AutoFibroNet: A deep learning and multi-photon microscopy-derived automated network for liver fibrosis quantification in MAFLD.

BACKGROUND: Liver fibrosis is the strongest histological risk factor for liver-related complications and mortality in metabolic dysfunction-associated fatty liver disease (MAFLD). Second harmonic generation/two-photon excitation fluorescence (SHG/TPEF) is a powerful tool for label-free two-dimensional and three-dimensional tissue visualisation that shows promise in liver fibrosis assessment. AIM: To investigate combining multi-photon microscopy (MPM) and deep learning techniques to develop and validate a new automated quantitative histological classification tool, named AutoFibroNet (Automated Liver Fibrosis Grading Network), for accurately staging liver fibrosis in MAFLD. METHODS: AutoFibroNet was developed in a training cohort that consisted of 203 Chinese adults with biopsy-confirmed MAFLD. Three deep learning models (VGG16, ResNet34, and MobileNet V3) were used to train pre-processed images and test data sets. Multi-layer perceptrons were used to fuse data (deep learning features, clinical features, and manual features) to build a joint model. This model was then validated in two further independent cohorts. RESULTS: AutoFibroNet showed good discrimination in the training set. For F0, F1, F2 and F3-4 fibrosis stages, the area under the receiver operating characteristic curves (AUROC) of AutoFibroNet were 1.00, 0.99, 0.98 and 0.98. The AUROCs of F0, F1, F2 and F3-4 fibrosis stages for AutoFibroNet in the two validation cohorts were 0.99, 0.83, 0.80 and 0.90 and 1.00, 0.83, 0.80 and 0.94, respectively, showing a good discriminatory ability in different cohorts. CONCLUSION: AutoFibroNet is an automated quantitative tool that accurately identifies histological stages of liver fibrosis in Chinese individuals with MAFLD.

The dysregulation of plasma miR-497/FGF23 axis, and its association with clinical characteristics and major adverse cardiovascular event in female premature acute coronary syndrome patients.

AIM: MicroRNA-497 (miR-497) directly targets fibroblast growth factor 23 (FGF23) to participate in the pathology of acute coronary syndrome (ACS) by regulating atherosclerosis, inflammatory response, lipid metabolism, etc. This study intended to investigate the dysregulation of the miR-497/FGF23 axis, and its association with the major adverse cardiovascular event (MACE) in female premature ACS. METHODS: MiR-497 and FGF23 from plasma samples were detected by RT-qPCR and ELISA in 979 newly diagnosed female premature ACS patients and 100 healthy controls (HCs). MACE was recorded during follow-up (median: 27.0, range: 1.0-54.0 months) in female premature ACS patients. RESULTS: MiR-497/FGF23 axis was reduced in female premature ACS patients versus HCs [median (interquartile range): 0.7 (0.1-1.2) versus 1.9 (1.1-3.4)] (P < 0.001). Meanwhile, miR-497 negatively correlated with FGF23 in femal e premature ACS patients (P < 0.001), but not in HCs (P = 0.157). In female premature ACS patients, the miR-497/FGF23 axis was negatively associated with serum creatinine (P < 0.001), serum uric acid (P = 0.003), high-sensitivity C-reactive protein (P < 0.001), total cholesterol (P = 0.031), and low-density lipoprotein cholesterol (P = 0.003). The 1-year, 2-year, 3-year, and 4-year accumulating MACE rate was 2.9%, 8.6%, 16.7%, and 26.0%, respectively. Interestingly, a high level of miR-497/FGF23 axis predicted decreased accumulating MACE risk (P < 0.001). After adjustment by multivariate Cox's regression analysis, the high miR-497/FGF23 axis (hazard ratio (HR) = 0.005, P = 0.001) independently correlated with reduced accumulating MACE risk. CONCLUSION: The plasma miR-497/FGF23 axis represents favorable kidney function, decreased inflammation, and reduced lipid level; meanwhile, this axis possesses prognostic value in predicting decreased accumulating MACE risk in female premature ACS patients.

FECC-Net: A Novel Feature Enhancement and Context Capture Network Based on Brain MRI Images for Lesion Segmentation.

