An accurate segmentation and quantification of the superficial foveal avascular zone(sFAZ)is important to facilitate the diagnosis and treatment of many retinal diseases,such as diabetic retinopathy and retinal vein o...An accurate segmentation and quantification of the superficial foveal avascular zone(sFAZ)is important to facilitate the diagnosis and treatment of many retinal diseases,such as diabetic retinopathy and retinal vein occlusion.We proposed a method based on deep learning for the automatic segmentation and quantification of the sFAZ in optical coherence tomography angiography(OCTA)images with robustness to brightness and contrast(B/C)variations.A dataset of 405 OCTA images from 45 participants was acquired with Zeiss Cirrus HD-OCT 5000 and the ground truth(GT)was manually segmented subsequently.A deep learning network with an encoder–decoder architecture was created to classify each pixel into an sFAZ or non-sFAZ class.Subsequently,we applied largestconnected-region extraction and hole-filling to fine-tune the automatic segmentation results.A maximum mean dice similarity coefficient(DSC)of 0.976±0.011 was obtained when the automatic segmentation results were compared against the GT.The correlation coefficient between the area calculated from the automatic segmentation results and that calculated from the GT was 0.997.In all nine parameter groups with various brightness/contrast,all the DSCs of the proposed method were higher than 0.96.The proposed method achieved better performance in the sFAZ segmentation and quantification compared to two previously reported methods.In conclusion,we proposed and successfully verified an automatic sFAZ segmentation and quantification method based on deep learning with robustness to B/C variations.For clinical applications,this is an important progress in creating an automated segmentation and quantification applicable to clinical analysis.展开更多
Since its introduction in the 1970’s,magnetic resonance imaging(MRI)has become a standard imaging modality.With its broad and standardized application,it is firmly established in the clinical routine and an essential...Since its introduction in the 1970’s,magnetic resonance imaging(MRI)has become a standard imaging modality.With its broad and standardized application,it is firmly established in the clinical routine and an essential element in cardiovascular and abdominal imaging.In addition to sonography and computer tomography,MRI is a valuable tool for diagnosing cardiovascular and abdominal diseases,for determining disease severity,and for assessing therapeutic success.MRI techniques have improved over the last few decades,revealing not just morphologic information,but functional information about perfusion,diffusion and hemodynamics as well.Four-dimensional(4D)flow MRI,a time-resolved phase contrast-MRI with three-dimensional(3D)anatomic coverage and velocity encoding along all three flow directions has been used to comprehensively assess complex cardiovascular hemodynamics in multiple regions of the body.The technique enables visualization of 3D blood flow patterns and retrospective quantification of blood flow parameters in a region of interest.Over the last few years,4D flow MRI has been increasingly performed in the abdominal region.By applying different acceleration techniques,taking 4D flow MRI measurements has dropped to a reasonable scanning time of 8 to 12 min.These new developments have encouraged a growing number of patient studies in the literature validating the technique’s potential for enhanced evaluation of blood flow parameters within the liver’s complex vascular system.The purpose of this review article is to broaden our understanding of 4D flow MRI for the assessment of liver hemodynamics by providing insights into acquisition,data analysis,visualization and quantification.Furthermore,in this article we highlight its development,focussing on the clinical application of the technique.展开更多
