Precise Segmentation of COVID-19 Infected Lung from CT Images Based on Adaptive First-Order Appearance Model with Morphological/Anatomical Constraints

A new segmentation technique is introduced for delineating the lung region in 3D computed tomography (CT) images. To accurately model the distribution of Hounsfield scale values within both chest and lung regions, a new probabilistic model is developed that depends on a linear combination of Gaussian (LCG). Moreover, we modified the conventional expectation-maximization (EM) algorithm to be run in a sequential way to estimate both the dominant Gaussian components (one for the lung region and one for the chest region) and the subdominant Gaussian components, which are used to refine the final estimated joint density. To estimate the marginal density from the mixed density, a modified k-means clustering approach is employed to classify the Gaussian subdominant components to determine which components belong properly to a lung and which components belong to a chest. The initial segmentation, based on the LCG-model, is then refined by the imposition of 3D morphological constraints based on a 3D Markov–Gibbs random field (MGRF) with analytically estimated potentials. The proposed approach was tested on CT data from 32 coronavirus disease 2019 (COVID-19) patients. Segmentation quality was quantitatively evaluated using four metrics: Dice similarity coefficient (DSC), overlap coefficient, 95th-percentile bidirectional Hausdorff distance (BHD), and absolute lung volume difference (ALVD), and it achieved 95.67±1.83%, 91.76±3.29%, 4.86±5.01, and 2.93±2.39, respectively. The reported results showed the capability of the proposed approach to accurately segment healthy lung tissues in addition to pathological lung tissues caused by COVID-19, outperforming four current, state-of-the-art deep learning-based lung segmentation approaches.

Integration of Dynamic Multi-Atlas and Deep Learning Techniques to Improve Segmentation of the Prostate in MR Images

Accurate delineation of the prostate in MR images is an essential step for treatment planning and volume estimation of the organ. Prostate segmentation is a challenging task due to its variable size and shape. Moreover, neighboring tissues have a low-contrast with the prostate. We propose a robust and precise automatic algorithm to define the prostate’s boundaries in MR images in this paper. First, we find the prostate’s ROI by a deep neural network and decrease the input image’s size. Next, a dynamic multi-atlas-based approach obtains the initial segmentation of the prostate. A watershed algorithm improves the initial segmentation at the next stage. Finally, an SSM algorithm keeps the result in the domain of allowable prostate shapes. The quantitative evaluation of 74 prostate volumes demonstrated that the proposed method yields a mean Dice coefficient of [Formula: see text]. In comparison with recent researches, our algorithm is robust against shape and size variations.

Bioinspired Inference System for MR Image Segmentation and Multiple Sclerosis Detection

Multiple sclerosis (MS) is a chronic autoimmune and inflammatory disease affecting the central nervous system (CNS). Magnetic resonance imaging (MRI) provides sufficient imaging contrast to visualize and detect MS lesions, particularly those in the white matter (WM). A robust and precise segmentation of WM lesions from MRI provide essential information about the disease status and evolution. The proposed FPSOPCM segmentation algorithm included an initial segmentation step using fuzzy particle swarm optimization (FPSO). After extraction of WM, atypical data (outliers) is eliminated using possibilistic C-means (PCM) algorithm, and finally, a Mamdani-type fuzzy model was applied to identify MS. The objective of the work presented in this paper is to obtain an improved accuracy in segmentation of MR images for MS detection.

Going to Extremes: Weakly Supervised Medical Image Segmentation

Medical image annotation is a major hurdle for developing precise and robust machine-learning models. Annotation is expensive, time-consuming, and often requires expert knowledge, particularly in the medical field. Here, we suggest using minimal user interaction in the form of extreme point clicks to train a segmentation model which, in effect, can be used to speed up medical image annotation. An initial segmentation is generated based on the extreme points using the random walker algorithm. This initial segmentation is then used as a noisy supervision signal to train a fully convolutional network that can segment the organ of interest, based on the provided user clicks. Through experimentation on several medical imaging datasets, we show that the predictions of the network can be refined using several rounds of training with the prediction from the same weakly annotated data. Further improvements are shown using the clicked points within a custom-designed loss and attention mechanism. Our approach has the potential to speed up the process of generating new training datasets for the development of new machine-learning and deep-learning-based models for, but not exclusively, medical image analysis.

EvoSeg: Automated Electron Microscopy Segmentation through Random Forests and Evolutionary Optimization

Electron Microscopy Maps are key in the study of bio-molecular structures, ranging from borderline atomic level to the sub-cellular range. These maps describe the envelopes that cover possibly a very large number of proteins that form molecular machines within the cell. Within those envelopes, we are interested to find what regions correspond to specific proteins so that we can understand how they function, and design drugs that can enhance or suppress a process that they are involved in, along with other experimental purposes. A classic approach by which we can begin the exploration of map regions is to apply a segmentation algorithm. This yields a mask where each voxel in 3D space is assigned an identifier that maps it to a segment; an ideal segmentation would map each segment to one protein unit, which is rarely the case. In this work, we present a method that uses bio-inspired optimization, through an Evolutionary-Optimized Segmentation algorithm, to iteratively improve upon baseline segments obtained from a classical approach, called watershed segmentation. The cost function used by the evolutionary optimization is based on an ideal segmentation classifier trained as part of this development, which uses basic structural information available to scientists, such as the number of expected units, volume and topology. We show that a basic initial segmentation with the additional information allows our evolutionary method to find better segmentation results, compared to the baseline generated by the watershed.

