Medical Image Segmentation Methods Research Articles

Automatic segmentation of medical images using a novel Harris Hawk optimization method and an active contour model.

Medical image segmentation is a key step to assist diagnosis of several diseases, and accuracy of a segmentation method is important for further treatments of different diseases. Different medical imaging modalities have different challenges such as intensity inhomogeneity, noise, low contrast, and ill-defined boundaries, which make automated segmentation a difficult task. To handle these issues, we propose a new fully automated method for medical image segmentation, which utilizes the advantages of thresholding and an active contour model. In this study, a Harris Hawks optimizer is applied to determine the optimal thresholding value, which is used to obtain the initial contour for segmentation. The obtained contour is further refined by using a spatially varying Gaussian kernel in the active contour model. The proposed method is then validated using a standard skin dataset (ISBI 2016), which consists of variable-sized lesions and different challenging artifacts, and a standard cardiac magnetic resonance dataset (ACDC, MICCAI 2017) with a wide spectrum of normal hearts, congenital heart diseases, and cardiac dysfunction. Experimental results show that the proposed method can effectively segment the region of interest and produce superior segmentation results for skin (overall Dice Score 0.90) and cardiac dataset (overall Dice Score 0.93), as compared to other state-of-the-art algorithms.

Epistemic and Heteroscedastic Uncertainty Estimation in Retinal Blood Vessel Segmentation

Current state-of-the-art medical image segmentation methods require high quality datasets to obtain good performance. However, medical specialists often disagree on diagnosis, hence, datasets contain contradictory annotations. This, in turn, leads to difficulties in the optimization process of Deep Learning models and hinder performance. We propose a method to estimate uncertainty in Convolutional Neural Network (CNN) segmentation models, that makes the training of CNNs more robust to contradictory annotations. In this work, we model two types of uncertainty, heteroscedastic and epistemic, without adding any additional supervisory signal other than the ground-truth segmentation mask. As expected, the uncertainty is higher closer to vessel boundaries, and on top of thinner and less visible vessels where it is more likely for medical specialists to disagree. Therefore, our method is more suitable to learn from datasets created with heterogeneous annotators. We show that there is a correlation between the uncertainty estimated by our method and the disagreement in the segmentation provided by two different medical specialists. Furthermore, by explicitly modeling the uncertainty, the Intersection over Union of the segmentation network improves 5.7 percentage points.

A Wavelet Transform and Neural Network Based Segmentation & Classification System For Bone Fracture Detection

This paper deals with fracture detection of a human bone from X-ray images applying image processing techniques. It describes the wavelet transform based segmentation and neural network-based classification method for medical images, especially X-ray images, to locate or detect any fracture in the bones. Among different image segmentation techniques, using Wavelet Transform based segmentation manifests particular significance compared to other conventional segmentation techniques for the images considered in this study. Also in terms of statistical image identifier, namely Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Structural similarity (SSIM), and Entropy etc. The proposed methods have observable advantages, particularly in medical image segmentation. The Haar Wavelet showed maximum correlation with the considered images. The detailed vertical, horizontal and diagonal components can decompose X-ray images based on the Wavelet Transform algorithm. The vertical detail component of third level decomposition of the Wavelet Transform has preferred because it shows the minimum Entropy. The Error Backpropagation Neural Network (EBP-NN) fed with the obtained medical images from wavelet-based segmentation technique. This neural network has trained with fractured and non-fractured images then tested on various other X-ray images. An EBP-NN classification system with the architecture of 1024−22-2 gives the maximum accuracy. The developed system can detect fractured bone images accurately.

Interactive Few-Shot Learning: Limited Supervision, Better Medical Image Segmentation.

Many known supervised deep learning methods for medical image segmentation suffer an expensive burden of data annotation for model training. Recently, few-shot segmentation methods were proposed to alleviate this burden, but such methods often showed poor adaptability to the target tasks. By prudently introducing interactive learning into the few-shot learning strategy, we develop a novel few-shot segmentation approach called Interactive Few-shot Learning (IFSL), which not only addresses the annotation burden of medical image segmentation models but also tackles the common issues of the known few-shot segmentation methods. First, we design a new few-shot segmentation structure, called Medical Prior-based Few-shot Learning Network (MPrNet), which uses only a few annotated samples (e.g., 10 samples) as support images to guide the segmentation of query images without any pre-training. Then, we propose an Interactive Learning-based Test Time Optimization Algorithm (IL-TTOA) to strengthen our MPrNet on the fly for the target task in an interactive fashion. To our best knowledge, our IFSL approach is the first to allow few-shot segmentation models to be optimized and strengthened on the target tasks in an interactive and controllable manner. Experiments on four few-shot segmentation tasks show that our IFSL approach outperforms the state-of-the-art methods by more than 20% in the DSC metric. Specifically, the interactive optimization algorithm (IL-TTOA) further contributes ~10% DSC improvement for the few-shot segmentation models.