Dear Editor,The rising prevalence of myopia has become a significant global public health issue,with pathologic myopia emerging as a major cause of irreversible vision impairment,particularly in China(Baird et al.,202...Dear Editor,The rising prevalence of myopia has become a significant global public health issue,with pathologic myopia emerging as a major cause of irreversible vision impairment,particularly in China(Baird et al.,2020).Fundus tessellation(FT),the earliest stage of myopic macular degeneration(MMD),serves as a key predictor for disease progression,as its severity correlates with choroidal thinning,axial elongation,and increased myopic refractive error(Foo et al.,2023b).展开更多
The morphological quantification of the proximal tibia of the knee joint is important in knee replacement.Accurate knowledge of these parameters provides the basis for design of the tibial prosthesis and its fixation....The morphological quantification of the proximal tibia of the knee joint is important in knee replacement.Accurate knowledge of these parameters provides the basis for design of the tibial prosthesis and its fixation.Ideally,a prosthesis that is suitable for the morphological characteristics of Chinese knees is needed.In this paper,a deep learning automatic network framework is designed to achieve automatic segmentation and automatic quantitative analysis of magnetic resonance images of the tibia.An enhanced feature fusion network structure is designed,including high and low-level feature fusion path modules to create accurate segmentation of the tibia.A new method of extracting feature points and lines from outline contours of the proximal tibia is designed to automatically calculate six clinical morphological linear parameters of the tibia in real-time.The final result is an automatic visualisation of the tibial contour and automated extraction of tibial morphometric parameters.Validation of the results from our system against a gold standard obtained by manual processing by expert clinicians showed the Dice coefficient to be 0.97,the accuracy to be 0.98,and the correlation coefficients for all six morphological parameters of the automatic quantification of the tibia are above 0.96.The gender-specific study found that the values of the proximal tibial linear parameters of internal and external tibial diameter,anterior and posterior diameter,lateral plateau length,lateral plateau width,medial plateau length,and medial plateau width in male patients are significantly greater than in female patients(all P values<0.01).The results enrich the use of deep learning in medicine,providing orthopaedic specialists with a valuable and intelligent quantitative tool that can assess the progression and changes in osteoarthritis of the knee joint.展开更多
