A Boundary-Enhanced Liver Segmentation Network for Multi-Phase CT Images with Unsupervised Domain Adaptation.

Multi-phase computed tomography (CT) images have gained significant popularity in the diagnosis of hepatic disease. There are several challenges in the liver segmentation of multi-phase CT images. (1) Annotation: due to the distinct contrast enhancements observed in different phases (i.e., each phase is considered a different domain), annotating all phase images in multi-phase CT images for liver or tumor segmentation is a task that consumes substantial time and labor resources. (2) Poor contrast: some phase images may have poor contrast, making it difficult to distinguish the liver boundary. In this paper, we propose a boundary-enhanced liver segmentation network for multi-phase CT images with unsupervised domain adaptation. The first contribution is that we propose DD-UDA, a dual discriminator-based unsupervised domain adaptation, for liver segmentation on multi-phase images without multi-phase annotations, effectively tackling the annotation problem. To improve accuracy by reducing distribution differences between the source and target domains, we perform domain adaptation at two levels by employing two discriminators, one at the feature level and the other at the output level. The second contribution is that we introduce an additional boundary-enhanced decoder to the encoder-decoder backbone segmentation network to effectively recognize the boundary region, thereby addressing the problem of poor contrast. In our study, we employ the public LiTS dataset as the source domain and our private MPCT-FLLs dataset as the target domain. The experimental findings validate the efficacy of our proposed methods, producing substantially improved results when tested on each phase of the multi-phase CT image even without the multi-phase annotations. As evaluated on the MPCT-FLLs dataset, the existing baseline (UDA) method achieved IoU scores of 0.785, 0.796, and 0.772 for the PV, ART, and NC phases, respectively, while our proposed approach exhibited superior performance, surpassing both the baseline and other state-of-the-art methods. Notably, our method achieved remarkable IoU scores of 0.823, 0.811, and 0.800 for the PV, ART, and NC phases, respectively, emphasizing its effectiveness in achieving accurate image segmentation.

MTL-ABS3Net: Atlas-Based Semi-Supervised Organ Segmentation Network With Multi-Task Learning for Medical Images.

Organ segmentation is one of the most important step for various medical image analysis tasks. Recently, semi-supervised learning (SSL) has attracted much attentions by reducing labeling cost. However, most of the existing SSLs neglected the prior shape and position information specialized in the medical images, leading to unsatisfactory localization and non-smooth of objects. In this paper, we propose a novel atlas-based semi-supervised segmentation network with multi-task learning for medical organs, named MTL-ABS3Net, which incorporates the anatomical priors and makes full use of unlabeled data in a self-training and multi-task learning manner. The MTL-ABS3Net consists of two components: an Atlas-Based Semi-Supervised Segmentation Network (ABS3Net) and Reconstruction-Assisted Module (RAM). Specifically, the ABS3Net improves the existing SSLs by utilizing atlas prior, which generates credible pseudo labels in a self-training manner; while the RAM further assists the segmentation network by capturing the anatomical structures from the original images in a multi-task learning manner. Better reconstruction quality is achieved by using MS-SSIM loss function, which further improves the segmentation accuracy. Experimental results from the liver and spleen datasets demonstrated that the performance of our method was significantly improved compared to existing state-of-the-art methods.

An Efficient and Accurate 3D Multiple-Contextual Semantic Segmentation Network for Medical Volumetric Images.

Convolutional neural networks have become popular in medical image segmentation, and one of their most notable achievements is their ability to learn discriminative features using large labeled datasets. Two-dimensional (2D) networks are accustomed to extracting multiscale features with deep convolutional neural network extractors, i.e., ResNet-101. However, 2D networks are inefficient in extracting spatial features from volumetric images. Although most of the 2D segmentation networks can be extended to three-dimensional (3D) networks, extended 3D methods are resource and time intensive. In this paper, we propose an efficient and accurate network for fully automatic 3D segmentation. We designed a 3D multiple-contextual extractor (MCE) to simulate multiscale feature extraction and feature fusion to capture rich global contextual dependencies from different feature levels. We also designed a light 3D ResU-Net for efficient volumetric image segmentation. The proposed multiple-contextual extractor and light 3D ResU-Net constituted a complete segmentation network. By feeding the multiple-contextual features to the light 3D ResU-Net, we realized 3D medical image segmentation with high efficiency and accuracy. To validate the 3D segmentation performance of our proposed method, we evaluated the proposed network in the context of semantic segmentation on a private spleen dataset and public liver dataset. The spleen dataset contains 50 patients' CT scans, and the liver dataset contains 131 patients' CT scans.

Acute Mesenteric Ischemia: Multidetector CT Findings and Endovascular Management.

Acute mesenteric ischemia is a rare life-threatening condition that accounts for approximately one in 1000 hospital admissions. The mortality rate is 50%-69% owing to the absence of specific symptoms and laboratory data, which makes early detection of this condition difficult. If the use of contrast material is possible, biphasic contrast material-enhanced multidetector computed tomography (CT) is the first-line imaging test for early diagnosis of the disease and for differentiation from other causes of acute abdomen. Multidetector CT can depict mesenteric ischemia, its underlying causes, and its severity. Mesenteric ischemia is classified as either acute or chronic. The causes of AMI include arterial embolism, arterial thrombosis, venous thrombosis, and nonocclusive mesenteric ischemia, among which arterial causes are far more common than venous causes. Recently, endovascular procedures such as thrombolysis, thrombectomy, thrombus fragmentation, and stent placement have been successfully and safely performed when the ischemia is reversible. Online DICOM image stacks are available for this article. ©RSNA, 2018.

Imaging findings of primary hepatic carcinoid tumor with an emphasis on MR imaging: case study.

