Search

Liver tumor segmentation (LiTS) is of primary importance in diagnosis and treatment of hepatocellular carcinoma. Known automated LiTS methods could not yield satisfactory results for clinical use since they were hard to model flexible tumor shapes and locations. In clinical practice, radiologists usually estimate tumor shape and size by a Response Evaluation Criteria in Solid Tumor (RECIST) mark. Inspired by this, in this paper, we explore a deep learning (DL) based interactive LiTS method, which incorporates guidance from user-provided RECIST marks. Our method takes a three-step framework to predict liver tumor boundaries. Under this architecture, we develop a RECIST mark propagation network (RMP-Net) to estimate RECIST-like marks in off-RECIST slices. We also devise a context-guided boundary-sensitive network (CGBS-Net) to distill tumors' contextual and boundary information from corresponding RECIST(-like) marks, and then predict tumor maps. To further refine the segmentation results, we process the tumor maps using a 3D conditional random field (CRF) algorithm and a morphology hole-filling operation. Verified on two clinical contrast-enhanced abdomen computed tomography (CT) image datasets, our proposed approach can produce promising segmentation results, and outperforms the state-of-the-art interactive segmentation methods.

Automatic segmentation of the liver and hepatic lesions from abdominal 3D computed tomography (CT) images is fundamental tasks in computer-assisted liver surgery planning. However, due to complex backgrounds, ambiguous boundaries, heterogeneous appearances and highly varied shapes of the liver, accurate liver segmentation and tumor detection are still challenging problems. To address these difficulties, we propose an automatic segmentation framework based on 3D U-net with dense connections and globally optimized refinement. Firstly, a deep U-net architecture with dense connections is trained to learn the probability map of the liver. Then the probability map goes into the following refinement step as the initial surface and prior shape. The segmentation of liver tumor is based on the similar network architecture with the help of segmentation results of liver. In order to reduce the influence of the surrounding tissues with the similar intensity and texture behavior with the tumor region, during the training procedure, I × liverlabel is the input of the network for the segmentation of liver tumor. By doing this, the accuracy of segmentation can be improved. The proposed method is fully automatic without any user interaction. Both qualitative and quantitative results reveal that the proposed approach is efficient and accurate for liver volume estimation in clinical application. The high correlation between the automatic and manual references shows that the proposed method can be good enough to replace the time-consuming and non-reproducible manual segmentation method.

This study aimed to investigate the efficacy, safety, and prognostic factors of drug-eluting beads transarterial chemoembolization (DEB-TACE) in treating Chinese patients with liver cancer. A total of 367 liver cancer patients from 24 medical centers were consecutively enrolled in this multiple-center, prospective cohort study, including 275 hepatocellular carcinoma (HCC) cases, 37 intrahepatic cholangiocarcinoma (ICC) cases, and 55 secondary liver cancer cases. All the patients received CalliSpheres® DEB-TACE treatment. Treatment response, overall survival (OS), change of liver function, and adverse events (AEs) were assessed. DEB-TACE treatment achieved 19.9% complete response (CR) and 79.6% objective response rate (ORR), with mean OS of 384 days [95% confidence interval (CI): 375‐393 days]. CR and ORR were both higher in HCC patients compared with primary ICC patients and secondary liver cancer patients, while no difference was discovered in OS. Portal vein invasion was an independent risk factor for CR, while portal vein invasion, previous conventional TACE (cTACE) treatment, and abnormal blood creatinine (BCr) were independent risk factors for ORR. In addition, largest nodule size ≥5.0 cm, abnormal albumin (ALB), and abnormal total bilirubin (TBIL) independently correlated with unfavorable OS. Most liver function indexes were recovered to baseline levels at 1‐3 months after DEB-TACE. Common AEs were pain, fever, vomiting, and nausea; most of them were at mild grade. CalliSpheres® DEB-TACE is efficient and well tolerated in Chinese liver cancer patients. Portal vein invasion, previous cTACE treatment, largest nodule size, abnormal BCr, ALB, and TBIL correlate with worse prognosis independently.