目的应用四维自动二尖瓣定量(4D Auto MVQ)技术评估风湿性心脏病二尖瓣重度狭窄(RMS)患者二尖瓣结构及功能变化。方法选取我院57例RMS患者(病例组)和同期30例健康受检者(对照组),应用4D Auto MVQ技术获取两组二尖瓣瓣环形态学参数、二...目的应用四维自动二尖瓣定量(4D Auto MVQ)技术评估风湿性心脏病二尖瓣重度狭窄(RMS)患者二尖瓣结构及功能变化。方法选取我院57例RMS患者(病例组)和同期30例健康受检者(对照组),应用4D Auto MVQ技术获取两组二尖瓣瓣环形态学参数、二尖瓣瓣叶形态学参数、二尖瓣瓣环动态参数及二尖瓣-主动脉瓣夹角(θ),其中二尖瓣瓣环形态学参数包括瓣环前后径(AP)、瓣环前外-后内侧直径(ALPM)、两纤维三角间距(ITD)、连合处直径(CD)、瓣环球度指数(SPI)、瓣环三维周长(CA3D)、瓣环二维面积(AA2D)、瓣环三维面积(AA3D)、瓣环非平面角度(θNPA)及瓣环高度(AH),二尖瓣瓣叶形态学参数包括幕状区高度(Htent)、幕状区容积(Vtent)、幕状区面积(Atent)、前叶面积(Aant)、后叶面积(Apost)、前叶长度(Lant)、后叶长度(Lpost)、后叶角度(θpost)及前叶角度(θant),二尖瓣瓣环动态参数包括瓣环最大位移(DAmax)、瓣环位移最大速率(VADmax)、瓣环面积分数(AAF),比较两组上述参数的差异。采用二尖瓣口三维描记法测量病例组三维二尖瓣瓣口面积(MVA3D),分析其与CA3D、AA2D、AA3D的相关性。结果病例组AP、ALPM、ITD、CD、SPI、CA3D、AA2D、AA3D、θNPA、Htent、Vtent、Atent、Aant、Apost、Lant、Lpost、θant、θ及AAF均大于对照组,DAmax、VADmax、AH及θpost均小于对照组,差异均有统计学意义(均P<0.05)。相关性分析显示,病例组MVA3D与CA3D、AA2D、AA3D均无相关性(r=-0.035、-0.100、-0.024,均P>0.05)。结论4D Auto MVQ技术可用于评估RMS患者二尖瓣结构及功能变化,具有良好的临床应用价值。展开更多
目的探讨四维自动右室定量(4D Auto RVQ)技术评价不同程度慢性心力衰竭(CHF)患者右室功能的临床价值。方法前瞻性选取在我院住院部确诊的CHF患者99例,依据6 min步行距离(6MWD)将其分为轻度CHF组(6MWD>450 m)、中度CHF组(150 m≤6MWD...目的探讨四维自动右室定量(4D Auto RVQ)技术评价不同程度慢性心力衰竭(CHF)患者右室功能的临床价值。方法前瞻性选取在我院住院部确诊的CHF患者99例,依据6 min步行距离(6MWD)将其分为轻度CHF组(6MWD>450 m)、中度CHF组(150 m≤6MWD≤450 m)、重度CHF组(6MWD<150 m),每组各33例。应用二维斑点追踪技术获取右室整体纵向应变(RVGLS)及右室游离壁纵向应变(RVFWLS),4D Auto RVQ技术获取四维右室射血分数(4D-RVEF)、右室舒张末期容积指数(4D-RVEDVI)、四维右室收缩末期容积指数(4D-RVESVI)、四维右室每搏量指数(4D-RVSVI)、四维三尖瓣环收缩期位移(4D-TAPSE)、四维右室面积变化分数(4D-RVFAC),比较各组上述参数的差异。采用有序Logistic回归分析4D Atuo RVQ参数及应变参数与患者CHF程度的关系。结果轻度CHF组、中度CHF组及重度CHF组4D-RVEF、4D-RVSVI、4D-TAPSE、4D-RVFAC、RVGLS及RVFWLS均依次降低,组间两两比较差异均有统计学意义(均P<0.05)。重度CHF组4D-RVEDVI、4D-RVESVI均增大,与轻度CHF组和中度CHF组比较差异均有统计学意义(均P<0.05)。有序Logistic回归分析显示,4D-RVEF对患者CHF程度具有显著负向影响(β=-1.302,P<0.001)。结论4D Auto RVQ技术可以定量评价不同程度CHF患者右室功能,具有一定的临床应用价值。展开更多
目的应用四维自动左房定量技术(4D Auto LAQ)评价甲状腺功能亢进症(以下简称甲亢)患者左房结构及功能变化,探讨其临床价值。方法选取我院甲亢患者59例(病例组)和同期健康志愿者41例(对照组),应用常规超声心动图获取左房收缩末期前后径(L...目的应用四维自动左房定量技术(4D Auto LAQ)评价甲状腺功能亢进症(以下简称甲亢)患者左房结构及功能变化,探讨其临床价值。方法选取我院甲亢患者59例(病例组)和同期健康志愿者41例(对照组),应用常规超声心动图获取左房收缩末期前后径(LADs)、左室舒张末期内径(LVDd)、左室射血分数(LVEF)、二尖瓣口舒张早期及晚期峰值血流速度(E、A)、二尖瓣环侧壁舒张早期及晚期运动速度(e’、a’)、E/e’,4D Auto LAQ获取左房最大容积(LAVmax)、左房最小容积(LAVmin)、左房收缩前容积(LAVpreA)、左房最大容积指数(LAVImax)、左房排空容积(LAEV)、左房排空分数(LAEF)、左房储存期纵向及圆周应变(LASr、LASr-c)、左房管道期纵向及圆周应变(LAScd、LAScd-c)、左房收缩期纵向及圆周应变(LASct、LASct-c),并计算左房僵硬指数(LASI)。比较两组上述参数的差异;分析所有研究对象4D Auto LAQ参数与游离三碘甲状腺原氨酸(FT3)、游离甲状腺素(FT4)、促甲状腺激素(TSH)的相关性。结果常规超声心动图检查结果显示,与对照组比较,病例组LADs、LVDd、A、a’均增高,差异均有统计学意义(均P<0.05);两组LVEF、E、e’、E/e’比较差异均无统计学意义。4D Auto LAQ检查结果显示,与对照组比较,病例组LAVmin、LAVpreA、LAVImax、LASI均增高,LAEF、LASr、LAScd、LASct、LASr-c、LASct-c均降低,差异均有统计学意义(均P<0.05);两组LAVmax、LAEV、LAScd-c比较差异均无统计学意义。相关性分析显示,所有研究对象LAVmin、LAEF、LASr、LAScd、LASct、LASr-c、LASct-c、LASI与FT3、FT4、TSH均相关(均P<0.05)。结论4D Auto LAQ可定量评价甲亢患者左房结构及功能变化,为临床精准诊断甲亢患者左房功能受损提供参考,具有一定的临床价值。展开更多
文摘An accurate segmentation and quantification of the superficial foveal avascular zone(sFAZ)is important to facilitate the diagnosis and treatment of many retinal diseases,such as diabetic retinopathy and retinal vein occlusion.We proposed a method based on deep learning for the automatic segmentation and quantification of the sFAZ in optical coherence tomography angiography(OCTA)images with robustness to brightness and contrast(B/C)variations.A dataset of 405 OCTA images from 45 participants was acquired with Zeiss Cirrus HD-OCT 5000 and the ground truth(GT)was manually segmented subsequently.A deep learning network with an encoder–decoder architecture was created to classify each pixel into an sFAZ or non-sFAZ class.Subsequently,we applied largestconnected-region extraction and hole-filling to fine-tune the automatic segmentation results.A maximum mean dice similarity coefficient(DSC)of 0.976±0.011 was obtained when the automatic segmentation results were compared against the GT.The correlation coefficient between