An automated approach for segmentation of intravascular ultrasound images based on parametric active contour models

Automated Segmentation of Fetal Ultrasound Images Using Feature Attention Supervised Network

ABSTRACT

Segmentation of anatomical structures from ultrasound images requires the expertise of an experienced clinician, but developing a machine automated segmentation process is complicated because of the existence of characteristic artifacts. In this article, we present a novel end-to-end network that enables automated measurements of the fetal head circumference (HC) and fetal abdomen circumference (AC) to be made from 2-dimensional (2D) ultrasound images during each pregnancy trimester. These measurements are necessary, because the HC and AC are used to predict gestational age and to monitor fetal growth. Automated HC and AC assessments are valuable for providing independent and objective results and are particularly useful for application in developing countries where trained sonographers are in short supply. We propose a scale attention expanding network that builds a feature pyramid inside the network, and the intermediate result of each scale is then concatenated to the feature with a fusion scheme for the next layer. Furthermore, a scale attention module is proposed for selecting the most useful scale and for reducing scale noise. To optimize the network, a deep supervision method based on boundary attention is employed. Results of experiments show that the scale attention expanding network obtained an absolute difference, Hausdorff distance, and dice similarity coefficient of 1.81 ± 1.69%, 1.22 ± 0.77%, and 97.94%, respectively, which were top results in the HC18 data set, and respective results on the abdomen set were 2.23 ± 2.38%, 0.42 ± 0.56%, and 98.04%. The experiments conducted demonstrate that our method provides a superior performance to existing fetal ultrasound segmentation methods.

A pipeline to quantify spinal cord atrophy with deep learning: Application to differentiation of MS and NMOSD patients

PURPOSE

Quantitative measurement of various anatomical regions of the brain and spinal cord (SC) in MRI images are used as unique biomarkers to consider progress and effects of demyelinating diseases of the central nervous system. This paper presents a fully-automated image processing pipeline which quantifies the SC volume of MRI images.

METHODS

In the proposed pipeline, after conducting some pre-processing tasks, a deep convolutional network is utilized to segment the spinal cord cross-sectional area (SCCSA) of each slice. After full segmentation, certain extra slices interpolate between each two adjacent slices using the shape-based interpolation method. Then, a 3D model of the SC is reconstructed, and, by counting the voxels of it, the SC volume is calculated. The performance of the proposed method for the SCCSA segmentation is evaluated on 140 MRI images. Subsequently, to demonstrate the application of the proposed pipeline, we study the differentiations of SC atrophy between 38 Multiple Sclerosis (MS) and 25 Neuromyelitis Optica Spectrum Disorder (NMOSD) patients.

RESULTS

The experimental results of the SCCSA segmentation indicate that the proposed method, adapted by Mask R-CNN, presented the most satisfactory result with the average Dice coefficient of 0.96. For this method, statistical metrics including sensitivity, specificity, accuracy, and precision are 97.51%, 99.98%, 99.92%, and 98.04% respectively. Moreover, the t-test result (p-value = 0.00089) verified a significant difference between the SC atrophy of MS and NMOSD patients.

CONCLUSION

The pipeline efficiently quantifies the SC volume of MRI images and can be utilized as an affordable computer-aided tool for diagnostic purposes.

Ultrasound Image Segmentation: A Deeply Supervised Network With Attention to Boundaries

OBJECTIVE

Segmentation of anatomical structures in ultrasound images requires vast radiological knowledge and experience. Moreover, the manual segmentation often results in subjective variations, therefore, an automatic segmentation is desirable. We aim to develop a fully convolutional neural network (FCNN) with attentional deep supervision for the automatic and accurate segmentation of the ultrasound images.

METHOD

FCNN/CNNs are used to infer high-level context using low-level image features. In this paper, a sub-problem specific deep supervision of the FCNN is performed. The attention of fine resolution layers is steered to learn object boundary definitions using auxiliary losses, whereas coarse resolution layers are trained to discriminate object regions from the background. Furthermore, a customized scheme for downweighting the auxiliary losses and a trainable fusion layer are introduced. This produces an accurate segmentation and helps in dealing with the broken boundaries, usually found in the ultrasound images.

RESULTS

The proposed network is first tested for blood vessel segmentation in liver images. It results in F1 score, mean intersection over union, and dice index of 0.83, 0.83, and 0.79, respectively. The best values observed among the existing approaches are produced by U-net as 0.74, 0.81, and 0.75, respectively. The proposed network also results in dice index value of 0.91 in the lumen segmentation experiments on MICCAI 2011 IVUS challenge dataset, which is near to the provided reference value of 0.93. Furthermore, the improvements similar to vessel segmentation experiments are also observed in the experiment performed to segment lesions.

CONCLUSION

Deep supervision of the network based on the input-output characteristics of the layers results in improvement in overall segmentation accuracy.

SIGNIFICANCE

Sub-problem specific deep supervision for ultrasound image segmentation is the main contribution of this paper. Currently the network is trained and tested for fixed size inputs. It requires image resizing and limits the performance in small size images.

