Automated pancreas segmentation from three-dimensional contrast-enhanced computed tomography

Background and objectiveThe size, shape, and position of the pancreas are affected by the patient characteristics such as age, sex, adiposity. Owing to more complex anatomical structures (size, shape, and position) of the pancreas, specialists have some difficulties in the analysis of pancreatic diseases (diabetes, pancreatic cancer, pancreatitis). Therefore, the treatment of the disease requires enormous time and depends on the experience of specialists. In order to decrease the rate of pancreatic disease deaths and to assist the specialist in the analysis of pancreatic diseases, automatic pancreas segmentation techniques have been actively developed in the research article for many years. MethodsAlthough the rapid growth of deep learning and proving satisfactory performance in many medical image processing and computer vision applications, the maximum Dice Similarity Coefficients (DSC) value of these techniques related to automatic pancreas segmentation is only around 85% due to complex structure of the pancreas and other factors. Contrary to previous techniques which are required significantly higher computational power and memory, this paper suggests a novel two-phase approach for high-accuracy automatic pancreas segmentation in computed tomography (CT) imaging. The proposed approach consists of two phases; (1) Pancreas Localization, where the rough pancreas position is detected on the 2D CT slice by adopting Mask R-CNN model, (2) Pancreas Segmentation, where the segmented pancreas region is produced by refining the candidate pancreas region with 3D U-Net on the 2D sub-CT slices generated in the first phase. Both qualitative and quantitative assessments of the proposed approach are performed on the NIH data set. ResultsIn order to evaluate the achievement of the recommended approach, a total of 16 different automatic pancreas segmentation techniques reported in the literature are compared by utilizing performance assessment procedures which are Dice Similarity Coefficient (DSC), Jaccard Index (JI), Precision (PRE), Recall (REC), Pixel Accuracy (ACC), Specificity (SPE), Receiver Operating Characteristics (ROC) and Area under ROC curve (AUC). The average values of DSC, JI, REC and ACC are computed as 86.15%, 75.93%, 86.27%, 86.27% and 99.95% respectively, which are the best values among well-established studies for automatic pancreas segmentation. ConclusionIt is demonstrated with qualitative and quantitative results that our suggested two-phase approach creates more favorable results than other existing approaches.

Extension–contraction transformation network for pancreas segmentation in abdominal CT scans

Automatic pancreas segmentation in abdominal CT images plays an important role in clinical applications. It can provide doctors with quantitative and qualitative information. Due to the small size, unclear edges, and the high anatomical differences between patients, it is a challenging task to accurately segment the pancreas with diseases. In this paper, we propose a new method to automatically segment the pancreas in abdominal CT images. First, we propose a contrast enhancement block. The block generates edge information and uses gating mechanism to enhance edge details of the pancreas. Second, we leverage a reverse attention block. This block utilizes the decoder feature map to guide the network to mine complementary discriminative regions. The proposed method is trained on 63 3D CT images, validated on 15 3D CT images, and tested on 28 3D CT images. Compared with manual segmentation, the mean Dice similarity coefficient can reach 86.11±8.02%. Experimental results show that our method can obtain more accurate segmentation results compared with existing segmentation methods.

This paper proposes a fully automated atlas-based pancreas segmentation method from CT volumes utilizing atlas localization by regression forest and atlas generation using blood vessel information. Previous probabilistic atlas-based pancreas segmentation methods cannot deal with spatial variations that are commonly found in the pancreas well. Also, shape variations are not represented by an averaged atlas. We propose a fully automated pancreas segmentation method that deals with two types of variations mentioned above. The position and size of the pancreas is estimated using a regression forest technique. After localization, a patient-specific probabilistic atlas is generated based on a new image similarity that reflects the blood vessel position and direction information around the pancreas. We segment it using the EM algorithm with the atlas as prior followed by the graph-cut. In evaluation results using 147 CT volumes, the Jaccard index and the Dice overlap of the proposed method were 62.1% and 75.1%, respectively. Although we automated all of the segmentation processes, segmentation results were superior to the other state-of-the-art methods in the Dice overlap.

