According to the World Health Organization(WHO),Brain Tumors(BrT)have a high rate of mortality across the world.The mortality rate,however,decreases with early diagnosis.Brain images,Computed Tomography(CT)scans,Magne...According to the World Health Organization(WHO),Brain Tumors(BrT)have a high rate of mortality across the world.The mortality rate,however,decreases with early diagnosis.Brain images,Computed Tomography(CT)scans,Magnetic Resonance Imaging scans(MRIs),segmentation,analysis,and evaluation make up the critical tools and steps used to diagnose brain cancer in its early stages.For physicians,diagnosis can be challenging and time-consuming,especially for those with little expertise.As technology advances,Artificial Intelligence(AI)has been used in various domains as a diagnostic tool and offers promising outcomes.Deep-learning techniques are especially useful and have achieved exquisite results.This study proposes a new Computer-Aided Diagnosis(CAD)system to recognize and distinguish between tumors and non-tumor tissues using a newly developed middleware to integrate two deep-learning technologies to segment brain MRI scans and classify any discovered tumors.The segmentation mechanism is used to determine the shape,area,diameter,and outline of any tumors,while the classification mechanism categorizes the type of cancer as slow-growing or aggressive.The main goal is to diagnose tumors early and to support the work of physicians.The proposed system integrates a Convolutional Neural Network(CNN),VGG-19,and Long Short-Term Memory Networks(LSTMs).A middleware framework is developed to perform the integration process and allow the system to collect the required data for the classification of tumors.Numerous experiments have been conducted on different five datasets to evaluate the presented system.These experiments reveal that the system achieves 97.98%average accuracy when the segmentation and classification functions were utilized,demonstrating that the proposed system is a powerful and valuable method to diagnose BrT early using MRI images.In addition,the system can be deployed in medical facilities to support and assist physicians to provide an early diagnosis to save patients’lives and avoid the high cost of treatments.展开更多
To expand the single-dose duration over which noninvasive clinical and preclinical cancer imaging can be conducted with high sensitivity,and well-defined spatial and temporal resolutions,a facile strategy to prepare u...To expand the single-dose duration over which noninvasive clinical and preclinical cancer imaging can be conducted with high sensitivity,and well-defined spatial and temporal resolutions,a facile strategy to prepare ultrasmall nanoparticulate X-ray contrast media(nano-XRCM)as dual-modality imaging agents for positron emission tomography(PET)and computed tomography(CT)has been established.Synthesized from controlled copolymerization of triiodobenzoyl ethyl acrylate and oligo(ethylene oxide)acrylate monomers,the amphiphilic statistical iodocopolymers(ICPs)could directly dissolve in water to afford thermodynamically stable solutions with high aqueous iodine concentrations(>140 mg iodine/mL water)and comparable viscosities to conventional small molecule XRCM.The formation of ultrasmall iodinated nanoparticles with hydrodynamic diameters of ca.10 nm in water was confirmed by dynamic and static light scattering techniques.In a breast cancer mouse model,in vivo biodistribution studies revealed that the64Cu-chelator-functionalized iodinated nano-XRCM exhibited extended blood residency and higher tumor accumulation compared to typical small molecule imaging agents.PET/CT imaging of tumor over 3 days showed good correlation between PET and CT signals,while CT imaging allowed continuous observation of tumor retention even after 10 days post-injection,enabling longitudinal monitoring of tumor retention for imaging or potentially therapeutic effect after a single administration of nano-XRCM.展开更多
Background: Tumor pathologies of the liver and bile ducts are relatively commonly diagnosed and the primary goal is to differentiate these lesions in the fastest possible time which determines the apropriate method of...Background: Tumor pathologies of the liver and bile ducts are relatively commonly diagnosed and the primary goal is to differentiate these lesions in the fastest possible time which determines the apropriate method of treatment. Aims and Objectives: Aim of this study is tracking and diagnostic imaging correlation of tumor pathologies of liver and bile ducts and determining the early diagnostic approach. Data obtained from this study are important for treatment procedures and succes of treatment. All cases with liver tumor pathologies from period 2012-2016 were