Missing Surface Estimation Based on Modified Tikhonov Regularization: Application for Destructed Dental Tissue

Estimation of missing digital information is mostly addressed by one or two-dimensional signal processing methods; however, this problem can emerge in multi-dimensional data including 3D images. Examples of 3D images dealing with missing edge information are often found using dental micro-CT, where the natural contours of dental enamel and dentine are partially dissolved or lost by caries. In this paper, we present a novel sequential approach to estimate the missing surface of an object. First, an initial correct contour is determined interactively or automatically, for the starting slice. This contour information defines the local search area and provides the overall estimation pattern for the edge candidates in the next slice. The search for edge candidates in the next slice is performed in the perpendicular direction to the obtained initial edge in order to find and label the corrupted edge candidates. Subsequently, the location information of both initial and nominated edge candidates are transformed and segregated into two independent signals (X-coordinates and Y-coordinates) and the problem is changed into error concealment. In the next step, the missing samples of these signals are estimated using a modified Tikhonov regularization model with two new terms. One term contributes in the denoising of the corrupted signal by defining an estimation model for a group of mildly destructed samples, and the other term contributes in the estimation of the missing samples with the highest similarity to the samples of the obtained signals from the previous slice. Finally, the reconstructed signals are transformed inversely to edge pixel representation. The estimated edges in each slice are considered as initial edge information for the next slice and this procedure is repeated slice by slice until the entire contour of the destructed surface is estimated. The visual results as well as quantitative results (using both contour-based and area-based metrics) for seven image datasets of tooth samples with considerable destruction of the dentin-enamel junction (DEJ) demonstrates that the proposed method can accurately interpolate the shape and the position of the missing surfaces in computed tomography images in both two and three dimensions (e.g. 14.87 ±3.87 μ m of mean distance (MD) error for the proposed method versus 7.33 ±0.27 μm of MD error between human experts and 1.25 ±~0 % error rate (ER) of the proposed method versus 0.64 ±~0 % of ER between human experts (~1% difference)).

Automatic segmentation of the lumen region in intravascular images of the coronary artery

Image assessment of the arterial system plays an important role in the diagnosis of cardiovascular diseases. The segmentation of the lumen and media-adventitia in intravascular (IVUS) images of the coronary artery is the first step towards the evaluation of the morphology of the vessel under analysis and the identification of possible atherosclerotic lesions. In this study, a fully automatic method for the segmentation of the lumen in IVUS images of the coronary artery is presented. The proposed method relies on the K-means algorithm and the mean roundness to identify the region corresponding to the potential lumen. An approach to identify and eliminate side branches on bifurcations is also proposed to delimit the area with the potential lumen regions. Additionally, an active contour model is applied to refine the contour of the lumen region. In order to evaluate the segmentation accuracy, the results of the proposed method were compared against manual delineations made by two experts in 326 IVUS images of the coronary artery. The average values of the Jaccard measure, Hausdorff distance, percentage of area difference and Dice coefficient were 0.88 ± 0.06, 0.29 ± 0.17  mm, 0.09 ± 0.07 and 0.94 ± 0.04, respectively, in 324 IVUS images successfully segmented. Additionally, a comparison with the studies found in the literature showed that the proposed method is slight better than the majority of the related methods that have been proposed. Hence, the new automatic segmentation method is shown to be effective in detecting the lumen in IVUS images without using complex solutions and user interaction.

Fast Medical Image Segmentation Using Energy-Based Method

Medical applications became a boon to the healthcare industry. It needs correct and fast segmentation associated with medical images for correct diagnosis. This assures high quality segmentation of medical images victimization. The Level Set Method (LSM) is a capable technique, however the quick process using correct segments remains difficult. The region based models like Active Contours, Globally Optimal Geodesic Active Contours (GOGAC) performs inadequately for intensity irregularity images. During this cardstock, we have a new tendency to propose an improved region based level set model motivated by the geodesic active contour models as well as the Mumford-Shah model. So that you can eliminate the re-initialization process of ancient level set model and removes the will need of computationally high priced re-initialization. Compared using ancient models, our model are sturdier against images using weak edge and intensity irregularity.

Segmenting breast cancerous regions in thermal images using fuzzy active contours

Breast cancer is the main cause of death among young women in developing countries. The human body temperature carries critical medical information related to the overall body status. Abnormal rise in total and regional body temperature is a natural symptom in diagnosing many diseases. Thermal imaging (Thermography) utilizes infrared beams which are fast, non-invasive, and non-contact and the output created images by this technique are flexible and useful to monitor the temperature of the human body. In some clinical studies and biopsy tests, it is necessary for the clinician to know the extent of the cancerous area. In such cases, the thermal image is very useful. In the same line, to detect the cancerous tissue core, thermal imaging is beneficial. This paper presents a fully automated approach to detect the thermal edge and core of the cancerous area in thermography images. In order to evaluate the proposed method, 60 patients with an average age of 44/9 were chosen. These cases were suspected of breast tissue disease. These patients referred to Tehran Imam Khomeini Imaging Center. Clinical examinations such as ultrasound, biopsy, questionnaire, and eventually thermography were done precisely on these individuals. Finally, the proposed model is applied for segmenting the proved abnormal area in thermal images. The proposed model is based on a fuzzy active contour designed by fuzzy logic. The presented method can segment cancerous tissue areas from its borders in thermal images of the breast area. In order to evaluate the proposed algorithm, Hausdorff and mean distance between manual and automatic method were used. Estimation of distance was conducted to accurately separate the thermal core and edge. Hausdorff distance between the proposed and the manual method for thermal core and edge was 0.4719 ± 0.4389, 0.3171 ± 0.1056 mm respectively, and the average distance between the proposed and the manual method for core and thermal edge was 0.0845 ± 0.0619, 0.0710 ± 0.0381 mm respectively. Furthermore, the sensitivity in recognizing the thermal pattern in breast tissue masses is 85 % and its accuracy is 91.98 %.A thermal imaging system has been proposed that is able to recognize abnormal breast tissue masses. This system utilizes fuzzy active contours to extract the abnormal regions automatically.