1.A region-level contrastive learning-based deep model for glomerular ultrastructure segmentation on electron microscope images.
Guoyu LIN ; Zhentai ZHANG ; Yanmeng LU ; Jian GENG ; Zhitao ZHOU ; Lijun LU ; Lei CAO
Journal of Southern Medical University 2023;43(5):815-824
OBJECTIVE:
We propose a novel region- level self-supervised contrastive learning method USRegCon (ultrastructural region contrast) based on the semantic similarity of ultrastructures to improve the performance of the model for glomerular ultrastructure segmentation on electron microscope images.
METHODS:
USRegCon used a large amount of unlabeled data for pre- training of the model in 3 steps: (1) The model encoded and decoded the ultrastructural information in the image and adaptively divided the image into multiple regions based on the semantic similarity of the ultrastructures; (2) Based on the divided regions, the first-order grayscale region representations and deep semantic region representations of each region were extracted by region pooling operation; (3) For the first-order grayscale region representations, a grayscale loss function was proposed to minimize the grayscale difference within regions and maximize the difference between regions. For deep semantic region representations, a semantic loss function was introduced to maximize the similarity of positive region pairs and the difference of negative region pairs in the representation space. These two loss functions were jointly used for pre-training of the model.
RESULTS:
In the segmentation task for 3 ultrastructures of the glomerular filtration barrier based on the private dataset GlomEM, USRegCon achieved promising segmentation results for basement membrane, endothelial cells, and podocytes, with Dice coefficients of (85.69 ± 0.13)%, (74.59 ± 0.13)%, and (78.57 ± 0.16)%, respectively, demonstrating a good performance of the model superior to many existing image-level, pixel-level, and region-level self-supervised contrastive learning methods and close to the fully- supervised pre-training method based on the large- scale labeled dataset ImageNet.
CONCLUSION
USRegCon facilitates the model to learn beneficial region representations from large amounts of unlabeled data to overcome the scarcity of labeled data and improves the deep model performance for glomerular ultrastructure recognition and boundary segmentation.
Humans
;
Electrons
;
Endothelial Cells
;
Learning
;
Podocytes
;
Kidney Diseases
2.Application of Statistical Process Control in Evaluation of Performance for Beam-matched Medical Electron Linacs.
Qing XIAO ; Guangjun LI ; Xiangbin ZHANG ; Sen BAI
Chinese Journal of Medical Instrumentation 2021;45(1):109-113
Clinically, beam matching can greatly improve the flexibility and efficiency of treating patients between different medical electron linacs. However, in addition to the regular quality assurance (QA) test of the machine performance of linacs, there is still a lack of comprehensive evaluation of the clinical radiotherapy performance of beam-matched linacs. In this paper, the performance of volumetric modulated arc therapy (VMAT) between three closely matched linacs was evaluated by statistical process control (SPC) technology. It was found that the average and median γ passing rates of the VMAT QA processes of the three linacs had little difference, but the process capability levels were at three different levels. The results show that SPC technology can effectively evaluate the performance of beam matching for medical electron linacs, improve the patient-specific VMAT QA processes, and guide clinical decision-making.
Electrons
;
Particle Accelerators
;
Quality Assurance, Health Care
;
Radiotherapy Dosage
;
Radiotherapy Planning, Computer-Assisted
;
Radiotherapy, Intensity-Modulated
3.Common Troubles of Vacuum Components in Elekta Linear Accelerator and Fast Solutions.
Daming LI ; Zhaoming PENG ; Pengfei YANG ; Huaiwen ZHANG
Chinese Journal of Medical Instrumentation 2021;45(1):114-118
The transportation of electron is inseparable from vacuum environment. The maintenance of the vacuum system of Elekta linear accelerator depends on two sputtering ionic pumps at the gun end and the target end. The traveling wave acceleration were used in Elekta linear accelerators. And the design of the electron gun filament is detachable. Because of these two reasons, the vacuum stability is relatively weak. Only two vacuum values are used to reflect the operation state of the whole vacuum system, which causes a few failures but will not trigger a the machine interlock. Considering the complexity of whole vacuum system, the problem of vacuum caused by the failure of various components in vacuum system is analyzed in this paper. It is hoped that some useful repairing experience and suggestions for the maintenance engineers of linear accelerator to solve the vacuum fault and rebuild the vacuum can be provided quickly.