examined with CT and MRI followed by other complementary imaging methods. Methods: CT examination was performed according to standard triple-phase protocol: non-enhanced phase, arterial phase and porto-venous phase, and in some cases with late phase after 5 minutes. In MRI examinations, standard protocol was performed: coronal T2 single-shot fast spin-echo (coronal T2 SSFs), Axial T2 respiratory-triggered fast spin-echo (axial T2-FRE)/or breath-hold fast-recovery fast spin-echo T2 body coil sizes XL, (axial T2-FRFSE-XL), Axial in-phase/out-of-phase, Axial/ coronal three-dimensional liver acquisition with volume acceleration (3D coronal pre lava). Results: For comparation, only patients with liver focal lesions were included in the study, and and patient were examined with both diagnostic imaging modalities (CT and MRI). 168 patients with liver tumor pathologies and biliary tree tumor pathologies are included in the study. Gender ratio was 85 males and 83 female (M/F ratio 1.03:1). Average age of patients was 58.41 years, (minimum age 1.5 years old and maximum 88 years of age). The most frequent age on diagnosis was 61 - 70 years (total of 49 patients or 29.16%). Benign tumors were found with 93 patients (55.35%) and malignant tumors in 79 patients (47.02%). Distribution in liver parenchyma was found in 113 patients (67.26%), while in 49 patients (29.17%) pathology was found in the biliary tract. The most affected liver segment was the fifth segment in 35 patients (20.83%), while the less affected segment was the second liver segment in 8 patients (4.73%). most of patients (62 patients or 36.90%) had more than two affected segments in time of diagnosis. Diagnostic criteria in this study require further future evaluation. Conclusion: Early diagnosis of are tumors remains a real challenge and has great impact in the survival rate of patients. Finally, our study showed that for our country’s institutions that there was no significant difference between both CT and MRI modalities in liver focal lesions assessment.展开更多
目的评估MR灌注参数(K^(trans))和扩散参数(ADC)在不同脑肿瘤的相关关系。方法回顾性研究13例脑肿瘤(男8例女5例平均年龄54.6±17.7岁,其中胶质母细胞瘤3例,低级别-间变性胶质瘤4例,脑膜瘤3例,转移瘤3例。所有患者均行T_1WI动态对...目的评估MR灌注参数(K^(trans))和扩散参数(ADC)在不同脑肿瘤的相关关系。方法回顾性研究13例脑肿瘤(男8例女5例平均年龄54.6±17.7岁,其中胶质母细胞瘤3例,低级别-间变性胶质瘤4例,脑膜瘤3例,转移瘤3例。所有患者均行T_1WI动态对比增强MR灌注和扩散成像(Magnetom Trio,A Tim System 3.0 T,Siemens)。对每个病例,在相应的K^(trans)和ADC图上选取兴趣区。记录所有兴趣区的K^(trans)和ADC的最大值(max),平均值(mean),最小值(min),并进行Pearson相关分析。结果 K^(trans)(max)与ADC(min)及ADC(mean)呈明显负相关,Pearson相关系数分别为(r=-0.536,P<0.001)(r=-0.465,P<0.001)。K^(trans)(mean)与ADC(mean)呈明显负相关(r=-0.228,P=0.038)。K^(trans)(min)亦与ADC(max)呈明显负相关(r=-0.355,P<0.001)。结论不论脑肿瘤的类型,ADC值与K^(trans)值始终呈负相关,这些发现说明微血管渗透性、肿瘤微环境等因素,可能调节和/或影响肿瘤细胞数量、缺血性损伤及复杂的细胞外环境变化。展开更多
文摘According to the World Health Organization(WHO),Brain Tumors(BrT)have a high rate of mortality across the world.The mortality rate,however,decreases with early diagnosis.Brain images,Computed Tomography(CT)scans,Magnetic Resonance Imaging scans(MRIs),segmentation,analysis,and evaluation make up the critical tools and steps used to diagnose brain cancer in its early stages.For physicians,diagnosis can be challenging and time-consuming,especially for those with little expertise.As technology advances,Artificial Intelligence(AI)has been used in various domains as a diagnostic tool and offers promising outcomes.Deep-learning techniques are especially useful and have achieved exquisite results.This study proposes a new Computer-Aided Diagnosis(CAD)system to recognize and distinguish between tumors and non-tumor tissues using a newly developed middleware to integrate two deep-learning technologies to segment brain MRI scans and classify any discovered tumors.The segmentation mechanism is used to determine the shape,area,diameter,and outline of any tumors,while the classification mechanism categorizes the type of cancer as slow-growing or aggressive.The main goal is to diagnose tumors early and to support the work of physicians.The proposed system integrates a Convolutional Neural Network(CNN),VGG-19,and Long Short-Term Memory Networks(LSTMs).A middleware framework is developed to perform the integration process and allow the system to collect the required data for the classification of tumors.Numerous experiments have been conducted on different five datasets to evaluate the presented system.These experiments reveal that the system achieves 97.98%average accuracy when the segmentation and classification functions were utilized,demonstrating that the proposed system is a powerful and valuable method to diagnose BrT early using MRI images.In addition,the system can be deployed in medical facilities to support and assist physicians to provide an early diagnosis to save patients’lives and avoid the high cost of treatments.
