Search

Background: The pancreas is a complex abdominal organ with many anatomical variations, and therefore automated pancreas segmentation from medical images is a challenging application., Purpose: In this paper, we present a framework for segmenting individual pancreatic subregions and the pancreatic duct from three-dimensional (3D) computed tomography (CT) images., Methods: A multiagent reinforcement learning (RL) network was used to detect landmarks of the head, neck, body, and tail of the pancreas, and landmarks along the pancreatic duct in a selected target CT image. Using the landmark detection results, an atlas of pancreases was nonrigidly registered to the target image, resulting in anatomical probability maps for the pancreatic subregions and duct. The probability maps were augmented with multilabel 3D U-Net architectures to obtain the final segmentation results., Results: To evaluate the performance of our proposed framework, we computed the Dice similarity coefficient (DSC) between the predicted and ground truth manual segmentations on a database of 82 CT images with manually segmented pancreatic subregions and 37 CT images with manually segmented pancreatic ducts. For the four pancreatic subregions, the mean DSC improved from 0.38, 0.44, and 0.39 with standard 3D U-Net, Attention U-Net, and shifted windowing (Swin) U-Net architectures, to 0.51, 0.47, and 0.49, respectively, when utilizing the proposed RL-based framework. For the pancreatic duct, the RL-based framework achieved a mean DSC of 0.70, significantly outperforming the standard approaches and existing methods on different datasets., Conclusions: The resulting accuracy of the proposed RL-based segmentation framework demonstrates an improvement against segmentation with standard U-Net architectures., (© 2024 The Author(s). Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)

Purpose: Prostate cancer classification has a significant impact on the prognosis and treatment planning of patients. Currently, this classification is based on the Gleason score analysis of biopsied tissues, which is neither accurate nor risk free. This study aims to learn discriminative features in prostate images and assist physicians in classifying prostate cancer automatically., Methods: We develop a novel multiparametric magnetic resonance transfer learning (MPTL) method to automatically stage prostate cancer. We first establish a deep convolutional neural network with three branch architectures, which transfer pretrained model to compute features from multiparametric MRI images (mp-MRI): T2w transaxial, T2w sagittal, and apparent diffusion coefficient (ADC). The learned features are concatenated to represent information of mp-MRI sequences. A new image similarity constraint is then proposed to enable the distribution of the features within the same category in a narrow angle region. With the joint constraints of softmax loss and image similarity loss in the fine-tuning process, the MPTL can provide descriptive features with intraclass compactness and interclass separability., Results: Two cohorts: 132 cases from our institutional review board-approved patient database and 112 cases from the PROSTATEx-2 Challenge are utilized to evaluate the robustness and effectiveness of the proposed MPTL model. Our model achieved high accuracy of prostate cancer classification (accuracy of 86.92%). Moreover, the comparison results demonstrate that our method outperforms both hand-crafted feature-based methods and existing deep learning models in prostate cancer classification with higher accuracy., Conclusion: The experiment results showed that the proposed method can learn discriminative features in prostate images and classify the cancer accurately. Our MPTL model could be further applied in the clinical practice to provide valuable information for cancer treatment and precision medicine., (© 2018 American Association of Physicists in Medicine.)

Segmentation of liver in abdominal computed tomography (CT) is an important step for radiation therapy planning of hepatocellular carcinoma. Practically, a fully automatic segmentation of liver remains challenging because of low soft tissue contrast between liver and its surrounding organs, and its highly deformable shape. The purpose of this work is to develop a novel superpixel-based and boundary sensitive convolutional neural network (SBBS-CNN) pipeline for automated liver segmentation. The entire CT images were first partitioned into superpixel regions, where nearby pixels with similar CT number were aggregated. Secondly, we converted the conventional binary segmentation into a multinomial classification by labeling the superpixels into three classes: interior liver, liver boundary, and non-liver background. By doing this, the boundary region of the liver was explicitly identified and highlighted for the subsequent classification. Thirdly, we computed an entropy-based saliency map for each CT volume, and leveraged this map to guide the sampling of image patches over the superpixels. In this way, more patches were extracted from informative regions (e.g. the liver boundary with irregular changes) and fewer patches were extracted from homogeneous regions. Finally, deep CNN pipeline was built and trained to predict the probability map of the liver boundary. We tested the proposed algorithm in a cohort of 100 patients. With 10-fold cross validation, the SBBS-CNN achieved mean Dice similarity coefficients of 97.31  ±  0.36% and average symmetric surface distance of 1.77  ±  0.49 mm. Moreover, it showed superior performance in comparison with state-of-art methods, including U-Net, pixel-based CNN, active contour, level-sets and graph-cut algorithms. SBBS-CNN provides an accurate and effective tool for automated liver segmentation. It is also envisioned that the proposed framework is directly applicable in other medical image segmentation scenarios.