Electrons
;
Particle Accelerators
;
Radiotherapy Dosage
;
Vacuum
4.Two-Dimensional Electron Beam Radiotherapy Planning System with Modeling Function.
Chinese Journal of Medical Instrumentation 2021;45(2):163-166
In order to adapt to different target shapes and protect the surrounding normal tissues, the design of two-dimensional electron beam radiotherapy planning requires additional lead blocks. But the Pinnacle treatment planning system can not directly shape the lead block conformity to the size of the beam field given by the doctor. Every time, physicists need to manually drag the lead block to form the required beam field. When meeting a two-dimensional electron beam treatment planning with the same field parameters as before, physicists need to rearrange the field for dose calculation, which greatly reduces the design efficiency of the two-dimensional electron beam treatment planning. In this study, we independently developed a two-dimensional electron beam radiotherapy planning system based on Qt Creator. The system can quickly design a two-dimensional electron beam radiotherapy plan, which reduces the repeated work of physicists.
Electrons
;
Radiotherapy Dosage
;
Radiotherapy Planning, Computer-Assisted
5.Design and Test of Automatic Dispensing and Injecting System for Positron Radiopharmaceuticals.
Ning GUO ; Tong WANG ; Li HUO ; Fang LI ; Li-Jie LIU ; Yi LI ; Jian-Tao BA
Acta Academiae Medicinae Sinicae 2021;43(3):429-434
Objective To design a novel automatic dispensing and injecting system of positron radiopharmaceuticals,for precise dose dispensing,simplified operation,and reduction of occupational radiation exposure. Methods The automatic dispensing and injecting system was fabricated with tungsten alloy as the shielding material.The performance and radiation protection of the device were assessed. Results The total time of injection using the automatic dispensing and injecting system was about 60 s.The ratio of successful injection in stability test was 100%.The deviation of the dispensing dose with the system was ≤3%.With the tungsten alloy shield(40 mmPb of the cabinet,60 mmPb of the countertop,15 mmPb of the protective shield,and 50 mmPb of the inbuilt jar for radiopharmaceuticals),the average dose rate at 30 cm from the device was 1.44 μSv/h,and the radiation dose at the operator's extremity was reduced by 99%. Conclusions This automatic dispensing and injecting system of positron radiopharmaceuticals is easy to operate with precise dispensing dose.It is safe and meets the requirements of radiation protection.
Electrons
;
Occupational Exposure/analysis*
;
Radiation Dosage
;
Radiation Protection
;
Radiopharmaceuticals
6.Progress in enhancing electron transfer rate between exoelectrogenic microorganisms and electrode interface.
Xiang LIU ; Junqi ZHANG ; Baocai ZHANG ; Chi YANG ; Feng LI ; Hao SONG
Chinese Journal of Biotechnology 2021;37(2):361-377
Exoelectrogenic microorganisms are the research basis of microbial electrochemical technologies such as microbial fuel cells, electrolytic cells and electrosynthesis. However, their applications are restricted in organic degradation, power generation, seawater desalination, bioremediation, and biosensors due to the weak ability of biofilm formation and the low extracellular electron transfer (EET) efficiency between exoelectrogenic microorganisms and electrode. Therefore, engineering optimization of interaction between exoelectrogenic microorganisms and electrode interface recently has been the research focus. In this article, we review the updated progress in strategies for enhancing microbe-electrode interactions based on microbial engineering modifications, with a focus on the applicability and limitations of these strategies. In addition, we also address research prospects of enhancing the interaction between electroactive cells and electrodes.
Bioelectric Energy Sources
;
Biofilms
;
Electrodes
;
Electron Transport
;
Electrons
7.Application of Virtual Monochromatic Images Reconstructed by Dual-energy Computed Tomography in Radiotherapy Treatment Planning System.
