Segmentation of Portal Vein in Multiphase CTA Image Based on Unsupervised Domain Transfer and Pseudo Label.

BACKGROUND: Clinically, physicians diagnose portal vein diseases on abdominal CT angiography (CTA) images scanned in the hepatic arterial phase (H-phase), portal vein phase (P-phase) and equilibrium phase (E-phase) simultaneously. However, existing studies typically segment the portal vein on P-phase images without considering other phase images. METHOD: We propose a method for segmenting portal veins on multiphase images based on unsupervised domain transfer and pseudo labels by using annotated P-phase images. Firstly, unsupervised domain transfer is performed to make the H-phase and E-phase images of the same patient approach the P-phase image in style, reducing the image differences caused by contrast media. Secondly, the H-phase (or E-phase) image and its style transferred image are input into the segmentation module together with the P-phase image. Under the constraints of pseudo labels, accurate prediction results are obtained. RESULTS: This method was evaluated on the multiphase CTA images of 169 patients. The portal vein segmented from the H-phase and E-phase images achieved DSC values of 0.76 and 0.86 and Jaccard values of 0.61 and 0.76, respectively. CONCLUSION: The method can automatically segment the portal vein on H-phase and E-phase images when only the portal vein on the P-phase CTA image is annotated, which greatly assists in clinical diagnosis.

Segmentation of multi-regional skeletal muscle in abdominal CT image for cirrhotic sarcopenia diagnosis.

Background: Sarcopenia is generally diagnosed by the total area of skeletal muscle in the CT axial slice located in the third lumbar (L3) vertebra. However, patients with severe liver cirrhosis cannot accurately obtain the corresponding total skeletal muscle because their abdominal muscles are squeezed, which affects the diagnosis of sarcopenia. Purpose: This study proposes a novel lumbar skeletal muscle network to automatically segment multi-regional skeletal muscle from CT images, and explores the relationship between cirrhotic sarcopenia and each skeletal muscle region. Methods: This study utilizes the skeletal muscle characteristics of different spatial regions to improve the 2.5D U-Net enhanced by residual structure. Specifically, a 3D texture attention enhancement block is proposed to tackle the issue of blurred edges with similar intensities and poor segmentation between different skeletal muscle regions, which contains skeletal muscle shape and muscle fibre texture to spatially constrain the integrity of skeletal muscle region and alleviate the difficulty of identifying muscle boundaries in axial slices. Subsequentially, a 3D encoding branch is constructed in conjunction with a 2.5D U-Net, which segments the lumbar skeletal muscle in multiple L3-related axial CT slices into four regions. Furthermore, the diagnostic cut-off values of the L3 skeletal muscle index (L3SMI) are investigated for identifying cirrhotic sarcopenia in four muscle regions segmented from CT images of 98 patients with liver cirrhosis. Results: Our method is evaluated on 317 CT images using the five-fold cross-validation method. For the four skeletal muscle regions segmented in the images from the independent test set, the avg. DSC is 0.937 and the avg. surface distance is 0.558 mm. For sarcopenia diagnosis in 98 patients with liver cirrhosis, the cut-off values of Rectus Abdominis, Right Psoas, Left Psoas, and Paravertebral are 16.67, 4.14, 3.76, and 13.20 cm2/m2 in females, and 22.51, 5.84, 6.10, and 17.28 cm2/m2 in males, respectively. Conclusion: The proposed method can segment four skeletal muscle regions related to the L3 vertebra with high accuracy. Furthermore, the analysis shows that the Rectus Abdominis region can be used to assist in the diagnosis of sarcopenia when the total muscle is not available.

HDAC6-G3BP2 promotes lysosomal-TSC2 and suppresses mTORC1 under ETV4 targeting-induced low-lactate stress in non-small cell lung cancer.

