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 MRI-based disease analysis.There are...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 MRI-based disease analysis.There are two main issues of the existing breast lesion segmentation techniques:requir ing 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 lear ning,while in real clinical or experimental settings,it is highly challenging to get suficient 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 opt imal performance of tumor extraction,we take extensive experiments to learn par ameters for tumor segmentation and dassification,and design 225 classifiers corresponding to diferent 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.展开更多
Background The onsets of needling sensation introduced by acupuncture stimulus can vary widely from subject to subject. This should be explicitly accounted for by the model blood oxygenation-level dependent (BOLD) t...Background The onsets of needling sensation introduced by acupuncture stimulus can vary widely from subject to subject. This should be explicitly accounted for by the model blood oxygenation-level dependent (BOLD) time course used in general linear model (GLM) analysis to obtain more consistent across-subject group results. However, in standard GLM analysis, the model BOLD time course obtained by convolving a canonical hemodynamic response function with an experimental paradigm time course is assumed identical across subjects. Although some added-on properties to the model BOLD time course, such as temporal and dispersion derivatives, may be used to account for different BOLD response onsets, they can only account for the BOLD onset deviations to the extent of less than one repetition time (TR). Methods In this study, we explicitly manipulated the onsets of model BOLD time course by shifting it with -2, -1, or 1 TR and used these temporally shifted BOLD model to analyze the functional magnetic resonance imaging (fMRI) data obtained from three acupuncture fMRI experiments with GLM analysis. One involved acupuncture stimulus on left ST42 acupoint and the other two on left GB40 and left BL64 acupoints. Results The model BOLD time course with temporal shifts, in addition to temporal and dispersion derivatives, could result in better statistical power of the data analysis in terms of the average correlation coefficients between the used BOLD models and extracted BOLD responses from individual subject data and the T-values of the activation clusters in the grouped random effects. Conclusions The GLM analysis with ordinary BOLD model failed to catch the large variability of the onsets of the BOLD responses associated with the acupuncture needling sensation. Shifts in time with more than a TR on model BOLD time course might be required to better extract the acupuncture stimulus-induced BOLD activities from individual fMRI data.展开更多
基金the National Natural Science Foundation of China(Grants No 61702274)the Natural Science Foundation of Jiangsu Province(Grants No BK20170958).
文摘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 MRI-based disease analysis.There are two main issues of the existing breast lesion segmentation techniques:requir ing 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 lear ning,while in real clinical or experimental settings,it is highly challenging to get suficient 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 opt imal performance of tumor extraction,we take extensive experiments to learn par ameters for tumor segmentation and dassification,and design 225 classifiers corresponding to diferent 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.
文摘Background The onsets of needling sensation introduced by acupuncture stimulus can vary widely from subject to subject. This should be explicitly accounted for by the model blood oxygenation-level dependent (BOLD) time course used in general linear model (GLM) analysis to obtain more consistent across-subject group results. However, in standard GLM analysis, the model BOLD time course obtained by convolving a canonical hemodynamic response function with an experimental paradigm time course is assumed identical across subjects. Although some added-on properties to the model BOLD time course, such as temporal and dispersion derivatives, may be used to account for different BOLD response onsets, they can only account for the BOLD onset deviations to the extent of less than one repetition time (TR). Methods In this study, we explicitly manipulated the onsets of model BOLD time course by shifting it with -2, -1, or 1 TR and used these temporally shifted BOLD model to analyze the functional magnetic resonance imaging (fMRI) data obtained from three acupuncture fMRI experiments with GLM analysis. One involved acupuncture stimulus on left ST42 acupoint and the other two on left GB40 and left BL64 acupoints. Results The model BOLD time course with temporal shifts, in addition to temporal and dispersion derivatives, could result in better statistical power of the data analysis in terms of the average correlation coefficients between the used BOLD models and extracted BOLD responses from individual subject data and the T-values of the activation clusters in the grouped random effects. Conclusions The GLM analysis with ordinary BOLD model failed to catch the large variability of the onsets of the BOLD responses associated with the acupuncture needling sensation. Shifts in time with more than a TR on model BOLD time course might be required to better extract the acupuncture stimulus-induced BOLD activities from individual fMRI data.