Volumetric Assessment of the Insula in a Normally Functioning Human Brain Using Magnetic Resonance Imaging / Evaluación Volumétrica de la Ínsula en un Cerebro Humano que Funciona Normalmente Utilizando Imágenes de Resonancia Magnética

SUMMARY: Volumetric assessment of brain structures is an important tool in neuroscience research and clinical practice. The volumetric measurement of normally functioning human brain helps detect age-related changes in some regions, which can be observed at varying degrees. This study aims to estimate the insular volume in the normally functioning human brain in both genders, different age groups, and side variations. A cross-sectional retrospective study was conducted on 42 adult Sudanese participants in Al-Amal Hospital, Sudan, between May to August 2022, using magnetic resonance imaging (MRI) and automatic brain segmentation through a software program (BrainSuite). The statistical difference in total insular volume on both sides of the cerebral hemisphere was small. The insular volume on the right side was greater in males, while the left side showed no difference between both genders. A statistically significant difference between males and females was found (p > 0.05), and no statistical difference in different age groups was found according to the one-way ANOVA test (p>0.05). Adult Sudanese males showed a larger insular volume than females. MRI can be used to morphometrically assess the insula to detect any pathological variations based on volume changes.

La evaluación volumétrica de las estructuras cerebrales es una herramienta importante en la investigación y la práctica clínica de la neurociencia. La medición volumétrica del cerebro humano, que funciona normalmente, ayuda a detectar cambios relacionados con la edad en algunas regiones, las cuales se pueden observar en diversos grados. Este estudio tuvo como objetivo estimar el volumen insular en el cerebro humano que funciona normalmente, en ambos sexos, de diferentes grupos de edad y sus variaciones laterales. Se realizó un estudio retrospectivo transversal en 42 participantes sudaneses adultos en el Hospital Al-Amal, Sudán, entre mayo y agosto de 2022, utilizando imágenes de resonancia magnética y segmentación automática del cerebro a través de un software (BrainSuite). Fue pequeña la diferencia estadística en el volumen insular total, en los hemisferios cerebrales. El volumen insular del lado derecho fue mayor en los hombres, mientras que el lado izquierdo no mostró diferencia entre ambos sexos. Se encontró una diferencia estadísticamente significativa entre hombres y mujeres (p > 0,05), y no se encontró diferencia estadística en los diferentes grupos de edad, según la prueba de ANOVA de una vía (p> 0,05). Los hombres sudaneses adultos mostraron un mayor volumen insular que las mujeres. La resonancia magnética se puede utilizar para evaluar morfométricamente la ínsula y para detectar cualquier variación patológica basada en cambios de volumen.

Medição automática de valva mitral a partir de ecocardiograma utilizando processamento digital de imagens / Automatic measurement of the mitral valve based on echocardiography using digital image processing

Fundamento: A avaliação da área valvar mitral por meio da reconstrução multiplano na ecocardiografia tridimensional é restrita a softwares específicos e à experiência dos ecocardiografistas. Eles precisam selecionar manualmente o frame do vídeo que contenha a área de abertura máxima da valva mitral, dimensão fundamental para a identificação de estenose mitral. Objetivo: Automatizar o processo de determinação da área de abertura máxima da valva mitral, por meio da aplicação de Processamento Digital de Imagens (PDI) em exames de ecocardiograma, desenvolvendo um algoritmo aberto com leitura de vídeo no formato avi. Método: Este estudo piloto observacional transversal foi realizado com vinte e cinco exames diferentes de ecocardiograma, sendo quinze com abertura normal e dez com estenose mitral reumática. Todos os exames foram realizados e disponibilizados por dois especialistas, com autorização do Comitê de Ética em Pesquisa, que utilizaram dois modelos de aparelhos ecocardiográficos: Vivid E95 (GE Healthcare) e Epiq 7 (Philips), com sondas multiplanares transesofágicas. Todos os vídeos em formato avi foram submetidos ao PDI através da técnica de segmentação de imagens. Resultados: As medidas obtidas manualmente por ecocardiografistas experientes e os valores calculados pelo sistema desenvolvido foram comparados utilizando o diagrama de Bland-Altman. Observou-se maior concordância entre valores no intervalo de 0,4 a 2,7 cm². Conclusão: Foi possível determinar automaticamente a área de máxima abertura das valvas mitrais, tanto para os casos advindos da GE quanto da Philips, utilizando apenas um vídeo como dado de entrada. O algoritmo demonstrou economizar tempo nas medições quando comparado com a mensuração habitual. (AU)