TSC-mTORC1 inhibition-mediated translational reprogramming is a major adaptation mechanism upon many stresses, such as low-oxygen, -ATP, and -amino acids. But how cancer cells hijack the adaptive pathway to survive under low-lactate stress when targeting glycolysis-related signaling remains uncertain. ETV4 is an oncogenic transcription factor frequently dysregulated in human cancer. We previously found that ETV4 is associated with tumor progression and poor prognosis in non-small cell lung cancer (NSCLC). In this study, we report that ETV4 controls HK1 expression and glycolysis-lactate production to activate mTORC1 by relieving TSC2 repression of Rheb in NSCLC cells. Targeting ETV4-induced low-lactate stress is an important input for TSC2 to inhibit mTORC1 and global protein synthesis, while the core stress granule components G3BP2 and HDAC6 are selectively translated. Mechanistically, G3BP2 recruits lysosomal-TSC2 to suppress mTORC1. HDAC6 deacetylates TSC2 to sustain protein stability and associates with G3BP2 to facilitate more recruiting of TSC2 to inactivate mTORC1. In addition, the microtubule retrograde transport activity of HDAC6 drives the aggregate-like perinuclear-mTOR distribution paralleled by lower mTORC1 activity under stress. Thus, HDAC6-G3BP2 is the key complex that promotes lysosomal-TSC2 and suppresses mTORC1 when targeting ETV4, which might represent a critical adaptive mechanism for cell survival under low-lactate challenges.

Limb expression 1-like protein promotes epithelial-mesenchymal transition and epidermal growth factor receptor-tyrosine kinase inhibitor resistance via nucleolin-mediated ribosomal RNA synthesis in non-small cell lung cancer.

Limb expression 1-like protein (LIX1L) might be an RNA-binding protein involved in post-transcriptional regulation. However, little is known regarding the biological function and mechanism of LIX1L in cancer cells. Here we demonstrate a clear correlation between LIX1L expression and epithelial-mesenchymal transition (EMT) markers in 81 non-small cell lung cancer (NSCLC) tissues and The Cancer Genome Atlas database, suggesting that LIX1L is a mesenchymal marker. Besides, LIX1L expression is obviously elevated in TGFß1-induced EMT NSCLC cells and enhances cell migration, invasion, anoikis resistance, epidermal growth factor receptor-tyrosine kinase inhibitor (EGFR-TKI) resistance, and proliferation. Interestingly, the increased LIX1L expression prominently localizes to the nucleoli, where it physically interacts with the key ribosome biogenesis regulator NCL protein, inducing ribosomal RNA (rRNA) synthesis in EMT NSCLC cells. NCL knockdown or inhibition of rRNA synthesis reverses the enhanced EMT functions and proliferation ability caused by LIX1L overexpression in NSCLC cells, indicating that NCL expression and rRNA synthesis participates in LIX1L-mediated biological functions during EMT. Collectively, our findings suggest that the LIX1L-NCL-rRNA synthesis axis is a novel EMT-activated mechanism. Targeting the pathway might be a therapeutic option for EMT and EGFR-TKI resistance in NSCLC.

Fusion of multimodality image and point cloud for spatial surface registration for knee arthroplasty.

BACKGROUND: Image-guided computer-aided navigation system is an indispensable part of computer assisted orthopaedic surgery. However, the location and number of fiducial markers, the time required to localise fiducial markers in existing systems affect their effectiveness. METHOD: The study proposed that spatial surface registration between the point cloud on the surface of the fusion model based on preoperative knee MRI and CT images and the point cloud on the cartilage surface captured by intraoperative laser scanner could solve the above limitations. RESULTS: The experimental results show that the registration error of the method is less than 2 mm, but the total time from scanning the point cloud on patient's cartilage surface to registering it with the point cloud in preoperative image space is less than 2 min. CONCLUSION: The method achieves the registration accuracy similar to existing methods without selecting anatomical corresponding points, which is of great help to the clinic.

Vertebrae Labeling via End-to-End Integral Regression Localization and Multi-Label Classification Network.

