Photoacoustic (PA) imaging with much deeper tissue penetration and better spatial resolution had been widely employed for the prevention and diagnosis of many diseases. In this study, a new type of hydrogen peroxide (H₂O2)-activated photoacoustic nanoprobe [Mn-AH nanoscale coordination polymer nanodots (NCPs)] was successfully synthesized by a simple one-step method in water phase containing 2,2′-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS), horse radish peroxidase (HRP), and manganese ion (Mn2+). After modification by polyethylene glycol (PEG), Mn-AH NCPs exhibited excellent stability and biocompatibility for in vivo H₂O₂-responsive chromogenic assay with great specificity and sensitivity. In the presence of H₂O₂, colorless ABTS would be converted by HRP into the oxidized form with strong near-infrared (NIR) absorbance, enabling photoacoustic detection of endogenous H₂O₂. Using H₂O₂-activated Mn-AH NCPs, we have successfully performed PA imaging and H₂O₂ detection of subcutaneous murine colon CT26 tumor and deep-seated orthotopic bladder tumor. Due to the inherent Mn element existence inside the Mn-AH, this nanoprobe also serves as a good T1-weighted magnetic resonance imaging (MRI) contrast agent simultaneously. Lastly, after accomplishing its imaging functions, the Mn-AH NCPs could be cleared out from the body without any long-term toxicity, providing a new opportunity for cancer diagnosis and treatment.Photoacoustic (PA) imaging with much deeper tissue penetration and better spatial resolution had been widely employed for the prevention and diagnosis of many diseases. In this study, a new type of hydrogen peroxide (H₂O2)-activated photoacoustic nanoprobe [Mn-AH nanoscale coordination polymer nanodots (NCPs)] was successfully synthesized by a simple one-step method in water phase containing 2,2′-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS), horse radish peroxidase (HRP), and manganese ion (Mn2+). After modification by polyethylene glycol (PEG), Mn-AH NCPs exhibited excellent stability and biocompatibility for in vivo H₂O₂-responsive chromogenic assay with great specificity and sensitivity. In the presence of H₂O₂, colorless ABTS would be converted by HRP into the oxidized form with strong near-infrared (NIR) absorbance, enabling photoacoustic detection of endogenous H₂O₂. Using H₂O₂-activated Mn-AH NCPs, we have successfully performed PA imaging and H₂O₂ detection of subcutaneous murine colon CT26 tumor and deep-seated orthotopic bladder tumor. Due to the inherent Mn element existence inside the Mn-AH, this nanoprobe also serves as a good T1-weighted magnetic resonance imaging (MRI) contrast agent simultaneously. Lastly, after accomplishing its imaging functions, the Mn-AH NCPs could be cleared out from the body without any long-term toxicity, providing a new opportunity for cancer diagnosis and treatment.

利用深度学习技术对颅脑核磁共振图像(MRI)中三叉神经区域进行自动检测可为后续三叉神经分割提供可靠的输入图像，有效解决了人工筛选三叉神经对临床医生专业素养要求高、耗时长等弊端。采用YOLO网络自动检测颅脑核磁共振图像中三叉神经区域提高推理速度，并系统性地评估NVIDIA TensorRT框架在不同计算平台下的推理性能。实验结果表明，通过YOLO目标检测网络能够准确检测出三叉神经所在的区域，同时在NVIDIA TensorRT框架下，当输入的颅脑MRI分辨率为(204×204)时，CPU平台、嵌入式GPU平台、桌面GPU平台及专业GPU计算卡平台下，YOLOv2网络检测优化后的三叉神经目标的每秒帧率分别可达到0.1 FPS, 23.4 FPS, 112.5FPS和793.7 FPS，这为后续开发便携式的三叉神经分割设备提供了可参考的重要依据。

为了自动定位头部核磁共振成像（Magnetic Resonance Imaging， MRI）中稳定解剖结构点，提出了一种基于沙漏网络（Hourglass Network， HN）的头部MRI图像解剖点自动定位方法。该方法使用HN的基本结构实现多尺度特征的提取与融合，并在融合多尺度特征时引入尺度注意力机制，提高解剖结构点的提取精度。利用DSNT（Differentiable Spatial to Numerical Transform）层将卷积神经网络生成的预测热图进行坐标回归来定位解剖点。500例头部MRI图像用于训练，300例图像用于测试，测试结果表明本文提出的方法对四个解剖点的定位准确率均超过了80%，与常用的关键点定位方法相比，该方法取得了最好的效果。该方法可辅助医生进行图像的解剖点标记，为头部图像的自动配准和头部疾病的大数据分析提供技术支持。

为了解决阿尔茨海默病3维正电子发射断层成像(PET)与核磁共振成像(MRI)相同位置强度不同问题, 同时保留MRI大脑皮质、脑回沟、海马体等的萎缩情况,首先将两幅源图像在统计参量图(SPM)中预处理, 再利用3维剪切波系统(ShearLab 3D)最优表达高维数据的能力对图像分解, 生成低高频子带, 并以方差作为阈值将高频子带分为中高频子带。低频子带使用3维扩展的加权局部能量与改进拉普拉斯算子的加权和加权的融合规则, 并引入锐化矩阵为权重参量, 使融合图像边缘清晰;中频子带以绝对值为活动度量增强图像的边缘信息;高频子带以3个3维底层特征加权融合规则增强图像的细节特征。最后, 利用ShearLab 3D逆变换获得PET/MRI图像。结果表明, ShearLab 3D变换的融合结果整体优于空域和小波变换; ShearLab 3D方法中将不同融合规则对比分析, 该算法融合结果的平均梯度、空间频率、边缘强度、综合熵分别提高了11.09%, 22.58%, 152.68%, 0.58%, 解决了边缘模糊、细节不清晰的问题。该研究为PET/MRI图像融合提供了参考。

