Comparison of supervised MRI segmentation methods for tumor volume determination during therapy

Two different multispectral pattern recognition methods are used to segment magnetic resonance images (MRI) of the brain for quantitative estimation of tumor volume and volume changes with therapy. A supervised k-nearest neighbor (kNN) rule and a semi-supervised fuzzy c-means (SFCM) method are used to segment MRI slice data. Tumor volumes as determined by the kNN and SFCM segmentation methods are compared with two reference methods, based on image grey scale, as a basis for an estimation of ground truth, namely: (a) a commonly used seed growing method that is applied to the contrast enhanced T₁-weighted image, and (b) a manual segmentation method using a custom-designed graphical user interface applied to the same raw image (T₁-weighted) dataset. Emphasis is placed on measurement of intra and inter observer reproducibility using the proposed methods. Intra- and interobserver variation for the kNN method was 9% and 5%, respectively. The results for the SFCM method was a little better at 6% and 4%, respectively. For the seed growing method, the intra-observer variation was 6% and the interobserver variation was 17%, significantly larger when compared with the multispectral methods. The absolute tumor volume determined by the multispectral segmentation methods was consistently smaller than that observed for the reference methods. The results of this study are found to be very patient case-dependent. The results for SFCM suggest that it should be useful for relative measurements of tumor volume during therapy, but further studies are required. This work demonstrates the need for minimally supervised or unsupervised methods for tumor volume measurements.     

Supervised Domain Adaptation for Automated Semantic Segmentation of the Atrial Cavity

Atrial fibrillation (AF) is the most common cardiac arrhythmia. At present, cardiac ablation is the main treatment procedure for AF. To guide and plan this procedure, it is essential for clinicians to obtain patient-specific 3D geometrical models of the atria. For this, there is an interest in automatic image segmentation algorithms, such as deep learning (DL) methods, as opposed to manual segmentation, an error-prone and time-consuming method. However, to optimize DL algorithms, many annotated examples are required, increasing acquisition costs. The aim of this work is to develop automatic and high-performance computational models for left and right atrium (LA and RA) segmentation from a few labelled MRI volumetric images with a 3D Dual U-Net algorithm. For this, a supervised domain adaptation (SDA) method is introduced to infer knowledge from late gadolinium enhanced (LGE) MRI volumetric training samples (80 LA annotated samples) to a network trained with balanced steady-state free precession (bSSFP) MR images of limited number of annotations (19 RA and LA annotated samples). The resulting knowledge-transferred model SDA outperformed the same network trained from scratch in both RA (Dice equals 0.9160) and LA (Dice equals 0.8813) segmentation tasks.     

Deep pancreas segmentation with uncertain regions of shadowed sets

Pancreas segmentation is a challenging task in medical image analysis especially for the patients with pancreatic cancer. First, the images often have poor contrast and blurred boundaries. Second, there exist large variations in gray scale, texture, location, shape and size among pancreas images. It becomes even worse with cases of pancreatic cancer. Besides, as an inevitable phenomenon, some of the slices have disconnected topology in pancreas part. All these problems lead to high segmentation uncertainties and make the results inaccurate. Existing pancreas segmentation methods rarely achieve sufficiently accurate and robust results especially for cancer cases. To tackle these problems, we propose a 2D deep learning-based method which can involve uncertainties in the process of segmentation iteratively. The proposed method describes the uncertain regions of pancreatic MRI images based on shadowed sets theory. The results are further corrected through increasing the weights of uncertain regions in iterative training. We evaluate our approach on a challenging pancreatic cancer MRI images dataset collected from the Changhai Hospital, and also validate our approach on the NIH pancreas segmentation dataset. The experimental results demonstrate that our proposed method outperforms the state-of-the-art methods in terms of the Dice similarity coefficient of 73.88% on cancer MRI dataset and 84.37% on NIH dataset respectively.     

