Search

Your search keyword '"Xiong, Xiaofan"' showing total 144 results
Start Over Author "Xiong, Xiaofan"
144 results on '"Xiong, Xiaofan"'

11. Deep convolutional neural network based analysis methods for radiation therapy applications

Author

Xiong, Xiaofan

Subjects
radiomics, PET-CT, segmentation, Radiation Oncology, deep learning, image processing
Abstract

Medical imaging is crucial for many modern clinical applications such as diagnostics, disease progression monitoring, and treatment planning. For a large number of these applications, image segmentation serve as the first processing step, followed by quantitative image feature extraction to assess size, volume, shape characteristics, and intensity-related features. These quantitative features provide valuable information for interpretation of pathology and prognostics. However, the segmentation process is mostly done manually, which is time-consuming and lacks consistency. Automated and semi-automated methods have been proposed over the years to increase the efficiency, consistency, and accuracy of segmentation. Among the many methods, there are simple ones like thresholding, region-growing, watershed and more advanced ones like active contour methods, active shape model, and more recently, deep learning-based methods. Deep learning models have yielded a new generation of image segmentation methods with remarkable performance improvements, typically beating standard and traditional machine learning methods in various benchmarks. Another branch of medical image analysis is radiomics. A radiomics approach refers to methods that extracts features from medical images using data-characterisation algorithms, which can be utilized to discover and quantify characteristics of tumors. In this field, deep learning-based approaches are also appearing, showing promising improvements compared to using handcrafted features., This thesis aims to investigate and develop deep learning-based methods for the use in radiation oncology to facilitate the efficient analysis of volumetric medical image datasets. In particular, the segmentation performance of several state-of-the-art convolutional neural networks (CNN) and more recent transformer-based models for segmenting both normal and abnormal structures in PET images were studied and compared. For cerebellum segmentation, we discovered a modified U-Net that has significantly better segmentation performance than the original U-Net and V-Net. For head and neck cancer (HNC) lesion segmentation, we proposed a U-Net-CBAM that slightly outperforms the U-Net and several state-of-the-art transformer-based models. We also proposed a combined localization and segmentation approach for efficient segmentation of the pelvis in CT images with variant volume sizes and image qualities, achieving up to four times faster processing speed compared to a standard approach. Furthermore, this single object combined localization and segmentation approach is extended to process multiple objects in a scan at once. Specifically, the algorithm is applied and studied in the context of lumbar and thoracic vertebrae segmentation. In addition, we explored the performance of using CNN as well as a transformer-based models for HNC outcome prediction and found that the transformer-based model shows the best prognostic performance., In conclusion, our joint localization and segmentation approach for pelvis and lumbar and thoracic vertebrae demonstrated a novel way of utilizing CNNs to substantially improve the segmentation efficiency. We assessed the segmentation performance difference of several CNN and transformer based models on two different data sets. The difference can be substantial. Therefore, testing different models before starting a new project is imperative. In addition, comparison between CNN models and transformer based models on HNC outcome prediction performance showed the potential of transformer based models for radiomics applications. Furthermore, annotation quality, data size and class balance were found to play an important role in deep learning-based segmentation and classification performance, respectively.

Published
2024
Full Text
View/download PDF

12. Lumbar and Thoracic Vertebrae Segmentation in CT Scans Using a 3D Multi-Object Localization and Segmentation CNN.

Author

Xiong, Xiaofan, Graves, Stephen A., Gross, Brandie A., Buatti, John M., and Beichel, Reinhard R.

