检索结果-内蒙古大学图书馆

Machine Learning Algorithms Utilizing Quantitative CT Features May Predict Eventual Onset of Bronchiolitis Obliterans Syndrome After Lung Transplantation

引用

ACADEMIC RADIOLOGY 2018年第9期25卷 1201-1212页

作者： Barbosa, Eduardo J. Mortani, Jr. Lanclus, Maarten Vos, Wim Van Holsbeke, Cedric De Backer, William De Backer, Jan Lee, James Univ Penn Sch Med Dept Radiol Perelman Sch Med 3400 Spruce St Philadelphia PA 19104 USA Univ Penn Sch Med Dept Med Perelman Sch Med 3400 Spruce St Philadelphia PA 19104 USA FLUIDDA Nv Kontich Belgium Univ Hosp Antwerp Dept Resp Med Edegem Belgium

Rationale and Objectives: Long-term survival after lung transplantation (LTx) is limited by bronchiolitis obliterans syndrome (BOS), defined as a sustained decline in forced expiratory volume in the first second (FEV1) not explained by other causes. We assessed whether machine learning (ML) utilizing quantitative computed tomography (qCT) metrics can predict eventual development of BOS. Materials and Methods: Paired inspiratory-expiratory CT scans of 71 patients who underwent LTx were analyzed retrospectively (BOS [n = 41] versus non-BOS [n = 30]), using at least two different time points. The BOS cohort experienced a reduction in FEV1 of >10% compared to baseline FEV1 post LTx. Multifactor analysis correlated declining FEV1 with qCT features linked to acute inflammation or BOS onset. Student t test and ML were applied on baseline qCT features to identify lung transplant patients at baseline that eventually developed BOS. Results: The FEV1 decline in the BOS cohort correlated with an increase in the lung volume (P = .027) and in the central airway volume at functional residual capacity (P = .018), not observed in non-BOS patients, whereas the non-BOS cohort experienced a decrease in the central airway volume at total lung capacity with declining FEV1 (P = .039). Twenty-three baseline qCT parameters could significantly distinguish between non-BOS patients and eventual BOS developers (P < .05), whereas no pulmonary function testing parameters could. Using ML methods (support vector machine), we could identify BOS developers at baseline with an accuracy of 85%, using only three qCT parameters. Conclusions: ML utilizing qCT could discern distinct mechanisms driving FEV1 decline in BOS and non-BOS LTx patients and predict eventual onset of BOS. This approach may become useful to optimize management of LTx patients.

关键词： Lung transplantation quantitative CT metrics computer-assisted image processing lung transplant rejection bronchiolitis obliterans syndrome

来源：评论

学校读者我要写书评

暂无评论

Radiomic features from pretreatment biparametric MRI predict prostate cancer biochemical recurrence: Preliminary findings

引用

JOURNAL OF MAGNETIC RESONANCE IMAGING 2018年第6期48卷 1626-1636页

作者： Shiradkar, Rakesh Ghose, Soumya Jambor, Ivan Taimen, Pekka Ettala, Otto Purysko, Andrei S. Madabhushi, Anant Case Western Reserve Univ Dept Biomed Engn 10900 Euclid Ave Cleveland OH 44106 USA Univ Turku Dept Diagnost Radiol Turku Finland Icahn Sch Med Mt Sinai Dept Radiol New York NY 10029 USA Univ Turku Inst Biomed Turku Finland Turku Univ Hosp Dept Pathol Turku Finland Turku Univ Hosp Dept Urol Turku Finland Cleveland Clin Imaging Inst Sect Abdominal Imaging Cleveland OH 44106 USA Cleveland Clin Imaging Inst Nucl Radiol Dept Cleveland OH 44106 USA