Automated segmentation of the portal vein (PV) for liver radiotherapy planning is a challenging task due to potentially low vasculature contrast, complex PV anatomy and image artifacts originated from fiducial markers and vasculature stents. In this paper, we propose a novel framework for automated segmentation of the PV from computed tomography (CT) images. We apply convolutional neural networks (CNNs) to learn the consistent appearance patterns of the PV using a training set of CT images with reference annotations and then enhance the PV in previously unseen CT images. Markov random fields (MRFs) were further used to smooth the results of the enhancement of the CNN enhancement and remove isolated mis-segmented regions. Finally, CNN-MRF-based enhancement was augmented with PV centerline detection that relied on PV anatomical properties such as tubularity and branch composition. The framework was validated on a clinical database with 72 CT images of patients scheduled for liver stereotactic body radiation therapy. The obtained accuracy of the segmentation was [Formula: see text] 0.83 and [Formula: see text] 1.08 mm in terms of the median Dice coefficient and mean symmetric surface distance, respectively, when segmentation is encompassed into the PV region of interest. The obtained results indicate that CNNs and anatomical analysis can be used for the accurate segmentation of the PV and potentially integrated into liver radiation therapy planning.

Purpose: Accurate segmentation of organs-at-risks (OARs) is the key step for efficient planning of radiation therapy for head and neck (HaN) cancer treatment. In the work, we proposed the first deep learning-based algorithm, for segmentation of OARs in HaN CT images, and compared its performance against state-of-the-art automated segmentation algorithms, commercial software, and interobserver variability., Methods: Convolutional neural networks (CNNs)-a concept from the field of deep learning-were used to study consistent intensity patterns of OARs from training CT images and to segment the OAR in a previously unseen test CT image. For CNN training, we extracted a representative number of positive intensity patches around voxels that belong to the OAR of interest in training CT images, and negative intensity patches around voxels that belong to the surrounding structures. These patches then passed through a sequence of CNN layers that captured local image features such as corners, end-points, and edges, and combined them into more complex high-order features that can efficiently describe the OAR. The trained network was applied to classify voxels in a region of interest in the test image where the corresponding OAR is expected to be located. We then smoothed the obtained classification results by using Markov random fields algorithm. We finally extracted the largest connected component of the smoothed voxels classified as the OAR by CNN, performed dilate-erode operations to remove cavities of the component, which resulted in segmentation of the OAR in the test image., Results: The performance of CNNs was validated on segmentation of spinal cord, mandible, parotid glands, submandibular glands, larynx, pharynx, eye globes, optic nerves, and optic chiasm using 50 CT images. The obtained segmentation results varied from 37.4% Dice coefficient (DSC) for chiasm to 89.5% DSC for mandible. We also analyzed the performance of state-of-the-art algorithms and commercial software reported in the literature, and observed that CNNs demonstrate similar or superior performance on segmentation of spinal cord, mandible, parotid glands, larynx, pharynx, eye globes, and optic nerves, but inferior performance on segmentation of submandibular glands and optic chiasm., Conclusion: We concluded that convolution neural networks can accurately segment most of OARs using a representative database of 50 HaN CT images. At the same time, inclusion of additional information, for example, MR images, may be beneficial to some OARs with poorly visible boundaries., (© 2016 American Association of Physicists in Medicine.)