the area calculated from the automatic segmentation results and that calculated from the GT was 0.997.In all nine parameter groups with various brightness/contrast,all the DSCs of the proposed method were higher than 0.96.The proposed method achieved better performance in the sFAZ segmentation and quantification compared to two previously reported methods.In conclusion,we proposed and successfully verified an automatic sFAZ segmentation and quantification method based on deep learning with robustness to B/C variations.For clinical applications,this is an important progress in creating an automated segmentation and quantification applicable to clinical analysis.
文摘Since its introduction in the 1970’s,magnetic resonance imaging(MRI)has become a standard imaging modality.With its broad and standardized application,it is firmly established in the clinical routine and an essential element in cardiovascular and abdominal imaging.In addition to sonography and computer tomography,MRI is a valuable tool for diagnosing cardiovascular and abdominal diseases,for determining disease severity,and for assessing therapeutic success.MRI techniques have improved over the last few decades,revealing not just morphologic information,but functional information about perfusion,diffusion and hemodynamics as well.Four-dimensional(4D)flow MRI,a time-resolved phase contrast-MRI with three-dimensional(3D)anatomic coverage and velocity encoding along all three flow directions has been used to comprehensively assess complex cardiovascular hemodynamics in multiple regions of the body.The technique enables visualization of 3D blood flow patterns and retrospective quantification of blood flow parameters in a region of interest.Over the last few years,4D flow MRI has been increasingly performed in the abdominal region.By applying different acceleration techniques,taking 4D flow MRI measurements has dropped to a reasonable scanning time of 8 to 12 min.These new developments have encouraged a growing number of patient studies in the literature validating the technique’s potential for enhanced evaluation of blood flow parameters within the liver’s complex vascular system.The purpose of this review article is to broaden our understanding of 4D flow MRI for the assessment of liver hemodynamics by providing insights into acquisition,data analysis,visualization and quantification.Furthermore,in this article we highlight its development,focussing on the clinical application of the technique.
基金supported by the National Natural Science Foundation of China(82220108017,82141128,82401283)the Capital Health Research and Development of Special(2024-1-2052)+3 种基金Science&Technology Project of Beijing Municipal Science&Technology Commission(Z201100005520045)Sanming Project of Medicine in Shenzhen(SZSM202311018)Scientific Research Common Program of Beijing Municipal Commission of Education(KM202410025011)the priming scientific research foundation for the junior researcher in Beijing Tongren Hospital,Capital Medical University(2023-YJJ-ZZL-003)。
文摘Dear Editor,The rising prevalence of myopia has become a significant global public health issue,with pathologic myopia emerging as a major cause of irreversible vision impairment,particularly in China(Baird et al.,2020).Fundus tessellation(FT),the earliest stage of myopic macular degeneration(MMD),serves as a key predictor for disease progression,as its severity correlates with choroidal thinning,axial elongation,and increased myopic refractive error(Foo et al.,2023b).