Background Radiomics or computer-extracted texture features derived from MRI have been shown to help quantitatively characterize prostate cancer (PCa). Radiomics have not been explored depth in the context of predicting biochemical recurrence (BCR) of PCa. Purpose To identify a set of radiomic features derived from pretreatment biparametric MRI (bpMRI) that may be predictive of PCa BCR. Study Type Retrospective. Subjects In all, 120 PCa patients from two institutions, I-1 and I-2, partitioned into training set D-1 (N=70) from I-1 and independent validation set D-2 (N=50) from I-2. All patients were followed for 3 years. Sequence 3T, T-2-weighted (T2WI) and apparent diffusion coefficient (ADC) maps derived from diffusion-weighted sequences. Assessment PCa regions of interest (ROIs) on T2WI were annotated by two experienced radiologists. Radiomic features from bpMRI (T2WI and ADC maps) were extracted from the ROIs. A machine-learning classifier (C-BCR) was trained with the best discriminating set of radiomic features to predict BCR (p(BCR)). Statistical Tests Wilcoxon rank-sum tests with P<0.05 were considered statistically significant. Differences in BCR-free survival at 3 years using p(BCR) was assessed using the Kaplan-Meier method and compared with Gleason Score (GS), PSA, and PIRADS-v2. Results Distribution statistics of co-occurrence of local anisotropic gradient orientation (CoLlAGe) and Haralick features from T2WI and ADC were associated with BCR (P<0.05) on D-1. C-BCR predictions resulted in a mean AUC=0.84 on D-1 and AUC=0.73 on D-2. A significant difference in BCR-free survival between the predicted classes (BCR+and BCR-) was observed (P=0.02) on D-2 compared to those obtained from GS (P=0.8), PSA (P=0.93) and PIRADS-v2 (P=0.23). Data ConclusionRadiomic features from pretreatment bpMRI can be predictive of PCa BCR after therapy and may help identify men who would benefit from adjuvant therapy.

关键词： prostate cancer computer-assisted image processing magnetic resonance imaging recurrence projections and predictions

来源：评论

学校读者我要写书评

暂无评论

DCE MRI reveals early decreased and later increased placenta perfusion after a stress challenge during pregnancy in a mouse model

引用

PLACENTA 2018年 65卷 15-19页

作者： Remus, Chressen Catharina Kording, Fabian Arck, Petra Solano, Emilia Sedlacik, Jan Adam, Gerhard Hecher, Kurt Forkert, Nils Daniel Univ Med Ctr Hamburg Eppendorf Ctr Radiol & Endoscopy Dept Diagnost & Intervent Radiol & Nucl Med Martinistr 52 D-20246 Hamburg Germany Univ Med Ctr Hamburg Eppendorf Ctr Obstet & Paediat Dept Obstet & Fetal Med Martinistr 52 D-20246 Hamburg Germany Univ Med Ctr Hamburg Eppendorf Ctr Radiol & Endoscopy Dept Diagnost & Intervent Neuroradiol Martinistr 52 D-20246 Hamburg Germany Univ Calgary Dept Radiol 3330 Hosp Dr NW Calgary AB T2N 4N1 Canada Univ Calgary Hotchkiss Brain Inst 3330 Hosp Dr NW Calgary AB T2N 4N1 Canada

Objectives: Stress during pregnancy is known to have negative effects on fetal outcome. The purpose of this exploratory study was to examine placental perfusion alterations after stress challenge during pregnancy in a mouse model. Material and Methods: Seven Tesla MRI was performed on pregnant mice at embrionic day (ED) 14.5 and 16.5. Twenty dams were exposed to an established acoustic stress challenge model while twenty nonexposed dams served as controls. Placental perfusion was analyzed in dynamic contrast-enhanced (DCE) MRI using the steepest slope model. The two functional placental compartments, the highly vascularized labyrinth and the endocrine junctional zone, were assessed separately. Results: Statistical analysis revealed decreased perfusion levels in the stress group at ED 14.5 compared to controls in both placenta compartments. On ED 16.5, the perfusion level increased significantly in the stress group while placenta perfusion in controls remained similar or even slightly decreased leading to an overall increased perfusion in the stress group on ED 16.5 compared to controls. Conclusion: MR imaging allows noninvasive placenta perfusion assessment in this fetal stress mimicking animal model. In this exploratory study, we demonstrated that stress challenge during pregnancy leads to an initial reduction followed by an increase of placenta perfusion. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Magnetic resonance imaging Placenta Perfusion computer-assisted image processing IUGR