面向对象的高分辨率遥感影像分割精度评价方法

在参考监督评价法原理的基础上,提出了三个高分辨率遥感影像分割精度评价指标:准确度、查全率和相对相似性,并以此为基础提出了遥感影像分割精度的评价方法。针对监督评价法的参考对象匹配问题,提出了一种双向局部最优对象匹配方法。同时,通过安徽省淮南市高分一号遥感影像分割结果的精度评价,进行了实验验证。结果表明:该评价指标能够较好地反映分割结果的优劣,符合地物对象分割的真实分布;还可为遥感影像分割算法的参数设置和多尺度分割的最优尺度选择提供依据。     

Magnetic resonance imaging segmentation techniques using batch-type learning vector quantization algorithms

In this article, we propose batch-type learning vector quantization (LVQ) segmentation techniques for the magnetic resonance (MR) images. Magnetic resonance imaging (MRI) segmentation is an important technique to differentiate abnormal and normal tissues in MR image data. The proposed LVQ segmentation techniques are compared with the generalized Kohonen's competitive learning (GKCL) methods, which were proposed by Lin et al. [Magn Reson Imaging 21 (2003) 863-870]. Three MRI data sets of real cases are used in this article. The first case is from a 2-year-old girl who was diagnosed with retinoblastoma in her left eye. The second case is from a 55-year-old woman who developed complete left side oculomotor palsy immediately after a motor vehicle accident. The third case is from an 84-year-old man who was diagnosed with Alzheimer disease (AD). Our comparisons are based on sensitivity of algorithm parameters, the quality of MRI segmentation with the contrast-to-noise ratio and the accuracy of the region of interest tissue. Overall, the segmentation results from batch-type LVQ algorithms present good accuracy and quality of the segmentation images, and also flexibility of algorithm parameters in all the comparison consequences. The results support that the proposed batch-type LVQ algorithms are better than the previous GKCL algorithms. Specifically, the proposed fuzzy-soft LVQ algorithm works well in segmenting AD MRI data set to accurately measure the hippocampus volume in AD MR images.     

An unmanned aerial vehicle identification and tracking system based on weakly supervised semantic segmentation technology

This paper presents an unmanned aerial vehicle (UAV) identification and tracking system aimed at monitoring UAVs based on weakly supervised semantic segmentation. A camera is equipped with a pan–tilt to collect images for semantic segmentation network in real time. The GrabCut+ algorithm and annotation boxes are employed to generate the UAV “pseudo pixel labels” for supervised model learning and reduce labelling costs. A new loss function combining the focus loss function and dice loss function is designed to balance positive and negative samples and improve the segmentation effect. The Mixup method is introduced for model training to prevent overfitting and enhance the generalization ability of the model. The semantic segmentation network outputs the prediction results by a fully connected conditional random field to smooth the target image. Furthermore, a region-based tracking method is proposed to solve the hysteresis problem of the pan–tilt control system and improve the system tracking performance. Finally, an experiment based on a dataset is carried out to prove the effectiveness of the segmentation algorithm with 66.3% mIoU. Considering that 10% of the central area of view is specified as the view centre, a UAV falling in the centre of the field accounts for more than 80% of this view area, demonstrating the real-time effectiveness of the designed UAV identification and tracking system.     

Dynamic pixel-wise weighting-based fully convolutional neural networks for left ventricle segmentation in short-axis MRI

Left ventricle (LV) segmentation in cardiac MRI is an essential procedure for quantitative diagnosis of various cardiovascular diseases. In this paper, we present a novel fully automatic left ventricle segmentation approach based on convolutional neural networks. The proposed network fully takes advantages of the hierarchical architecture and integrate the multi-scale feature together for segmenting the myocardial region of LV. Moreover, we put forward a dynamic pixel-wise weighting strategy, which can dynamically adjust the weight of each pixel according to the segmentation accuracy of upper layer and force the pixel classifier to take more attention on the misclassified ones. By this way, the LV segmentation performance of our method can be improved a lot especially for the apical and basal slices in cine MR images. The experiments on the CAP database demonstrate that our method achieves a substantial improvement compared with other well-know deep learning methods. Beside these, we discussed two major limitations in convolutional neural networks-based semantic segmentation methods for LV segmentation.     

Hepatic vessel segmentation using variational level set combined with non-local robust statistics

Hepatic vessel segmentation is a challenging step in therapy guided by magnetic resonance imaging (MRI). This paper presents an improved variational level set method, which uses non-local robust statistics to suppress the influence of noise in MR images. The non-local robust statistics, which represent vascular features, are learned adaptively from seeds provided by users. K-means clustering in neighborhoods of seeds is utilized to exclude inappropriate seeds, which are obviously corrupted by noise. The neighborhoods of appropriate seeds are placed in an array to calculate the non-local robust statistics, and the variational level set formulation can be constructed. Bias correction is utilized in the level set formulation to reduce the influence of intensity inhomogeneity of MRI. Experiments were conducted over real MR images, and showed that the proposed method performed better on small hepatic vessel segmentation compared with other segmentation methods.     

