Both functional magnetic resonance imaging （fMRI） and diffusion tensor imaging （DTI） can provide different information of the human brain, so using the wavelet transform method can achieve a fusion of these two ty...Both functional magnetic resonance imaging （fMRI） and diffusion tensor imaging （DTI） can provide different information of the human brain, so using the wavelet transform method can achieve a fusion of these two types of image data and can effectively improve the depression recognition accuracy. Multi-resolution wavelet decomposition is used to transform each type of images to the frequency domain in order to obtain the frequency components of the images. To each subject, decomposition components of two images are then added up separately according to their frequencies. The inverse discrete wavelet transform is used to reconstruct the fused images. After that, principal component analysis （PCA） is applied to reduce the dimension and obtain the features of the fusion data before classification. Based on the features of the fused images, an accuracy rate of 80. 95 % for depression recognition is achieved using a leave-one-out cross-validation test. It can be concluded that this wavelet fusion scheme has the ability to improve the current diagnosis of depression.展开更多
Objective. To compare and match metabolic images of PET with anatomic images of CT and MRI. Methods. The CT or MRI images of the patients were obtained through a photo scanner, and then transferred to the remote works...Objective. To compare and match metabolic images of PET with anatomic images of CT and MRI. Methods. The CT or MRI images of the patients were obtained through a photo scanner, and then transferred to the remote workstation of PET scanner with a floppy disk. A fusion method was developed to match the 2- dimensional CT or MRI slices with the correlative slices of 3- dimensional volume PET images. Results. Twenty－ nine metabolically changed foci were accurately localized in 21 epilepsy patients’ MRI images, while MRI alone had only 6 true positive findings. In 53 cancer or suspicious cancer patients, 53 positive lesions detected by PET were compared and matched with the corresponding lesions in CT or MRI images, in which 10 lesions were missed. On the other hand, 23 lesions detected from the patients’ CT or MRI images were negative or with low uptake in the PET images, and they were finally proved as benign. Conclusions. Comparing and matching metabolic images with anatomic images helped obtain a full understanding about the lesion and its peripheral structures. The fusion method was simple, practical and useful for localizing metabolically changed lesions.展开更多
文摘目的评估经直肠超声与磁共振融合成像（transrectal ultrasound／magnetic resonance imaging，TRUS／MR）靶向穿刺技术（targetedbiopsy，TB）在首次诊断性前列腺穿刺中的价值。方法回顾性分析2015年9月至2016年9月我院经多参数磁共振（multiparametric magnetic resonanceimaging，mpMRI）扫描发现可疑病灶，且前列腺影像报告和数据系统（prostate imaging and reporting and datasystem，PI—RADS）评分／〉3分的91例患者的临床资料，所有患者均为首次行诊断性穿刺。年龄46～83岁，中位年龄68岁。穿刺前血清PSA1．2～85．0ng／ml，中位PSA11．2ng／ml，其中PSA〈10ng／ml者36例，10～20ng／ml者30例，〉20ng／ml者25例。使用实时超声多影像融合系统对mpMRI提示的可疑病灶进行靶向穿刺2针，同时进行常规12针的系统穿刺。自身对照研究比较TB和系统穿刺的前列腺癌和临床有意义前列腺癌（clinically significant prostate cancer，CsPCa）的检出率。结果本组91例中，总的前列腺癌检出率为57．1％（52／91）。TB和系统穿刺前列腺癌的检出率分别为44．0％（40／91）和51．7％（47／91），差异无统计学意义（P=0．14）。CsPCa检出比例TB高于系统穿刺，分别为80．O％（32／40）和68．1％（32／47），但差异无统计学意义（P=0．21）。对于PI．RADS评分为5分和3分的病灶，TB的前列腺癌检出率分别为77．1％（27／35）和10．3％（3／29），差异有统计学意义（P〈0．001）。TB和系统穿刺前列腺癌的检出率在PSA〈10ng／ml[27．8％（10／36）和36．1％（13／36）]、10～20ng／ml[50．0％（15／30）和56．7％（17／30）]、〉20rig／ml[60．0％（15／25）和68．0％（17／25）]中差异均无统计学意义（均P〉0．05）。结论对位于不同PSA区间的首次诊断性前列腺穿刺患者，2针TRUS／MR融合成像TB可以获得与12针系统穿刺相似的前列腺癌检出率，同时，TB可检出更高比例的CsPCa。PI．RADS评分系统对选择合适患者进行TB穿刺有指导作用。
基金The National Natural Science Foundation of China(No.30900356,81071135)
文摘Both functional magnetic resonance imaging （fMRI） and diffusion tensor imaging （DTI） can provide different information of the human brain, so using the wavelet transform method can achieve a fusion of these two types of image data and can effectively improve the depression recognition accuracy. Multi-resolution wavelet decomposition is used to transform each type of images to the frequency domain in order to obtain the frequency components of the images. To each subject, decomposition components of two images are then added up separately according to their frequencies. The inverse discrete wavelet transform is used to reconstruct the fused images. After that, principal component analysis （PCA） is applied to reduce the dimension and obtain the features of the fusion data before classification. Based on the features of the fused images, an accuracy rate of 80. 95 % for depression recognition is achieved using a leave-one-out cross-validation test. It can be concluded that this wavelet fusion scheme has the ability to improve the current diagnosis of depression.
文摘Objective. To compare and match metabolic images of PET with anatomic images of CT and MRI. Methods. The CT or MRI images of the patients were obtained through a photo scanner, and then transferred to the remote workstation of PET scanner with a floppy disk. A fusion method was developed to match the 2- dimensional CT or MRI slices with the correlative slices of 3- dimensional volume PET images. Results. Twenty－ nine metabolically changed foci were accurately localized in 21 epilepsy patients’ MRI images, while MRI alone had only 6 true positive findings. In 53 cancer or suspicious cancer patients, 53 positive lesions detected by PET were compared and matched with the corresponding lesions in CT or MRI images, in which 10 lesions were missed. On the other hand, 23 lesions detected from the patients’ CT or MRI images were negative or with low uptake in the PET images, and they were finally proved as benign. Conclusions. Comparing and matching metabolic images with anatomic images helped obtain a full understanding about the lesion and its peripheral structures. The fusion method was simple, practical and useful for localizing metabolically changed lesions.
