The results showed that the TMSF-Net can improve the network performance by multiseries fusion, and its expressiveness is better than many classic networks. CONCLUSION: The TMSF-Net is a many-to-one structure network, which can enhance the network learning ability and improve the analysis of potential features. Therefore, it yields good results in colorectal tumor segmentation. It can provide a new direction for neural network models based on feature fusion.

DW-UNet: Loss Balance under Local-Patch for 3D Infection Segmentation from COVID-19 CT Images.

(1) Background: COVID-19 has been global epidemic. This work aims to extract 3D infection from COVID-19 CT images; (2) Methods: Firstly, COVID-19 CT images are processed with lung region extraction and data enhancement. In this strategy, gradient changes of voxels in different directions respond to geometric characteristics. Due to the complexity of tubular tissues in lung region, they are clustered to the lung parenchyma center based on their filtered possibility. Thus, infection is improved after data enhancement. Then, deep weighted UNet is established to refining 3D infection texture, and weighted loss function is introduced. It changes cost calculation of different samples, causing target samples to dominate convergence direction. Finally, the trained network effectively extracts 3D infection from CT images by adjusting driving strategy of different samples. (3) Results: Using Accuracy, Precision, Recall and Coincidence rate, 20 subjects from a private dataset and eight subjects from Kaggle Competition COVID-19 CT dataset tested this method in hold-out validation framework. This work achieved good performance both in the private dataset (99.94-00.02%, 60.42-11.25%, 70.79-09.35% and 63.15-08.35%) and public dataset (99.73-00.12%, 77.02-06.06%, 41.23-08.61% and 52.50-08.18%). We also applied some extra indicators to test data augmentation and different models. The statistical tests have verified the significant difference of different models. (4) Conclusions: This study provides a COVID-19 infection segmentation technology, which provides an important prerequisite for the quantitative analysis of COVID-19 CT images.

CSR-Net: Cross-Scale Residual Network for multi-objective scaphoid fracture segmentation.

The scaphoid is located in the carpals. Owing to the body structure and location of the scaphoid, scaphoid fractures are common and it is difficult to heal. Three-dimensional reconstruction of scaphoid fracture can accurately display the fracture surface and provide important support for the surgical plan involving screw placement. To achieve this goal, in this study, the cross-scale residual network (CSR-Net) is proposed for scaphoid fracture segmentation. In the CSR-Net, the features of different layers are used to achieve fusion through cross-scale residual connection, which realizes scale and channel conversions between the features of different layers. It can establish close connections between different scale features. The structures of the output layer and channel are designed to establish the CSR-Net as a multi-objective architecture, which can realize scaphoid fracture and hand bone segmentations synchronously. In this study, 65 computed tomography images of scaphoid fracture are tested. Quantitative metrics are used for assessment, and the results obtained show that the CSR-Net achieves higher performance in hand bone and scaphoid fracture segmentations. In the visually detailed display, the fracture surface is clearer and more intuitive than those obtained from other methods. Therefore, the CSR-Net can achieve accurate and rapid scaphoid fracture segmentation. Its multi-objective design provides not only an accurate digital model, but also a prerequisite for navigation in the hand bone.

Cerebrovascular segmentation from TOF-MRA based on multiple-U-net with focal loss function.

BACKGROUND AND OBJECTIVE: Accurate cerebrovascular segmentation plays an important role in the diagnosis of cerebrovascular diseases. Considering the complexity and uncertainty of doctors' manual segmentation of cerebral vessels, this paper proposed an automatic segmentation algorithm based on Multiple-U-net (M-U-net) to segment cerebral vessel structures from the Time-of-flight Magnetic Resonance Angiography (TOF-MRA) data. METHODS: First, the TOF-MRA data was normalized by volume and then divided into three groups through slices of axial, coronal and sagittal directions respectively. Three single U-nets were trained by divided dataset. To solve the problem of uneven distribution of positive and negative samples, the focal loss function was adopted in training. After obtaining the prediction results of three single U-nets, the voting feature fusion and the post-processing process based on connected domain analysis would be performed. 95 volumes of TOF-MRA provided by the MIDAS platform were applied to the experiment, among which 20 volumes were treated as the training dataset, 5 volumes were used as the validation dataset and the remaining 70 volumes were divided into 10 groups to test the trained model respectively. RESULTS: Experiments showed that the proposed M-U-net based algorithm achieved 88.60% and 87.93% Dice Similarity Coefficient (DSC) on the verification dataset and testing dataset, which performed better than any single U-net. CONCLUSIONS: Compared with other existing algorithms, our algorithm reached the state of the art level. The feature fusion of three single U-nets could effectively complement the segmentation results.

