Recently,research has been conducted to assist in the processing and analysis of histopathological images using machine learning algorithms.In this study,we established machine learning-based algorithms to detect phot...Recently,research has been conducted to assist in the processing and analysis of histopathological images using machine learning algorithms.In this study,we established machine learning-based algorithms to detect photothrombotic lesions in histological images of photothrombosis-induced rabbit brains.Six machine learning-based algorithms for binary classification were applied,and the accu-racies were compared to classify normal tissues and photothrombotic lesions.The lesion classification model consisting of a 3-layered neural network with a rectified linear unit(ReLU)activation function,Xavier initialization,and Adam optimization using datasets with a unit size of 128×128 pixels yielded the highest accuracy(0.975).In the validation using the tested histological images,it was confirmed that the model could identify regions where brain damage occurred due to photochemical ischemic stroke.Through the development of machine learning-based photothrombotic lesion classi-fication models and performance comparisons,we confirmed that machine learning algorithms have the potential to be utilized in histopathology and various medical diagnostic techniques.展开更多
Acute hemorrhagic anemia can decrease blood flow and oxygen supply to brain, and affect its physiological function. While detecting changes in brain function in patients with acute hemorrhagic anemia is helpful for pr...Acute hemorrhagic anemia can decrease blood flow and oxygen supply to brain, and affect its physiological function. While detecting changes in brain function in patients with acute hemorrhagic anemia is helpful for preventing neurological complications and evaluating therapeutic effects, clinical changes in the nervous systems of these patients have not received much attention. In part, this is because current techniques can only indirectly detect changes in brain function following onset of anemia, which leads to lags between real changes in brain function and their detection.展开更多
Changes in the activity of Na^+, K^+-ATPase and in the water, sodium, and potassium levels in the ischemic brain were investigated in rabbits 2, 4, and 24h following occlusion of middle cerebral artery (MCAo) and in s...Changes in the activity of Na^+, K^+-ATPase and in the water, sodium, and potassium levels in the ischemic brain were investigated in rabbits 2, 4, and 24h following occlusion of middle cerebral artery (MCAo) and in shamoccluded control. An increase in Na^+, K^+-ATPase activity was observed in 2h and 4h groups, with a subsequent decrease in the enzyme activity. The elevation in Na^+, K^+-ATPase activity was accompanied by an increase in the sodium content and a slight decrease in the potassium content. These changes are presumed to occure because of stimilated active transport of sodium from blood to brain across the brain capillaries. We suggest that the elevated activity of Na^+, K^+-A TPase may participate in the pathogenesis of ischemic brain edema.展开更多
目的基于3.0 T磁共振成像(MRI)技术,活体观察WHBE兔脑部形态解剖结构,累积WHBE兔脑的影像学基本生物学数据,为进一步拓宽WHBE兔的应用提供背景资料。方法成年雄性WHBE兔9只,用3%戊巴比妥钠溶液静脉注射麻醉,行3.0 T MRI加兔脑专用线圈...目的基于3.0 T磁共振成像(MRI)技术,活体观察WHBE兔脑部形态解剖结构,累积WHBE兔脑的影像学基本生物学数据,为进一步拓宽WHBE兔的应用提供背景资料。方法成年雄性WHBE兔9只,用3%戊巴比妥钠溶液静脉注射麻醉,行3.0 T MRI加兔脑专用线圈常规横断面和矢状面扫描,并测量分析脑部的各种结构大小。结果 MRI扫描可成功获得活体WHBE兔脑矢状面和横断面T2WI或T1WI图像,可完整清晰地观察到活体WHBE兔的嗅球、大脑、小脑和垂体等基本结构,并发现了4只兔脑T2WI中左右两侧颞叶海马区高信号,相应区域在T1WI出现低信号外,其余均无异常。同时,获得了额叶、海马、大脑、侧脑室、垂体等相关解剖结构的参考值。结论采用3.0 T磁共振成像系统加上兔脑专用线圈,可以清晰地观察到WHBE兔脑部的各种形态解剖结构,并初步建立了WBHE兔脑影像学基本数据。展开更多
基金This research was supported by grants from the Korea Health Technology R&D Project through the Korea Health Industry Development Institute(KHIDI)funded by the Ministry of Health&Welfare(Hl17C1501)from Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Science&ICT(NRF-2020R1C1C1012230)S.H,Cho was supported by the semester internship program between Daegu Catholic University and Daegu-Gyeongbuk Medical Innovation Foundation.
文摘Recently,research has been conducted to assist in the processing and analysis of histopathological images using machine learning algorithms.In this study,we established machine learning-based algorithms to detect photothrombotic lesions in histological images of photothrombosis-induced rabbit brains.Six machine learning-based algorithms for binary classification were applied,and the accu-racies were compared to classify normal tissues and photothrombotic lesions.The lesion classification model consisting of a 3-layered neural network with a rectified linear unit(ReLU)activation function,Xavier initialization,and Adam optimization using datasets with a unit size of 128×128 pixels yielded the highest accuracy(0.975).In the validation using the tested histological images,it was confirmed that the model could identify regions where brain damage occurred due to photochemical ischemic stroke.Through the development of machine learning-based photothrombotic lesion classi-fication models and performance comparisons,we confirmed that machine learning algorithms have the potential to be utilized in histopathology and various medical diagnostic techniques.
基金supported by the Science and Technology Project of Shenzhen,No.JCY20120613170958482the First Affiliated Hospital of Shenzhen University Breeding Program,No.2012015
文摘Acute hemorrhagic anemia can decrease blood flow and oxygen supply to brain, and affect its physiological function. While detecting changes in brain function in patients with acute hemorrhagic anemia is helpful for preventing neurological complications and evaluating therapeutic effects, clinical changes in the nervous systems of these patients have not received much attention. In part, this is because current techniques can only indirectly detect changes in brain function following onset of anemia, which leads to lags between real changes in brain function and their detection.
基金This work was supported by a grant from National Seventh-Five Year Plan's Cerebrovascular Diseases Research Project
文摘Changes in the activity of Na^+, K^+-ATPase and in the water, sodium, and potassium levels in the ischemic brain were investigated in rabbits 2, 4, and 24h following occlusion of middle cerebral artery (MCAo) and in shamoccluded control. An increase in Na^+, K^+-ATPase activity was observed in 2h and 4h groups, with a subsequent decrease in the enzyme activity. The elevation in Na^+, K^+-ATPase activity was accompanied by an increase in the sodium content and a slight decrease in the potassium content. These changes are presumed to occure because of stimilated active transport of sodium from blood to brain across the brain capillaries. We suggest that the elevated activity of Na^+, K^+-A TPase may participate in the pathogenesis of ischemic brain edema.