Jing LI ; Qing XIAO ; Xiangbin ZHANG ; Guyu DAI ; Sen BAI ; Renming ZHONG
Chinese Journal of Medical Instrumentation 2021;45(5):568-572
Virtual monochromatic images (VMI) that reconstructed on dual-energy computed tomography (DECT) have further application prospects in radiotherapy, and there is still a lack of clinical dose verification. In this study, GE Revolution CT scanner was used to perform conventional imaging and gemstone spectral imaging on the simulated head and body phantom. The CT images were imported to radiotherapy treatment planning system (TPS), and the same treatment plans were transplanted to compare the CT value and the dose distribution. The results show that the VMI can be imported into TPS for CT value-relative electron density conversion and dose calculation. Compared to conventional images, the VMI varies from 70 to 140 keV, has little difference in dose distribution of 6 MV photon treatment plan.
Electrons
;
Phantoms, Imaging
;
Tomography Scanners, X-Ray Computed
;
Tomography, X-Ray Computed
8.Potential of electron transfer and its application in dictating routes of biochemical processes associated with metabolic reprogramming.
Ronghui YANG ; Guoguang YING ; Binghui LI
Frontiers of Medicine 2021;15(5):679-692
Metabolic reprogramming, such as abnormal utilization of glucose, addiction to glutamine, and increased de-novo lipid synthesis, extensively occurs in proliferating cancer cells, but the underneath rationale has remained to be elucidated. Based on the concept of the degree of reduction of a compound, we have recently proposed a calculation termed as potential of electron transfer (PET), which is used to characterize the degree of electron redistribution coupled with metabolic transformations. When this calculation is combined with the assumed model of electron balance in a cellular context, the enforced selective reprogramming could be predicted by examining the net changes of the PET values associated with the biochemical pathways in anaerobic metabolism. Some interesting properties of PET in cancer cells were also discussed, and the model was extended to uncover the chemical nature underlying aerobic glycolysis that essentially results from energy requirement and electron balance. Enabling electron transfer could drive metabolic reprogramming in cancer metabolism. Therefore, the concept and model established on electron transfer could guide the treatment strategies of tumors and future studies on cellular metabolism.
Electrons
;
Energy Metabolism
;
Glucose
;
Glycolysis
;
Humans
;
Neoplasms
9.Recent progress of positron radionuclide labeled small molecule inhibitors of prostate specific membrane antigen for PET/CT imaging of prostate cancer.
Lili PAN ; Xiaoai WU ; Wei DIAO ; Lin LI
Journal of Biomedical Engineering 2020;37(2):219-224
Prostate cancer is the most common tumor of the urinary system, and its mortality rate is second only to lung cancer. With the specific and high expression on the surface of prostate cancer cells, prostate-specific membrane antigen (PSMA) has been an ideal theranostic target of prostate cancer with great clinical significance and research value. Positron emission tomography/computed tomography (PET/CT), a new modality of molecular imaging combining functional metabolic information and anatomical structure, provides high diagnostic performance for cancer detection. This paper mainly reviewed recent progress of PSMA inhibitors labeled by positron-emitting radionuclides for early diagnosis, preoperative staging, response assessment, restaging and metastasis detection of prostate cancer.
Electrons
;
Humans
;
Kallikreins
;
antagonists & inhibitors
;
Male
;
Positron Emission Tomography Computed Tomography
;
Prostate-Specific Antigen
;
antagonists & inhibitors
;
Prostatic Neoplasms
;
diagnostic imaging
;
Radioisotopes
;
chemistry
10.Performance of F-18 Fluorocholine PET/CT for Detection of Hyperfunctioning Parathyroid Tissue in Patients with Elevated Parathyroid Hormone Levels and Negative or Discrepant Results in conventional Imaging
Lebriz USLU-BEŞLI ; Kerim SONMEZOGLU ; Serkan TEKSOZ ; Elife AKGUN ; Emre KARAYEL ; Huseyin PEHLIVANOGLU ; Baresh Razavi KHOSROSHAHI ; Meltem OCAK ; Levent KABASAKAL ; Sait SAGER ; Yusuf BUKEY
Korean Journal of Radiology 2020;21(2):236-247

Result Analysis
Print
Save
E-mail