Learning With Context Feedback Loop for Robust Medical Image Segmentation.

Deep learning has successfully been leveraged for medical image segmentation. It employs convolutional neural networks (CNN) to learn distinctive image features from a defined pixel-wise objective function. However, this approach can lead to less output pixel interdependence producing incomplete and unrealistic segmentation results. In this paper, we present a fully automatic deep learning method for robust medical image segmentation by formulating the segmentation problem as a recurrent framework using two systems. The first one is a forward system of an encoder-decoder CNN that predicts the segmentation result from the input image. The predicted probabilistic output of the forward system is then encoded by a fully convolutional network (FCN)-based context feedback system. The encoded feature space of the FCN is then integrated back into the forward system's feed-forward learning process. Using the FCN-based context feedback loop allows the forward system to learn and extract more high-level image features and fix previous mistakes, thereby improving prediction accuracy over time. Experimental results, performed on four different clinical datasets, demonstrate our method's potential application for single and multi-structure medical image segmentation by outperforming the state of the art methods. With the feedback loop, deep learning methods can now produce results that are both anatomically plausible and robust to low contrast images. Therefore, formulating image segmentation as a recurrent framework of two interconnected networks via context feedback loop can be a potential method for robust and efficient medical image analysis.

Global guidance network for breast lesion segmentation in ultrasound images.

Automatic breast lesion segmentation in ultrasound helps to diagnose breast cancer, which is one of the dreadful diseases that affect women globally. Segmenting breast regions accurately from ultrasound image is a challenging task due to the inherent speckle artifacts, blurry breast lesion boundaries, and inhomogeneous intensity distributions inside the breast lesion regions. Recently, convolutional neural networks (CNNs) have demonstrated remarkable results in medical image segmentation tasks. However, the convolutional operations in a CNN often focus on local regions, which suffer from limited capabilities in capturing long-range dependencies of the input ultrasound image, resulting in degraded breast lesion segmentation accuracy. In this paper, we develop a deep convolutional neural network equipped with a global guidance block (GGB) and breast lesion boundary detection (BD) modules for boosting the breast ultrasound lesion segmentation. The GGB utilizes the multi-layer integrated feature map as a guidance information to learn the long-range non-local dependencies from both spatial and channel domains. The BD modules learn additional breast lesion boundary map to enhance the boundary quality of a segmentation result refinement. Experimental results on a public dataset and a collected dataset show that our network outperforms other medical image segmentation methods and the recent semantic segmentation methods on breast ultrasound lesion segmentation. Moreover, we also show the application of our network on the ultrasound prostate segmentation, in which our method better identifies prostate regions than state-of-the-art networks.

COVID-19 Chest CT Image Segmentation Network by Multi-Scale Fusion and Enhancement Operations.

A novel coronavirus disease 2019 (COVID-19) was detected and has spread rapidly across various countries around the world since the end of the year 2019. Computed Tomography (CT) images have been used as a crucial alternative to the time-consuming RT-PCR test. However, pure manual segmentation of CT images faces a serious challenge with the increase of suspected cases, resulting in urgent requirements for accurate and automatic segmentation of COVID-19 infections. Unfortunately, since the imaging characteristics of the COVID-19 infection are diverse and similar to the backgrounds, existing medical image segmentation methods cannot achieve satisfactory performance. In this article, we try to establish a new deep convolutional neural network tailored for segmenting the chest CT images with COVID-19 infections. We first maintain a large and new chest CT image dataset consisting of 165,667 annotated chest CT images from 861 patients with confirmed COVID-19. Inspired by the observation that the boundary of the infected lung can be enhanced by adjusting the global intensity, in the proposed deep CNN, we introduce a feature variation block which adaptively adjusts the global properties of the features for segmenting COVID-19 infection. The proposed FV block can enhance the capability of feature representation effectively and adaptively for diverse cases. We fuse features at different scales by proposing Progressive Atrous Spatial Pyramid Pooling to handle the sophisticated infection areas with diverse appearance and shapes. The proposed method achieves state-of-the-art performance. Dice similarity coefficients are 0.987 and 0.726 for lung and COVID-19 segmentation, respectively. We conducted experiments on the data collected in China and Germany and show that the proposed deep CNN can produce impressive performance effectively. The proposed network enhances the segmentation ability of the COVID-19 infection, makes the connection with other techniques and contributes to the development of remedying COVID-19 infection.

Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation.

A common shortfall of supervised deep learning for medical imaging is the lack of labeled data, which is often expensive and time consuming to collect. This article presents a new semisupervised method for medical image segmentation, where the network is optimized by a weighted combination of a common supervised loss only for the labeled inputs and a regularization loss for both the labeled and unlabeled data. To utilize the unlabeled data, our method encourages consistent predictions of the network-in-training for the same input under different perturbations. With the semisupervised segmentation tasks, we introduce a transformation-consistent strategy in the self-ensembling model to enhance the regularization effect for pixel-level predictions. To further improve the regularization effects, we extend the transformation in a more generalized form including scaling and optimize the consistency loss with a teacher model, which is an averaging of the student model weights. We extensively validated the proposed semisupervised method on three typical yet challenging medical image segmentation tasks: 1) skin lesion segmentation from dermoscopy images in the International Skin Imaging Collaboration (ISIC) 2017 data set; 2) optic disk (OD) segmentation from fundus images in the Retinal Fundus Glaucoma Challenge (REFUGE) data set; and 3) liver segmentation from volumetric CT scans in the Liver Tumor Segmentation Challenge (LiTS) data set. Compared with state-of-the-art, our method shows superior performance on the challenging 2-D/3-D medical images, demonstrating the effectiveness of our semisupervised method for medical image segmentation.

Medical image segmentation algorithm based on multilayer boundary perception-self attention deep learning model

Traditional medical image segmentation methods have problems such as low segmentation accuracy and low adaptive ability. Therefore, many scholars have proposed a medical image segmentation method based on deep learning, which has achieved good results in the field of medical image segmentation. However, this type of method has the following problems in the application process: (1) Medical image segmentation target boundary positioning problem. Constrained by factors such as medical image contrast, heterogeneity, and boundary resolution, existing convolution models still cannot accurately locate boundaries. (2) Deep adaptability of deep learning network structure to medical images. Because medical images have more distinct and different feature information than natural images, the current deep learning-based medical segmentation methods have not fully considered this feature. In view of this, this paper proposes a multi-level boundary-aware RUNet segmentation model. The network structure consists of a U-Net-based segmentation network and a multi-level boundary detection network. It can solve the problem of boundary positioning. At the same time, in order to solve the problem of poor adaptability of deep learning network structures to medical images, this paper proposes to introduce a new interactive self-attention module into deep learning models. It can make the feature map get global information, and realize the effective extraction of medical image feature information. It solves the problem of weak matching between the deep learning network structure and medical images. Based on the above ideas, this paper proposes an image segmentation algorithm based on a multi-layer boundary perception-self-attention mechanism deep learning model. This method and other mainstream segmentation algorithms are used to perform experiments on related medical databases. The results show that the proposed method not only improves the segmentation effect significantly compared with traditional machine learning methods, but also improves it to a certain extent compared with other deep learning methods.

Medical image segmentation algorithm based on positive scaling invariant-self encoding CCA

