GrowCut Algorithm Research Articles

An Unsupervised Threshold-based GrowCut Algorithm for Mammography Lesion Detection

Breast cancer causes numerous deaths worldwide; yet the numbers have decreased in the past years as a result of computer-aided diagnosis and proper treatment. The current paper is addressed to the base of such diagnosis system: pre-processing and segmentation. After a robust pre-processing, an unsupervised version of GrowCut is applied to define the location of the abnormality. We present a method to automatically define the foreground seeds used in GrowCut. For experiments, mammograms from mini-MIAS dataset are used and a precision of 93.63% for the foreground seeds masks is achieved, which leads to promising segmentation results.

Fully automated segmentation of lumbar bone marrow in sagittal, high-resolution T1-weighted magnetic resonance images using 2D U-NET

BackgroundWe investigated a 2-dimensional (2D) U-Net model to delineate lumbar bone marrow (BM) using a high resolution T1-weighted magnetic resonance imaging. MethodHealthy controls (n = 44, 836 images) and patients with hematologic diseases (n = 56, 1064 images) received MRI of the lumbar spines. Lumbar BM on each image was manually delineated by an experienced radiologist as a ground-truth. The 2D U-Net models were trained using a healthy lumbar BM only, diseased BM only, and using healthy and diseased BM combined, respectively. The models were validated using healthy and diseased subjects, separately. A repeated-measures analysis of variance was performed to compare segmentation accuracies with 2 validation cohorts among U-Net trained with healthy subjects (UNET_HC), U-Net trained with diseased subjects (UNET_HD), U-Net trained with all subjects including both healthy and diseased subjects (UNET_HCHD), and 3-dimensional Grow-Cut algorithm (3DGC). ResultsWhen validated with the healthy subjects, UNET_HC, UNET_HD, UNET_HCHD and 3DGC achieved the mean and standard deviation of the Dice Similarity Coefficient (DSC) of 0.9415 ± 0.07056, 0.9583 ± 0.05146, 0.9602 ± 0.0486 and 0.9139 ± 0.2039, respectively. When validated with the diseased subjects, DSCs of UNET_HC, UNET_HD, UNET_HCHD and 3DGC were 0.8303 ± 0.1073, 0.9502 ± 0.0217, 0.9502 ± 0.0217 and 0.8886 ± 0.2179, respectively. The U-Net models segmented BM better than the semi-automatic 3DGC (P < 0.0001), and UNET_HD produced better results than UNET_HC (P < 0.0001). ConclusionsWe successfully constructed a fully automatic lumbar BM segmentation model for a high-resolution T1-weighted MRI using U-Net, which outperformed most of the previously reported approaches and the existing semi-automatic algorithm.

Predicting 1p/19q chromosomal deletion of brain tumors using machine learning

Advances in molecular and genetic technologies have enabled the study of mutation and molecular changes in gliomas. The 1p/19q coding state of gliomas is important in predicting pathogenesis-based pharmacological treatments and determining innovative immunotherapeutic strategies. In this study, T1-weighted and T2-weighted fluid-attenuated inversion recovery magnetic resonance imaging (MRI) images of 121 low-grade glioma patients with biopsy-proven 1p/19q coding status and no deletion (n = 40) or co-deletion (n = 81) were used. First, regions of interests were segmented with the grow-cut algorithm. Later, 851 radiomic features including three-dimensional wavelet preprocessed and non-preprocessed ones were extracted from six different matrices such as first order, shape and texture. The extracted features were preprocessed with the synthetic minority over-sampling technique algorithm. Next, the 1p/19q decoding states of gliomas were classified using machine-learning algorithms. The best classification in the classification of glioma grades (grade II and grade III) according to 1p/19q coding status was obtained by using the logistic regression algorithm, with 93.94% accuracy and 94.74% area under the curve values. In conclusion, it was determined that non-invasive estimation of 1p/19q status from MRI images enables the selection of effective treatment strategies with early diagnosis using machine-learning algorithms without the need for surgical biopsy.