Background: The evaluation of mitral valve area through multiplanar reconstruction in 3-dimensional echocardiography is restricted to specific software and to the experience of echocardiographers. They need to manually select the video frame that contains the maximum mitral valve opening area, as this dimension is fundamental to identification of mitral stenosis. Objective: To automate the process of determining the maximum mitral valve opening area, through the application of digital image processing (DIP) in echocardiography tests, developing an open algorithm with video reading in avi format. Method: This cross-sectional observational pilot study was conducted with 25 different echocardiography exams, 15 with normal aperture and 10 with rheumatic mitral stenosis. With the authorization of the Research Ethics Committee, all exams were performed and made available by 2 specialists who used 2 models of echocardiographic devices: Vivid E95 (GE Healthcare) and Epiq 7 (Philips), with multiplanar transesophageal probes. All videos in avi format were submitted to DIP using the image segmentation technique. Results: The measurements obtained manually by experienced echocardiographers and the values calculated by the developed system were compared using a Bland-Altman diagram. There was greater agreement between values in the range from 0.4 to 2.7 cm². Conclusion: It was possible to automatically determine the maximum mitral valve opening area, for cases from both GE and Philips, using only 1 video as input data. The algorithm has been demonstrated to save time on measurements when compared to the usual method. (AU)

A semi-supervised material quantitative intelligent imaging algorithm for spectral CT based on prior information perception learning / 南方医科大学学报

OBJECTIVE@#To propose a semi-supervised material quantitative intelligent imaging algorithm based on prior information perception learning (SLMD-Net) to improve the quality and precision of spectral CT imaging.@*METHODS@#The algorithm includes a supervised and a self- supervised submodule. In the supervised submodule, the mapping relationship between low and high signal-to-noise ratio (SNR) data was constructed through mean square error loss function learning based on a small labeled dataset. In the self- supervised sub-module, an image recovery model was utilized to construct the loss function incorporating the prior information from a large unlabeled low SNR basic material image dataset, and the total variation (TV) model was used to to characterize the prior information of the images. The two submodules were combined to form the SLMD-Net method, and pre-clinical simulation data were used to validate the feasibility and effectiveness of the algorithm.@*RESULTS@#Compared with the traditional model-driven quantitative imaging methods (FBP-DI, PWLS-PCG, and E3DTV), data-driven supervised-learning-based quantitative imaging methods (SUMD-Net and BFCNN), a material quantitative imaging method based on unsupervised learning (UNTV-Net) and semi-supervised learning-based cycle consistent generative adversarial network (Semi-CycleGAN), the proposed SLMD-Net method had better performance in both visual and quantitative assessments. For quantitative imaging of water and bone materials, the SLMD-Net method had the highest PSNR index (31.82 and 29.06), the highest FSIM index (0.95 and 0.90), and the lowest RMSE index (0.03 and 0.02), respectively) and achieved significantly higher image quality scores than the other 7 material decomposition methods (P < 0.05). The material quantitative imaging performance of SLMD-Net was close to that of the supervised network SUMD-Net trained with labeled data with a doubled size.@*CONCLUSIONS@#A small labeled dataset and a large unlabeled low SNR material image dataset can be fully used to suppress noise amplification and artifacts in basic material decomposition in spectral CT and reduce the dependence on labeled data-driven network, which considers more realistic scenario in clinics.

Application of U-Net network in automatic image segmentation of adenoid and airway of nasopharynx / 临床耳鼻咽喉头颈外科杂志

Objective:To explore the effect of fully automatic image segmentation of adenoid and nasopharyngeal airway by deep learning model based on U-Net network. Methods:From March 2021 to March 2022, 240 children underwent cone beam computed tomography（CBCT） in the Department of Otolaryngology, Head and Neck Surgery, General Hospital of Shenzhen University. 52 of them were selected for manual labeling of nasopharynx airway and adenoid, and then were trained and verified by the deep learning model. After applying the model to the remaining data, compare the differences between conventional two-dimensional indicators and deep learning three-dimensional indicators in 240 datasets. Results:For the 52 cases of modeling and training data sets, there was no significant difference between the prediction results of deep learning and the manual labeling results of doctors（P>0.05）. The model evaluation index of nasopharyngeal airway volume: Mean Intersection over Union（MIOU） s （86.32±0.54）%; Dice Similarity Coefficient（DSC）: （92.91±0.23）%; Accuracy: （95.92±0.25）%; Precision: （91.93±0.14）%; and the model evaluation index of Adenoid volume: MIOU: （86.28±0.61）%; DSC: （92.88±0.17）%; Accuracy: （95.90±0.29）%; Precision: （92.30±0.23）%. There was a positive correlation between the two-dimensional index A/N and the three-dimensional index AV/（AV+NAV） in 240 children of different age groups（P<0.05）, and the correlation coefficient of 9-13 years old was 0.74. Conclusion:The deep learning model based on U-Net network has a good effect on the automatic image segmentation of adenoid and nasopharynx airway, and has high application value. The model has a certain generalization ability.

