Threshold-based Segmentation Research Articles

Deep Learning-Based Skin Lesion Diagnosis Model Using Dermoscopic Images

In recent years, intelligent automation in the healthcare sector becomes more familiar due to the integration of artificial intelligence (AI) techniques. Intelligent healthcare systems assist in making better decisions, which further enable the patient to provide improved medical services. At the same time, skin lesion is a deadly disease that affects people of all age groups. Skin lesion segmentation and classification play a vital part in the earlier and precise skin cancer diagnosis by intelligent systems. However, the automated diagnosis of skin lesions in dermoscopic images is challenging because of the problems such as artifacts (hair, gel bubble, ruler marker), blurry boundary, poor contrast, and variable sizes and shapes of the lesion images. This study develops intelligent multilevel thresholding with deep learning (IMLT-DL) based skin lesion segmentation and classification model using dermoscopic images to address these problems. Primarily, the presented IMLT-DL model incorporates the Top hat filtering and inpainting technique for the pre-processing of the dermoscopic images. In addition, the Mayfly Optimization (MFO) with multilevel Kapur’s thresholding-based segmentation process is involved in determining the infected regions. Besides, an Inception v3 based feature extractor is applied to derive a valuable set of feature vectors. Finally, the classification process is carried out using a gradient boosting tree (GBT) model. The presented model’s performance takes place against the International Skin Imaging Collaboration (ISIC) dataset, and the experimental outcomes are inspected in different evaluation measures. The resultant experimental values ensure that the proposed IMLT-DL model outperforms the existing methods by achieving higher accuracy of 0.992.

AlgaeNet: A Deep-Learning Framework to Detect Floating Green Algae From Optical and SAR Imagery

This article developed a scalable deep-learning model, the AlgaeNet model, for floating Ulva prolifera ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> ) detection in moderate resolution imaging spectroradiometer (MODIS) and synthetic aperture radar (SAR) images. We labeled 1055/4071 pairs of samples, among which 70%/30% were used for training/validation. As a result, the model reached an accuracy of 97.03%/99.83% and a mean intersection over union of 48.57%/88.43% for the MODIS/SAR images. The model was designed based on the classic U-Net model with two tailored modifications. First, the physics information input was a multichannel multisource remote sensing data. Second, a new loss function was developed to resolve the class-unbalanced samples (algae and seawater) and improve model performance. In addition, this model is expandable to process images from optical sensors (e.g., MODIS/GOCI/Landsat) and SAR (e.g., Sentinel-1/GF-3/Radarsat-1 or 2), reducing the potential biases due to the selection of extraction thresholds during the traditional threshold-based segmentation. We process satellite images containing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> in the Yellow Sea and draw two conclusions. First, adding the 10-m high-resolution SAR imagery shows a 63.66% increase in algae detection based on the 250-m resolution MODIS image alone. Second, we define a floating and submerged ratio number (FS ratio) based on the floating and submerged parts of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> detected by SAR and MODIS. A research vessel measurement confirms the FS ratio to be a good indicator for representing different life phases of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">U. prolifera</i> .

A novel image processing technique for detection of pseudo occluded bubbles and identification of flow regimes in a bubble column reactor

Pseudo bubble occlusion is a challenging situation for an image analysis tool as it involves a 2D projection of a 3D object. In this work, a robust algorithm has been developed to detect the bubbles from pseudo occlusion. Images of the flow are captured using a high-speed camera. The algorithm employed for bubble detection comprises Adaptive Threshold-based Image Segmentation which comprises segmentation, edge detection, segment grouping, and ellipse fitting. The bubble size is detected and the bubble size distributions for different air flow rates are obtained. The regime identification has been done based on the cell averaged projected void fraction, bubble dimensions, and the distribution of the bubbles. As the superficial air velocity increases in the range of 0–2 cm/s, bubble break up becomes prominent, and hence, the number of smaller size bubbles increases.

View-Consistent Metal Segmentation in the Projection Domain for Metal Artifact Reduction in CBCT – An Investigation of Potential Improvement