Accurate identification and localization of the vertebrae in CT scans is a critical and standard pre-processing step for clinical spinal diagnosis and treatment. Existing methods are mainly based on the integration of multiple neural networks, and most of them use heatmaps to locate the vertebrae's centroid. However, the process of obtaining vertebrae's centroid coordinates using heatmaps is non-differentiable, so it is impossible to train the network to label the vertebrae directly. Therefore, for end-to-end differential training of vertebrae coordinates on CT scans, a robust and accurate automatic vertebral labeling algorithm is proposed in this study. First, a novel end-to-end integral regression localization and multi-label classification network is developed, which can capture multi-scale features and also utilize the residual module and skip connection to fuse the multi-level features. Second, to solve the problem that the process of finding coordinates is non-differentiable and the spatial structure of location being destroyed, an integral regression module is used in the localization network. It combines the advantages of heatmaps representation and direct regression coordinates to achieve end-to-end training and can be compatible with any key point detection methods of medical images based on heatmaps. Finally, multi-label classification of vertebrae is carried out to improve the identification rate, which uses bidirectional long short-term memory (Bi-LSTM) online to enhance the learning of long contextual information of vertebrae. The proposed method is evaluated on a challenging data set, and the results are significantly better than state-of-the-art methods (identification rate is 91.1% and the mean localization error is 2.2 mm). The method is evaluated on a new CT data set, and the results show that our method has good generalization.

Formation of α-helical and ß-sheet structures in membrane-bound human IAPP monomer and the resulting membrane deformation.

The amyloid formation of human islet amyloid polypeptide (hIAPP)-an intrinsically disordered peptide, is associated with type II diabetes. Cellular membranes, especially those composed of negatively-charged lipids, accelerate the hIAPP amyloid fibrillation, and their integrity is disrupted during the aggregation process, leading to cell apoptosis. However, the underlying molecular mechanism is not well understood. Herein, we investigated the conformational dynamics during the interactions of hIAPP monomer with POPG membrane bilayer, by carrying out µs-long all-atom molecular dynamics simulations. Starting from the metastable coiled conformations in water, hIAPP monomers tend to adopt transient α-helical and ß-sheet structures when adsorbing to the membrane surface. The amphiphilic N-terminal region further inserts into the membrane interior and is located at the lipid head-tail interface, mainly in turn and α-helical structures. In contrast, the ß-hairpin structures reside on the membrane surface without insertion, and expand laterally with the hydrophobic residues exposed to the solvent. Moreover, the adsorption and insertion of hIAPP monomers induce two distinct local membrane deformations: (1) the hIAPP adsorption on the membrane surface mainly causes membrane bending; (2) the insertion of both turns and α-helices synchronizes with the formation of hydrophobic defects on the POPG membrane, leading to stronger membrane stretching and a longer coherence length of membrane thinning. Based on the structural and dynamical results, we propose that ß-hairpin structures may be a precursor for the fibrillation on the membrane surface due to the flat geometry and hydrophobic regions exposed to solvent, while N-terminal amphiphilic α-helices would facilitate hIAPP assembling into toxic oligomers inside the membrane.

Computer-aided detection in chest radiography based on artificial intelligence: a survey.

As the most common examination tool in medical practice, chest radiography has important clinical value in the diagnosis of disease. Thus, the automatic detection of chest disease based on chest radiography has become one of the hot topics in medical imaging research. Based on the clinical applications, the study conducts a comprehensive survey on computer-aided detection (CAD) systems, and especially focuses on the artificial intelligence technology applied in chest radiography. The paper presents several common chest X-ray datasets and briefly introduces general image preprocessing procedures, such as contrast enhancement and segmentation, and bone suppression techniques that are applied to chest radiography. Then, the CAD system in the detection of specific disease (pulmonary nodules, tuberculosis, and interstitial lung diseases) and multiple diseases is described, focusing on the basic principles of the algorithm, the data used in the study, the evaluation measures, and the results. Finally, the paper summarizes the CAD system in chest radiography based on artificial intelligence and discusses the existing problems and trends.

Multimodal image registration based on binary gradient angle descriptor.

