3D hippocampal segmentation based on spatial and frequency domain features adaptive fusion and inter⁃class boundary region enhancement / 解剖学报

Objective Hippocampal atrophy is a clinically important marker for the diagnosis of many psychiatric disorders such as Alzheimer’s disease‚ so accurate segmentation of the hippocampus is an important scientific issue. With the development of deep learning‚ a large number of advanced automatic segmentation method have been proposed. However‚ 3D hippocampal segmentation is still challenging due to the effects of various noises in MRI and unclear boundaries between various classes of the hippocampus. Therefore‚ the aim of this paper is to propose new method to segment the hippocampal head‚ body‚ and tail more accurately. Methods To overcome these challenges‚ this paper proposed two strategies. One was the spatial and frequency domain features adaptive fusion strategy‚ which reduced the influence of noise on feature extraction by automatically selecting the appropriate frequency combination through fast Fourier transform and convolution. The other was an inter-class boundary region enhancement strategy‚ which allowed the network to focus on learning the boundary regions by weighting the loss function of the boundary regions between each class to achieve the goal of pinpointing the boundaries and regulating the size of the hippocampal head‚ body and tail. Results Experiments performed on a 50-case teenager brain MRI dataset show that our method achieves state-of-the-art hippocampal segmentation. Hippocampal head‚ body and tail had been improved compared to the existing method. Ablation experiments demonstrated the effectiveness of our two proposed strategies‚ and we also validated that the network had a strong generalization ability on a 260-case Task04_Hippocampus dataset. It was shown that the method proposed in this paper could be used in more hippocampal segmentation scenarios. Conclusion The method proposed in this paper can help clinicians to observe hippocampal atrophy more clearly and accomplish more accurate diagnosis and follow-up of the condition.

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.

A generative adversarial network-based unsupervised domain adaptation method for magnetic resonance image segmentation / 生物医学工程学杂志

Intelligent medical image segmentation methods have been rapidly developed and applied, while a significant challenge is domain shift. That is, the segmentation performance degrades due to distribution differences between the source domain and the target domain. This paper proposed an unsupervised end-to-end domain adaptation medical image segmentation method based on the generative adversarial network (GAN). A network training and adjustment model was designed, including segmentation and discriminant networks. In the segmentation network, the residual module was used as the basic module to increase feature reusability and reduce model optimization difficulty. Further, it learned cross-domain features at the image feature level with the help of the discriminant network and a combination of segmentation loss with adversarial loss. The discriminant network took the convolutional neural network and used the labels from the source domain, to distinguish whether the segmentation result of the generated network is from the source domain or the target domain. The whole training process was unsupervised. The proposed method was tested with experiments on a public dataset of knee magnetic resonance (MR) images and the clinical dataset from our cooperative hospital. With our method, the mean Dice similarity coefficient (DSC) of segmentation results increased by 2.52% and 6.10% to the classical feature level and image level domain adaptive method. The proposed method effectively improves the domain adaptive ability of the segmentation method, significantly improves the segmentation accuracy of the tibia and femur, and can better solve the domain transfer problem in MR image segmentation.

An algorithm for three-dimensional plumonary parenchymal segmentation by integrating surfacelet transform with pulse coupled neural network / 生物医学工程学杂志

In order to overcome the difficulty in lung parenchymal segmentation due to the factors such as lung disease and bronchial interference, a segmentation algorithm for three-dimensional lung parenchymal is presented based on the integration of surfacelet transform and pulse coupled neural network (PCNN). First, the three-dimensional computed tomography of lungs is decomposed into surfacelet transform domain to obtain multi-scale and multi-directional sub-band information. The edge features are then enhanced by filtering sub-band coefficients using local modified Laplacian operator. Second, surfacelet inverse transform is implemented and the reconstructed image is fed back to the input of PCNN. Finally, iteration process of the PCNN is carried out to obtain final segmentation result. The proposed algorithm is validated on the samples of public dataset. The experimental results demonstrate that the proposed algorithm has superior performance over that of the three-dimensional surfacelet transform edge detection algorithm, the three-dimensional region growing algorithm, and the three-dimensional U-NET algorithm. It can effectively suppress the interference coming from lung lesions and bronchial, and obtain a complete structure of lung parenchyma.

Automatic Segmentation of Anatomical Areas in X-ray Images Based on Fully Convolutional Networks / 中国医疗器械杂志

OBJECTIVE@#Medical image segmentation is a key step in medical image processing. An architecture of fully convolutional networks was proposed to realize automatic segmentation of anatomical areas in X-ray images.@*METHODS@#Enlightened by the advantages of convolutional neural networks on features extraction, fully convolutional networks consisting of 9 layers were designed to segment medical images. The networks used convolution kernels of various sizes to extract multi-dimensional image features in the images, meanwhile, eliminated pooling layers to avoid the loss of image details during downsampling procedures.@*RESULTS@#The experiment was conducted in accordance with the specific scene of X-ray images segmentation. Compared with traditional segmentation methods, this approach achieved more accurate segmentation of anatomical areas.@*CONCLUSIONS@#Fully convolutional networks can extract representative and multidimensional features of medical images, avoid the loss of image details during downsampling procedures, and complete automatic segmentation of anatomical areas accurately in X-ray images.