The purpose of this study was to investigate the efficacy and safety of drug-eluting beads transarterial chemoembolization (DEB-TACE) treatment in Chinese hepatocellular carcinoma (HCC) patients and the prognostic factors for treatment response as well as survival. A total of 275 HCC patients were included in this prospective study. Treatment response was assessed by modified Response Evaluation Criteria in Solid Tumors (mRECIST), and progression-free survival (PFS) as well as overall survival (OS) were determined. Liver function and adverse events (AEs) were assessed before and after DEB-TACE operation. Complete response (CR), partial response (PR), and objective response rate (ORR) were 22.9%, 60.7%, and 83.6%, respectively. The mean PFS was 362 (95% CI: 34.9‐375) days, the 6-month PFS rate was 89.4 ± 2.1%, while the mean OS was 380 (95% CI: 370‐389) days, and the 6-month OS rate was 94.4 ± 1.7%. Multivariate logistic regression revealed that portal vein invasion (p = 0.011) was an independent predictor of worse clinical response. Portal vein invasion (p = 0.040), previous cTACE treatment (p = 0.030), as well as abnormal serum creatinine level (BCr) (p = 0.017) were independent factors that predicted worse ORR. In terms of survival, higher Barcelona Clinic Liver Cancer (BCLC) stage (p = 0.029) predicted for worse PFS, and abnormal albumin (ALB) (p = 0.011) and total serum bilirubin (TBIL) (p = 0.009) predicted for worse OS. The number of patients with abnormal albumin, total protein (TP), TBIL, alanine aminotransferase (ALT), and aspartate aminotransferase (AST) were augmented at 1 week posttreatment and were similar at 1‐3 months compared with baseline. The most common AEs were pain, fever, nausea, and vomiting, and no severe AEs were observed in this study. DEB-TACE was effective and tolerable in treating Chinese HCC patients, and portal vein invasion, previous cTACE treatment, abnormal BCr, ALB, and TBIL appear to be important factors that predict worse clinical outcome.

Purpose: Accurate lymph node (LN) status evaluation for intrahepatic cholangiocarcinoma (ICC) patients is essential for surgical planning. This study aimed to develop and validate a prediction model for preoperative LN status evaluation in ICC patients. Methods and Materials: A group of 106 ICC patients, who were diagnosed between April 2011 and February 2016, was used for prediction model training. Image features were extracted from T1-weighted contrast-enhanced MR images. A support vector machine (SVM) model was built by using the most LN status-related features, which were selected using the maximum relevance minimum redundancy (mRMR) algorithm. The mRMR method ranked each feature according to its relevance to the LN status and redundancy with other features. An SVM score was calculated for each patient to reflect the LN metastasis (LNM) probability from the SVM model. Finally, a combination nomogram was constructed by incorporating the SVM score and clinical features. An independent group of 42 patients who were diagnosed from March 2016 to November 2017 was used to validate the prediction models. The model performances were evaluated on discrimination, calibration, and clinical utility. Results: The SVM model was constructed based on five selected image features. Significant differences were found between patients with LNM and non-LNM in SVM scores in both groups (the training group: 0.5466 (interquartile range (IQR), 0.4059-0.6985) vs. 0.3226 (IQR, 0.0527-0.4659), P

Coronavirus Disease 2019 (COVID-19) has rapidly spread in 2020, emerging a mass of studies for lung infection segmentation from CT images. Though many methods have been proposed for this issue, it is a challenging task because of infections of various size appearing in different lobe zones. To tackle these issues, we propose a Graph-based Pyramid Global Context Reasoning (Graph-PGCR) module, which is capable of modeling long-range dependencies among disjoint infections as well as adapt size variation. We first incorporate graph convolution to exploit long-term contextual information from multiple lobe zones. Different from previous average pooling or maximum object probability, we propose a saliency-aware projection mechanism to pick up infection-related pixels as a set of graph nodes. After graph reasoning, the relation-aware features are reversed back to the original coordinate space for the down-stream tasks. We further construct multiple graphs with different sampling rates to handle the size variation problem. To this end, distinct multi-scale long-range contextual patterns can be captured. Our Graph- PGCR module is plug-and-play, which can be integrated into any architecture to improve its performance. Experiments demonstrated that the proposed method consistently boost the performance of state-of-the-art backbone architectures on both of public and our private COVID-19 datasets.