The quality of medical image segmentation results directly affect disease analysis and diagnosis. Although traditional medical image segmentation methods have achieved certain results, this type of method is not only computationally inefficient, but also difficult to achieve fully automatic segmentation. Deep learning has a good generalization ability, which provides a new technical approach to solve the above problems. However, the following problems exist in the application of deep learning in medical image segmentation: (1) Optimization of deep learning models. The parameters of the existing deep learning model have not been well optimized; it is easy to cause wrong medical image segmentation. (2) Overfitting problem. As the number of deep learning model layers increases, it makes the deep model fit the training data easily, but its generalization performance on the test set will be poor. In view of this, in order to solve the problem of deep learning model optimization, this paper first reveals that the weight space of deep learning is not equivalent to its parameter space, and explains in detail how to optimize the deep learning model in a positive scaling invariant space. The method of mapping the derivative of the base path back to the weight, and analyzed the stochastic optimization algorithm in F space. In addition, to solve the overfitting problem of deep learning models, this paper first gives a method of self-encoding Canonical Correlation Analysis (Self-encoding CCA) to optimize both self-coding loss and correlation loss in the fine-tuning stage. Based on the above ideas, this paper proposes a medical image segmentation algorithm based on positive scaling invariant-self encoding CCA. The experimental results show that the index obtained by the method proposed in this paper is not only improved by a large margin compared with traditional machine learning methods, but also improved to a certain extent compared with other deep learning methods.

A Review of Deep-Learning-Based Medical Image Segmentation Methods

As an emerging biomedical image processing technology, medical image segmentation has made great contributions to sustainable medical care. Now it has become an important research direction in the field of computer vision. With the rapid development of deep learning, medical image processing based on deep convolutional neural networks has become a research hotspot. This paper focuses on the research of medical image segmentation based on deep learning. First, the basic ideas and characteristics of medical image segmentation based on deep learning are introduced. By explaining its research status and summarizing the three main methods of medical image segmentation and their own limitations, the future development direction is expanded. Based on the discussion of different pathological tissues and organs, the specificity between them and their classic segmentation algorithms are summarized. Despite the great achievements of medical image segmentation in recent years, medical image segmentation based on deep learning has still encountered difficulties in research. For example, the segmentation accuracy is not high, the number of medical images in the data set is small and the resolution is low. The inaccurate segmentation results are unable to meet the actual clinical requirements. Aiming at the above problems, a comprehensive review of current medical image segmentation methods based on deep learning is provided to help researchers solve existing problems.

Anatomy-Regularized Representation Learning for Cross-Modality Medical Image Segmentation.

An increasing number of studies are leveraging unsupervised cross-modality synthesis to mitigate the limited label problem in training medical image segmentation models. They typically transfer ground truth annotations from a label-rich imaging modality to a label-lacking imaging modality, under an assumption that different modalities share the same anatomical structure information. However, since these methods commonly use voxel/pixel-wise cycle-consistency to regularize the mappings between modalities, high-level semantic information is not necessarily preserved. In this paper, we propose a novel anatomy-regularized representation learning approach for segmentation-oriented cross-modality image synthesis. It learns a common feature encoding across different modalities to form a shared latent space, where 1) the input and its synthesis present consistent anatomical structure information, and 2) the transformation between two images in one domain is preserved by their syntheses in another domain. We applied our method to the tasks of cross-modality skull segmentation and cardiac substructure segmentation. Experimental results demonstrate the superiority of our method in comparison with state-of-the-art cross-modality medical image segmentation methods.

A topology constrained geometric deformable model for medical image segmentation

BackgroundThe analysis and segmentation of Magnetic Resonance images are usually performed by experts. This process is tedious and time consuming. While many automatic and semi-automatic methods have been proposed in the literature, most of them are not reliable or accurate enough for medical image segmentation. Geometric Deformable Models have been widely used as a method of medical image segmentation using only geometric measures. They have proved their efficiency, ease of implementation and ability to handle automatic topology changes. Since, in medical images, the topology of the target to be segmented is known beforehand, different concepts of topology preserving have been implemented along with Geometric Deformable Models as a term to constrain their topology while evolving. MethodIn this paper, we propose a new approach for image segmentation, called the Selective Binary Level Set function and a new variant of the Topology Preserving Selective Binary Level Set model. ResultsThe proposed approach successfully achieves either global or local segmentations. Different metrics were used to evaluate and compare our segmentation results of the heart ventricle to other methods. ConclusionResults show the effectiveness of our proposed method, which proved accurate as a primary step for medical image analysis.