来源：评论

学校读者我要写书评

暂无评论

Fully automated contour detection of the ascending aorta in cardiac 2D phase-contrast MRI

引用

MAGNETIC RESONANCE IMAGING 2018年 47卷 77-82页

作者： Codari, Marina Scarabello, Marco Secchi, Francesco Sforza, Chiarella Baselli, Giuseppe Sardanelli, Francesco IRCCS Policlin San Donato Unit Radiol Via Morandi 30 I-20097 Milan Italy Univ Milan Postgrad Sch Radiodiagnost Via Festa Perdono 7 I-20122 Milan Italy Univ Milan Dept Biomed Sci Hlth Via Mangiagalli 31 I-20133 Milan Italy Politecn Milan Dept Elect Informat & Bioengn Piazza Leonardo Da Vinci 32 I-20133 Milan Italy Univ Milan Dept Biomed Sci Hlth Via Morandi 30 I-20097 Milan Italy

Purpose: In this study we proposed a fully automated method for localizing and segmenting the ascending aortic lumen with phase-contrast magnetic resonance imaging (PC-MRI). Material and methods: Twenty-five phase-contrast series were randomly selected out of a large population dataset of patients whose cardiac MRI examination, performed from September 2008 to October 2013, was unremarkable. The local Ethical Committee approved this retrospective study. The ascending aorta was automatically identified on each phase of the cardiac cycle using a priori knowledge of aortic geometry. The frame that maximized the area, eccentricity, and solidity parameters was chosen for unsupervised initialization. Aortic segmentation was performed on each frame using active contouring without edges techniques. The entire algorithm was developed using Matlab R2016b. To validate the proposed method, the manual segmentation performed by a highly experienced operator was used. Dice similarity coefficient, Bland-Altman analysis, and Pearson's correlation coefficient were used as performance metrics. Results: Comparing automated and manual segmentation of the aortic lumen on 714 images, Bland-Altman analysis showed a bias of -6.68 mm(2), a coefficient of repeatability of 91.22 mm(2), a mean area measurement of 581.40 mm(2), and a reproducibility of 85%. Automated and manual segmentation were highly correlated (R = 0.98). The Dice similarity coefficient versus the manual reference standard was 94.6 +/- 2.1% (mean +/- standard deviation). Conclusion: A fully automated and robust method for identification and segmentation of ascending aorta on PC-MRI was developed. Its application on patients with a variety of pathologic conditions is advisable.

关键词： Aorta Magnetic resonance imaging computer-assisted image processing

来源：评论

学校读者我要写书评

暂无评论

Correlation-based perfusion mapping using time-resolved MR angiography: A feasibility study for patients with suspicions of steno-occlusive craniocervical arteries

引用

EUROPEAN RADIOLOGY 2018年第11期28卷 4890-4899页

作者： Nam, Yoonho Jang, Jinhee Park, Sonya Youngju Choi, Hyun Seok Jung, So-Lyung Ahn, Kook-Jin Kim, Bum-soo Catholic Univ Korea Seoul St Marys Hosp Coll Med Dept Radiol 222 Banpo Daero Seoul 06591 South Korea