The positive outcome of a trauma intervention depends on an intraoperative evaluation of inserted metallic implants. Due to occurring metal artifacts, the quality of this evaluation heavily depends on the performance of so-called Metal Artifact Reduction methods (MAR). The majority of these MAR methods require prior segmentation of the inserted metal objects. Therefore, typically a rather simple thresholding-based segmentation method in the reconstructed 3D volume is applied, despite some major disadvantages. With this publication, the potential of shifting the segmentation task to a learning-based, view-consistent 2D projection-based method on the downstream MAR's outcome is investigated. For segmenting the present metal, a rather simple learning-based 2D projection-wise segmentation network that is trained using real data acquired during cadaver studies, is examined. To overcome the disadvantages that come along with a 2D projection-wise segmentation, a Consistency Filter is proposed. The influence of the shifted segmentation domain is investigated by comparing the results of the standard fsMAR with a modified fsMAR version using the new segmentation masks. With a quantitative and qualitative evaluation on real cadaver data, the investigated approach showed an increased MAR performance and a high insensitivity against metal artifacts. For cases with metal outside the reconstruction's FoV or cases with vanishing metal, a significant reduction in artifacts could be shown. Thus, increases of up to roughly 3 dB w.r.t. the mean PSNR metric over all slices and up to 9 dB for single slices were achieved. The shown results reveal a beneficial influence of the shift to a 2D-based segmentation method on real data for downstream use with a MAR method, like the fsMAR. The nature of the method further suggests the same beneficial behavior for all (also recent data-driven) MAR methods, that for now comprise a 3D-volume-based segmentation step for subsequent inpainting.

A fast and efficient CNN model for B‐ALL diagnosis and its subtypes classification using peripheral blood smear images

The definitive diagnosis of acute lymphoblastic leukemia (ALL), as a highly prevalent cancer, requires invasive, expensive, and time-consuming diagnostic tests. ALL diagnosis using peripheral blood smear (PBS) images plays a vital role in the initial screening of cancer from non-cancer cases. The examination of these PBS images by laboratory users is riddled with problems such as diagnostic error because the nonspecific nature of ALL signs and symptoms often leads to misdiagnosis. Herein, a model based on deep convolutional neural networks (CNNs) is proposed to detect ALL from hematogone cases and then determine ALL subtypes. In this paper, we build a publicly available ALL data set, comprised 3562 PBS images from 89 patients suspected of ALL, including 25 healthy individuals with a benign diagnosis (hematogone) and 64 patients with a definitive diagnosis of ALL subtypes. After color thresholding-based segmentation in the HSV color space by designing a two-channel network, 10 well-known CNN architectures (EfficientNet, MobileNetV3, VGG-19, Xception, InceptionV3, ResNet50V2, VGG-16, NASNetLarge, InceptionResNetV2, and DenseNet201) were employed for feature extraction of different data classes. Of these 10 models, DenseNet201 achieved the best performance in diagnosis and classification. Finally, a model was developed and proposed based on this state-of-the-art technology. This deep learning-based model attained an accuracy, sensitivity, and specificity of 99.85, 99.52, and 99.89%, respectively. The proposed method may help to distinguish ALL from benign cases. This model is also able to assist hematologists and laboratory personnel in diagnosing ALL subtypes and thus determining the treatment protocol associated with these subtypes. The proposed data set is available at https://www.kaggle.com/mehradaria/leukemia and the implementation (source code) of proposed method is made publicly available at https://github.com/MehradAria/ALL-Subtype-Classification.

An Introspective Performance Analysis of Threshold-based Segmentation Techniques on Digital Mammograms

Image segmentation, as a pre-processing step, plays a vital role in medical image analysis. The variants of threshold-based image segmentation methods are proved to offer feasible and optimal solutions to extract the region of interest (RoI), from medical images. Digital mammograms are used as a reliable source of breast cancer prognosis and diagnosis. Thresholding is a simple and effective strategy that finds applications in image processing and analysis. This research aimed to analyze the performance behaviour of a few threshold-based segmentation methods with respect to the intensity distribution of the input mammograms. For this analytical research, six automated thresholding segmentation techniques were chosen: Kapur, Otsu’s, Isoentropic, Ridler &amp; Calvard’s, Kittler &amp; Illingworth's, and Yen. The performance and behaviour of those methods were validated on the digital mammogram images of mini-MIAS database featured with Fatty (F), Fatty-Glandular (G), and Dense-Glandular (D) breast tissues. Those methods were analyzed on two metrics viz., Region Non-Uniformity (RNU) and computation time. The results of this research confirm that Ridler &amp; Calvard’s method gives the best segmentation results for Dense-Glandular, Isoentropic method gives better segmentation results for Fatty and Yen method works well on the Fatty-Glandular normal mammogram images.

Drill bit state-oriented drilling process classification with time-series data for wheeled drilling rigs

This paper represents an analysis of the wheeled drilling rig’s drilling process. Thanks to data from the onboard measurement unit of the machine, the characteristics of the drilling process regarding state of the drill bit are identified and calculated. The aim of the work is to provide a comparison between different drill qualities and process classification using Threshold-based segmentation with feed pressure levels and duration of single hole drilling. Second methodology is hierarchical clustering to create cluster analysis. Thanks to these approaches, it is possible to detect the time when the drill bit should be changed. The obtained results state that the average drill time for a new drill bit is shorter approximately by 50% than for the worn-out bit in terms of average drilling duration. Moreover, these changes are visible in the subsystem pressure level of the machine under specific drilling regimes.