Mammography Lesion Detection Using an Improved GrowCut Algorithm

Breast cancer is one of the most common types of cancer amongst women, but it is also one of the most frequently cured cancers. Because of this, early detection is crucial, and this can be done through mammography screening. With the increasing need of an automated interpretation system, a lot of methods have been proposed so far and, regardless of the algorithms, they all share a step: segmentation. That is, identifying the region of interest in order to further analyze and classify it either as benign or malignant. However, due to the different types of mammary tissues, mammography segmentation can prove to be a difficult task.Various techniques of mammography segmentation have been proposed so far. Yet, since obtaining the ground-truth for mam-mographic images might be problematic, recent literature leans towards unsupervised techniques. In this paper we present a segmentation approach based on the GrowCut algorithm. The original method starts with a number of seed points inside and outside the region of interest, selected by a human expert, and iterates over the pixels multiple times, until it reaches a stable state where all the pixels have been assigned to a class. Our proposal aims to reduce the human intervention by eliminating the need of selecting initial background seeds and, also, to reduce the computational time by limiting the process of parsing the entire image to a small, fixed number of iterations.The proposed approach was compared to the original method, using three variants: (1) automatically constructing the initial background seeds surrounding the foreground ones; (2) using mammograms’s background as initial background seeds; (3) not using initial background seeds. Experimental results obtained for the Mini-MIAS dataset show that, for the variations that use background seeds outside the breast and that do not use any background seeds, our approach yields much better results than the original method.

A new approach to diagnosing prostate cancer through magnetic resonance imaging

This paper combines improved GrowCut and Zernik feature extraction and ensemble learning techniques such as KNN, SVM, and MLP algorithms to prostate cancer detection and lesion segmentation in MRI. We use improved GrowCut algorithm for segmentation of the suspected cancer area and the combination of machine learning algorithms such as KNN, SVM, and MLP in the ensemble learning system to detect prostate cancer. We found that the accuracy of this method, which is a combination of several methods, improved by about 20% compared to other methods. Other metrics such as precision, recall, and error of proposed method have been improved.

Classification of brain tumours using radiomic features on MRI

Glioma is one of the most common brain tumours among the diagnoses of existing brain tumours. Glioma grades are important factors that should be known in the treatment of brain tumours. In this study, the radiomic features of gliomas were analysed and glioma grades were classified by Gaussian Naive Bayes algorithm. Glioma tumours of 121 patients of Grade II and Grade III were examined. The glioma tumours were segmented with the Grow Cut Algorithm and the 3D feature of tumour magnetic resonance imaging images were obtained with the 3D Slicer programme. The obtained quantitative values were statistically analysed with Spearman and Mann–Whitney U tests and 21 features with statistically significant properties were selected from 107 features. The results showed that the best performing among the algorithms was Gaussian Naive Bayes algorithm with 80% accuracy. Machine learning and feature selection techniques can be used in the analysis of gliomas as well as pathological evaluations in glioma grading processes.&#x0D; &#x0D; Keywords: Radiomics, glioma, naive bayes.

Automated segmentation of hyperreflective foci in spectral domain optical coherence tomography with diabetic retinopathy.

We propose an automated segmentation method to detect, segment, and quantify hyperreflective foci (HFs) in three-dimensional (3-D) spectral domain optical coherence tomography (SD-OCT). The algorithm is divided into three stages: preprocessing, layer segmentation, and HF segmentation. In this paper, a supervised classifier (random forest) was used to produce the set of boundary probabilities in which an optimal graph search method was then applied to identify and produce the layer segmentation using the Sobel edge algorithm. An automated grow-cut algorithm was applied to segment the HFs. The proposed algorithm was tested on 20 3-D SD-OCT volumes from 20 patients diagnosed with proliferative diabetic retinopathy (PDR) and diabetic macular edema (DME). The average dice similarity coefficient and correlation coefficient ([Formula: see text]) are 62.30%, 96.90% for PDR, and 63.80%, 97.50% for DME, respectively. The proposed algorithm can provide clinicians with accurate quantitative information, such as the size and volume of the HFs. This can assist in clinical diagnosis, treatment, disease monitoring, and progression.

Semi-automatic segmentation of the placenta into fetal and maternal compartments using intravoxel incoherent motion MRI.

