基于配准方法的颅脑CT图像病变信息自动提取算法

医学图像中病变信息的计算机自动提取是实现计算机智能辅助诊断的关键与难点,本研究的目的就是提出一个解决该难题的算法,称之为PATHOINFER。该算法的基本过程是首先选择一幅具有代表性的模板图像M0和一系列与其相应的正常图像样本Mi,利用非刚性配准分别建立表示“正常图像”灰度变化的灰度均值图谱,表示正常变异的统计概率图谱和反映其解剖结构空间关系的分割模板,以实现对“正常图像”的计算机描述。再通过M0与目标图像S的配准,达到“正常图像”与S在空间关系上的一致,然后通过S与“正常图像”的比较,利用模糊逻辑推理,自动检出S中的病变区域,并实现对其病变特征信息的自动提取。实验结果表明,PATHOINFER算法可自动地检出并分割病变区域,并能够自动地提取包括病变发生部位在内的特征信息,实现了计算机智能辅助诊断研究中病变信息自动提取的难题。

基于KFCM与多特征融合的皮肤镜病变区域提取

病变轮廓的检测是病灶提取、定性研究和探明病灶与其周围组织间关系的基础。针对皮肤镜图像病变区域灰度强度不均匀导致病变区域难以提取的问题,本文提出一种基于模糊核聚类算法(KFCM)与多特征融合的病变区域提取算法。首先,将原始图像进行模糊核聚类,把得到的聚类结果作为多特征融合轮廓提取模型的初始轮廓,其次利用轮廓曲线演化对图像全局信息与局部信息采用自适应加权,构建符号压力函数(Signed Pressure Force, SPF),最后利用轮廓曲线演化来分割图像,提取出病变区域。通过真实皮肤镜图像验证了提出的模型在SPF函数和自适应函数引入两方面均能提升提取性能,且在定性和定量对比评价上均优于其他方法,同时对噪声具有鲁棒性。

Rocket “Eruca sativa”:A salad herb with potential gastric anti-ulcer activity

AIM： To validate gastric anti-ulcer properties of Rocket ＂Eruca sativa＂ on experimentally-induced gastric secretion and ulceration in albino rats. METHODS： Gastric acid secretion studies were undertaken using pylorus-ligated rats. Gastric lesions in the rats were induced by noxious chemicals including ethanol, strong alkalis, indomethacin and hypothermic restraint stress. The levels of gastric wall mucus （GWM）, nonprotein sulfhydryls （NP-SH） and malondialdehyde （MDA） were also measured in the glandular stomach of rats following ethanol administration. The gastric tissue was also examined histologically. The extract was used in two doses （250 and 500 mg/kg body weight） in all experiments. RESULTS： In pylorus-ligated Shay rats, the ethanolic extract of Rocket ＂Eruca sativa L.＂ （EER） significantly and dose-dependently reduced the basal gastric acid secretion, titratable acidity and ruminal ulceration. Rocket extract significantly attenuated gastric ulceration induced by necrotizing agents （80% ethanol, 0.2 mol/L NaOH, 25% NaCl）, indomethacin and hypothermic restraint stress. The anti-ulcer effect was further confirmed histologically. On the other hand, the extract significantly replenished GWM and NP-SH levels, as well as the MDA level significantly reduced by extract pretreatment. CONCLUSION： Rocket extract possesses antisecretory, cytoprotective, and anti-ulcer activities against experimentally-induced gastric lesions. The anti-ulcer effect is possibly through prostaglandinmediated activity and/or through its anti-secretory and antioxidant properties.