面向心音分割的个性化高斯混合建模方法

准确的心音分割是分析和处理心音信号的基本前提。主流的心音分割算法采用监督式预先训练的方法构建统计模型,它不仅依赖于繁琐的手工标注,还存在模型与被分割数据之间的不匹配问题。提出了一种面向心音分割的个性化高斯混合建模方法,避免了手工标注和预先训练,而且在线训练获得的个性化模型能够高度匹配被分割的心音数据。由于心音信号的周期在一段短时间内很稳定,因此假设在包含若干心动周期的分析窗内,心音信号具有稳定的周期性,通过主成分分析提取本征心动周期信号,通过无监督学习构建个性化的统计模型,根据模型实现窗内每一心动周期的分割。实验表明,算法的平均分割准确率比主流的LRHSMM算法高3%。     

State of the art survey on MRI brain tumor segmentation

Brain tumor segmentation consists of separating the different tumor tissues (solid or active tumor, edema, and necrosis) from normal brain tissues: gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). In brain tumor studies, the existence of abnormal tissues may be easily detectable most of the time. However, accurate and reproducible segmentation and characterization of abnormalities are not straightforward. In the past, many researchers in the field of medical imaging and soft computing have made significant survey in the field of brain tumor segmentation. Both semiautomatic and fully automatic methods have been proposed. Clinical acceptance of segmentation techniques has depended on the simplicity of the segmentation, and the degree of user supervision. Interactive or semiautomatic methods are likely to remain dominant in practice for some time, especially in these applications where erroneous interpretations are unacceptable. This article presents an overview of the most relevant brain tumor segmentation methods, conducted after the acquisition of the image. Given the advantages of magnetic resonance imaging over other diagnostic imaging, this survey is focused on MRI brain tumor segmentation. Semiautomatic and fully automatic techniques are emphasized.     

Tsallis-Entropy Segmentation through MRF and Alzheimer anatomic reference for Brain Magnetic Resonance Parcellation

Quantifying the intracranial tissue volume changes in magnetic resonance imaging (MRI) assists specialists to analyze the effects of natural or pathological changes. Since these changes can be subtle, the accuracy of the automatic compartmentalization method is always criticized by specialists. We propose and then evaluate an automatic segmentation method based on modified q-entropy (Mqe) through a modified Markov Random Field (MMRF) enhanced by Alzheimer anatomic reference (AAR) to provide a high accuracy brain tissues parcellation approach (Mqe-MMRF). We underwent two strategies to evaluate Mqe-MMRF; a simulation of different levels of noise and non-uniformity effect on MRI data (7 subjects) and a set of twenty MRI data available from MRBrainS13 as patient brain tissue segmentation challenge. We accessed eleven quality metrics compared to reference tissues delineations to evaluate Mqe-MMRF. MRI segmentation scores decreased by only 4.6% on quality metrics after noise and non-uniformity simulations of 40% and 9%, respectively. We found significant mean improvements in the metrics of the five training subjects, for whole-brain 0.86%, White Matter 3.20%, Gray Matter 3.99%, and Cerebrospinal Fluid 4.16% (p-values < 0.02) when Mqe-MMRF compared to the other reference methods. We also processed the Mqe-MMRF on 15 evaluation subjects group from MRBrainS13 online challenge, and the results held a higher rank than the reference tools; FreeSurfer, SPM, and FSL. Since the proposed method improved the precision of brain segmentation, specifically, for GM, and thus one can use it in quantitative and morphological brain studies.     

Compensating for B1 inhomogeneity using active transmit power modulation

The effect of poor B₁ homogeneity on MRI images not only affects the appearance of the images, but produces difficulty in automated segmentation and in certain quantification methods. While improved RF coil design is the first line in reducing such artifact, compensation methods can significantly improve the quality of images.

Existing methods of compensation typically apply a filter during the image reconstruction. Here a method is presented that compensates for part of the inhomogeneity by actively modulating the RF transmit power as a function of slice position. The method is demonstrated both quantitatively on a phantom and qualitatively on a human brain.     