Kurdish Text Segmentation using Projection-Based Approaches

An optical character recognition (OCR) system may be the solution to data entry problems for saving the printed document as a soft copy of them. Therefore, OCR systems are being developed for all languages, and Kurdish is no exception. Kurdish is one of the languages that present special challenges to OCR. The main challenge of Kurdish is that it is mostly cursive. Therefore, a segmentation process must be able to specify the beginning and end of the characters. This step is important for character recognition. This paper presents an algorithm for Kurdish character segmentation. The proposed algorithm uses the projection-based approach concepts to separate lines, words, and characters. The algorithm works through the vertical projection of a word and then identifies the splitting areas of the word characters. Then, a post-processing stage is used to handle the over-segmentation problems that occur in the initial segmentation stage. The proposed method is tested using a data set consisting of images of texts that vary in font size, type, and style of more than 63,000 characters. The experiments show that the proposed algorithm can segment Kurdish words with an average accuracy of 98.6%.

A Disparity Refinement Algorithm for Satellite Remote Sensing Images Based on Mean-Shift Plane Segmentation

Objects in satellite remote sensing image sequences often have large deformations, and the stereo matching of this kind of image is so difficult that the matching rate generally drops. A disparity refinement method is needed to correct and fill the disparity. A method for disparity refinement based on the results of plane segmentation is proposed in this paper. The plane segmentation algorithm includes two steps: Initial segmentation based on mean-shift and alpha-expansion-based energy minimization. According to the results of plane segmentation and fitting, the disparity is refined by filling missed matching regions and removing outliers. The experimental results showed that the proposed plane segmentation method could not only accurately fit the plane in the presence of noise but also approximate the surface by plane combination. After the proposed plane segmentation method was applied to the disparity refinement of remote sensing images, many missed matches were filled, and the elevation errors were reduced. This proved that the proposed algorithm was effective. For difficult evaluations resulting from significant variations in remote sensing images of different satellites, the edge matching rate and the edge matching map are proposed as new stereo matching evaluation and analysis tools. Experiment results showed that they were easy to use, intuitive, and effective.

Fast Mumford-Shah Two-Phase Image Segmentation Using Proximal Splitting Scheme

The Mumford-Shah model is extensively used in image segmentation. Its energy functional causes the content of the segments to remain homogeneous and the segment boundaries to become short. However, the problem is that optimization of the functional can be very slow. To attack this problem, we propose a reduced two-phase Mumford-Shah model to segment images having one prominent object. First, initial segmentation is obtained by the k-means clustering technique, further minimizing the Mumford-Shah functional by the Douglas-Rachford algorithm. Evaluation of segmentations with various error metrics shows that 70 percent of the segmentations keep the error values below 50%. Compared to the level set method to solve the Chan-Vese model, our algorithm is significantly faster. At the same time, it gives almost the same or better segmentation results. When compared to the recent k-means variant, it also gives much better segmentation with convex boundaries. The proposed algorithm balances well between time and quality of the segmentation. A crucial step in the design of machine vision systems is the extraction of discriminant features from the images, which is based on low-level segmentation which can be obtained by our approach.

Unsupervised Classification of Polarimetric SAR Image Based on Geodesic Distance and Non-Gaussian Distribution Feature

Polarimetric synthetic aperture radar (PolSAR) image classification plays a significant role in PolSAR image interpretation. This letter presents a novel unsupervised classification method for PolSAR images based on the geodesic distance and K-Wishart distribution. The geodesic distance is obtained between the Kennaugh matrices of the observed target and canonical targets, and it is further utilized to define scattering similarity. According to the maximum scattering similarity, initial segmentation is produced, and the image is divided into three main categories: surface scattering, double-bounce scattering, and random volume scattering. Then, using the shape parameter α of K-distribution, each scattering category is further divided into three sub-categories with different degrees of heterogeneity. Finally, the K-Wishart maximum likelihood classifier is applied iteratively to update the results and improve the classification accuracy. Experiments are carried out on three real PolSAR images, including L-band AIRSAR, L-band ESAR, and C-band GaoFen-3 datasets, containing different resolutions and various terrain types. Compared with four other classic and recently developed methods, the final classification results demonstrate the effectiveness and superiority of the proposed method.

Individual Tree Extraction from Terrestrial LiDAR Point Clouds Based on Transfer Learning and Gaussian Mixture Model Separation

Individual tree extraction is an important process for forest resource surveying and monitoring. To obtain more accurate individual tree extraction results, this paper proposed an individual tree extraction method based on transfer learning and Gaussian mixture model separation. In this study, transfer learning is first adopted in classifying trunk points, which can be used as clustering centers for tree initial segmentation. Subsequently, principal component analysis (PCA) transformation and kernel density estimation are proposed to determine the number of mixed components in the initial segmentation. Based on the number of mixed components, the Gaussian mixture model separation is proposed to separate canopies for each individual tree. Finally, the trunk stems corresponding to each canopy are extracted based on the vertical continuity principle. Six tree plots with different forest environments were used to test the performance of the proposed method. Experimental results show that the proposed method can achieve 87.68% average correctness, which is much higher than that of other two classical methods. In terms of completeness and mean accuracy, the proposed method also outperforms the other two methods.