A Multi-Objective Randomly Updated Beetle Swarm and Multi-Verse Optimization for Brain Tumor Segmentation and Classification

Abstract This paper plans to develop the optimal brain tumor classification model with diverse intelligent methods. The main phases of the proposed model are ‘(a) image pre-processing, (b) skull stripping, (c) tumor segmentation, (d) feature extraction and (e) classification’. At first, pre-processing of the image is performed by converting the image from red green blue to gray followed by median filtering. Further, skull stripping is done for removing the extra-meningeal tissue from the head image, which is done by Otsu thresholding. As the main contribution, the tumor segmentation is done by the optimized threshold-based tumor segmentation using multi-objective randomly updated beetle swarm and multi-verse optimization (RBS-MVO). The objective constraints considered for the segmentation of the tumor is entropy and variance. Next, the feature extraction techniques like gray level co-occurrence matrix, local binary pattern and gray-level run length matrix is accomplished to extract the set of features. The classification side uses the combination of neural network (NN) and deep learning model called convolutional neural network (CNN) for tumor classification. The extracted features are subjected to NN, and the segmented image is taken as input to CNN. In addition, the weight function of NN and hidden neurons of CNN is optimized by the RBS-MVO.

A Threshold-based Brain Tumour Segmentation from MR Images using Multi-Objective Particle Swarm Optimization

The Pareto optimal solution is unique in single objective Particle Swarm Optimization (SO-PSO) problems as the emphasis is on the variable space of the decision. A multi-objective-based optimization technique called Multi-Objective Particle Swarm Optimization (MO-PSO) is introduced in this paper for image segmentation. The multi-objective Particle Swarm Optimization (MO-PSO) technique extends the principle of optimization by facilitating simultaneous optimization of single objectives. It is used in solving various image processing problems like image segmentation, image enhancement, etc. This technique is used to detect the tumour of the human brain on MR images. To get the threshold, the suggested algorithm uses two fitness(objective) functions- Image entropy and Image variance. These two objective functions are distinct from each other and are simultaneously optimized to create a sequence of pareto-optimal solutions. The global best (Gbest) obtained from MO-PSO is treated as threshold. The MO-PSO technique tested on various MRI images provides its efficiency with experimental findings. In terms of “best, worst, mean, median, standard deviation” parameters, the MO-PSO technique is also contrasted with the existing Single-objective PSO (SO-PSO) technique. Experimental results show that Multi Objective-PSO is 28% advanced than SO-PSO for ‘best’ parameter with reference to image entropy function and 92% accuracy than Single Objective-PSO with reference to image variance function.

Non-Cooperative Iris Segmentation: A Two-Stage Approach

Aim: The accuracy of the non-cooperative iris recognition is highly dependent on the proper segmentation of the iris region from the input eye image. The traditional non-cooperative iris segmentation algorithms decrease significantly because of several noise factors such as specular reflections, occlusions, eyelashes, and eyelids. However, several techniques are developed to overcome these drawbacks in the iris segmentation process; it is still a challenging task to localize the iris texture regions. Background: Recently, segmentation of iris image is the most important process in a robust iris recognition system due to the images captured from non-cooperative environments which introduce occlusions, blur, specular reflections, and off-axis. However, several techniques are developed to overcome these drawbacks in the iris segmentation process; it is still a challenging task to localize the iris texture regions. In this research, an effective two-stage of iris segmentation technique is proposed in a non-cooperative environment. Objective: To proposed an effective two-stage of iris segmentation technique in a non-cooperative environment. Methods: Modified Geodesic Active Contour-based level set segmentation with Particle Swarm Optimization (PSO) is employed for iris segmentation. In this, the PSO algorithm is used to minimize the energy of the gradient descent equation in a region-based level set segmentation algorithm. The global threshold-based segmentation (enhanced Otsu’s method) is employed for pupil region segmentation. Results: The experiment considered two well-known databases such as UBIRIS.V1 and UBIRIS.V2. The simulation outcomes demonstrate that the proposed novel approach attained more accurate and robust iris segmentation under non-cooperative conditions. Also, the results of the modified Geodesic Active Contour-based level set segmentation with the PSO algorithm attained better results than the conventional segmentation techniques. Conclusion: An effective two-stage of iris segmentation is proposed in a non-cooperative environment using Geodesic active contour-based level set segmentation with particle swarm optimization and an enhanced Otsu method is employed for pupil segmentation. The proposed two-stage of iris segmentation technique segments the iris in its genuine shape which will provide a more robust and precise iris recognition system.