Localization and detection of isolated hot spots in single-photon emission computed tomography (SPECT) may be aided by the addition of anatomical information from X-ray computed tomography (CT). A method for registering SPECT and CT volumes was developed, using two planar transmission views of the patient acquired immediately before or after a SPECT scan by placing a sheet source on one head of a dual-head camera system. Corresponding reprojected CT (rCT) images were simultaneously registered to the transmission images, using a region of interest (ROI) containing the lung boundaries. Six parameters (translations in three dimensions and rotations through three Euler angles) were calculated by iteratively transforming and reprojecting until a correlation between the rCT and transmission data within the ROI was maximized. Final values of the transformation parameters were used to register the entire CT volume to the SPECT volume. An experiment was performed using a torso phantom and spherical lesions containing Ga-67, representing the distribution in a lymphoma patient. Accuracy was assessed by calculating the differences between coordinates of centroids of five tumors in the CT and SPECT images. The magnitudes of the differences in x, y and z averaged over the five tumors were 1.55 mm +/-1.30, 036 mm +/-2.23 and 0.13 mm +/-1.47. Precision was assessed by perturbing the orientation of the CT volume over a range of translations and rotations. Effects on the perturbed parameter and on the other parameters that were held constant were examined by calculating the standard deviation about the mean of each parameter's final value following registration. The values varied from 0.06 to 0.62 mm and from 0.05 to 1.68 deg for translation and rotation, respectively. Acceptable accuracy and precision for registration of CT to SPECT volumes were achieved with the use of the paired transmission and rCT images.

Automated pancreas segmentation in medical images is a prerequisite for many clinical applications, such as diabetes inspection, pancreatic cancer diagnosis, and surgical planing. In this paper, we formulate pancreas segmentation in magnetic resonance imaging (MRI) scans as a graph based decision fusion process combined with deep convolutional neural networks (CNN). Our approach conducts pancreatic detection and boundary segmentation with two types of CNN models respectively: 1) the tissue detection step to differentiate pancreas and non-pancreas tissue with spatial intensity context; 2) the boundary detection step to allocate the semantic boundaries of pancreas. Both detection results of the two networks are fused together as the initialization of a conditional random field (CRF) framework to obtain the final segmentation output. Our approach achieves the mean dice similarity coefficient (DSC) 76.1% with the standard deviation of 8.7% in a dataset containing 78 abdominal MRI scans. The proposed algorithm achieves the best results compared with other state of the arts.

Pancreas segmentation in computed tomography imaging has been historically difficult for automated methods because of the large shape and size variations between patients. In this work, we describe a custom-build 3D fully convolutional network (FCN) that can process a 3D image including the whole pancreas and produce an automatic segmentation. We investigate two variations of the 3D FCN architecture; one with concatenation and one with summation skip connections to the decoder part of the network. We evaluate our methods on a dataset from a clinical trial with gastric cancer patients, including 147 contrast enhanced abdominal CT scans acquired in the portal venous phase. Using the summation architecture, we achieve an average Dice score of 89.7 $\pm$ 3.8 (range [79.8, 94.8]) % in testing, achieving the new state-of-the-art performance in pancreas segmentation on this dataset.