PURPOSE: Multimodal image registration plays an important role in image-guided interventions/therapy and atlas building, and it is still a challenging task due to the complex intensity variations in different modalities. METHODS: The paper addresses the problem and proposes a simple, compact, fast and generally applicable modality-independent binary gradient angle descriptor (BGA) based on the rationale of gradient orientation alignment. The BGA can be easily calculated at each voxel by coding the quadrant in which a local gradient vector falls, and it has an extremely low computational complexity, requiring only three convolutions, two multiplication operations and two comparison operations. Meanwhile, the binarized encoding of the gradient orientation makes the BGA more resistant to image degradations compared with conventional gradient orientation methods. The BGA can extract similar feature descriptors for different modalities and enable the use of simple similarity measures, which makes it applicable within a wide range of optimization frameworks. RESULTS: The results for pairwise multimodal and monomodal registrations between various images (T1, T2, PD, T1c, Flair) consistently show that the BGA significantly outperforms localized mutual information. The experimental results also confirm that the BGA can be a reliable alternative to the sum of absolute difference in monomodal image registration. The BGA can also achieve an accuracy of [Formula: see text], similar to that of the SSC, for the deformable registration of inhale and exhale CT scans. Specifically, for the highly challenging deformable registration of preoperative MRI and 3D intraoperative ultrasound images, the BGA achieves a similar registration accuracy of [Formula: see text] compared with state-of-the-art approaches, with a computation time of 18.3 s per case. CONCLUSIONS: The BGA improves the registration performance in terms of both accuracy and time efficiency. With further acceleration, the framework has the potential for application in time-sensitive clinical environments, such as for preoperative MRI and intraoperative US image registration for image-guided intervention.

Trellis-based feed-forward carrier recovery for coherent optical systems.

An efficient trellis-based phase noise mitigation algorithm is proposed to highly improve the performance of coherent transmission systems, especially in high order modulation formats. The proposed method targets the coherent optical systems where the performance is limited by various sources of phase noise including laser line-width, fiber non-linearity, and phase noise induced by phase-locked loop. Considering hardware limitations of ultra-high data rate processing in optical systems, a hardware-efficient parallelized and pipelined architecture is utilized. Experimental results in 200 Gb/s DP-16QAM co-propagated with 10-G channels demonstrate significant performance improvement over other existing methods.

miLBP: a robust and fast modality-independent 3D LBP for multimodal deformable registration.

PURPOSE: Computer-assisted intervention often depends on multimodal deformable registration to provide complementary information. However, multimodal deformable registration remains a challenging task. METHODS: This paper introduces a novel robust and fast modality-independent 3D binary descriptor, called miLBP, which integrates the principle of local self-similarity with a form of local binary pattern and can robustly extract the similar geometry features from 3D volumes across different modalities. miLBP is a bit string that can be computed by simply thresholding the voxel distance. Furthermore, the descriptor similarity can be evaluated efficiently using the Hamming distance. RESULTS: miLBP was compared to vector-valued self-similarity context (SSC) in artificial image and clinical settings. The results show that miLBP is more robust than SSC in extracting local geometry features across modalities and achieved higher registration accuracy in different registration scenarios. Furthermore, in the most challenging registration between preoperative magnetic resonance imaging and intra-operative ultrasound images, our approach significantly outperforms the state-of-the-art methods in terms of both accuracy ([Formula: see text]) and speed (29.2 s for one case). CONCLUSIONS: Registration performance and speed indicate that miLBP has the potential of being applied to the time-sensitive intra-operative computer-assisted intervention.

Alteration of the Intra- and Cross- Hemisphere Posterior Default Mode Network in Frontal Lobe Glioma Patients.

Patients with frontal lobe gliomas often experience neurocognitive dysfunctions before surgery, which affects the default mode network (DMN) to different degrees. This study quantitatively analyzed this effect from the perspective of cerebral hemispheric functional connectivity (FC). We collected resting-state fMRI data from 20 frontal lobe glioma patients before treatment and 20 healthy controls. All of the patients and controls were right-handed. After pre-processing the images, FC maps were built from the seed defined in the left or right posterior cingulate cortex (PCC) to the target regions determined in the left or right temporal-parietal junction (TPJ), respectively. The intra- and cross-group statistical calculations of FC strength were compared. The conclusions were as follows: (1) the intra-hemisphere FC strength values between the PCC and TPJ on the left and right were decreased in patients compared with controls; and (2) the correlation coefficients between the FC pairs in the patients were increased compared with the corresponding controls. When all of the patients were grouped by their tumor's hemispheric location, (3) the FC of the subgroups showed that the dominant hemisphere was vulnerable to glioma, and (4) the FC in the dominant hemisphere showed a significant correlation with WHO grade.

[Research of the key technique in virtual endoscopy and its clinical application].

Studying the critical technique of virtual endoscopy (VE), we developed a VE system for clinical application. Computerized tomograph (CT) VE images built by the VE system were compared to those by fiberscopy and pathology. The results showed that the VE system could satisfy the demand of clinical application. The technique being applied to VE system is feasible.