利用三维自适应分裂-合并的MRI图像分割算法设计

该文提出一种基于3D几何特征分裂-合并(ASM)的脑部MRI图像分割算法。首先构建简单平行六面体的12种3D区域分割策略,体积分割技术将整个体积划分为许多大的均匀三维几何区;然后,在体积内定义更多小的均匀区域,以便在随后的合并步骤中有更大的生存概率;最后,进行多级区域合并,合并阶段只涉及复杂ASM树的叶子,考虑灰度相似性和共同边界区的大小,将小的区域合并为大邻近区。相比其他几种MRI图像分割算法,提出的方法在分割过程对噪声具有鲁棒性,提高了分割性能和准确率。另外提出的方法不需要训练数据集。     

Weakly Supervised Building Semantic Segmentation Based on Spot-Seeds and Refinement Process

Automatic building semantic segmentation is the most critical and relevant task in several geospatial applications. Methods based on convolutional neural networks (CNNs) are mainly used in current building segmentation. The requirement of huge pixel-level labels is a significant obstacle to achieve the semantic segmentation of building by CNNs. In this paper, we propose a novel weakly supervised framework for building segmentation, which generates high-quality pixel-level annotations and optimizes the segmentation network. A superpixel segmentation algorithm can predict a boundary map for training images. Then, Superpixels-CRF built on the superpixel regions is guided by spot seeds to propagate information from spot seeds to unlabeled regions, resulting in high-quality pixel-level annotations. Using these high-quality pixel-level annotations, we can train a more robust segmentation network and predict segmentation maps. To iteratively optimize the segmentation network, the predicted segmentation maps are refined, and the segmentation network are retrained. Comparative experiments demonstrate that the proposed segmentation framework achieves a marked improvement in the building’s segmentation quality while reducing human labeling efforts.     

Cellular neural networks for welding arc thermograms segmentation

Machine vision systems are used in many areas for monitoring of technological processes. Among this processes welding takes important place, where often infrared cameras are used. Besides reliable hardware, successful application of vision systems requires suitable software based on proper algorithms. One of most important group of image processing algorithms is connected to image segmentation. Obtainment of exact boundary of an object that changes shape in time, such as the welding arc, represented on a thermogram is not a trivial task. In the paper a segmentation method using supervised approach based on a cellular neural networks is presented. Simulated annealing and genetic algorithm were used for training of the network (template optimization). Comparison of proposed method to a well elaborated segmentation method based on region growing approach was made. Obtained results prove that the cellular neural network can be a valuable tool for infrared welding pool images segmentation.     

Segmentation techniques for tissue differentiation in MRI of ophthalmology using fuzzy clustering algorithms

This paper presents MRI segmentation techniques to differentiate abnormal and normal tissues in Ophthalmology using fuzzy clustering algorithms. Applying the best-known fuzzy c-means (FCM) clustering algorithm, a newly proposed algorithm, called an alternative fuzzy c-mean (AFCM), was used for MRI segmentation in Ophthalmology. These unsupervised segmentation algorithms can help Ophthalmologists to reduce the medical imaging noise effects originating from low resolution sensors and/or the structures that move during the data acquisition. They may be particularly helpful in the clinical oncological field as an aid to the diagnosis of Retinoblastoma, an inborn oncological disease in which symptoms usually show in early childhood. For the purpose of early treatment with radiotherapy and surgery, the newly proposed AFCM is preferred to provide more information for medical images used by Ophthalmologists. Comparisons between FCM and AFCM segmentations are made. Both fuzzy clustering segmentation techniques provide useful information and good results. However, the AFCM method has better detection of abnormal tissues than FCM according to a window selection. Overall, the newly proposed AFCM segmentation technique is recommended in MRI segmentation.     

An improved lesion detection approach based on similarity measurement between fuzzy intensity segmentation and spatial probability maps

The application of automatic segmentation methods in lesion detection is desirable. However, such methods are restricted by intensity similarities between lesioned and healthy brain tissue. Using multi-spectral magnetic resonance imaging (MRI) modalities may overcome this problem but it is not always practicable. In this article, a lesion detection approach requiring a single MRI modality is presented, which is an improved method based on a recent publication. This new method assumes that a low similarity should be found in the regions of lesions when the likeness between an intensity based fuzzy segmentation and a location based tissue probabilities is measured. The usage of a normalized similarity measurement enables the current method to fine-tune the threshold for lesion detection, thus maximizing the possibility of reaching high detection accuracy. Importantly, an extra cleaning step is included in the current approach which removes enlarged ventricles from detected lesions. The performance investigation using simulated lesions demonstrated that not only the majority of lesions were well detected but also normal tissues were identified effectively. Tests on images acquired in stroke patients further confirmed the strength of the method in lesion detection. When compared with the previous version, the current approach showed a higher sensitivity in detecting small lesions and had less false positives around the ventricle and the edge of the brain.     