Purpose When a surgeon examines the morphology of skull of patient, locations of craniometric landmarks of 3D computed tomography(CT) volume are one of the most important information for surgical purpose. The locations of craniometric landmarks can be found manually by surgeon from the 3D rendered volume or 2D sagittal, axial, and coronal slices which are taken by CT. Since there are many landmarks on the skull, finding these manually is time-consuming, exhaustive, and occasionally inexact. These inefficiencies raise a demand for a automatic localization technique for craniometric landmark points. So in this paper, we propose a novel method through which we can automatically find these landmark points, which are useful for surgical purpose. Materials and Methods At first, we align the experimental data (CT volumes) using Frankfurt Horizontal Plane (FHP) and Mid Sagittal Plane(MSP) which are defined by 3 and 2 cranial landmark points each. The target landmark of our experiment is the anterior nasal spine. Prior to constructing a statistical cubic model which would be used for detecting the location of the landmark from a given CT volume, reference points for the anterior nasal spine were manually chosen by a surgeon from several CT volume sets. The statistical cubic model is constructed by calculating weighted intensity means of these CT sets around the reference points. By finding the location where similarity function (squared difference function) has the minimal value with this model, the location of the landmark can be found from any given CT volume. Results In this paper, we used 5 CT volumes to construct the statistical cubic model. The 20 CT volumes including the volumes, which were used to construct the model, were used for testing. The range of age of subjects is up to 2 years (24 months) old. The found points of each data are almost close to the reference point which were manually chosen by surgeon. Also it has been seen that the similarity function always has the global minimum at the detection point. Conclusion Through the experiment, we have seen the proposed method shows the outstanding performance in searching the landmark point. This algorithm would make surgeons efficiently work with morphological informations of skull. We also expect the potential of our algorithm for searching the anatomic landmarks not only cranial landmarks.

Computed tomography (CT) is the preferred imaging modality for diagnosis of hemorrhage. The hematoma appears as hyper intense mass in the image. Computer aided diagnosis assists clinicians for making a better prediction and helps in surgery planning. Computer assistive method based on random walker is proposed for detection and delineation of hemorrhagic mass or hematoma from Computed Tomography (CT) volumes. 20 patients affected by hemorrhage is considered for this study. Each subject’s image has a size of 512 × 512 × 96. Every case has 96 images. In a CT volume each case has 96 slices. Each slice is of 512 × 512. The slice, which contains hematoma mass or ischemic lesion, is selected using one layer autoencoder. 60% of the patient volume is used for training and 40% of the patient volume is used for testing. The training accuracy of auto encoder was 100%, and testing accuracy was 99.5%. After the slices are classified as healthy and non-healthy, k-means clustering was applied on non-healthy slices for localization of hematoma. Random walker algorithm was applied on the localized lesion for delineation of hematoma from CT images. The computer generated output is compared with the manually delineated output with the help of similarity indices. The Dice similarity index and Jaccard coefficient was calculated as 0.768 ± 0.101 and 0.634 ± 0.128 respectively. The proposed algorithm suggests an alternate method for detection of hematoma using CT images.

Pancreas is one of the most challenging organs in segmentation due to its different shape, position and size in each human being. With the development of machine learning, various deep learning methods are applied to segment the pancreas among organs in the abdominal region. In this study, pancreas segmentation is performed using the U-Net model, which is one of the convolutional neural networks (CNN) models. The results of pancreas segmentation performed on the Pancreas CT data set obtained from The Cancer Imaging Archive (TCIA) database containing computed tomography images of 82 patients are presented in detail. According to the results, Dice similarity coefficient and Jaccard similarity coefficient are found to be 0.78 and 0.66, respectively.