Intravoxel incoherent motion (IVIM) magnetic resonance imaging is an emerging non-invasive technique that has been recently applied to quantify in vivo global placental perfusion. We propose a robust semi-automated method for segmenting the placenta into fetal and maternal compartments from IVIM data, using a multi-label image segmentation algorithm called 'GrowCut'. Placental IVIM data were acquired on a 1.5T scanner from 16 healthy pregnant women between 21-37 gestational weeks. The voxel-wise perfusion fraction was then estimated after non-rigid image registration. The seed regions of the fetal and maternal compartments were determined using structural T2-weighted reference images, and improved progressively through an iterative process of the GrowCut algorithm to accurately encompass fetal and maternal compartments. We demonstrated that the placental perfusion fraction decreased in both fetal (-0.010/week) and maternal compartments (-0.013/week) while their relative difference (ffetal-fmaternal) gradually increased with advancing gestational age (+0.003/week, p=0.065). Our preliminary results show that the proposed method was effective in distinguishing placental compartments using IVIM.

Hybrid positron emission tomography segmentation of heterogeneous lung tumors using 3D Slicer: improved GrowCut algorithm with threshold initialization.

This paper presents an improved GrowCut (IGC), a positron emission tomography-based segmentation algorithm, and tests its clinical applicability. Contrary to the traditional method that requires the user to provide the initial seeds, the IGC algorithm starts with a threshold-based estimate of the tumor and a three-dimensional morphologically grown shell around the tumor as the foreground and background seeds, respectively. The repeatability of IGC from the same observer at multiple time points was compared with the traditional GrowCut algorithm. The algorithm was tested in 11 nonsmall cell lung cancer lesions and validated against the clinician-defined manual contour and compared against the clinically used 25% of the maximum standardized uptake value [SUV-(max)], 40% [Formula: see text], and adaptive threshold methods. The time to edit IGC-defined functional volume to arrive at the gross tumor volume (GTV) was compared with that of manual contouring. The repeatability of the IGC algorithm was very high compared with the traditional GrowCut ([Formula: see text]) and demonstrated higher agreement with the manual contour with respect to threshold-based methods. Compared with manual contouring, editing the IGC achieved the GTV in significantly less time ([Formula: see text]). The IGC algorithm offers a highly repeatable functional volume and serves as an effective initial guess that can well minimize the time spent on labor-intensive manual contouring.

A semi-supervised fuzzy GrowCut algorithm to segment and classify regions of interest of mammographic images

According to the World Health Organization, breast cancer is the most common form of cancer in women. It is the second leading cause of death among women round the world, becoming the most fatal form of cancer. Despite the existence of several imaging techniques useful to aid at the diagnosis of breast cancer, x-ray mammography is still the most used and effective imaging technology. Consequently, mammographic image segmentation is a fundamental task to support image analysis and diagnosis, taking into account shape analysis of mammary lesions and their borders. However, mammogram segmentation is a very hard process, once it is highly dependent on the types of mammary tissues. The GrowCut algorithm is a relatively new method to perform general image segmentation based on the selection of just a few points inside and outside the region of interest, reaching good results at difficult segmentation cases when these points are correctly selected. In this work we present a new semi-supervised segmentation algorithm based on the modification of the GrowCut algorithm to perform automatic mammographic image segmentation once a region of interest is selected by a specialist. In our proposal, we used fuzzy Gaussian membership functions to modify the evolution rule of the original GrowCut algorithm, in order to estimate the uncertainty of a pixel being object or background. The main impact of the proposed method is the significant reduction of expert effort in the initialization of seed points of GrowCut to perform accurate segmentation, once it removes the need of selection of background seeds. Furthermore, the proposed method is robust to wrong seed positioning and can be extended to other seed based techniques. These characteristics have impact on expert and intelligent systems, once it helps to develop a segmentation method with lower required specialist knowledge, being robust and as efficient as state of the art techniques. We also constructed an automatic point selection process based on the simulated annealing optimization method, avoiding the need of human intervention. The proposed approach was qualitatively compared with other state-of-the-art segmentation techniques, considering the shape of segmented regions. In order to validate our proposal, we built an image classifier using a classical multilayer perceptron. We used Zernike moments to extract segmented image features. This analysis employed 685 mammograms from IRMA breast cancer database, using fat and fibroid tissues. Results show that the proposed technique could achieve a classification rate of 91.28% for fat tissues, evidencing the feasibility of our approach.