Subjects
THORACIC vertebrae, LUMBAR vertebrae, COMPUTED tomography, CONVOLUTIONAL neural networks, VERTEBRAE, CERVICAL cancer
Abstract

Radiation treatment of cancers like prostate or cervix cancer requires considering nearby bone structures like vertebrae. In this work, we present and validate a novel automated method for the 3D segmentation of individual lumbar and thoracic vertebra in computed tomography (CT) scans. It is based on a single, low-complexity convolutional neural network (CNN) architecture which works well even if little application-specific training data are available. It is based on volume patch-based processing, enabling the handling of arbitrary scan sizes. For each patch, it performs segmentation and an estimation of up to three vertebrae center locations in one step, which enables utilizing an advanced post-processing scheme to achieve high segmentation accuracy, as required for clinical use. Overall, 1763 vertebrae were used for the performance assessment. On 26 CT scans acquired for standard radiation treatment planning, a Dice coefficient of 0.921 ± 0.047 (mean ± standard deviation) and a signed distance error of 0.271 ± 0.748 mm was achieved. On the large-sized publicly available VerSe2020 data set with 129 CT scans depicting lumbar and thoracic vertebrae, the overall Dice coefficient was 0.940 ± 0.065 and the signed distance error was 0.109 ± 0.301 mm. A comparison to other methods that have been validated on VerSe data showed that our approach achieved a better overall segmentation performance. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

31. Chronic stress inhibits testosterone synthesis in Leydig cells through mitochondrial damage via Atp5a1

Author

Xiong, Xiaofan, primary, Wu, Qiuhua, additional, Zhang, Lingyu, additional, Gao, Shanfeng, additional, Li, Rufeng, additional, Han, Lin, additional, Fan, Meiyang, additional, Wang, Miaomiao, additional, Liu, Liying, additional, Wang, Xiaofei, additional, Zhang, Chunli, additional, Xin, Yanlong, additional, Li, Zongfang, additional, Huang, Chen, additional, and Yang, Juan, additional

Published
2021
Full Text
View/download PDF

35. SERPINA5 promotes tumour cell proliferation by modulating the PI3K/AKT/mTOR signalling pathway in gastric cancer.

Author

Fan, Meiyang, Xiong, Xiaofan, Han, Lin, Zhang, Lingyu, Gao, Shanfeng, Liu, Liying, Wang, Xiaofei, Huang, Chen, Tong, Dongdong, Yang, Juan, Zhao, Lingyu, and Shao, Yuan

Subjects
CELL proliferation, STOMACH cancer, CELLULAR signal transduction, PROGRESSION-free survival, CELL migration
Abstract

SERPINA5 belongs to the serine protease inhibitor superfamily and has been reported to be lowly expressed in a variety of malignancies. However, few report of SERPINA5 in gastric cancer has been found. The purpose of this study was to determine the role of SERPINA5 in GC and to investigate potential tumorigenic mechanisms. We performed qPCR to determine the level of SERPINA5 expression in GC. We used public databases to evaluate whether SERPINA5 could be utilized to predict overall survival and disease‐free survival in GC patients. We also knocked down the expression of SERPINA5 and evaluated its effect on cell proliferation and migration. Furthermore, we explored the signal pathways and regulatory mechanisms related to SERPINA5 functions. According to our findings, SERPINA5 was shown to exhibit high expression in GC. Notably, SERPINA5 was prognostic in GC with high expression being unfavourable. SERPINA5 was further observed to promote GC tumorigenesis by modulating GC cell proliferation ability. Mechanically, SERPINA5 could inhibit CBL to regulate the PI3K/AKT/mTOR signalling pathway, thereby promoting GC carcinogenesis progression. These results highlight the important role of SERPINA5 in GC cell proliferation and suggest that SERPINA5 could be a novel target for GC treatment and a predictor for GC prognosis. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

40. Chronic stress inhibits testosterone synthesis in Leydig cells through mitochondrial damage via Atp5a1.

Author

Xiong, Xiaofan, Wu, Qiuhua, Zhang, Lingyu, Gao, Shanfeng, Li, Rufeng, Han, Lin, Fan, Meiyang, Wang, Miaomiao, Liu, Liying, Wang, Xiaofei, Zhang, Chunli, Xin, Yanlong, Li, Zongfang, Huang, Chen, and Yang, Juan