MRI-derived radiomics models for diagnosis, aggressiveness, and prognosis evaluation in prostate cancer / 浙江大学学报（英文版）（B辑：生物医学和生物技术）

Prostate cancer (PCa) is a pernicious tumor with high heterogeneity, which creates a conundrum for making a precise diagnosis and choosing an optimal treatment approach. Multiparametric magnetic resonance imaging (mp-MRI) with anatomical and functional sequences has evolved as a routine and significant paradigm for the detection and characterization of PCa. Moreover, using radiomics to extract quantitative data has emerged as a promising field due to the rapid growth of artificial intelligence (AI) and image data processing. Radiomics acquires novel imaging biomarkers by extracting imaging signatures and establishes models for precise evaluation. Radiomics models provide a reliable and noninvasive alternative to aid in precision medicine, demonstrating advantages over traditional models based on clinicopathological parameters. The purpose of this review is to provide an overview of related studies of radiomics in PCa, specifically around the development and validation of radiomics models using MRI-derived image features. The current landscape of the literature, focusing mainly on PCa detection, aggressiveness, and prognosis evaluation, is reviewed and summarized. Rather than studies that exclusively focus on image biomarker identification and method optimization, models with high potential for universal clinical implementation are identified. Furthermore, we delve deeper into the critical concerns that can be addressed by different models and the obstacles that may arise in a clinical scenario. This review will encourage researchers to design models based on actual clinical needs, as well as assist urologists in gaining a better understanding of the promising results yielded by radiomics.

A survey of loss function of medical image segmentation algorithms / 生物医学工程学杂志

Medical image segmentation based on deep learning has become a powerful tool in the field of medical image processing. Due to the special nature of medical images, image segmentation algorithms based on deep learning face problems such as sample imbalance, edge blur, false positive, false negative, etc. In view of these problems, researchers mostly improve the network structure, but rarely improve from the unstructured aspect. The loss function is an important part of the segmentation method based on deep learning. The improvement of the loss function can improve the segmentation effect of the network from the root, and the loss function is independent of the network structure, which can be used in various network models and segmentation tasks in plug and play. Starting from the difficulties in medical image segmentation, this paper first introduces the loss function and improvement strategies to solve the problems of sample imbalance, edge blur, false positive and false negative. Then the difficulties encountered in the improvement of the current loss function are analyzed. Finally, the future research directions are prospected. This paper provides a reference for the reasonable selection, improvement or innovation of loss function, and guides the direction for the follow-up research of loss function.

Colorectal polyp segmentation method based on fusion of transformer and cross-level phase awareness / 生物医学工程学杂志

In order to address the issues of spatial induction bias and lack of effective representation of global contextual information in colon polyp image segmentation, which lead to the loss of edge details and mis-segmentation of lesion areas, a colon polyp segmentation method that combines Transformer and cross-level phase-awareness is proposed. The method started from the perspective of global feature transformation, and used a hierarchical Transformer encoder to extract semantic information and spatial details of lesion areas layer by layer. Secondly, a phase-aware fusion module (PAFM) was designed to capture cross-level interaction information and effectively aggregate multi-scale contextual information. Thirdly, a position oriented functional module (POF) was designed to effectively integrate global and local feature information, fill in semantic gaps, and suppress background noise. Fourthly, a residual axis reverse attention module (RA-IA) was used to improve the network's ability to recognize edge pixels. The proposed method was experimentally tested on public datasets CVC-ClinicDB, Kvasir, CVC-ColonDB, and EITS, with Dice similarity coefficients of 94.04%, 92.04%, 80.78%, and 76.80%, respectively, and mean intersection over union of 89.31%, 86.81%, 73.55%, and 69.10%, respectively. The simulation experimental results show that the proposed method can effectively segment colon polyp images, providing a new window for the diagnosis of colon polyps.