Carcinoid tumors are slow-growing tumors originating in the neuroendocrine cells, and occur most frequently within the gastrointestinal tract. Although the liver is the most common site for metastatic carcinoid tumors, primary hepatic carcinoid tumors are exceedingly rare and reports of the imaging findings have been very scarce. We herein report imaging findings with an emphasis on magnetic resonance imaging in two cases of primary hepatic carcinoid tumors. In both cases, the tumors showed cystic areas with hemorrhagic components and early enhanced solid areas.

Computer-aided diagnosis and quantification of cirrhotic livers based on morphological analysis and machine learning.

It is widely known that morphological changes of the liver and the spleen occur during the clinical course of chronic liver diseases. In this paper, we proposed a morphological analysis method based on statistical shape models (SSMs) of the liver and spleen for computer-aided diagnosis and quantification of the chronic liver. We constructed not only the liver SSM but also the spleen SSM and a joint SSM of the liver and the spleen for a morphologic analysis of the cirrhotic liver in CT images. The effective modes are selected based on both its accumulation contribution rate and its correlation with doctor's opinions (stage labels). We then learn a mapping function between the selected mode and the stage of chronic liver. The mapping function was used for diagnosis and staging of chronic liver diseases.

Assessment of small bowel motility function with cine-MRI using balanced steady-state free precession sequence.

PURPOSE: To evaluate the use of cine-magnetic resonance imaging (MRI) with a steady-state free precession sequence to monitor and assess small bowel motility. MATERIALS AND METHODS: Sequential MRI, using a balanced steady-state free precession sequence, was performed in eight healthy male volunteers at 0, 15, 30, 45, and 60 minutes after oral administration of 1500 mL of nonabsorbable fluid to monitor small bowel contractions. Using the cine-mode display, small bowel contractions were reviewed and the luminal diameter was measured on each image to obtain frequency and amplitude of bowel contractions. RESULTS: The oral preparation was well tolerated without major complications. Cine-MRI provided high temporal, spatial, and contrast resolution for monitoring bowel contractions. Mean values with standard deviations of frequency and amplitude of bowel contractions were 6.0 ± 2.98/min and 10.4 ± 4.53 mm, respectively, and were 5.1 ± 3.38/min and 9.59 ± 5.57 mm at the jejunal loops and 6.9 ± 2.22/min and 11.2 ± 3.06 mm at the ileal loops. With the passage of luminal fluid, frequency of bowel contractions decreased and the bowels tended to pause their contractions. CONCLUSION: Cine-MRI provides sufficient dynamic images to observe small bowel contractions. Measurement of bowel caliber permits calculation of amplitude and frequency of the contractions for characterization and quantitative assessment of small bowel motility function.

Basic investigation of vascular interventional radiology (IR) using large rabbits.

The purpose of this study was to determine the usefulness of large rabbits for basic vascular interventional radiology (IR) experiments. We used 5 Akita large rabbits (Akita) and 5 Japanese white rabbits (JW). We conducted measurements of vessel diameters such as the aorta, and the iliac, renal, superior mesenteric, celiac, and proper hepatic arteries, and of the growth rates of VX2 liver tumors. There were significant differences between Akita and JW in the diameters of the thoracic aorta, lower abdominal aorta, and celiac artery. In other blood vessels, no significant differences were found. There was no difference in the growth rates of the VX2 tumors between Akita and JW. The possibility that Akita large rabbits could be utilized for vascular IR was demonstrated.

[A case of idiopathic omental bleeding treated successfully with transarterial embolization].

A 58-year-old man was brought to our hospital with left upper abdominal pain which suddenly appeared on the previous evening. An abdominal CT scan showed localized retention of ascites, a slightly high density mass under the left upper abdominal wall, with a high density area detected within the mass, which was suggestive of leakage of contrast medium from peripheral branches of the omental artery. From these findings intraperitoneal hemorrhage caused by bleeding from the greater omentum was suspected. Angiographic examination of the abdomen indicated extravasation of contrast medium from blood vessels of the right gastroepiploic artery. Transarterial embolization was carried out and permanent hemostasis was achieved. Injury, anticoagulant, neoplasms, varix, torsion of the omentum, and segmental arterial mediolysis (SAM) etc have been reported as causes of omental bleeding, but none of these were found in our case. We diagnosed the present case as idiopathic omental bleeding.

CT diagnosis of acute mesenteric ischemia from various causes.

OBJECTIVE: Acute mesenteric ischemia can be caused by various conditions such as arterial occlusion, venous occlusion, strangulating obstruction, and hypoperfusion associated with nonocclusive vascular disease, and the CT findings vary widely depending on the cause and underlying pathophysiology. The aim of this article is to review the CT appearances of acute mesenteric ischemia in various conditions. CONCLUSION: Recognition of characteristic CT appearances and the variations associated with each cause may help in the accurate interpretation of CT in the diagnosis of mesenteric ischemia.

CT diagnosis of small bowel obstruction: scanning technique, interpretation and role in the diagnosis.

Intestinal obstruction is a relatively common condition with diagnosis based on the clinical signs, patient history, and radiographical findings. Once suspected, its presence should be determined and if present, the site and cause of obstruction, and presence of strangulation should be assessed for the appropriate patient management. With the recent technological developments, the role of computed tomography (CT) in the diagnosis of bowel obstruction has expanded. The examination should be performed with intravenous contrast administration and thinner sections and multi-planner image reformation are recommended to evaluate a site of particular interest. CT is reported to have a sensitivity refer to detection of a small bowel obstruction at over 90% for complete or high-grade obstruction and to disclose causes of obstruction in 70% to 95% of cases. CT also provides characteristic findings indicating the presence of closed-loop obstruction and intestinal ischemia, which leads to appropriate and timely management for these emergent cases.