In recent years, the increasing incidence of morbidity of brain stroke has made fast and accurate segmentation of lesion areas from brain MRI images important. With the development of deep learning, segmentation methods based on the computer have become a solution to assist clinicians in early diagnosis and treatment planning. Nevertheless, the variety of lesion sizes in brain MRI images and the roughness of the boundary of the lesion pose challenges to the accuracy of the segmentation algorithm. Current mainstream medical segmentation models are not able to solve these challenges due to their insufficient use of image features and context information. This paper proposes a novel feature enhancement and context capture network (FECC-Net), which is mainly composed of an atrous spatial pyramid pooling (ASPP) module and an enhanced encoder. In particular, the ASPP model uses parallel convolution operations with different sampling rates to enrich multi-scale features and fully capture image context information in order to process lesions of different sizes. The enhanced encoder obtains deep semantic features and shallow boundary features in the feature extraction process to achieve image feature enhancement, which is helpful for restoration of the lesion boundaries. We divide the pathological image into three levels according to the number of pixels in the real mask area and evaluate FECC-Net on an open dataset called Anatomical Tracings of Lesions After Stroke (ATLAS). The experimental results show that our FECC-Net outperforms mainstream methods, such as DoubleU-Net and TransUNet. Especially in small target tasks, FECC-Net is 4.09% ahead of DoubleU-Net on the main indicator DSC. Therefore, FECC-Net is encouraging and can be relied upon for brain MRI image applications.

Refined Voting and Scene Feature Fusion for 3D Object Detection in Point Clouds.

An essential task for 3D visual world understanding is 3D object detection in lidar point clouds. To predict directly bounding box parameters from point clouds, existing voting-based methods use Hough voting to obtain the centroid of each object. However, it may be difficult for the inaccurately voted centers to regress boxes accurately, leading to the generation of redundant bounding boxes. For objects in indoor scenes, there are several co-occurrence patterns for objects in indoor scenes. Concurrently, semantic relations between object layouts and scenes can be used as prior context to guide object detection. We propose a simple, yet effective network, RSFF-Net, which adds refined voting and scene feature fusion for indoor 3D object detection. The RSFF-Net consists of three modules: geometric function, refined voting, and scene constraint. First, a geometric function module is used to capture the geometric features of the nearest object of the voted points. Then, the coarse votes are revoted by a refined voting module, which is based on the fused feature between the coarse votes and geometric features. Finally, a scene constraint module is used to add the association information between candidate objects and scenes. RSFF-Net achieves competitive results on indoor 3D object detection benchmarks: ScanNet V2 and SUN RGB-D.

Point Cloud Semantic Segmentation Network Based on Multi-Scale Feature Fusion.

The semantic segmentation of small objects in point clouds is currently one of the most demanding tasks in photogrammetry and remote sensing applications. Multi-resolution feature extraction and fusion can significantly enhance the ability of object classification and segmentation, so it is widely used in the image field. For this motivation, we propose a point cloud semantic segmentation network based on multi-scale feature fusion (MSSCN) to aggregate the feature of a point cloud with different densities and improve the performance of semantic segmentation. In our method, random downsampling is first applied to obtain point clouds of different densities. A Spatial Aggregation Net (SAN) is then employed as the backbone network to extract local features from these point clouds, followed by concatenation of the extracted feature descriptors at different scales. Finally, a loss function is used to combine the different semantic information from point clouds of different densities for network optimization. Experiments were conducted on the S3DIS and ScanNet datasets, and our MSSCN achieved accuracies of 89.80% and 86.3%, respectively, on these datasets. Our method showed better performance than the recent methods PointNet, PointNet++, PointCNN, PointSIFT, and SAN.

Spatial Aggregation Net: Point Cloud Semantic Segmentation Based on Multi-Directional Convolution.

Semantic segmentation of 3D point clouds plays a vital role in autonomous driving, 3D maps, and smart cities, etc. Recent work such as PointSIFT shows that spatial structure information can improve the performance of semantic segmentation. Motivated by this phenomenon, we propose Spatial Aggregation Net (SAN) for point cloud semantic segmentation. SAN is based on multi-directional convolution scheme that utilizes the spatial structure information of point cloud. Firstly, Octant-Search is employed to capture the neighboring points around each sampled point. Secondly, we use multi-directional convolution to extract information from different directions of sampled points. Finally, max-pooling is used to aggregate information from different directions. The experimental results conducted on ScanNet database show that the proposed SAN has comparable results with state-of-the-art algorithms such as PointNet, PointNet++, and PointSIFT, etc. In particular, our method has better performance on flat, small objects, and the edge areas that connect objects. Moreover, our model has good trade-off in segmentation accuracy and time complexity.

[High tibial osteotomy for the treatment of osteoarthritis of the knee].