Purpose To explore the feasibility of using correlation-based time-delay (CTD) maps produced from time-resolved MR angiography (TRMRA) to diagnose perfusion abnormalities in patients suspected to have steno-occlusive lesions in the craniocervical arteries. Materials and methods Twenty-seven patients who were suspected to have steno-occlusive lesions in the craniocervical arteries underwent both TRMRA and brain single-photon emission computed tomography (SPECT). TRMRA was performed on the supra-aortic area after intravenous injection of a 0.03 mmol/kg gadolinium-based contrast agent. Time-to-peak (TTP) maps and CTD maps of the brain were automatically generated from TRMRA data, and their quality was assessed. Detection of perfusion abnormalities was compared between CTD maps and the time-series maximal intensity projection (MIP) images from TRMRA and TTP maps. Correlation coefficients between quantitative changes in SPECT and parametric maps for the abnormal perfusion areas were calculated. Results The CTD maps were of significantly superior quality than TTP maps (p < 0.01). For perfusion abnormality detection, CTD maps (kappa 0.84, 95% confidence interval [CI] 0.67-1.00) showed better agreement with SPECT than TTP maps (0.66, 0.46-0.85). For perfusion deficit detection, CTD maps showed higher accuracy (85.2%, 95% CI 66.3-95.8) than MIP images (66.7%, 46-83.5), with marginal significance (p = 0.07). In abnormal perfusion areas, correlation coefficients between SPECT and CTD (r = 0.74, 95% CI 0.34-0.91) were higher than those between SPECT and TTP (r = 0.66, 0.20-0.88). Conclusion CTD maps generated from TRMRA were of high quality and offered good diagnostic performance for detecting perfusion abnormalities associated with steno-occlusive arterial lesions in the craniocervical area.

关键词： Magnetic resonance angiography Perfusion Stenosis computer-assisted image processing Comparative study

来源：评论

学校读者我要写书评

暂无评论

Multimodal quantitative magnetic resonance imaging analysis with individualized postprocessing in patients with drug-resistant focal epilepsy and conventional visual inspection negative for epileptogenic lesions

引用

CLINICS 2019年 74卷 e908-e908页

作者： Abud, Lucas Giansante Velasco, Tonicarlo Rodrigues Garrido Salmon, Carlos Ernesto Sakamoto, Americo Ceiki Abud, Thiago Giansante Pessini, Rodrigo Antonio Abud, Daniel Giansante Leite, Joao Pereira dos Santos, Antonio Carlos Univ Sao Paulo Fac Med Ribeirao Preto Div Neurorradiol Ribeirao Preto SP Brazil Univ Sao Paulo Fac Med Ribeirao Preto Dept Neurol Ribeirao Preto SP Brazil Univ Sao Paulo Fac Filosofia Ciencias & Letras Ribeirao Preto Dept Fis & Matemat Ribeirao Preto SP Brazil Univ Fed Sao Paulo Escola Paulista Med Dept Diagnost Imagem Sao Paulo SP Brazil Univ Sao Paulo Fac Med Ribeirao Preto Div Ciencias Imagem & Fis Med Ribeirao Preto SP Brazil

OBJECTIVES: Approximately one-third of candidates for epilepsy surgery have no visible abnormalities on conventional magnetic resonance imaging. This is extremely discouraging, as these patients have a less favorable prognosis. We aimed to evaluate the utility of quantitative magnetic resonance imaging in patients with drug-resistant neocortical focal epilepsy and negative imaging. METHODS: A prospective study including 46 patients evaluated through individualized postprocessing of five quantitative measures: cortical thickness, white and gray matter junction signal, relaxation rate, magnetization transfer ratio, and mean diffusivity. Scalp video-electroencephalography was used to suggest the epileptogenic zone. A volumetric fluid-attenuated inversion recovery sequence was performed to aid visual inspection. A critical assessment of follow-up was also conducted throughout the study. RESULTS: In the subgroup classified as having an epileptogenic zone, individualized postprocessing detected abnormalities within the region of electroclinical origin in 9.7% to 31.0% of patients. Abnormalities outside the epileptogenic zone were more frequent, up to 51.7%. In five patients initially included with negative imaging, an epileptogenic structural abnormality was identified when a new visual magnetic resonance imaging inspection was guided by information gleaned from postprocessing. In three patients, epileptogenic lesions were detected after visual evaluation with volumetric fluid-attenuated sequence guided by video electroencephalography. CONCLUSION: Although quantitative magnetic resonance imaging analyses may suggest hidden structural lesions, caution is warranted because of the apparent low specificity of these findings for the epileptogenic zone. Conversely, these methods can be used to prevent visible lesions from being ignored, even in referral centers. In parallel, we need to highlight the positive contribution of the volumetric fluid-attenuated sequence.