Seismically induced soft-sediment deformation structures revealed by X-ray computed tomography of boring cores

X-ray computed tomography (CT) allows us to visualize three-dimensional structures hidden in boring cores nondestructively. We applied medical X-ray CT to cores containing seismically induced soft-sediment deformation structures (SSDSs) obtained from the Kanto region of Japan, where the 2011 off the Pacific coast of Tohoku Earthquake occurred. The CT images obtained clearly revealed various types of the seismically induced SSDSs embedded in the cores: a propagating sand dyke bent complexly by the preexisting geological structure, deformed laminations of fluidized sandy layers, and two types of downward mass movement (ductile downward folding and brittle normal faulting) as compensation for upward sand transport through sand dykes. Two advanced image analysis techniques were applied to the sand dyke CT images for the first time. The GrowCut algorithm, a specific digital image segmentation technique that uses cellular automata, was used successfully to extract the three-dimensional complex sand dyke structures embedded in the sandy sediments, which would have been difficult to achieve using a conventional image processing technique. Local autocorrelation image analysis was performed to detect the flow pattern aligned along the sand dykes objectively. The results demonstrate that X-ray CT coupled with advanced digital image analysis techniques is a promising approach to studying the seismically induced SSDSs in boring cores.

Localization and segmentation of optic disc in retinal images using circular Hough transform and grow-cut algorithm.

Automated retinal image analysis has been emerging as an important diagnostic tool for early detection of eye-related diseases such as glaucoma and diabetic retinopathy. In this paper, we have presented a robust methodology for optic disc detection and boundary segmentation, which can be seen as the preliminary step in the development of a computer-assisted diagnostic system for glaucoma in retinal images. The proposed method is based on morphological operations, the circular Hough transform and the grow-cut algorithm. The morphological operators are used to enhance the optic disc and remove the retinal vasculature and other pathologies. The optic disc center is approximated using the circular Hough transform, and the grow-cut algorithm is employed to precisely segment the optic disc boundary. The method is quantitatively evaluated on five publicly available retinal image databases DRIVE, DIARETDB1, CHASE_DB1, DRIONS-DB, Messidor and one local Shifa Hospital Database. The method achieves an optic disc detection success rate of 100% for these databases with the exception of 99.09% and 99.25% for the DRIONS-DB, Messidor, and ONHSD databases, respectively. The optic disc boundary detection achieved an average spatial overlap of 78.6%, 85.12%, 83.23%, 85.1%, 87.93%, 80.1%, and 86.1%, respectively, for these databases. This unique method has shown significant improvement over existing methods in terms of detection and boundary extraction of the optic disc.

An adaptive semi-supervised Fuzzy GrowCut algorithm to segment masses of regions of interest of mammographic images

According to the World Health Organization, breast cancer is the most common cancer in women worldwide, becoming one of the most fatal types of cancer. Mammography image analysis is still the most effective imaging technology for breast cancer diagnosis, which is based on texture and shape analysis of mammary lesions. The GrowCut algorithm is a general-purpose segmentation method based on cellular automata, able to perform relatively accurate segmentation through the adequate selection of internal and external seed points. In this work we propose an adaptive semi-supervised version of the GrowCut algorithm, based on the modification of the automaton evolution rule by adding a Gaussian fuzzy membership function in order to model non-defined borders. In our proposal, manual selection of seed points of the suspicious lesion is changed by a semiautomatic stage, where just the internal points are selected by using a differential evolution algorithm. We evaluated our proposal using 57 lesion images obtained from MiniMIAS database. Results were compared with the semi-supervised state-of-the-art approaches BEMD, BMCS, Wavelet Analysis, LBI, Topographic Approach and MCW. Results show that our method achieves better results for circumscribed, spiculated lesions and ill-defined lesions, considering the similarity between segmentation results and ground-truth images.

Kidney segmentation in CT sequences using SKFCM and improved GrowCut algorithm.

