Objective To develop a neural network architecture based on deep learning to assist knee CT images automatic segmentation, and validate its accuracy. Methods A knee CT scans database was established, and the bony structure was manually annotated. A deep learning neural network architecture was developed independently, and the labeled database was used to train and test the neural network. Metrics of Dice coefficient, average surface distance (ASD), and Hausdorff distance (HD) were calculated to evaluate the accuracy of the neural network. The time of automatic segmentation and manual segmentation was compared. Five orthopedic experts were invited to score the automatic and manual segmentation results using Likert scale and the scores of the two methods were compared. Results The automatic segmentation achieved a high accuracy. The Dice coefficient, ASD, and HD of the femur were 0.953±0.037, (0.076±0.048) mm, and (3.101±0.726) mm, respectively; and those of the tibia were 0.950±0.092, (0.083±0.101) mm, and (2.984±0.740) mm, respectively. The time of automatic segmentation was significantly shorter than that of manual segmentation [(2.46±0.45) minutes vs. (64.73±17.07) minutes; t=36.474, P<0.001). The clinical scores of the femur were 4.3±0.3 in the automatic segmentation group and 4.4±0.2 in the manual segmentation group, and the scores of the tibia were 4.5±0.2 and 4.5±0.3, respectively. There was no significant difference between the two groups (t=1.753, P=0.085; t=0.318, P=0.752). Conclusion The automatic segmentation of knee CT images based on deep learning has high accuracy and can achieve rapid segmentation and three-dimensional reconstruction. This method will promote the development of new technology-assisted techniques in total knee arthroplasty.
To address the challenges faced by current brain midline segmentation techniques, such as insufficient accuracy and poor segmentation continuity, this paper proposes a deep learning network model based on a two-stage framework. On the first stage of the model, prior knowledge of the feature consistency of adjacent brain midline slices under normal and pathological conditions is utilized. Associated midline slices are selected through slice similarity analysis, and a novel feature weighting strategy is adopted to collaboratively fuse the overall change characteristics and spatial information of these associated slices, thereby enhancing the feature representation of the brain midline in the intracranial region. On the second stage, the optimal path search strategy for the brain midline is employed based on the network output probability map, which effectively addresses the problem of discontinuous midline segmentation. The method proposed in this paper achieved satisfactory results on the CQ500 dataset provided by the Center for Advanced Research in Imaging, Neurosciences and Genomics, New Delhi, India. The Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), and normalized surface Dice (NSD) were 67.38 ± 10.49, 24.22 ± 24.84, 1.33 ± 1.83, and 0.82 ± 0.09, respectively. The experimental results demonstrate that the proposed method can fully utilize the prior knowledge of medical images to effectively achieve accurate segmentation of the brain midline, providing valuable assistance for subsequent identification of the brain midline by clinicians.
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.
The diagnosis of pancreatic cancer is very important. The main method of diagnosis is based on pathological analysis of microscopic image of Pap smear slide. The accurate segmentation and classification of images are two important phases of the analysis. In this paper, we proposed a new automatic segmentation and classification method for microscopic images of pancreas. For the segmentation phase, firstly multi-features Mean-shift clustering algorithm (MFMS) was applied to localize regions of nuclei. Then, chain splitting model (CSM) containing flexible mathematical morphology and curvature scale space corner detection method was applied to split overlapped cells for better accuracy and robustness. For classification phase, 4 shape-based features and 138 textural features based on color spaces of cell nuclei were extracted. In order to achieve optimal feature set and classify different cells, chain-like agent genetic algorithm (CAGA) combined with support vector machine (SVM) was proposed. The proposed method was tested on 15 cytology images containing 461 cell nuclei. Experimental results showed that the proposed method could automatically segment and classify different types of microscopic images of pancreatic cell and had effective segmentation and classification results. The mean accuracy of segmentation is 93.46%±7.24%. The classification performance of normal and malignant cells can achieve 96.55%±0.99% for accuracy, 96.10%±3.08% for sensitivity and 96.80%±1.48% for specificity.