In this paper, we propose a phase attention residual network (PA-ResSeg) to model multi-phase features for accurate liver tumor segmentation, in which a phase attention (PA) is newly proposed to additionally exploit the images of arterial (ART) phase to facilitate the segmentation of portal venous (PV) phase. The PA block consists of an intra-phase attention (Intra-PA) module and an inter-phase attention (Inter-PA) module to capture channel-wise self-dependencies and cross-phase interdependencies, respectively. Thus it enables the network to learn more representative multi-phase features by refining the PV features according to the channel dependencies and recalibrating the ART features based on the learned interdependencies between phases. We propose a PA-based multi-scale fusion (MSF) architecture to embed the PA blocks in the network at multiple levels along the encoding path to fuse multi-scale features from multi-phase images. Moreover, a 3D boundary-enhanced loss (BE-loss) is proposed for training to make the network more sensitive to boundaries. To evaluate the performance of our proposed PA-ResSeg, we conducted experiments on a multi-phase CT dataset of focal liver lesions (MPCT-FLLs). Experimental results show the effectiveness of the proposed method by achieving a dice per case (DPC) of 0.77.87, a dice global (DG) of 0.8682, a volumetric overlap error (VOE) of 0.3328 and a relative volume difference (RVD) of 0.0443 on the MPCT-FLLs. Furthermore, to validate the effectiveness and robustness of PA-ResSeg, we conducted extra experiments on another multi-phase liver tumor dataset and obtained a DPC of 0.8290, a DG of 0.9132, a VOE of 0.2637 and a RVD of 0.0163. The proposed method shows its robustness and generalization capability in different datasets and different backbones., Comment: A self-archive version to be published in Medical Physics, awaiting minor revision

Objective: To study the effects of absorbable materials in non-weight-bearing bone fractures of extremities. Methods: After 66 patients with non-weight-bearing bone fractures of extremities were selected, absorbable materials were used in the observation group and metal materials were used in the control group. Results: After treatment, the bone healing in the observation group was significantly improved (P

Objective: To study the effect of minimally invasive spinal trauma surgery on spinal trauma. Methods: After 60 patients with spinal trauma were selected, the patients in observation group was treated by minimally invasive spinal trauma surgery, while the patients in control group was given the routine treatment. Results: After treatment, the observation group improved significantly in operation related indexes, complication rate, pain degree, quality of life, JOA score and 0DI score(P

Background This study aimed to assess the treatment response, short-term overall survival (OS) and safety profiles of drug-eluting beads transarterial chemoembolization (DEB-TACE) in patients with secondary liver cancer. Methods Fifty-five patients with secondary liver cancer underwent DEB-TACE were enrolled in this prospective cohort study. Treatment response was assessed by modified Response Evaluation Criteria in Solid Tumors (mRECIST). OS was calculated from the time of DEB-TACE operation until the date of death. Results The complete response (CR) and objective response rate (ORR) at 1–3 months post DEB-TACE were 12.7% and 67.3%. Mean OS was 383 d (95% CI: 360–406), and 6-month OS rate was 93.4%±3.7%. Subgroup analysis revealed previous conventional TACE (cTACE) treatment was correlated with worse ORR (P=0.028), and it was a risk factor for ORR achievement (P=0.021). As for liver function, the percentages of abnormal TP (P=0.031), TBIL (P=0.022), ALT (P=0.002) and AST (P=0.035) were increased at 1 week post DEB-TACE compared to baseline, while these four indexes returned to baseline (all P>0.05) at 1–3 months post DEB-TACE. As to safety profiles, 41 (66.1%), 28 (45.2%), 17 (27.4%), 8 (12.9%) and 6 (9.7%) cases had pain, vomiting, fever, nausea and other adverse events (AEs) respectively during DEB-TACE operation, while 26 (41.9%), 9 (14.5%), 8 (12.9%), 4 (6.5%), 1 (1.6%) and 2 (3.2%) cases had pain, fever, vomiting, nausea, bone marrow toxicity and other AEs respectively at 1 month after DEB-TACE operation. Conclusions DEB-TACE was efficient and well tolerated in treating patients with secondary liver cancer.