基金National Natural Science Foundation of China(Project Nos.11772214 and 11972243)supported by the Shanxi Huajin Orthopaedic Public Foundation.
文摘The morphological quantification of the proximal tibia of the knee joint is important in knee replacement.Accurate knowledge of these parameters provides the basis for design of the tibial prosthesis and its fixation.Ideally,a prosthesis that is suitable for the morphological characteristics of Chinese knees is needed.In this paper,a deep learning automatic network framework is designed to achieve automatic segmentation and automatic quantitative analysis of magnetic resonance images of the tibia.An enhanced feature fusion network structure is designed,including high and low-level feature fusion path modules to create accurate segmentation of the tibia.A new method of extracting feature points and lines from outline contours of the proximal tibia is designed to automatically calculate six clinical morphological linear parameters of the tibia in real-time.The final result is an automatic visualisation of the tibial contour and automated extraction of tibial morphometric parameters.Validation of the results from our system against a gold standard obtained by manual processing by expert clinicians showed the Dice coefficient to be 0.97,the accuracy to be 0.98,and the correlation coefficients for all six morphological parameters of the automatic quantification of the tibia are above 0.96.The gender-specific study found that the values of the proximal tibial linear parameters of internal and external tibial diameter,anterior and posterior diameter,lateral plateau length,lateral plateau width,medial plateau length,and medial plateau width in male patients are significantly greater than in female patients(all P values<0.01).The results enrich the use of deep learning in medicine,providing orthopaedic specialists with a valuable and intelligent quantitative tool that can assess the progression and changes in osteoarthritis of the knee joint.