Segmentation of prostate region in magnetic resonance images based on improved V-Net / 生物医学工程学杂志

Magnetic resonance (MR) imaging is an important tool for prostate cancer diagnosis, and accurate segmentation of MR prostate regions by computer-aided diagnostic techniques is important for the diagnosis of prostate cancer. In this paper, we propose an improved end-to-end three-dimensional image segmentation network using a deep learning approach to the traditional V-Net network (V-Net) network in order to provide more accurate image segmentation results. Firstly, we fused the soft attention mechanism into the traditional V-Net's jump connection, and combined short jump connection and small convolutional kernel to further improve the network segmentation accuracy. Then the prostate region was segmented using the Prostate MR Image Segmentation 2012 (PROMISE 12) challenge dataset, and the model was evaluated using the dice similarity coefficient (DSC) and Hausdorff distance (HD). The DSC and HD values of the segmented model could reach 0.903 and 3.912 mm, respectively. The experimental results show that the algorithm in this paper can provide more accurate three-dimensional segmentation results, which can accurately and efficiently segment prostate MR images and provide a reliable basis for clinical diagnosis and treatment.

CT and MRI fusion based on generative adversarial network and convolutional neural networks under image enhancement / 生物医学工程学杂志

Aiming at the problems of missing important features, inconspicuous details and unclear textures in the fusion of multimodal medical images, this paper proposes a method of computed tomography (CT) image and magnetic resonance imaging (MRI) image fusion using generative adversarial network (GAN) and convolutional neural network (CNN) under image enhancement. The generator aimed at high-frequency feature images and used double discriminators to target the fusion images after inverse transform; Then high-frequency feature images were fused by trained GAN model, and low-frequency feature images were fused by CNN pre-training model based on transfer learning. Experimental results showed that, compared with the current advanced fusion algorithm, the proposed method had more abundant texture details and clearer contour edge information in subjective representation. In the evaluation of objective indicators, Q AB/F, information entropy (IE), spatial frequency (SF), structural similarity (SSIM), mutual information (MI) and visual information fidelity for fusion (VIFF) were 2.0%, 6.3%, 7.0%, 5.5%, 9.0% and 3.3% higher than the best test results, respectively. The fused image can be effectively applied to medical diagnosis to further improve the diagnostic efficiency.

A meta-learning based method for segmentation of few-shot magnetic resonance images / 生物医学工程学杂志

When applying deep learning algorithms to magnetic resonance (MR) image segmentation, a large number of annotated images are required as data support. However, the specificity of MR images makes it difficult and costly to acquire large amounts of annotated image data. To reduce the dependence of MR image segmentation on a large amount of annotated data, this paper proposes a meta-learning U-shaped network (Meta-UNet) for few-shot MR image segmentation. Meta-UNet can use a small amount of annotated image data to complete the task of MR image segmentation and obtain good segmentation results. Meta-UNet improves U-Net by introducing dilated convolution, which can increase the receptive field of the model to improve the sensitivity to targets of different scales. We introduce the attention mechanism to improve the adaptability of the model to different scales. We introduce the meta-learning mechanism, and employ a composite loss function for well-supervised and effective bootstrapping of model training. We use the proposed Meta-UNet model to train on different segmentation tasks, and then use the trained model to evaluate on a new segmentation task, where the Meta-UNet model achieves high-precision segmentation of target images. Meta-UNet has a certain improvement in mean Dice similarity coefficient (DSC) compared with voxel morph network (VoxelMorph), data augmentation using learned transformations (DataAug) and label transfer network (LT-Net). Experiments show that the proposed method can effectively perform MR image segmentation using a small number of samples. It provides a reliable aid for clinical diagnosis and treatment.

Discussion on Technical Evaluation of Tongue Diagnosis Equipment of Traditional Chinese Medicine / 中国医疗器械杂志

This study briefly introduces the tongue diagnostic equipment of traditional Chinese medicine. It analyzes and discusses the key points of technical evaluation of tongue diagnostic equipment from the aspects of product name, performance parameters, image processing functions, product use methods, clinical evaluation, etc. It analyzes the safety risks and effectiveness indicators of tongue diagnostic equipment, hoping to bring some help to the gradual standardization of tongue diagnostic equipment and the registration of enterprises.