With the change of medical diagnosis and treatment mode, the quality of medical image directly affects the diagnosis and treatment of the disease for doctors. Therefore, realization of intelligent image quality control by computer will have a greater auxiliary effect on the radiographer’s filming work. In this paper, the research methods and applications of image segmentation model and image classification model in the field of deep learning and traditional image processing algorithm applied to medical image quality evaluation are described. The results demonstrate that deep learning algorithm is more accurate and efficient than the traditional image processing algorithm in the effective training of medical image big data, which explains the broad application prospect of deep learning in the medical field. This paper developed a set of intelligent quality control system for auxiliary filming, and successfully applied it to the Radiology Department of West China Hospital and other city and county hospitals, which effectively verified the feasibility and stability of the quality control system.
In response to the issues of single-scale information loss and large model parameter size during the sampling process in U-Net and its variants for medical image segmentation, this paper proposes a multi-scale medical image segmentation method based on pixel encoding and spatial attention. Firstly, by redesigning the input strategy of the Transformer structure, a pixel encoding module is introduced to enable the model to extract global semantic information from multi-scale image features, obtaining richer feature information. Additionally, deformable convolutions are incorporated into the Transformer module to accelerate convergence speed and improve module performance. Secondly, a spatial attention module with residual connections is introduced to allow the model to focus on the foreground information of the fused feature maps. Finally, through ablation experiments, the network is lightweighted to enhance segmentation accuracy and accelerate model convergence. The proposed algorithm achieves satisfactory results on the Synapse dataset, an official public dataset for multi-organ segmentation provided by the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), with Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) scores of 77.65 and 18.34, respectively. The experimental results demonstrate that the proposed algorithm can enhance multi-organ segmentation performance, potentially filling the gap in multi-scale medical image segmentation algorithms, and providing assistance for professional physicians in diagnosis.
In view of the evaluation of fundus image segmentation, a new evaluation method was proposed to make up insufficiency of the traditional evaluation method which only considers the overlap of pixels and neglects topology structure of the retinal vessel. Mathematical morphology and thinning algorithm were used to obtain the retinal vascular topology structure. Then three features of retinal vessel, including mutual information, correlation coefficient and ratio of nodes, were calculated. The features of the thinned images taken as topology structure of blood vessel were used to evaluate retinal image segmentation. The manually-labeled images and their eroded ones of STARE database were used in the experiment. The result showed that these features, including mutual information, correlation coefficient and ratio of nodes, could be used to evaluate the segmentation quality of retinal vessel on fundus image through topology structure, and the algorithm was simple. The method is of significance to the supplement of traditional segmentation evaluation of retinal vessel on fundus image.
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.
This paper presents a kind of automatic segmentation method for white blood cell based on HSI corrected space information fusion. Firstly, the original cell image is transformed to HSI colour space conversion. Because the transformation formulas of H component piecewise function was discontinuous, the uniformity of uniform visual cytoplasm area in the original image was lead to become lower in this channel. We then modified formulas, and then fetched information of nucleus, cytoplasm, red blood cells and background region according to distribution characteristics of the H, S and I-channel, using the theory and method of information fusion to build fusion imageⅠand fusion imageⅡ, which only contained cytoplasm and a small amount of interference, and fetched nucleus and cytoplasm respectively. Finally, we marked the nucleus and cytoplasm region and obtained the final result of segmentation. The simulation results showed that the new algorithm of image segmentation for white blood cell had high accuracy, robustness and universality.
To address the issue of a large number of network parameters and substantial floating-point operations in deep learning networks applied to image segmentation for cardiac magnetic resonance imaging (MRI), this paper proposes a lightweight dilated parallel convolution U-Net (DPU-Net) to decrease the quantity of network parameters and the number of floating-point operations. Additionally, a multi-scale adaptation vector knowledge distillation (MAVKD) training strategy is employed to extract latent knowledge from the teacher network, thereby enhancing the segmentation accuracy of DPU-Net. The proposed network adopts a distinctive way of convolutional channel variation to reduce the number of parameters and combines with residual blocks and dilated convolutions to alleviate the gradient explosion problem and spatial information loss that might be caused by the reduction of parameters. The research findings indicate that this network has achieved considerable improvements in reducing the number of parameters and enhancing the efficiency of floating-point operations. When applying this network to the public dataset of the automatic cardiac diagnosis challenge (ACDC), the dice coefficient reaches 91.26%. The research results validate the effectiveness of the proposed lightweight network and knowledge distillation strategy, providing a reliable lightweighting idea for deep learning in the field of medical image segmentation.