Subjects
LEYDIG cells, PSYCHOLOGICAL stress, TESTOSTERONE, TWO-dimensional electrophoresis, MITOCHONDRIA, MALE infertility, INFERTILITY
Abstract

Stress is one of the leading causes of male infertility, but its exact function in testosterone synthesis has scarcely been reported. We found that adult male rats show a decrease in bodyweight, genital index and serum testosterone level after continual chronic stress for 21 days. Two‐dimensional gel electrophoresis (2‐DE) and MALDI‐TOF‐MS analysis identified 10 differentially expressed proteins in stressed rats compared with controls. A strong protein interaction network was found to be centred on Atp5a1 among these proteins. Atp5a1 expression significantly decreased in Leydig cells after chronic stress. Transfection of Atp5a1 siRNAs decreased StAR, CYP11A1, and 17β‐HSD expression by damaging the structure of mitochondria in TM3 cells. This study confirmed that chronic stress plays an important role in testosterone synthesis by regulating Atp5a1 expression in Leydig cells. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

42. Dietary nano‐selenium enhances antioxidant capacity and hypoxia tolerance of grass carp Ctenopharyngodon idella fed with high‐fat diet

Author

Yu, Haibo, primary, Zhang, Cheng, additional, Zhang, Xiaotian, additional, Wang, Chi, additional, Li, Pengju, additional, Liu, Guohao, additional, Yan, Xianfang, additional, Xiong, Xiaofan, additional, Zhang, Li, additional, Hou, Jingyao, additional, Liu, Sha, additional, Zhou, Jishu, additional, and Ji, Hong, additional

Published
2019
Full Text
View/download PDF

45. Dietary nano‐selenium enhances antioxidant capacity and hypoxia tolerance of grass carp Ctenopharyngodon idella fed with high‐fat diet.

Author

Yu, Haibo, Zhang, Cheng, Zhang, Xiaotian, Wang, Chi, Li, Pengju, Liu, Guohao, Yan, Xianfang, Xiong, Xiaofan, Zhang, Li, Hou, Jingyao, Liu, Sha, Zhou, Jishu, and Ji, Hong

Subjects
CTENOPHARYNGODON idella, ASPARTATE aminotransferase, HIGH-fat diet, OXIDANT status, HYPOXEMIA, GLUTATHIONE peroxidase
Abstract

To evaluate the effects of dietary nano‐selenium (Nano‐Se) on antioxidant capacity and hypoxia tolerance of grass carp fed with high‐fat diet, experimental fishes were fed Nano‐Se supplemented diets at doses of 0 (Control), 0.3, 0.6, 0.9 and 1.2 mg/kg for 10 weeks. After feeding trial, a part of the fishes were exposed to hypoxia stress. Results showed that the survival ratio of grass carp significantly increased in 0.6 and 0.9 mg/kg Nano‐Se group, and the content of serum alanine aminotransferase (ALT) and aspartate aminotransferase (AST) significantly decreased in 0.6–1.2 mg/kg Nano‐Se groups compared with the control group. In addition, dietary Nano‐Se significantly enhanced glutathione peroxidase (GPX) activity and reduced the malondialdehyde (MDA) content in fishes fed diets with 0.3 and 0.6 mg/kg Nano‐Se. Dietary Nano‐Se significantly elevated mRNA expression of GPX1 and catalase (CAT) by promoting the mRNA expression of NF‐E2‐related nuclear factor 2 (Nrf2) in the hepatopancreas. After hypoxia stress, the GPX and superoxide dismutase (SOD) activities were significantly enhanced, and the MDA content and mortality rate consequently decreased in fishes fed diets with 0.3 and 0.6 mg/kg Nano‐Se. In summary, these results suggested that optimal Nano‐Se in diet enhanced the antioxidant capacity and hypoxia tolerance of grass carp. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results