Evaluation of PET Mainstream Scattering Correction Methods / 中国医疗器械杂志

OBJECTIVE@#Current mainstream PET scattering correction methods are introduced and evaluated horizontally, and finally, the existing problems and development direction of scattering correction are discussed.@*METHODS@#Based on NeuWise Pro PET/CT products of Neusoft Medical System Co. Ltd. , the simulation experiment is carried out to evaluate the influence of radionuclide distribution out of FOV (field of view) on the scattering estimation accuracy of each method.@*RESULTS@#The scattering events produced by radionuclide out of FOV have an obvious impact on the spatial distribution of scattering, which should be considered in the model. The scattering estimation accuracy of Monte Carlo method is higher than single scatter simulation (SSS).@*CONCLUSIONS@#Clinically, if the activity of the adjacent parts out of the FOV is high, such as brain, liver, kidney and bladder, it is likely to lead to the deviation of scattering estimation. Considering the Monte Carlo scattering estimation of the distribution of radionuclide out of FOV, it's helpful to improve the accuracy of scattering distribution estimation.

Application of Novel Down-sampling Method in Retinal Vessel Segmentation / 中国医疗器械杂志

Accurate segmentation of retinal blood vessels is of great significance for diagnosing, preventing and detecting eye diseases. In recent years, the U-Net network and its various variants have reached advanced level in the field of medical image segmentation. Most of these networks choose to use simple max pooling to down-sample the intermediate feature layer of the image, which is easy to lose part of the information, so this study proposes a simple and effective new down-sampling method Pixel Fusion-pooling (PF-pooling), which can well fuse the adjacent pixel information of the image. The down-sampling method proposed in this study is a lightweight general module that can be effectively integrated into various network architectures based on convolutional operations. The experimental results on the DRIVE and STARE datasets show that the F1-score index of the U-Net model using PF-pooling on the STARE dataset improved by 1.98%. The accuracy rate is increased by 0.2%, and the sensitivity is increased by 3.88%. And the generalization of the proposed module is verified by replacing different algorithm models. The results show that PF-pooling has achieved performance improvement in both Dense-UNet and Res-UNet models, and has good universality.

Analysis on characteristic of stage Ⅰ occupational cement pneumoconiosis patients / 中华劳动卫生职业病杂志

Objective: To analyze the clinical and imaging characteristics of stage Ⅰ occupational cement pneumoconiosis patients. Methods: In October 2021, the data of patients with occupational cement pneumoconiosis diagnosed by the Third Hospital of Peking University from 2014 to 2020 were collected, and the data of the patients' initial exposure age, dust exposure duration, diagnosis age, incubation period, chest X-ray findings, lung function and other data were analyzed retrospectively. Spearman grade correlation was used for correlation analysis of grade count data. The influencing factors of lung function were analyzed by binary logistic regression. Results: A total of 107 patients were enrolled in the study. There were 80 male patients and 27 female patients. The inital exposure age was (26.2±7.7) years, the diagnosis age was (59.4±7.9) years, the dust exposure duration was (17.9±8.0) years, and the incubation period was (33.1±10.3) years. The initial dust exposure age and the dust exposure duration in female patients were less than those in men, and the incubation period was longer than that in men (P<0.05). The imaging analysis showed the small opacities as"pp"accounted for 54.2%. 82 patients (76.6%) had small opacities distributed in two lung areas. The lung areas distribution of small opacities in female patients was less than that in male patients (2.04±0.19 vs 2.41±0.69, P<0.001). There were 57 cases of normal pulmonary function, 41 cases of mild abnormality and 9 cases of moderate abnormality. The number of lung regions with small opacities on X-ray was the risk factor for abnormal lung function in cement pneumoconiosis patients (OR=2.491, 95%CI=1.197-5.183, P=0.015) . Conclusion: The patients with occupational cement pneumoconiosis had long dust exposure duration and incubation period, light imaging changes and pulmonary function damage. The abnormal lung function was related to the range of pulmonary involvement.

Research status and outlook of deep learning in oral and maxillofacial medical imaging / 中华口腔医学杂志

Artificial intelligence, represented by deep learning, has received increasing attention in the field of oral and maxillofacial medical imaging, which has been widely studied in image analysis and image quality improvement. This narrative review provides an insight into the following applications of deep learning in oral and maxillofacial imaging: detection, recognition and segmentation of teeth and other anatomical structures, detection and diagnosis of oral and maxillofacial diseases, and forensic personal identification. In addition, the limitations of the studies and the directions for future development are summarized.

