为了提高磁共振图像分割的准确度, 提出一种基于残差网络和小波变换的磁共振图像分割方法。采用离散小波变换对核共振图像的不同序列进行融合, 使融合图像包含更加丰富的纹理信息和结构信息; 提出了包含通道注意力模块和空间注意力模块的残差网络模型, 使网络重点关注于目标分割区域, 并加入残差块来缓解深度神经网络的梯度消失问题。最终在公开的Brain Tumor Segmentation Challenge 2015数据集上完成了验证实验, 结果显示该方法在对完整肿瘤区域、核心肿瘤区域及增强肿瘤区域的平均 Dice 相似性系数均取得了较好的效果。

Photoacoustic imaging, which can provide the maximum intensity contrast in tissue depth imaging without ionizing radiation, will be a promising imaging trend for tumor detection. In this paper, a column diffusion fiber was employed to carry a pulsed laser for irradiating stomach directly through esophagus based on the characteristics of gastric tissue structure. A long focused ultrasonic transducer was placed outside the body to detect photoacoustic signals of gastric tissue. Phantom and in vitro experiments of submucosal gastric tumors were carried out to check the sensitivity of scanning photoacoustic tomography system, including the lateral and longitudinal resolution of the system, sensitivity of different absorption coe±cient in imaging, capability of transversal detection, and probability of longitudinal detection. The results demonstrate that our innovative technique can improve the parameters of imaging. The lateral resolution reaches 2.09 mm. Then a depth of 5.5mm with a longitudinal accuracy of 0.36mm below gastric mucosa of early gastric cancer (EGC) has been achieved. In addition, the optimal absorption coe±cient differences among absorbers of system are 3.3–3.9 times. Results indicate that our photoacoustic imaging (PAI) system, is based on a long focusing transducer, can provide a potential application for detecting submucosal EGC without obvious symptoms.

针对目前传统方法脑肿瘤检测准确率低的问题, 提出一种基于深度学习的三维脑肿瘤检测方法.首先将不同模态的脑肿瘤磁共振成像影像进行融合, 获取不同模态下的脑肿瘤病灶三维空间特征; 然后在卷积层和池化层之间增加实列归一化层, 提高网络的收敛速度, 缓解过拟合的问题; 并对损失函数进行改进, 采用加权损失函数加强对病灶区域的特征学习; 最后结合后处理方法解决假阳脑肿瘤病灶多的问题.实验结果表明：提出的脑肿瘤检测方法可有效进行肿瘤病灶定位; 相关性系数、敏感性和特异性三种评价指标分别达到了0.926 7、0.928 1和0.997 7, 与二维检测网络相比, 提高了4.6%、3.96%和0.04%, 较初始的单模态脑肿瘤检测方法提升了13.2%、10.42%和0.12%.

本文建立了一套微波热声实时成像系统, 该系统由脉冲微波发生器, 多元环形探测器, 多通道数据采集装置和数据重建装置共同组成。在实验中, 利用填充盐水的两个塑料管验证其实时成像的性能, 结果表明, 该系统能够实现每秒16.7帧的成像速度。随后, 对活体小鼠的正常区域和肿瘤区域分别进行热声成像, 得到肿瘤和正常区域的对比度为1.7∶1, 证明了该系统在肿瘤检测中有较高的对比度。最后, 利用该系统监控细管趋近离体肿瘤的过程。因此该系统有望应用于实时监测。综上所述, 该热声成像系统具有无损, 成像速度快和大视场的良好性能, 有望在生物医学中得到广泛的应用, 尤其在肿瘤筛查和实时监控方面发挥作用。

本文报道了一种一体化光声乳腺成像系统, 利用光纤束与柔性探测器相匹配形成一体化光声激发-耦合-探测, 因此与传统的光声成像系统相比, 该系统具有形态适应性的优势, 并可以实现大视场的光声成像。本文通过样品实验和离体乳腺肿瘤成像实验, 探究该系统的成像能力, 证明该系统具有大规模临床乳腺肿瘤筛查的潜力。

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.

拉曼光谱是基于拉曼散射效应而发展起来的一种光谱分析技术, 体现的是分子的振动或转动信息。 由于拉曼光谱技术与常规化学分析技术相比, 具有对样品无损、 样品制备简单和所需样品量少等特点, 广泛用于生物大分子结构变化的研究。 拉曼光谱不仅可以用于蛋白质、 核酸和脂类等生物大分子损伤的快速检测, 而且可以用于癌症的诊断与手术治疗。 通过对比正常组织与癌变组织的拉曼光谱, 可以找到两种组织特征吸收峰的差异, 从而为癌症的最终确诊和确定肿瘤切除范围提供重要信息。 文章综述了拉曼光谱检测生物大分子损伤的研究进展, 介绍了利用表面增强拉曼光谱、 傅里叶变换拉曼光谱和紫外共振拉曼光谱等技术在检测蛋白质二级结构、 膜脂及DNA损伤中的应用, 并展望了未来拉曼光谱技术的发展前景。

简要介绍了光声成像技术的基本原理，采集系统和成像算法。重点阐述了光声成像技术在肿瘤的早期检测和疗效监测，脑成像和脑功能监测以及临床血管监测等生物医学领域的应用。对光声成像技术应用前景进行了展望。