基金financial support from the National Science Foundation(DMR-1905818 and REU Grant CHE1062840,USA)the Robert A.Welch Foundation through the W.T.Doherty-Welch Chair in Chemistry(A-0001,USA)。
文摘To expand the single-dose duration over which noninvasive clinical and preclinical cancer imaging can be conducted with high sensitivity,and well-defined spatial and temporal resolutions,a facile strategy to prepare ultrasmall nanoparticulate X-ray contrast media(nano-XRCM)as dual-modality imaging agents for positron emission tomography(PET)and computed tomography(CT)has been established.Synthesized from controlled copolymerization of triiodobenzoyl ethyl acrylate and oligo(ethylene oxide)acrylate monomers,the amphiphilic statistical iodocopolymers(ICPs)could directly dissolve in water to afford thermodynamically stable solutions with high aqueous iodine concentrations(>140 mg iodine/mL water)and comparable viscosities to conventional small molecule XRCM.The formation of ultrasmall iodinated nanoparticles with hydrodynamic diameters of ca.10 nm in water was confirmed by dynamic and static light scattering techniques.In a breast cancer mouse model,in vivo biodistribution studies revealed that the64Cu-chelator-functionalized iodinated nano-XRCM exhibited extended blood residency and higher tumor accumulation compared to typical small molecule imaging agents.PET/CT imaging of tumor over 3 days showed good correlation between PET and CT signals,while CT imaging allowed continuous observation of tumor retention even after 10 days post-injection,enabling longitudinal monitoring of tumor retention for imaging or potentially therapeutic effect after a single administration of nano-XRCM.
文摘Background: Tumor pathologies of the liver and bile ducts are relatively commonly diagnosed and the primary goal is to differentiate these lesions in the fastest possible time which determines the apropriate method of treatment. Aims and Objectives: Aim of this study is tracking and diagnostic imaging correlation of tumor pathologies of liver and bile ducts and determining the early diagnostic approach. Data obtained from this study are important for treatment procedures and succes of treatment. All cases with liver tumor pathologies from period 2012-2016 were examined with CT and MRI followed by other complementary imaging methods. Methods: CT examination was performed according to standard triple-phase protocol: non-enhanced phase, arterial phase and porto-venous phase, and in some cases with late phase after 5 minutes. In MRI examinations, standard protocol was performed: coronal T2 single-shot fast spin-echo (coronal T2 SSFs), Axial T2 respiratory-triggered fast spin-echo (axial T2-FRE)/or breath-hold fast-recovery fast spin-echo T2 body coil sizes XL, (axial T2-FRFSE-XL), Axial in-phase/out-of-phase, Axial/ coronal three-dimensional liver acquisition with volume acceleration (3D coronal pre lava). Results: For comparation, only patients with liver focal lesions were included in the study, and and patient were examined with both diagnostic imaging modalities (CT and MRI). 168 patients with liver tumor pathologies and biliary tree tumor pathologies are included in the study. Gender ratio was 85 males and 83 female (M/F ratio 1.03:1). Average age of patients was 58.41 years, (minimum age 1.5 years old and maximum 88 years of age). The most frequent age on diagnosis was 61 - 70 years (total of 49 patients or 29.16%). Benign tumors were found with 93 patients (55.35%) and malignant tumors in 79 patients (47.02%). Distribution in liver parenchyma was found in 113 patients (67.26%), while in 49 patients (29.17%) pathology was found in the biliary tract. The most affected liver segment was the fifth segment in 35 patients (20.83%), while the less affected segment was the second liver segment in 8 patients (4.73%). most of patients (62 patients or 36.90%) had more than two affected segments in time of diagnosis. Diagnostic criteria in this study require further future evaluation. Conclusion: Early diagnosis of are tumors remains a real challenge and has great impact in the survival rate of patients. Finally, our study showed that for our country’s institutions that there was no significant difference between both CT and MRI modalities in liver focal lesions assessment.
文摘目的评估MR灌注参数(K^(trans))和扩散参数(ADC)在不同脑肿瘤的相关关系。方法回顾性研究13例脑肿瘤(男8例女5例平均年龄54.6±17.7岁,其中胶质母细胞瘤3例,低级别-间变性胶质瘤4例,脑膜瘤3例,转移瘤3例。所有患者均行T_1WI动态对比增强MR灌注和扩散成像(Magnetom Trio,A Tim System 3.0 T,Siemens)。对每个病例,在相应的K^(trans)和ADC图上选取兴趣区。记录所有兴趣区的K^(trans)和ADC的最大值(max),平均值(mean),最小值(min),并进行Pearson相关分析。结果 K^(trans)(max)与ADC(min)及ADC(mean)呈明显负相关,Pearson相关系数分别为(r=-0.536,P<0.001)(r=-0.465,P<0.001)。K^(trans)(mean)与ADC(mean)呈明显负相关(r=-0.228,P=0.038)。K^(trans)(min)亦与ADC(max)呈明显负相关(r=-0.355,P<0.001)。结论不论脑肿瘤的类型,ADC值与K^(trans)值始终呈负相关,这些发现说明微血管渗透性、肿瘤微环境等因素,可能调节和/或影响肿瘤细胞数量、缺血性损伤及复杂的细胞外环境变化。