Metal artifact reduction and clinical verification in oral and maxillofacial region based on deep learning / 中华口腔医学杂志

Objective: To construct a kind of neural network for eliminating the metal artifacts in CT images by training the generative adversarial networks (GAN) model, so as to provide reference for clinical practice. Methods: The CT data of patients treated in the Department of Radiology, West China Hospital of Stomatology, Sichuan University from January 2017 to June 2022 were collected. A total of 1 000 cases of artifact-free CT data and 620 cases of metal artifact CT data were obtained, including 5 types of metal restorative materials, namely, fillings, crowns, titanium plates and screws, orthodontic brackets and metal foreign bodies. Four hundred metal artifact CT data and 1 000 artifact-free CT data were utilized for simulation synthesis, and 1 000 pairs of simulated artifacts and metal images and simulated metal images (200 pairs of each type) were constructed. Under the condition that the data of the five metal artifacts were equal, the entire data set was randomly (computer random) divided into a training set (800 pairs) and a test set (200 pairs). The former was used to train the GAN model, and the latter was used to evaluate the performance of the GAN model. The test set was evaluated quantitatively and the quantitative indexes were root-mean-square error (RMSE) and structural similarity index measure (SSIM). The trained GAN model was employed to eliminate the metal artifacts from the CT data of the remaining 220 clinical cases of metal artifact CT data, and the elimination results were evaluated by two senior attending doctors using the modified LiKert scale. Results: The RMSE values for artifact elimination of fillings, crowns, titanium plates and screws, orthodontic brackets and metal foreign bodies in test set were 0.018±0.004, 0.023±0.007, 0.015±0.003, 0.019±0.004, 0.024±0.008, respectively (F=1.29, P=0.274). The SSIM values were 0.963±0.023, 0.961±0.023, 0.965±0.013, 0.958±0.022, 0.957±0.026, respectively (F=2.22, P=0.069). The intra-group correlation coefficient of 2 evaluators was 0.972. For 220 clinical cases, the overall score of the modified LiKert scale was (3.73±1.13), indicating a satisfactory performance. The scores of modified LiKert scale for fillings, crowns, titanium plates and screws, orthodontic brackets and metal foreign bodies were (3.68±1.13), (3.67±1.16), (3.97±1.03), (3.83±1.14), (3.33±1.12), respectively (F=1.44, P=0.145). Conclusions: The metal artifact reduction GAN model constructed in this study can effectively remove the interference of metal artifacts and improve the image quality.

Review on ultrasonographic diagnosis of thyroid diseases based on deep learning / 生物医学工程学杂志

In recent years, the incidence of thyroid diseases has increased significantly and ultrasound examination is the first choice for the diagnosis of thyroid diseases. At the same time, the level of medical image analysis based on deep learning has been rapidly improved. Ultrasonic image analysis has made a series of milestone breakthroughs, and deep learning algorithms have shown strong performance in the field of medical image segmentation and classification. This article first elaborates on the application of deep learning algorithms in thyroid ultrasound image segmentation, feature extraction, and classification differentiation. Secondly, it summarizes the algorithms for deep learning processing multimodal ultrasound images. Finally, it points out the problems in thyroid ultrasound image diagnosis at the current stage and looks forward to future development directions. This study can promote the application of deep learning in clinical ultrasound image diagnosis of thyroid, and provide reference for doctors to diagnose thyroid disease.

An attention-guided network for bilateral ventricular segmentation in pediatric echocardiography / 生物医学工程学杂志

Accurate segmentation of pediatric echocardiograms is a challenging task, because significant heart-size changes with age and faster heart rate lead to more blurred boundaries on cardiac ultrasound images compared with adults. To address these problems, a dual decoder network model combining channel attention and scale attention is proposed in this paper. Firstly, an attention-guided decoder with deep supervision strategy is used to obtain attention maps for the ventricular regions. Then, the generated ventricular attention is fed back to multiple layers of the network through skip connections to adjust the feature weights generated by the encoder and highlight the left and right ventricular areas. Finally, a scale attention module and a channel attention module are utilized to enhance the edge features of the left and right ventricles. The experimental results demonstrate that the proposed method in this paper achieves an average Dice coefficient of 90.63% in acquired bilateral ventricular segmentation dataset, which is better than some conventional and state-of-the-art methods in the field of medical image segmentation. More importantly, the method has a more accurate effect in segmenting the edge of the ventricle. The results of this paper can provide a new solution for pediatric echocardiographic bilateral ventricular segmentation and subsequent auxiliary diagnosis of congenital heart disease.

Non-local attention and multi-task learning based lung segmentation in chest X-ray / 生物医学工程学杂志

Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.