This study aimed to investigate the efficacy, safety, and prognostic factors of drug-eluting beads transarterial chemoembolization (DEB-TACE) in treating Chinese patients with liver cancer. A total of 367 liver cancer patients from 24 medical centers were consecutively enrolled in this multiple-center, prospective cohort study, including 275 hepatocellular carcinoma (HCC) cases, 37 intrahepatic cholangiocarcinoma (ICC) cases, and 55 secondary liver cancer cases. All the patients received CalliSpheres® DEB-TACE treatment. Treatment response, overall survival (OS), change of liver function, and adverse events (AEs) were assessed. DEB-TACE treatment achieved 19.9% complete response (CR) and 79.6% objective response rate (ORR), with mean OS of 384 days [95% confidence interval (CI): 375–393 days]. CR and ORR were both higher in HCC patients compared with primary ICC patients and secondary liver cancer patients, while no difference was discovered in OS. Portal vein invasion was an independent risk factor for CR, while portal vein invasion, previous conventional TACE (cTACE) treatment, and abnormal blood creatinine (BCr) were independent risk factors for ORR. In addition, largest nodule size ≥5.0 cm, abnormal albumin (ALB), and abnormal total bilirubin (TBIL) independently correlated with unfavorable OS. Most liver function indexes were recovered to baseline levels at 1–3 months after DEB-TACE. Common AEs were pain, fever, vomiting, and nausea; most of them were at mild grade. CalliSpheres® DEB-TACE is efficient and well tolerated in Chinese liver cancer patients. Portal vein invasion, previous cTACE treatment, largest nodule size, abnormal BCr, ALB, and TBIL correlate with worse prognosis independently.

The purpose of this study was to investigate the efficacy and safety of drug-eluting beads transarterial chemoembolization (DEB-TACE) treatment in Chinese hepatocellular carcinoma (HCC) patients and the prognostic factors for treatment response as well as survival. A total of 275 HCC patients were included in this prospective study. Treatment response was assessed by modified Response Evaluation Criteria in Solid Tumors (mRECIST), and progression-free survival (PFS) as well as overall survival (OS) were determined. Liver function and adverse events (AEs) were assessed before and after DEB-TACE operation. Complete response (CR), partial response (PR), and objective response rate (ORR) were 22.9%, 60.7%, and 83.6%, respectively. The mean PFS was 362 (95% CI: 34.9–375) days, the 6-month PFS rate was 89.4 ± 2.1%, while the mean OS was 380 (95% CI: 370–389) days, and the 6-month OS rate was 94.4 ± 1.7%. Multivariate logistic regression revealed that portal vein invasion (p = 0.011) was an independent predictor of worse clinical response. Portal vein invasion (p = 0.040), previous cTACE treatment (p = 0.030), as well as abnormal serum creatinine level (BCr) (p = 0.017) were independent factors that predicted worse ORR. In terms of survival, higher Barcelona Clinic Liver Cancer (BCLC) stage (p = 0.029) predicted for worse PFS, and abnormal albumin (ALB) (p = 0.011) and total serum bilirubin (TBIL) (p = 0.009) predicted for worse OS. The number of patients with abnormal albumin, total protein (TP), TBIL, alanine aminotransferase (ALT), and aspartate aminotransferase (AST) were augmented at 1 week posttreatment and were similar at 1–3 months compared with baseline. The most common AEs were pain, fever, nausea, and vomiting, and no severe AEs were observed in this study. DEB-TACE was effective and tolerable in treating Chinese HCC patients, and portal vein invasion, previous cTACE treatment, abnormal BCr, ALB, and TBIL appear to be important factors that predict worse clinical outcome.