Atlas-based segmentation utilizes a library of previously delineated contours of similar cases to facilitate automatic segmentation. The problem, however, remains challenging because of limited information carried by the contours in the library. In this studying, we developed a narrow-shell strategy to enhance the information of each contour in the library and to improve the accuracy of the exiting atlas-based approach. This study presented a new concept of atlas based segmentation method. Instead of using the complete volume of the target organs, only information along the organ contours from the atlas images was used for guiding segmentation of the new image. In setting up an atlas-based library, we included not only the coordinates of contour points, but also the image features adjacent to the contour. In this work, 139 CT images with normal appearing livers collected for radiotherapy treatment planning were used to construct the library. The CT images within the library were first registered to each other using affine registration. The nonlinear narrow shell was generated alongside the object contours of registered images. Matching voxels were selected inside common narrow shell image features of a library case and a new case using a speed-up robust features (SURF) strategy. A deformable registration was then performed using a thin plate splines (TPS) technique. The contour associated with the library case was propagated automatically onto the new image by exploiting the deformation field vectors. The liver contour was finally obtained by employing level set based energy optimization within the narrow shell. The performance of the proposed method was evaluated by comparing quantitatively the auto-segmentation results with that delineated by physicians. A novel atlas-based segmentation technique with inclusion of neighborhood image features through the introduction of a narrow-shell surrounding the target objects was established. Application of the technique to 30 liver cases suggested that the technique was capable to reliably segment liver cases from CT, 4D-CT, and CBCT images with little human interaction. The accuracy and speed of the proposed method are quantitatively validated by comparing automatic segmentation results with the manual delineation results. The Jaccard similarity metric between the automatically generated liver contours obtained by the proposed method and the physician delineated results are on an average 90%-96% for planning images. Incorporation of image features into the library contours improves the currently available atlas-based auto-contouring techniques and provides a clinically practical solution for auto-segmentation. The proposed mountainous narrow shell atlas based method can achieve efficient automatic liver propagation for CT, 4D-CT and CBCT images with following treatment planning and should find widespread application in future treatment planning systems.

Cephalometric analysis is an essential clinical and research tool in orthodontics for the orthodontic analysis and treatment planning. This paper presents the evaluation of the methods submitted to the Automatic Cephalometric X-Ray Landmark Detection Challenge, held at the IEEE International Symposium on Biomedical Imaging 2014 with an on-site competition. The challenge was set to explore and compare automatic landmark detection methods in application to cephalometric X-ray images. Methods were evaluated on a common database including cephalograms of 300 patients aged six to 60 years, collected from the Dental Department, Tri-Service General Hospital, Taiwan, and manually marked anatomical landmarks as the ground truth data, generated by two experienced medical doctors. Quantitative evaluation was performed to compare the results of a representative selection of current methods submitted to the challenge. Experimental results show that three methods are able to achieve detection rates greater than 80% using the 4 mm precision range, but only one method achieves a detection rate greater than 70% using the 2 mm precision range, which is the acceptable precision range in clinical practice. The study provides insights into the performance of different landmark detection approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.

A novel game-theoretic framework for landmark-based image segmentation is presented. Landmark detection is formulated as a game, in which landmarks are players, landmark candidate points are strategies, and likelihoods that candidate points represent landmarks are payoffs, determined according to the similarity of image intensities and spatial relationships between the candidate points in the target image and their corresponding landmarks in images from the training set. The solution of the formulated game-theoretic problem is the equilibrium of candidate points that represent landmarks in the target image and is obtained by a novel iterative scheme that solves the segmentation problem in polynomial time. The object boundaries are finally extracted by applying dynamic programming to the optimal path searching problem between the obtained adjacent landmarks. The performance of the proposed framework was evaluated for segmentation of lung fields from chest radiographs and heart ventricles from cardiac magnetic resonance cross sections. The comparison to other landmark-based segmentation techniques shows that the results obtained by the proposed game-theoretic framework are highly accurate and precise in terms of mean boundary distance and area overlap. Moreover, the framework overcomes several shortcomings of the existing techniques, such as sensitivity to initialization and convergence to local optima.