BackgroundOrgan segmentation is an important step in computer-aided diagnosis and pathology detection. Accurate kidney segmentation in abdominal computed tomography (CT) sequences is an essential and crucial task for surgical planning and navigation in kidney tumor ablation. However, kidney segmentation in CT is a substantially challenging work because the intensity values of kidney parenchyma are similar to those of adjacent structures.ResultsIn this paper, a coarse-to-fine method was applied to segment kidney from CT images, which consists two stages including rough segmentation and refined segmentation. The rough segmentation is based on a kernel fuzzy C-means algorithm with spatial information (SKFCM) algorithm and the refined segmentation is implemented with improved GrowCut (IGC) algorithm. The SKFCM algorithm introduces a kernel function and spatial constraint into fuzzy c-means clustering (FCM) algorithm. The IGC algorithm makes good use of the continuity of CT sequences in space which can automatically generate the seed labels and improve the efficiency of segmentation. The experimental results performed on the whole dataset of abdominal CT images have shown that the proposed method is accurate and efficient. The method provides a sensitivity of 95.46% with specificity of 99.82% and performs better than other related methods.ConclusionsOur method achieves high accuracy in kidney segmentation and considerably reduces the time and labor required for contour delineation. In addition, the method can be expanded to 3D segmentation directly without modification.

2D-gel spot detection and segmentation based on modified image-aware grow-cut and regional intensity information

BackgroundProteomics, the study of proteomes, has been increasingly utilized in a wide variety of biological problems. The Two-Dimensional Gel Electrophoresis (2D-PAGE) technique is a powerful proteomics technique aiming at separation of the complex protein mixtures. Spot detection and segmentation are fundamental components of 2D-gel image analysis but remain arduous and difficult tasks. Several software packages and academic approaches are available for 2D-gel image spot detection and segmentation. Each one has its respective advantages and disadvantages and achieves a different level of success in dealing with the challenges of 2D-gel image analysis. A common characteristic of the available methods is their dependency on user intervention in order to achieve optimal results, a process that can lead to subjective and non-reproducible results. In this work, the authors propose a novel spot detection and segmentation methodology for 2D-gel images. MethodsThis work introduces a novel spot detection and spot segmentation methodology that is based on a multi-thresholding scheme applied on overlapping regions of the image, a custom grow-cut algorithm, a region growing scheme and morphological operators. The performance of the proposed methodology is evaluated on real as well as synthetic 2D-gel images using well established statistical measures, including precision, sensitivity, and their weighted measure, F-measure, as well as volumetric overlap, volumetric error and volumetric overlap error. ResultsExperimental results show that the proposed methodology outperforms state-of-the-art software packages and methods proposed in the literature and results in more plausible spot boundaries and more accurate segmentation. The proposed method achieved the highest F-measure (94.8%) for spot detection and the lowest volumetric overlap error (8.3%) for the segmentation process. ConclusionsEvaluation against state-of-the-art 2D-gel image analysis software packages and techniques proposed in the literature, including Melanie 7, Delta2D, PDQuest and Scimo, demonstrates that the proposed approach outperforms the other methods evaluated in this work and constitutes an advantageous and reliable solution for 2D-gel image analysis.

Grow-cut based automatic cDNA microarray image segmentation.

Complementary DNA (cDNA) microarray is a well-established tool for simultaneously studying the expression level of thousands of genes. Segmentation of microarray images is one of the main stages in a microarray experiment. However, it remains an arduous and challenging task due to the poor quality of images. Images suffer from noise, artifacts, and uneven background, while spots depicted on images can be poorly contrasted and deformed. In this paper, an original approach for the segmentation of cDNA microarray images is proposed. First, a preprocessing stage is applied in order to reduce the noise levels of the microarray image. Then, the grow-cut algorithm is applied separately to each spot location, employing an automated seed selection procedure, in order to locate the pixels belonging to spots. Application on datasets containing synthetic and real microarray images shows that the proposed algorithm performs better than other previously proposed methods. Moreover, in order to exploit the independence of the segmentation task for each separate spot location, both a multithreaded CPU and a graphics processing unit (GPU) implementation were evaluated.