关键词： Drug-Resistant Epilepsy Magnetic Resonance Imaging Multimodal Imaging computer-assisted image processing

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Screentone Patterns of Manga Characters

Synthesis of Screentone Patterns of Manga Characters

引用

IEEE International Symposium on Multimedia

作者： Koki Tsubota Daiki Ikami Kiyoharu Aizawa The University of Tokyo Tokyo Japan

ISBN: (数字)9781728156064

ISBN: (纸本)9781728156071

Manga or Japanese comics are a popular medium and their images comprise line drawings and screentones. This study investigates the screentone synthesis task that involves translation from line drawings to manga images. Screentones have regular patterns that are difficult to synthesize. To address this problem, we propose a method to translate line drawings into manga images by generating pixel-wise screentone class labels instead of generating manga images directly. To train a screentone label generator, we create paired data of line drawings and pixel-wise screentone class labels that we obtain by applying to manga images a screentone removal and a screentone classifier, respectively. We train the screentone classifier using paired data of simulated manga images and pixel-wise screentone class labels. In tests, we conduct post-processing to reduce noise in the generated pixel-wise screentone labels. Experiments show that our proposed method produces reasonable screentone patterns. In comparison with results obtained using a baseline method of image-to-image translations, our results are comparable or more visually appealing.

关键词： Manga Screentone image processing and computer vision image generation Line drawings image generation Paired Data images baseline method computer-assisted image processing synthesis

来源：评论

学校读者我要写书评

暂无评论

Radiomics of liver MRI predict metastases in mice

引用

EUROPEAN RADIOLOGY EXPERIMENTAL 2018年第1期2卷 1-10页

作者： Becker, Anton S. Schneider, Marcel A. Wurnig, Moritz C. Wagner, Matthias Clavien, Pierre A. Boss, Andreas Univ Hosp Zurich Inst Diagnost & Intervent Radiol Raemistr 100 CH-8091 Zurich Switzerland Univ Hosp Zurich Div Transplantat & Visceral Surg Raemistr 100 CH-8091 Zurich Switzerland

Background The purpose of this study was to investigate whether any texture features show a correlation with intrahepatic tumor growth before the metastasis is visible to the human eye. Methods Eight male C57BL6 mice (age 8-10 weeks) were injected intraportally with syngeneic MC-38 colon cancer cells and two mice were injected with phosphate-buffered saline (sham controls). Small animal magnetic resonance imaging (MRI) at 4.7 T was performed at baseline and days 4, 8, 12, 16, and 20 after injection applying a T2-weighted spin-echo sequence. Texture analysis was performed on the images yielding 32 texture features derived from histogram, gray-level co-occurrence matrix, gray-level run-length matrix, and gray-level size-zone matrix. The features were examined with a linear regression model/Pearson correlation test and hierarchical cluster analysis. From each cluster, the feature with the lowest variance was selected. Results Tumors were visible on MRI after 20 days. Eighteen features from histogram and the gray-level-matrices exhibited statistically significant correlations before day 20 in the experiment group, but not in the control animals. Cluster analysis revealed three distinct clusters of independent features. The features with the lowest variance were Energy, Short Run Emphasis, and Gray Level Non-Uniformity. Conclusions Texture features may quantitatively detect liver metastases before they become visually detectable by the radiologist.