Sistema de Apoyo para la Cuantificación Semiautomática de Fibrosis Pulmonar en Imágenes de TAC / Support System for Semiautomatic Quantification of Pulmonary Fibrosis in CT Images

Resumen: En este trabajo se presenta un método para calcular los niveles de fibrosis pulmonar en imágenes de tomografía axial computarizada. Se utilizó un algoritmo de segmentación semiautomática basado en el método de Chan-Vese. El método mostró similitudes de forma cualitativa en la región de la fibrosis con respecto al experto clínico. Sin embargo es necesario validar los resultados con una base de datos mayor. El método propuesto aproxima un porcentaje de fibrosis de forma fácil para apoyar su implementación en la práctica clínica minimizando la subjetividad del experto médico y generando una estimación cuantitativa de la región de fibrosis.

Abstract: A method to estimate the pulmonary fibrosis in computed tomography (CT) imaging is presented. A semi-automatic segmentation algorithm based on the Chan-Vese method was used. The proposed method shows a similar fibrosis región with respect to clinical expert. However, the results need to be validated in a bigger data base. The proposed method approximates a fibrosis percentage that allows to achieve this procedure easily in order to support its implementation in the clinical practice minimizing the clinical expert subjectivity and generating a quantitative estimation of fibrosis region.

A method of generating synthetic medical image for the validation of segmentation algorithms / 国际生物医学工程杂志

Objective To develop a synthetic medical image generation system which can provide test images for the validation of medical image segmentation algorithms.Methods The synthetic image was created based on the deformation of region of interest (ROI) in original clinical images.First the synthetic foreground boundarywas generated by the resampling of the Fourier descriptors of manually segmented foreground boundary in original image.Then all the ROI pixels were divided into 4 categories and their intensities were calculated by texture matching techniques.Results The intracranial hemorrhage image was selected as the original image,and the generated synthetic images were applied to validate the precision and accuracy of multi-threshold segmentation and level set algorithm.Conclusion The proposed system can rapidly generate synthetic images with realistic appearance of clinical cases and well define ground truth foreground boundary.It has strong practicality for quantitative validation of segmentation algorithms.

Fast 3D Medical Image Segmentation Based on CUDA / 中国医学物理学杂志

Objective: 3D segmentation is an important part of medical image analysis and visualization. It also continues to be large challenge in the medical image segmentation. While level sets have demonstrated a great potential for 3D medical image segmentation, these algorithms have a large computational burden thus are not suitable for real time processing requirement. To solve this problem, we propose a parallel accerelated method based on CUDA. Methods: We implement C-V level set algorithm in the CUDA environment which is the NVIDIA's GPGPU model.The segmentation speed can greatly improved by using independence of image pixel and concurrence of partial differential equation .The paper shows the flow chart of the parallel computing and gives the detailed introduction of the C-V level set algorithm which is implemented in the CUDA environment. Results: Realizing the C-V level set parallel accerelated algorithm. This method has faster segmentation speed while preserving the qualitative results, Conclusions: This method is viable and makes the fast 3D medical image segmentation come hue.

MEDICAL IMAGE SEGMENTATION BASED ON A MODIFIED LEVEL SET ALGORITHM / 药物分析学报

Objective To present a novel modified level set algorithm for medical image segmentation. Methods The algorithm is developed by substituting the speed function of level set algorithm with the region and gradient information of the image instead of the conventional gradient information. This new algorithm has been tested by a series of different modality medical images. Results We present various examples and also evaluate and compare the performance of our method with the classical level set method on weak boundaries and noisy images. Conclusion Experimental results show the proposed algorithm is effective and robust.

Edge detection of medical image and methods for tracking & showing of gray level in special regions / 医疗卫生装备

By using the image processing function and programming tomography,the following functions are realized: the contour line,edge line and gradation histogram of medical images are displayed;the selected regions of medical images are freely zoomed;the gray level of discretional regions is displayed using medical image processing tool and the distance of the given points is freely measured.

Progress of medical image segmentation technology / 医疗卫生装备

Medical image segmentation is a classical puzzle for researchers.Image segmentation is the method to delineate anatomic structures or other interested regions automatically or semi-automatically,which is helpful to diagnosis and plays a crucial role in many medical imaging applications.In this article,a rather complete survey to medical image segmentation methods and their characteristics are given,especially to the new methods or improvement of the classical methods which was put forward recently.The prospects and the challenge of medical image segmentation is discussed.