An Effective Deep Neural Network for Lung Lesions Segmentation From COVID-19 CT Images.

Automatic segmentation of lung lesions from COVID-19 computed tomography (CT) images can help to establish a quantitative model for diagnosis and treatment. For this reason, this article provides a new segmentation method to meet the needs of CT images processing under COVID-19 epidemic. The main steps are as follows: First, the proposed region of interest extraction implements patch mechanism strategy to satisfy the applicability of 3-D network and remove irrelevant background. Second, 3-D network is established to extract spatial features, where 3-D attention model promotes network to enhance target area. Then, to improve the convergence of network, a combination loss function is introduced to lead gradient optimization and training direction. Finally, data augmentation and conditional random field are applied to realize data resampling and binary segmentation. This method was assessed with some comparative experiment. By comparison, the proposed method reached the highest performance. Therefore, it has potential clinical applications.

Pathological lung segmentation in chest CT images based on improved random walker.

BACKGROUND AND OBJECTIVE: Pathological lung segmentation as a pretreatment step in the diagnosis of lung diseases has been widely explored. Because of the complexity of pathological lung structures and gray blur of the border, accurate lung segmentation in clinical 3D computed tomography images is a challenging task. In view of the current situation, the work proposes a fast and accurate pathological lung segmentation method. The following contributions have been made: First, the edge weights introduce spatial information and clustering information, so that walkers can use more image information during walking. Second, a Gaussian Distribution of seed point set is established to further expand the possibility of selection between fake seed points and real seed points. Finally, the pre-parameter is calculated using original seed points, and the final results are fitted with new seed points. METHODS: This study proposes a segmentation method based on an improved random walker algorithm. The proposed method consists of the following steps: First, a gray value is used as the sample distribution. Gaussian mixture model is used to obtain the clustering probability of an image. Thus, the spatial distance and clustering result are added as new weights, and the new edge weights are used to construct a random walker map. Second, a large number of marked points are automatically selected, and the intermediate results are obtained from the newly constructed map and retained only as pre-parameters. When new seed points are introduced, the probability value of the walker is quickly calculated from the new parameters and pre-parameters, and the final segmentation result can be obtained. RESULTS: The proposed method was tested on 65 sets of CT cases. Quantitative evaluation with different methods confirms the high accuracy on our dataset (98.55%) and LOLA11 dataset (97.41%). Similarly, the average segmentation time (10.5s) is faster than random walker (1,332.5s). CONCLUSIONS: The comparison of the experimental results show that the proposed method can accurately and quickly obtain pathological lung processing results. Therefore, it has potential clinical applications.

Segmentation of Cerebrovascular Anatomy from TOF-MRA Using Length-Strained Enhancement and Random Walker.

Cerebrovascular rupture can cause a severe stroke. Three-dimensional time-of-flight (TOF) magnetic resonance angiography (MRA) is a common method of obtaining vascular information. This work proposes a fully automated segmentation method for extracting the vascular anatomy from TOF-MRA. The steps of the method are as follows. First, the brain is extracted on the basis of regional growth and path planning. Next, the brain's highlighted connected area is explored to obtain seed point information, and the Hessian matrix is used to enhance the contrast of image. Finally, a random walker combined with seed points and enhanced images is used to complete vascular anatomy segmentation. The method is tested using 12 sets of data and compared with two traditional vascular segmentation methods. Results show that the described method obtains an average Dice coefficient of 90.68%, and better results were obtained in comparison with the traditional methods.

Radiomics Nomogram for Prediction of Peritoneal Metastasis in Patients With Gastric Cancer.