准确可靠的脑胶质瘤分割是脑胶质瘤诊断、治疗方案制定和治疗效果评价的重要前提。为了有效针对脑胶质瘤MRI的特性和基于CNNs的脑胶质瘤分割方法的不足, 提出了一种融合三个密集连接型2D-CNNs分割结果的方法。将三维多模态MRI数据沿轴状面、冠状面和矢状面切片化, 并在预处理后的切片上按比例截取33×33大小的图像块, 得到三个视图的训练集; 将三个训练集分别送入到密集连接型2D-CNNs模型中进行训练, 得到三个分割模型; 然后, 将测试病人的各视图图像块依次输入到训练好的分割模型, 得到脑胶质瘤三个视图的粗分割结果; 将三个视图的粗分割结果进行融合处理和后处理, 得到脑胶质瘤的最终分割结果, 并具体划分为水肿、增强和坏死/非增强三种区域。本研究包含了BraTS2018和BraTS2013的数据集并利用Dice系数、阳性预测值、灵敏度三个指标对分割结果进行评价。实验结果表明, 所提出的分割方法不仅能够精确的分割脑胶质瘤, 而且可以利用多个2D-CNNs实现脑胶质瘤的三维分割。

非Gd型T1造影剂的开发是近年来MRI造影剂的重要研究方向。本工作通过高温热分解法制备了粒径为(3.02±0.62)nm的掺杂Zn的氧化铁纳米颗粒(ZnFe2O4), 其r1弛豫度为2.5 L/(mmol·s), r2/r1比值为2.2。合成方法简便、经济, 容易实现大量制备。以生物相容性的PO-PEG分子对颗粒进行修饰, 使颗粒相转移至水溶液中, 可保持长期稳定分散。最后, 以ZnFe2O4为造影剂, 对小鼠肿瘤部位进行MR成像, 获得~11%的信号增强。本研究工作显示ZnFe2O4@PO-PEG具备作为高安全性非钆型T1造影剂并应用于实际MR造影成像的良好潜力。

Magnetic resonance imaging (MRI) has been a prevalence technique for breast cancer diagnosis. Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRIbased disease analysis. There are two main issues of the existing breast lesion segmentation techniques: requiring manual delineation of Regions of Interests (ROIs) as a step of initialization; and requiring a large amount of labeled images for model construction or parameter learning, while in real clinical or experimental settings, it is highly challenging to get su±cient labeled MRIs. To resolve these issues, this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies. After image segmentation with advanced cluster techniques, we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI. To obtain the optimal performance of tumor extraction, we take extensive experiments to learn parameters for tumor segmentation and classification, and design 225 classifiers corresponding to different parameter settings. We call the proposed method as Semi-supervised Tumor Segmentation (SSTS), and apply it to both mass and nonmass lesions. Experimental results show better performance of SSTS compared with five state-of-the-art methods.

上转换发光纳米颗粒是一类遵循反斯托克斯原理的新型发光材料, 具有发光强度高、发光稳定、无组织背景荧光、无光漂白、低毒性以及较好的生物相容性等优点, 其激发光为红外或者近红外光, 活体组织穿透深度高, 在生物医学检测、诊断以及疾病治疗等方面均具有潜在的应用价值。磁共振成像是目前医学临床常用的影像检测手段之一, 具有软组织成像质量高、空间分辨率高、无辐射、无损伤等优点, 在心脑血管、肿瘤等疾病的影像诊断方面具有重要作用。本文将聚焦于近年来稀土上转换发光纳米材料在磁共振影像方面的研究进展, 通过介绍磁共振成像机理、磁共振造影剂的构建、上转换发光纳米材料的设计及在磁共振医学影像、疾病治疗等方面的应用, 并结合我们课题组基于UCNP医学磁共振多模态影像的相关研究进展, 对上转换发光纳米颗粒在磁共振成像方面的应用研究进行探讨和展望。

Here, we report a new method using combined magnetic resonance (MR)–Photoacoustic (PA)– Thermoacoustic (TA) imaging techniques, and demonstrate its unique ability for in vivo cancer detection using tumor-bearing mice. Circular scanning TA and PA imaging systems were used to recover the dielectric and optical property distributions of three colon carcinoma bearing mice While a 7.0-T magnetic resonance imaging (MRI) unit with a mouse body volume coil was utilized for high resolution structural imaging of the same mice. Three plastic tubes filled with soybean sauce were used as fiducial markers for the co-registration of MR, PA and TA images. The resulting fused images provided both enhanced tumor margin and contrast relative to the surrounding normal tissues. In particular, some finger-like protrusions extending into the surrounding tissues were revealed in the MR/TA infused images. These results show that the tissue functional optical and dielectric properties provided by PA and TA images along with the anatomical structure by MRI in one picture make accurate tumor identification easier. This combined MR–PA–TA-imaging strategy has the potential to offer a clinically useful triplemodality tool for accurate cancer detection and for intraoperative surgical navigation.