Accuracy and reproducibility of automated white matter hyperintensities segmentation with lesion segmentation tool: A European multi-site 3T study

Brain vascular damage accumulate in aging and often manifest as white matter hyperintensities (WMHs) on MRI. Despite increased interest in automated methods to segment WMHs, a gold standard has not been achieved and their longitudinal reproducibility has been poorly investigated. The aim of present work is to evaluate accuracy and reproducibility of two freely available segmentation algorithms. A harmonized MRI protocol was implemented in 3T-scanners across 13 European sites, each scanning five volunteers twice (test-retest) using 2D-FLAIR. Automated segmentation was performed using Lesion segmentation tool algorithms (LST): the Lesion growth algorithm (LGA) in SPM8 and 12 and the Lesion prediction algorithm (LPA). To assess reproducibility, we applied the LST longitudinal pipeline to the LGA and LPA outputs for both the test and retest scans. We evaluated volumetric and spatial accuracy comparing LGA and LPA with manual tracing, and for reproducibility the test versus retest. Median volume difference between automated WMH and manual segmentations (mL) was −0.22[IQR = 0.50] for LGA-SPM8, −0.12[0.57] for LGA-SPM12, −0.09[0.53] for LPA, while the spatial accuracy (Dice Coefficient) was 0.29[0.31], 0.33[0.26] and 0.41[0.23], respectively. The reproducibility analysis showed a median reproducibility error of 20%[IQR = 41] for LGA-SPM8, 14% [31] for LGA-SPM12 and 10% [27] with the LPA cross-sectional pipeline. Applying the LST longitudinal pipeline, the reproducibility errors were considerably reduced (LGA: 0%[IQR = 0], p < 0.001; LPA: 0% [3], p < 0.001) compared to those derived using the cross-sectional algorithms. The DC using the longitudinal pipeline was excellent (median = 1) for LGA [IQR = 0] and LPA [0.02]. LST algorithms showed moderate accuracy and good reproducibility. Therefore, it can be used as a reliable cross-sectional and longitudinal tool in multi-site studies.     

Automatic segmentation of brain MRI in high-dimensional local and non-local feature space based on sparse representation

Automatic extraction of the varying regions of magnetic resonance images is required as a prior step in a diagnostic intelligent system. The sparsest representation and high-dimensional feature are provided based on learned dictionary. The classification is done by employing the technique that computes the reconstruction error locally and non-locally of each pixel. The acquired results from the real and simulated images are superior to the best MRI segmentation method with regard to the stability advantages. In addition, it is segmented exactly through a formula taken from the distance and sparse factors. Also, it is done automatically taking sparse factor in unsupervised clustering methods whose results have been improved.     

Multispectral MR images segmentation based on fuzzy knowledge and modified seeded region growing

Magnetic resonance imaging (MRI) is a valuable diagnostic tool in medical science due to its capability for soft-tissue characterization and three-dimensional visualization. One potential application of MRI in clinical practice is brain parenchyma classification and segmentation. Based on fuzzy knowledge and modified seeded region growing, this work proposes a novel image segmentation method, called Fuzzy Knowledge-Based Seeded Region Growing (FKSRG), for multispectral MR images. In this work, fuzzy knowledge includes the fuzzy edge, fuzzy similarity and fuzzy distance, which are obtained from relationships between pixels in multispectral MR images and are applied to the modified seeded regions growing process. In conventional regions merging, the final number of regions is unknown. Therefore, a Target Generation Process is proposed and applied to support conventional regions merging, such that the FKSRG method does not over- or undersegment images. Finally, two image sets, namely, computer-generated phantom images and real MR images, are used in experiments to assess the effectiveness of the proposed FKSRG method. Experimental results demonstrate that the FKSRG method segments multispectral MR images much more effectively than the Functional MRI of the Brain Automated Segmentation Tool, K-means and Support Vector Machine methods.