Introduction: Precise segmentation of the liver from computed tomography (CT) scans is an essential component in the diagnosis and treatment of liver diseases such as hepatocellular carcinoma. Manual segmentation can be time-consuming and subject to variability, spurring the application of automated systems based on deep learning. We introduce a 3D U-Net-based convolutional neural network for end-to-end segmentation of the liver from volumetric CT images. The model is trained and tested on the LiTS dataset using a standard preprocessing pipeline and an in-house composite loss function—AdvancedComboLoss—combining Dice Loss, Binary Cross-Entropy, and Focal Tversky Loss to balance class imbalance and boundary accuracy. The network handles entire 3D volumes with spatial context retained between anatomical planes and is trained on a GPU-enabled setup with the PyTorch environment. Objectives: To develop a highly accurate and computationally efficient 3D U-Net-based deep learning model for automated liver segmentation from volumetric CT scans, addressing challenges like class imbalance, anatomical variability, and low tissue contrast, using a custom loss function (AdvancedComboLoss) and a standardized preprocessing pipeline. Methods: The methodology adopted is volumetric liver segmentation from a specially designed 3D U-Net architecture specific to medical CT scans. The process entails preprocessing of raw CT scans into a common shape and intensity range and training a fully convolutional 3D neural network that learns the spatial relationships among all three anatomical planes. The model uses an encoder-decoder architecture with skip connections to maintain fine-grained structural information, allowing for accurate delineation of liver regions. A hybrid loss function—integrating Dice, Binary Cross-Entropy, and Focal Tversky losses—is used to direct the learning process to optimize overlap of regions, accuracy of classification, and class imbalance. Results: Experimental outcomes demonstrate that the model has a Dice score of 0.9604 and voxel-wise accuracy of 0.9979, indicating excellent performance in segmentation as well as strong agreement with expert annotations. The model presented in this paper presents a solid, scalable, and clinically valuable approach to automated liver segmentation with future potential to integrate into multi-stage liver and tumor analysis workflows. Conclusions: Herein, we built and tested a 3D U-Net deep learning architecture for unsupervised liver segmentation from abdominal CT volumes. Through utilization of volumetric convolutions as well as through a well-engineered composite loss function, the model was successful in capturing complicated liver anatomy as well as being able to hold high performance even on varied CT volumes. The power of the method is not just in its quantitative performance but also in its capability to generate anatomically consistent and visually plausible segmentations, making it extremely relevant to actual clinical workflows. Although there are some limitations—constrained batch size and absence of data augmentation—there is room for improvement, the findings affirm that deep learning can be an effective tool for automating key tasks in medical image analysis. As a whole, this paper adds a robust and effective segmentation model that would be potentially embedded in wider diagnostic workflows, ending up improving the accuracy, speed, and scalability of liver evaluation in clinical practice. In brief, this paper adds a high-fidelity, scalable, and computationally effective solution for computer-aided liver segmentation, pushing the application of artificial intelligence in clinical decision-making and medical image analysis.

Feasibility of MR-Generated Synthetic CT Images for Planning Stereotactic Radiosurgery of Brain Metastases

Pancreas segmentation in computed tomography (CT) is a challenging task because of the high inter-patient anatomical variability in both shape and size between patients. In this work, we proposed a convolutional neural networks based level set framework that can automatically segment a 3D images with the whole pancreas. Convolutional neural networks is applied to obtain an initial level set contour and then level set model is used to produce accurate segmentation results. Our method was compared with the state-of-the-art methods and evaluated on 20 CT images. The experiment results show that our approach achieves the highest dice scores than other methods.

Deep pancreas segmentation with uncertain regions of shadowed sets

The segmentation of organs in CT volumes is a prerequisite for diagnosis and treatment planning. In this paper, we focus on liver segmentation from contrast-enhanced abdominal CT volumes, a challenging task due to intensity overlapping, blurred edges, large variability in liver shape, and complex background with cluttered features. The algorithm integrates multidiscriminative cues (i.e., prior domain information, intensity model, and regional characteristics of liver in a graph-cut image segmentation framework). The paper proposes a swarm intelligence inspired edge-adaptive weight function for regulating the energy minimization of the traditional graph-cut model. The model is validated both qualitatively (by clinicians and radiologists) and quantitatively on publically available computed tomography (CT) datasets (MICCAI 2007 liver segmentation challenge, 3D-IRCAD). Quantitative evaluation of segmentation results is performed using liver volume calculations and a mean score of 80.8% and 82.5% on MICCAI and IRCAD dataset, respectively, is obtained. The experimental result illustrates the efficiency and effectiveness of the proposed method.