Active contour modal based on density-oriented BIRCH clustering method for medical image segmentation

Currently, medical image segmentation has attracted more attention from researchers, which can assist in medical diagnosis. However, in the process of traditional medical image segmentation, it is sensitive to the initial contour and noise, which is difficult to deal with the weak edge image, complex iterative process. In this paper, we propose a new medical image segmentation method, which adopts density-oriented BIRCH (balanced iterative reducing and clustering using hierarchies) clustering method to modify active contour model and improve the robustness of noise. The BIRCH is a multi-stage clustering method using clustering feature tree. The improved model can effectively deal with the gray non-uniformity of real medical images. And we also introduce a new energy function in active contour model to make the contour curve approach to the edge, and finally stay at the edge of the image to complete the object segmentation. Experimental results show that this new model can overcome the influence of complex background on medical image segmentation and improve the speed and accuracy of medical segmentation results.

ADR-Net: Context extraction network based on M-Net for medical image segmentation.

Medical image segmentation is an essential component of medical image analysis. Accurate segmentation can assist doctors in diagnosis and relieve their fatigue. Although several image segmentation methods based on U-Net have been proposed, their performances have been observed to be suboptimal in the case of small-sized objects. To address this shortcoming, a novel network architecture is proposed in this study to enhance segmentation performance on small medical targets. In this paper, we propose a joint multi-scale context attention network architecture to simultaneously capture higher level semantic information and spatial information. In order to obtain a greater number of feature maps during decoding, the network concatenates the images of side inputs by down-sampling during the encoding phase. In the bottleneck layer of the network, dense atrous convolution (DAC) and multi-scale residual pyramid pooling (RMP) modules are exploited to better capture high-level semantic information and spatial information. To improve the segmentation performance on small targets, the attention gate (AG) block is used to effectively suppress feature activation in uncorrelated regions and highlight the target area. The proposed model is first evaluated on the public dataset DRIVE, on which it performs significantly better than the basic framework in terms of sensitivity (SE), intersection-over-union (IOU), and area under the receiver operating characteristic curve (AUC). In particular, the SE and IOU are observed to increase by 7.46% and 5.97%, respectively. Further, the evaluation indices exhibit improvements compared to those of state-of-the-art methods as well, with SE and IOU increasing by 3.58% and 3.26%, respectively. Additionally, in order to demonstrate the generalizability of the proposed architecture, we evaluate our model on three other challenging datasets. The respective performances are observed to be better than those of state-of-the-art network architectures on the same datasets. Moreover, we use lung segmentation as a comparative experiment to demonstrate the transferability of the advantageous properties of the proposed approach in the context of small target segmentation to the segmentation of large targets. Finally, an ablation study is conducted to investigate the individual contributions of the AG block, the DAC block, and the RMP block to the performance of the network. The proposed method is evaluated on various datasets. Experimental results demonstrate that the proposed model performs better than state-of-the-art methods in medical image segmentation of small targets.

A deep learning method for real-time intraoperative US image segmentation in prostate brachytherapy.

This paper addresses the detection of the clinical target volume (CTV) in transrectal ultrasound (TRUS) image-guided intraoperative for permanent prostate brachytherapy. Developing a robust and automatic method to detect the CTV on intraoperative TRUS images is clinically important to have faster and reproducible interventions that can benefit both the clinical workflow and patient health. We present a multi-task deep learning method for an automatic prostate CTV boundary detection in intraoperative TRUS images by leveraging both the low-level and high-level (prior shape) information. Our method includes a channel-wise feature calibration strategy for low-level feature extraction and learning-based prior knowledge modeling for prostate CTV shape reconstruction. It employs CTV shape reconstruction from automatically sampled boundary surface coordinates (pseudo-landmarks) to detect the low-contrast and noisy regions across the prostate boundary, while being less biased from shadowing, inherent speckles, and artifact signals from the needle and implanted radioactive seeds. The proposed method was evaluated on a clinical database of 145 patients who underwent permanent prostate brachytherapy under TRUS guidance. Our method achieved a mean accuracy of [Formula: see text] and a mean surface distance error of [Formula: see text]. Extensive ablation and comparison studies show that our method outperformed previous deep learning-based methods by more than 7% for the Dice similarity coefficient and 6.9 mm reduced 3D Hausdorff distance error. Our study demonstrates the potential of shape model-based deep learning methods for an efficient and accurate CTV segmentation in an ultrasound-guided intervention. Moreover, learning both low-level features and prior shape knowledge with channel-wise feature calibration can significantly improve the performance of deep learning methods in medical image segmentation.

Fast interactive medical image segmentation with weakly supervised deep learning method.