Background We aimed to investigate treatment response, survival profiles, safety profiles, and predictive factors of drug‐eluting beads‐transarterial chemoembolization (DEB‐TACE) with CalliSpheres® Microspheres (CSM) in treating Chinese hepatocellular carcinoma (HCC) patients. Methods A total of 66 HCC patients about to receive DEB‐TACE with CSM therapy were consecutively enrolled in this prospective cohort study. Treatment response was recorded. Besides, progression‐free survival (PFS) and overall survival (OS) were also recorded. All adverse events including pain, nausea, vomiting, fever, and liver function damage were recorded during hospitalization. Results 37.9% of patients achieved complete response (CR) and 81.8% of patients achieved an objective response rate (ORR). For survival, mean PFS and OS were 13.7 (11.7‐15.8) months and 18.8 (95% CI: 16.3‐21.2) months, respectively. Multivariate logistic regression analysis revealed that a number of nodules ≥2 was an independent factor for worse CR; moreover, multivariate Cox's regression analysis disclosed that largest sample size ≥5 cm was an independent factor for shorter PFS, and Child‐Pugh B and BCLC stage B/C were independent predictive factors for unfavorable OS. As to AEs, numbers of patients suffered liver function damage, pain, nausea, vomiting, and fever were 29 (43.9%), 27 (40.9%), 22 (33.3%), 13 (19.7%), and 37 (56.1%), respectively. Conclusion Drug‐eluting beads‐transarterial chemoembolization with CSM is an effective and tolerated treatment for Chinese HCC patients, and number of nodules ≥2, largest nodule size ≥5 cm, Child‐Pugh stage B, and BCLC stage B/C correlates with unfavorable prognosis.

This study aimed to investigate the efficacy and safety of drug-eluting beads (DEB) transarterial chemoembolization (TACE) treatment in Chinese intrahepatic cholangiocarcinoma (ICC) patients.37 ICC patients underwent DEB-TACE treatment in CTILC study (registered on clinicaltrials.gov with registry No. NCT03317483) were included in this present study. Treatment response was assessed according to modified Response Evaluation Criteria in Solid Tumors (mRECIST). Overall survival (OS) was calculated from the time of DEB-TACE operation until the date of death from any causes. Liver function change and adverse events (AEs) were recorded during and after DEB-TACE operation.3 (8.1%) patients achieved complete response (CR) and 22 (59.5%) patients achieved partial response (PR), with objective response rate (ORR) of 67.6%. After DEB-TACE treatment, mean OS was 376 days (95%CI: 341-412 days). Multivariate logistic regression analysis revealed that Bilobar disease (P = .040, OR: 0.105, 95% CI: 0.012-0.898) and portal vein invasion (P = .038, OR: 0.104, 95% CI: 0.012-0.881) could independently predict less possibility of ORR. Patients with ALB abnormal, TP abnormal, ALT abnormal and AST abnormal were increased at 1-week post DEB-TACE treatment (P = .034, P = .001, P .050). Besides, most of the AEs were mild including pain, fever, vomiting, and nausea in this study.DEB-TACE was effective and well tolerated in treating ICC patients, and bilobar disease as well as portal vein invasion were independently correlated with less probability of ORR achievement.