关键词： Colorectal neoplasms computer-assisted image processing Liver Magnetic resonance imaging (MRI) Neoplasm micrometastases

来源：评论

学校读者我要写书评

暂无评论

Virtual Dental Patient: How Long Until It’s Here?

引用

Current Oral Health Reports 2018年第2期5卷 116-120页

作者： Joda, Tim Wolfart, Stefan Reich, Sven Zitzmann, Nicola U. Department of Reconstructive Dentistry & Gerodontology School of Dental Medicine University of Bern Freiburgstr. 7 Bern 3010 Switzerland Department of Reconstructive Dentistry University Center for Dental Medicine Basel University of Basel Basel Switzerland Department of Prosthodontics & Biomaterials Center for Implantology Medical Faculty RWTH Aachen University Aachen Germany

Purpose of Review: Recent developments in digital technology to be generated by superimposing different 3D imaging datasets. The aim of this literature review was to provide an update on the current status of knowledge, to report on the progress in virtual patient science, and to identify further research needed to facilitate the translation to clinical practice. Recent Findings: Case reports were identified describing different dental patient simulation techniques. Publications focused mainly on methodological feasibility of combining skeletal, facial, and dental imaging to produce virtual simulations. Clinical randomized controlled trials were scarce. Summary: Superimposition of 3D medical data files is a feasible technique to create a virtual patient under static conditions. 3D image fusion is of interest and importance in all fields of dental medicine including diagnostics, treatment, science, and education. Future research should focus on simplifying the technology, to enable virtual patient simulation to be generated in a single-step approach. © 2018, Springer International Publishing AG, part of Springer Nature.

关键词： computer-assisted image processing Digital dental medicine image fusion Patient simulation Superimposition technique Three-dimensional imaging

来源：评论

学校读者我要写书评

暂无评论

Quantification of dental plaque in oral cavity was enabled by a novel algorithm of image processing

引用

JOURNAL OF ORAL BIOSCIENCES 2017年第3期59卷 157-162页

作者： Sueishi, Naho Ohshima, Tomoko Oikawa, Takashi Takemura, Hiroshi Kasai, Mai Maeda, Nobuko Nakamura, Yoshiki Tsurumi Univ Sch Dent Med Dept Orthodont Tsurumi Ku 2-1-3 Tsurumi Yokohama Kanagawa 2308501 Japan Tsurumi Univ Sch Dent Med Dept Oral Microbiol Tsurumi Ku 2-1-3 Tsurumi Yokohama Kanagawa 2308501 Japan Tokyo Univ Sci Fac Sci & Technol Dept Mech Engn 2641 Yamazaki Noda Chiba 2788510 Japan

Objectives: Quantitative analysis of the biofilm has been critical for pathogenicity of oral diseases such as caries and periodontal disease. Currently, the plaque control record (PCR) is used most frequently to evaluate the presence of plaque on teeth, but no quantification methods exist so far. The aim of this study was to establish a method to quantify plaque adhesion on teeth. Methods: A novel algorithm and executing program was developed to calculate the staining volume of biofilm on plastic disks or extracted teeth inoculated by Streptococcus mutans from photographic image data. The biofilm's volume on plastic disks was determined using a confocal microscope, and correlations between image analysis data were analyzed. Subsequently, the amount of plaque in the oral cavity was clinically evaluated using this algorithm. Results: A strong correlation was observed between the biofilm's volume and the image analysis data. Similar results were also obtained with the biofilm model using extracted teeth. Clinically, it was revealed that an assessment of the amount of plaque adhesion for every tooth was possible, which could not be determined by PCR in the oral cavity. Conclusions: We successfully developed a novel method, designated "plaque volume ratio," to quantify the plaque accurately from photographic image data. Our findings indicated that this method may be useful for the evaluation of the amount of plaque on the surfaces of not only teeth but also dental materials in the oral cavity. (C) 2017 Japanese Association for Oral Biology. Published by Elsevier B.V. All rights reserved.

关键词： Dental plaque Biofilm Quantification computer-assisted image processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：