Color Image Segmentation Based on Secondary Watershed and GrowCut Algorithm

GrowCut algorithm is not only an interactive algorithm on the basis of cell automata, but also a multi-label algorithm based on seeds point. Aiming at the GrowCut algorithm usually asks users to partition foreground and background manually and mark a lot more initial seeds. This paper presents an automatic object segmentation method which combining secondary watershed and GrowCut algorithm, here in the following paper refers it to as SWGC algorithm. It firstly using the twice used watershed algorithm to partition the input image, the segmented regions are labeled using Mahalanobis distance, and merged according to the image color and space information, thereafter applying the GrowCut algorithm to perform globally optimized segmentation. The main contribution focuses on performing automatic segmentation which consist of obtain the foreground and background region and generate the seed template of GrowCut algorithm automatically. Thus not only leave out the constraints of user interaction operation, but also avoid the subjectivity and uncertainty. The proposed method reduces the runtime significantly as well as improves the segmentation accuracy and robustness of GrowCut algorithm. Experimental results show SWGC algorithm has superior performance compared to the other related methods.

SU-E-J-238: Monitoring Lymph Node Volumes During Radiotherapy Using Semi-Automatic Segmentation of MRI Images

Purpose: Identification and image-based monitoring of lymph nodes growing due to disease, could be an attractive alternative to prophylactic head and neck irradiation. We evaluated the accuracy of the user-interactive Grow Cut algorithm for volumetric segmentation of radiotherapy relevant lymph nodes from MRI taken weekly during radiotherapy. Method: The algorithm employs user drawn strokes in the image to volumetrically segment multiple structures of interest. We used a 3D T2-wturbo spin echo images with an isotropic resolution of 1 mm3 and FOV of 492×492×300 mm3 of head and neck cancer patients who underwent weekly MR imaging during the course of radiotherapy. Various lymph node (LN) levels (N2, N3, N4'5) were individually contoured on the weekly MR images by an expert physician and used as ground truth in our study. The segmentation results were compared with the physician drawn lymph nodes based on DICE similarity score. Results: Three head and neck patients with 6 weekly MR images were evaluated. Two patients had level 2 LN drawn and one patient had level N2, N3 and N4'5 drawn on each MR image. The algorithm took an average of a minute to segment the entire volume (512×512×300 mm3). The algorithm achieved an overall DICE similarity score of 0.78. The time taken for initializing and obtaining the volumetric mask was about 5 mins for cases with only N2 LN and about 15 mins for the case with N2,N3 and N4'5 level nodes. The longer initialization time for the latter case was due to the need for accurate user inputs to separate overlapping portions of the different LN. The standard deviation in segmentation accuracy at different time points was utmost 0.05. Conclusions: Our initial evaluation of the grow cut segmentation shows reasonably accurate and consistent volumetric segmentations of LN with minimal user effort and time.

Automatic Generation of Statistical Pose and Shape Models for Articulated Joints

Statistical analysis of motion patterns of body joints is potentially useful for detecting and quantifying pathologies. However, building a statistical motion model across different subjects remains a challenging task, especially for a complex joint like the wrist. We present a novel framework for simultaneous registration and segmentation of multiple 3-D (CT or MR) volumes of different subjects at various articulated positions. The framework starts with a pose model generated from 3-D volumes captured at different articulated positions of a single subject (template). This initial pose model is used to register the template volume to image volumes from new subjects. During this process, the Grow-Cut algorithm is used in an iterative refinement of the segmentation of the bone along with the pose parameters. As each new subject is registered and segmented, the pose model is updated, improving the accuracy of successive registrations. We applied the algorithm to CT images of the wrist from 25 subjects, each at five different wrist positions and demonstrated that it performed robustly and accurately. More importantly, the resulting segmentations allowed a statistical pose model of the carpal bones to be generated automatically without interaction. The evaluation results show that our proposed framework achieved accurate registration with an average mean target registration error of 0.34 ±0.27 mm. The automatic segmentation results also show high consistency with the ground truth obtained semi-automatically. Furthermore, we demonstrated the capability of the resulting statistical pose and shape models by using them to generate a measurement tool for scaphoid-lunate dissociation diagnosis, which achieved 90% sensitivity and specificity.

Segmentation of Kidneys from Computed Tomography Using 3D Fast GrowCut Algorithm

This paper proposes a fast GrowCut (FGC) algorithm and applies the new algorithm in three-dimensional (3D)kidney segmentation from computed tomography (CT) volume data. Users could mark the object of interest with different labels in CT slices.FGC propagates the labels using monotonically decreasing function and color features to derive an optimal cut for a given data in space. The color features play a great role in comparing with neighborhood cells. The experimental results clearly demonstrate the superiority of FGC in accuracy and speed.