文摘目的应用四维自动二尖瓣定量(4D Auto MVQ)技术评估风湿性心脏病二尖瓣重度狭窄(RMS)患者二尖瓣结构及功能变化。方法选取我院57例RMS患者(病例组)和同期30例健康受检者(对照组),应用4D Auto MVQ技术获取两组二尖瓣瓣环形态学参数、二尖瓣瓣叶形态学参数、二尖瓣瓣环动态参数及二尖瓣-主动脉瓣夹角(θ),其中二尖瓣瓣环形态学参数包括瓣环前后径(AP)、瓣环前外-后内侧直径(ALPM)、两纤维三角间距(ITD)、连合处直径(CD)、瓣环球度指数(SPI)、瓣环三维周长(CA3D)、瓣环二维面积(AA2D)、瓣环三维面积(AA3D)、瓣环非平面角度(θNPA)及瓣环高度(AH),二尖瓣瓣叶形态学参数包括幕状区高度(Htent)、幕状区容积(Vtent)、幕状区面积(Atent)、前叶面积(Aant)、后叶面积(Apost)、前叶长度(Lant)、后叶长度(Lpost)、后叶角度(θpost)及前叶角度(θant),二尖瓣瓣环动态参数包括瓣环最大位移(DAmax)、瓣环位移最大速率(VADmax)、瓣环面积分数(AAF),比较两组上述参数的差异。采用二尖瓣口三维描记法测量病例组三维二尖瓣瓣口面积(MVA3D),分析其与CA3D、AA2D、AA3D的相关性。结果病例组AP、ALPM、ITD、CD、SPI、CA3D、AA2D、AA3D、θNPA、Htent、Vtent、Atent、Aant、Apost、Lant、Lpost、θant、θ及AAF均大于对照组,DAmax、VADmax、AH及θpost均小于对照组,差异均有统计学意义(均P<0.05)。相关性分析显示,病例组MVA3D与CA3D、AA2D、AA3D均无相关性(r=-0.035、-0.100、-0.024,均P>0.05)。结论4D Auto MVQ技术可用于评估RMS患者二尖瓣结构及功能变化,具有良好的临床应用价值。
文摘目的探讨四维自动右室定量(4D Auto RVQ)技术评价不同程度慢性心力衰竭(CHF)患者右室功能的临床价值。方法前瞻性选取在我院住院部确诊的CHF患者99例,依据6 min步行距离(6MWD)将其分为轻度CHF组(6MWD>450 m)、中度CHF组(150 m≤6MWD≤450 m)、重度CHF组(6MWD<150 m),每组各33例。应用二维斑点追踪技术获取右室整体纵向应变(RVGLS)及右室游离壁纵向应变(RVFWLS),4D Auto RVQ技术获取四维右室射血分数(4D-RVEF)、右室舒张末期容积指数(4D-RVEDVI)、四维右室收缩末期容积指数(4D-RVESVI)、四维右室每搏量指数(4D-RVSVI)、四维三尖瓣环收缩期位移(4D-TAPSE)、四维右室面积变化分数(4D-RVFAC),比较各组上述参数的差异。采用有序Logistic回归分析4D Atuo RVQ参数及应变参数与患者CHF程度的关系。结果轻度CHF组、中度CHF组及重度CHF组4D-RVEF、4D-RVSVI、4D-TAPSE、4D-RVFAC、RVGLS及RVFWLS均依次降低,组间两两比较差异均有统计学意义(均P<0.05)。重度CHF组4D-RVEDVI、4D-RVESVI均增大,与轻度CHF组和中度CHF组比较差异均有统计学意义(均P<0.05)。有序Logistic回归分析显示,4D-RVEF对患者CHF程度具有显著负向影响(β=-1.302,P<0.001)。结论4D Auto RVQ技术可以定量评价不同程度CHF患者右室功能,具有一定的临床应用价值。
文摘目的应用四维自动左房定量技术(4D Auto LAQ)评价甲状腺功能亢进症(以下简称甲亢)患者左房结构及功能变化,探讨其临床价值。方法选取我院甲亢患者59例(病例组)和同期健康志愿者41例(对照组),应用常规超声心动图获取左房收缩末期前后径(LADs)、左室舒张末期内径(LVDd)、左室射血分数(LVEF)、二尖瓣口舒张早期及晚期峰值血流速度(E、A)、二尖瓣环侧壁舒张早期及晚期运动速度(e’、a’)、E/e’,4D Auto LAQ获取左房最大容积(LAVmax)、左房最小容积(LAVmin)、左房收缩前容积(LAVpreA)、左房最大容积指数(LAVImax)、左房排空容积(LAEV)、左房排空分数(LAEF)、左房储存期纵向及圆周应变(LASr、LASr-c)、左房管道期纵向及圆周应变(LAScd、LAScd-c)、左房收缩期纵向及圆周应变(LASct、LASct-c),并计算左房僵硬指数(LASI)。比较两组上述参数的差异;分析所有研究对象4D Auto LAQ参数与游离三碘甲状腺原氨酸(FT3)、游离甲状腺素(FT4)、促甲状腺激素(TSH)的相关性。结果常规超声心动图检查结果显示,与对照组比较,病例组LADs、LVDd、A、a’均增高,差异均有统计学意义(均P<0.05);两组LVEF、E、e’、E/e’比较差异均无统计学意义。4D Auto LAQ检查结果显示,与对照组比较,病例组LAVmin、LAVpreA、LAVImax、LASI均增高,LAEF、LASr、LAScd、LASct、LASr-c、LASct-c均降低,差异均有统计学意义(均P<0.05);两组LAVmax、LAEV、LAScd-c比较差异均无统计学意义。相关性分析显示,所有研究对象LAVmin、LAEF、LASr、LAScd、LASct、LASr-c、LASct-c、LASI与FT3、FT4、TSH均相关(均P<0.05)。结论4D Auto LAQ可定量评价甲亢患者左房结构及功能变化,为临床精准诊断甲亢患者左房功能受损提供参考,具有一定的临床价值。