Rationale: Computed tomography (CT) and magnetic resonance imaging (MRI) are conventional used to evaluate liver tumors. Detection of fat component is considered an important clue to the imaging diagnosis of hepatic myxoid liposarcoma. However, the positron emission tomography (PET)/CT report of hepatic myxoid liposarcoma is scarce, and the metabolic characteristics of primary hepatic myxoid liposarcoma are still unknown. Patient Concerns: In this report, we report the PET/CT manifestations of a rare case of primary hepatic myxoid liposarcoma that was confirmed by pathologic examination. A 29-year-old male patient presented with a nodule adjacent to the umbilicus that had been present for 2 weeks. PET/CT showed a hypoattenuating mass with moderate uptake (maximum standardized uptake value [SUVmax] 1.9), except for a slightly hyperattenuating focal area with intense uptake (SUVmax 3.1). Diagnoses: The final pathologic diagnosis was confirmed, by means of laparotomy, to be a primary hepatic myxoid liposarcoma with multiple extrahepatic metastases. Interventions: The lesions in the left liver and periumbilical abdominal wall were punctured. During the laparotomy, hepatic malignant tumors were confirmed and metastasized widely in the abdominal cavity. Outcomes: An abdominal CT performed 4 months after initial presentation showed extensive metastasis. Lessons: Primary hepatic myxoid liposarcoma may manifest as moderate metabolism with less fat on PET/CT. PET/CT is not only valuable in reflecting the round cell component of hepatic myxoid liposarcoma, but also in estimating its origin.

Purpose: Efficient and accurate 3D liver segmentations from contrast-enhanced computed tomography (CT) images play an important role in therapeutic strategies for hepatic diseases. However, inhomogeneous appearances, ambiguous boundaries, and large variance in shape often make it a challenging task. The existence of liver abnormalities poses further difficulty. Despite the significant intensity difference, liver tumors should be segmented as part of the liver. This study aims to address these challenges, especially when the target livers contain subregions with distinct appearances. Methods: The authors propose a novel multiregion-appearance based approach with graph cuts to delineate the liver surface. For livers with multiple subregions, a geodesic distance based appearance selection scheme is introduced to utilize proper appearance constraint for each subregion. A special case of the proposed method, which uses only one appearance constraint to segment the liver, is also presented. The segmentation process is modeled with energy functions incorporating both boundary and region information. Rather than a simple fixed combination, an adaptive balancing weight is introduced and learned from training sets. The proposed method only calls initialization inside the liver surface. No additional constraints from user interaction are utilized. Results: The proposed method was validated on 50 3D CT images from threemore » datasets, i.e., Medical Image Computing and Computer Assisted Intervention (MICCAI) training and testing set, and local dataset. On MICCAI testing set, the proposed method achieved a total score of 83.4 ± 3.1, outperforming nonexpert manual segmentation (average score of 75.0). When applying their method to MICCAI training set and local dataset, it yielded a mean Dice similarity coefficient (DSC) of 97.7% ± 0.5% and 97.5% ± 0.4%, respectively. These results demonstrated the accuracy of the method when applied to different computed tomography (CT) datasets. In addition, user operator variability experiments showed its good reproducibility. Conclusions: A multiregion-appearance based method is proposed and evaluated to segment liver. This approach does not require prior model construction and so eliminates the burdens associated with model construction and matching. The proposed method provides comparable results with state-of-the-art methods. Validation results suggest that it may be suitable for the clinical use.« less

Segmentation of the liver from abdominal computed tomography (CT) images is an essential step in some computer-assisted clinical interventions, such as surgery planning for living donor liver transplant, radiotherapy and volume measurement. In this work, we develop a deep learning algorithm with graph cut refinement to automatically segment the liver in CT scans. The proposed method consists of two main steps: (i) simultaneously liver detection and probabilistic segmentation using 3D convolutional neural network; (ii) accuracy refinement of the initial segmentation with graph cut and the previously learned probability map. The proposed approach was validated on forty CT volumes taken from two public databases MICCAI-Sliver07 and 3Dircadb1. For the MICCAI-Sliver07 test dataset, the calculated mean ratios of volumetric overlap error (VOE), relative volume difference (RVD), average symmetric surface distance (ASD), root-mean-square symmetric surface distance (RMSD) and maximum symmetric surface distance (MSD) are 5.9, 2.7 %, 0.91, 1.88 and 18.94 mm, respectively. For the 3Dircadb1 dataset, the calculated mean ratios of VOE, RVD, ASD, RMSD and MSD are 9.36, 0.97 %, 1.89, 4.15 and 33.14 mm, respectively. The proposed method is fully automatic without any user interaction. Quantitative results reveal that the proposed approach is efficient and accurate for hepatic volume estimation in a clinical setup. The high correlation between the automatic and manual references shows that the proposed method can be good enough to replace the time-consuming and nonreproducible manual segmentation method.