Objective: The aim of this study is to evaluate whether radiomics imaging signatures based on computed tomography (CT) could predict peritoneal metastasis (PM) in gastric cancer (GC) and to develop a nomogram for preoperative prediction of PM status. Methods: We collected CT images of pathological T4 gastric cancer in 955 consecutive patients of two cancer centers to analyze the radiomics features retrospectively and then developed and validated the prediction model built from 292 quantitative image features in the training cohort and two validation cohorts. Lasso regression model was applied for selecting feature and constructing radiomics signature. Predicting model was developed by multivariable logistic regression analysis. Radiomics nomogram was developed by the incorporation of radiomics signature and clinical T and N stage. Calibration, discrimination, and clinical usefulness were used to evaluate the performance of the nomogram. Results: In training and validation cohorts, PM status was associated with the radiomics signature significantly. It was found that the radiomics signature was an independent predictor for peritoneal metastasis in multivariable logistic analysis. For training and internal and external validation cohorts, the area under the receiver operating characteristic curves (AUCs) of radiomics signature for predicting PM were 0.751 (95%CI, 0.703-0.799), 0.802 (95%CI, 0.691-0.912), and 0.745 (95%CI, 0.683-0.806), respectively. Furthermore, for training and internal and external validation cohorts, the AUCs of radiomics nomogram for predicting PM were 0.792 (95%CI, 0.748-0.836), 0.870 (95%CI, 0.795-0.946), and 0.815 (95%CI, 0.763-0.867), respectively. Conclusions: CT-based radiomics signature could predict peritoneal metastasis, and the radiomics nomogram can make a meaningful contribution for predicting PM status in GC patient preoperatively.

Erratum to radiographic assessment of the cup orientation after total hip arthroplasty: a literature review.

[This corrects the article DOI: 10.21037/atm.2019.12.150.].

Machine learning techniques for biomedical image segmentation: An overview of technical aspects and introduction to state-of-art applications.

In recent years, significant progress has been made in developing more accurate and efficient machine learning algorithms for segmentation of medical and natural images. In this review article, we highlight the imperative role of machine learning algorithms in enabling efficient and accurate segmentation in the field of medical imaging. We specifically focus on several key studies pertaining to the application of machine learning methods to biomedical image segmentation. We review classical machine learning algorithms such as Markov random fields, k-means clustering, random forest, etc. Although such classical learning models are often less accurate compared to the deep-learning techniques, they are often more sample efficient and have a less complex structure. We also review different deep-learning architectures, such as the artificial neural networks (ANNs), the convolutional neural networks (CNNs), and the recurrent neural networks (RNNs), and present the segmentation results attained by those learning models that were published in the past 3 yr. We highlight the successes and limitations of each machine learning paradigm. In addition, we discuss several challenges related to the training of different machine learning models, and we present some heuristics to address those challenges.

Radiographic assessment of the cup orientation after total hip arthroplasty: a literature review.

Optimal acetabular cup orientation is of substantial importance to good long-term function and low complication rates after total hip arthroplasty (THA). The radiographic anteversion (RA) and inclination (RI) angles of the cup are typically studied due to the practicability, simplicity, and ease of interpretation of their measurements. A great number of methods have been developed to date, most of which have been performed on pelvic or hip anteroposterior radiographs. However, there are primarily two influencing factors for these methods: X-ray offset and pelvic rotation. In addition, there are three types of pelvic rotations about the transverse, longitudinal, and anteroposterior axes of the body. Their effects on the RA and RI angles of the cup are interactively correlated with the position and true orientation of the cup. To date, various fitted or analytical models have been established to disclose the correlations between the X-ray offset and pelvic rotation and the RA and RI angles of the cup. Most of these models do not incorporate all the potential influencing parameters. Advanced methods for performing X-ray offset and pelvic rotation corrections are mainly performed on a single pelvic AP radiograph, two synchronized radiographs, or a two-dimensional/three-dimensional (2D-3D) registration system. Some measurement systems, originally developed for evaluating implant migration or wear, could also be used for correcting the X-ray offset and pelvic rotation simultaneously, but some drawbacks still exist with these systems. Above all, the 2D-3D registration technique might be an alternative and powerful tool for accurately measuring cup orientation. In addition to the current methods used for postoperative assessment, navigation systems and augmented reality are also used for the preoperative planning and intraoperative guidance of cup placement. With the continuing development of artificial intelligence and machine learning, these techniques could be incorporated into robot-assisted orthopaedic surgery in the future.