To achieve accurate image segmentation, which is the first critical step in medical image analysis and interventions, using deep neural networks seems a promising approach provided sufficiently large and diverse annotated data from experts. However, annotated datasets are often limited because it is prone to variations in acquisition parameters and require high-level expert's knowledge, and manually labeling targets by tracing their contour is often laborious. Developing fast, interactive, and weakly supervised deep learning methods is thus highly desirable. We propose a new efficient deep learning method to accurately segment targets from images while generating an annotated dataset for deep learning methods. It involves a generative neural network-based prior-knowledge prediction from pseudo-contour landmarks. The predicted prior knowledge (i.e., contour proposal) is then refined using a convolutional neural network that leverages the information from the predicted prior knowledge and the raw input image. Our method was evaluated on a clinical database of 145 intraoperative ultrasound and 78 postoperative CT images of image-guided prostate brachytherapy. It was also evaluated on a cardiac multi-structure segmentation from 450 2D echocardiographic images. Experimental results show that our model can segment the prostate clinical target volume in 0.499 s (i.e., 7.79 milliseconds per image) with an average Dice coefficient of 96.9 ± 0.9% and 95.4 ± 0.9%, 3D Hausdorff distance of 4.25 ± 4.58 and 5.17 ± 1.41 mm, and volumetric overlap ratio of 93.9 ± 1.80% and 91.3 ± 1.70 from TRUS and CT images, respectively. It also yielded an average Dice coefficient of 96.3 ± 1.3% on echocardiographic images. We proposed and evaluated a fast, interactive deep learning method for accurate medical image segmentation. Moreover, our approach has the potential to solve the bottleneck of deep learning methods in adapting to inter-clinical variations and speed up the annotation processes.

A medical image segmentation method based on hybrid active contour model with global and local features

SummaryIn this article, we proposed an improved region‐based active contour model based on curve evolution theory and variational level set method. Our method can be used to segment image with intensity inhomogeneity, such as medical computed tomography images. Our model contains a local intensity fitting term that makes the evolution curve stop at boundaries of the object and a global expansion term that makes the evolution curve have the chance to get to every location in the image. Therefore, our model has a good performance to solve the problem of flexible initialization, which exposed in region‐scalable fitting energy model. For the curvature term that occurs during the calculation, we calculated it with a more efficiency and accuracy method. Compared with other models, our model shows good segmentation result and less computation expense. Finally, we will present some experimental results, especially the result of contrast experiment.

Md-Net: Multi-scale Dilated Convolution Network for CT Images Segmentation

Accurate CT image segmentation is of great importance to the clinical diagnosis. Due to the high similarity of gray values in CT image, the segmented areas are easily affected by their surroundings, which leads to the loss of semantic information. In this paper, we propose a multi-scale dilated convolution network (Md-Net) for CT image segmentation with superior segmentation performance compared with state-of-the-art methods. Specifically, our Md-Net utilizes the dilated convolutions with different sizes to form feature pyramids for extracting the semantic information. Moreover, we use a weighted Diceloss to accelerate the convergence in training process. Meanwhile, the bilinear interpolation and multiple convolutions are taken to reduce the computational cost. Experiment results show that our proposed Md-Net outperforms the representative medical image segmentation methods, including Unet, Unet++, MaskRcnn and CE-Net, in terms of sensitivity, accuracy and area under curve both on lung dataset and Bladder dataset.

Multi-step medical image segmentation based on reinforcement learning

Image segmentation technology has made a remarkable effect in medical image analysis and processing, which is used to help physicians get a more accurate diagnosis. Manual segmentation of the medical image requires a lot of effort by professionals, which is also a subjective task. Therefore, developing an advanced segmentation method is an essential demand. We propose an end-to-end segmentation method for medical images, which mimics physicians delineating a region of interest (ROI) on the medical image in a multi-step manner. This multi-step operation improves the performance from a coarse result to a fine result progressively. In this paper, the segmentation process is formulated as a Markov decision process and solved by a deep reinforcement learning (DRL) algorithm, which trains an agent for segmenting ROI in images. The agent performs a serial action to delineate the ROI. We define the action as a set of continuous parameters. Then, we adopted a DRL algorithm called deep deterministic policy gradient to learn the segmentation model in continuous action space. The experimental result shows that the proposed method has 7.24% improved to the state-of-the-art method on three prostate MR data sets and has 3.52% improved on one retinal fundus image data set.