Efficient and accurate 3D liver segmentations from contrast-enhanced computed tomography (CT) images play an important role in therapeutic strategies for hepatic diseases. However, inhomogeneous appearances, ambiguous boundaries, and large variance in shape often make it a challenging task. The existence of liver abnormalities poses further difficulty. Despite the significant intensity difference, liver tumors should be segmented as part of the liver. This study aims to address these challenges, especially when the target livers contain subregions with distinct appearances.The authors propose a novel multiregion-appearance based approach with graph cuts to delineate the liver surface. For livers with multiple subregions, a geodesic distance based appearance selection scheme is introduced to utilize proper appearance constraint for each subregion. A special case of the proposed method, which uses only one appearance constraint to segment the liver, is also presented. The segmentation process is modeled with energy functions incorporating both boundary and region information. Rather than a simple fixed combination, an adaptive balancing weight is introduced and learned from training sets. The proposed method only calls initialization inside the liver surface. No additional constraints from user interaction are utilized.The proposed method was validated on 50 3D CT images from three datasets, i.e., Medical Image Computing and Computer Assisted Intervention (MICCAI) training and testing set, and local dataset. On MICCAI testing set, the proposed method achieved a total score of 83.4 ± 3.1, outperforming nonexpert manual segmentation (average score of 75.0). When applying their method to MICCAI training set and local dataset, it yielded a mean Dice similarity coefficient (DSC) of 97.7% ± 0.5% and 97.5% ± 0.4%, respectively. These results demonstrated the accuracy of the method when applied to different computed tomography (CT) datasets. In addition, user operator variability experiments showed its good reproducibility.A multiregion-appearance based method is proposed and evaluated to segment liver. This approach does not require prior model construction and so eliminates the burdens associated with model construction and matching. The proposed method provides comparable results with state-of-the-art methods. Validation results suggest that it may be suitable for the clinical use.

Background Ischemic stroke and glioblastoma multiforme have similar features on anatomic magnetic resonance imaging (MRI) and thus may require a surgical biopsy for a definitive diagnosis. Case presentation A 55-year-old male complained of dysphasia for 4 weeks and continuous deterioration for 5 days. Cerebral infarction was considered based on MRI, which showed hyperintensity at the border zone of the left hemisphere, and computed tomography angiography (CTA) showed left carotid artery severe stenosis. The patient underwent placement of a left carotid artery stent, and his symptoms recurred 2 months after carotid artery stent (CAS). MRI showed multiple ring-enhanced lesions in the left temporal, parietal, and occipital lobes accompanied by massive brain edema. The final pathologic diagnosis was glioblastoma multiforme. Conclusion Although there is no evidence that stent therapy for carotid artery stenosis will worsen an ipsilateral glioblastoma, we should be careful to perform surgeries involving carotid artery stents when the patient has a glioblastoma.

The segmentation of liver, especially the abnormal liver with tumors, is a challenging task. Due to the presence of tumor and intensity inhomogeneity in CT scans, the liver consists of multiple sub-regions with distinct appearances. Moreover, the liver and the tumor share the similar intensity and ambiguous boundaries with neighboring structures/organs, which make the separating surfaces ambiguous. Under the framework of active contour, we construct a joint model of delineating the whole liver with a single level set representation. The final result and computational efficiency is improved compared to segmenting the parts independently. The level set evolution on the multiple regions is guided to the desired boundary by a novel geodesic selection scheme. As a result, in each sub-region the most relevant appearance and boundary knowledge are automatically used. Besides, a weighted histogram for the local appearance description is introduced for the precise boundary detection. A quantitative and comparative performance assessment is carried out over a publicly available benchmark with competitive results.