OBJECTIVE: To summarize clinical application of the high tibial osteatomy (HTO) with lateral closing-wedge for the treatment of pain of unicompartmental osteoarthritis of the knee. METHODS: From February 2000 to February 2004,9 patients (3 males and 6 females, ranging in age from 52 to 58 years, with an average of 56 years) with unicompartmental osteoarthritis of the knee treated by HTO with lateral closing-wedge. The proximal tibiofibular joint was exposed, the anterior part of the capsule was incised, and to remove a laterally based wedge with saw cuts and osteotomes. Stepped staples were used for the fixation of tibial osteotomies after closing the defect of osteotomy. RESULTS: The operative course was uneventful. There were no complications after operation. The postoperative follow-up period ranged from 2 to 5.5 years (mean, 3.5 years). The results were evaluated with functional assessment criterion of the osteoarthritis of the knee, among the 9 cases, excellent was in 5 cases, good in 3 cases, fair in 1 case. CONCLUSION: HTO with lateral closing-wedge is an effective operative method for the treatment of pain of unicompartmental osteoarthritis of the knee, but except for older patients over 60 years.

[Repair of scalp defect using V-Y-S rotation flap].

OBJECTIVE: To report the clinical results of scalp defect using V-Y-S rotation flap. METHODS: From March 2003 to October 2005, 5 cases scalp defect (4 male, 1 female) were reconstructed with the technique. The age ranged from 26 to 52 years (mean 32 years). The scalp defect ranged from 3 cmx3.5 cm to 4 cmx5 cm. Four cases were reconstructed with bilateral flap and one case was reconstructed with unilateral flaps. RESULTS: All patients were followed-up from 10 to 42 months (mean, 28 months). All the flaps survived completely and showed good hair growth and had satisfactory clinical results. CONCLUSION: Repair of scalp defect using V-Y-S rotation flap technique is simple with no need for a skin graft and can be performed quickly, there is minimal morbidity and the outcome is highly successful.

Total synthesis of the cyclodepsipeptide apratoxin A and its analogues and assessment of their biological activities.

A novel total synthesis of apratoxin A is described, with key steps including the assembly of its ketide segment through a D-proline-catalyzed direct aldol reaction and Oppolzer's anti aldol reaction and the preparation of its thiazoline unit in a biomimetic synthesis. An oxazoline analogue of apratoxin A has also been elaborated by a similar approach. This compound has a potency against HeLa cell proliferation only slightly lower than that of apratoxin A, whilst a C(40)-demethylated oxazoline analogue of apratoxin A displays a much lower cytotoxicity and the C(37)-epimer and C(37) demethylation product of this new analogue are inactive. These results suggest that the two methyl groups at C(37) and C(40) and the stereochemistry at C(37) are essential for the potent cellular activity of the oxazoline analogue of apratoxin A. Further biological analysis revealed that both synthetic apratoxin A and its oxazoline analogue inhibited cell proliferation by causing cell cycle arrest in the G1 phase.

A formal [3+2] cycloaddition process with nonactivated aziridines to polysubstituted indolizidines.

[chemical reaction: see text]. Heating a mixture of ethyl 7-iodo-2-heptynoate (or its analogues), 2-aryl aziridines, and K2CO3 in dry CH(3)CN delivers polysubstituted indolizidines. This reaction goes through an S(N)2/formal [3+2] cycloaddition process and represents the first synthetically useful example of the formal [3+2] cycloaddition process through a C-N bond cleavage of nonactivated aziridines.

CuI/L-proline-catalyzed coupling reactions of aryl halides with activated methylene compounds.

[reaction: see text] The arylation of ethyl acetoacetate, ethyl benzoyl acetate, and diethyl malonate under the catalysis of CuI/L-proline in DMSO proceeds smoothly at 40-50 degrees C in the presence of Cs2CO3 to provide the 2-aryl-1,3-dicarbonyl compounds in good yields. Both aryl iodides and aryl bromides are compatible with these reaction conditions.

Synthesis of an oxazoline analogue of apratoxin A.

[structure: see text] Michael addition of Me(2)Cu(CN)Li(2) to alpha,beta-unsaturated lactone 7 derived from beta-hydroxyl ketone 5 provides lactone 8, which is converted to alcohol 11 using Oppolzer's methodology as the key step. Connection of 11 with the l-proline moiety and subsequent installation of an oxazoline ring affords 16, which is coupled with tripeptide 21; subsequent macrocyclization then furnishes 4, an oxazoline analogue of apratoxin A.