MudrockNet: Semantic segmentation of mudrock SEM images through deep learning

Segmentation and analysis of individual pores and grains of mudrocks from scanning electron microscope images is non-trivial because of imaging artifacts, variation in pixel grayscale values across images, and overlaps in grayscale values among different physical features such as silt grains, clay grains and pores, which make identifications difficult. Moreover, because grains and pores often have overlapping grayscale values, direct application of threshold-based segmentation techniques is not sufficient. Recent advances in the field of computer vision have made it easier and faster to segment images and identify multiple occurrences of such features in an image, provided that ground-truth data for training the algorithm are available. Here we propose a deep learning SEM image segmentation model, MudrockNet based on Google's DeepLab-v3+ architecture implemented with the TensorFlow library. The ground-truth data were obtained from an image-processing workflow applied to scanning electron microscope images of uncemented muds from the Kumano Basin offshore Japan at depths <1.1 km. The trained deep learning model obtained a pixel-accuracy > 90%, and predictions for the test data obtained a mean intersection over union (IoU) of 0.6663 for silt grains, 0.7797 for clay grains and 0.6751 for pores. We also compared our model with the random forest classifier using trainable Weka segmentation in ImageJ, and it was observed that MudrockNet gave better predictions for silt grains, clay grains and pores in most cases. The size, concentration, and spatial arrangement of the silt and clay grains can affect the petrophysical properties of a mudrock, and an automated method to accurately identify the different grains and pores in mudrocks can help improve reservoir and seal characterization for petroleum exploration and anthropogenic waste sequestration.

Semi-automated and interactive segmentation of contrast-enhancing masses on breast DCE-MRI using spatial fuzzy clustering

Multiparametric Magnetic Resonance Imaging (MRI) is the most sensitive imaging modality for breast cancer detection and is increasingly playing a key role in lesion characterization. In this context, accurate and reliable quantification of the shape and extent of breast cancer is crucial in clinical research environments. Since conventional lesion delineation procedures are still mostly manual, automated segmentation approaches can improve this time-consuming and operator-dependent task by annotating the regions of interest in a reproducible manner. In this work, a semi-automated and interactive approach based on the spatial Fuzzy C-Means (sFCM) algorithm is proposed, used to segment masses on dynamic contrast-enhanced (DCE) MRI of the breast. Our method was compared against existing approaches based on classic image processing, namely (i) Otsu’s method for thresholding-based segmentation, and (ii) the traditional FCM algorithm. A further comparison was performed against state-of-the-art Convolutional Neural Networks (CNNs) for medical image segmentation, namely SegNet and U-Net, in a 5-fold cross-validation scheme. The results showed the validity of the proposed approach, by significantly outperforming the competing methods in terms of the Dice similarity coefficient (84.47±4.75). Moreover, a Pearson’s coefficient of ρ=0.993 showed a high correlation between segmented volume and the gold standard provided by clinicians. Overall, the proposed method was confirmed to outperform the competing literature methods. The proposed computer-assisted approach could be deployed into clinical research environments by providing a reliable tool for volumetric and radiomics analyses.

Deep Learning Based Capsule Neural Network Model for Breast Cancer Diagnosis Using Mammogram Images.

Breast cancer is a commonly occurring disease in women all over the world. Mammogram is an efficient technique used for screening and identification of abnormalities over the breast region. Earlier identification of breast cancer enhances the prognosis of patients and is mainly based on the experience of the radiologist in interpretation of mammogram with quality of image. The advent of Deep Learning (DL) and Computer Vision techniques is widely used to perform breast cancer diagnosis. This paper presents a new Optimal Multi-Level Thresholding-based Segmentation with DL enabled Capsule Network (OMLTS-DLCN) breast cancer diagnosis model utilizing digital mammograms. The OMLTS-DLCN model involves an Adaptive Fuzzy based median filtering (AFF) technique as a pre-processing step to eradicate the noise that exists in the mammogram images. Besides, Optimal Kapur's based Multilevel Thresholding with Shell Game Optimization (SGO) algorithm (OKMT-SGO) is applied for breast cancer segmentation. In addition, the proposed model involves a CapsNet based feature extractor and Back-Propagation Neural Network (BPNN) classification model is employed to detect the existence of breast cancer. The diagnostic outcomes of the presented OMLTS-DLCN technique is examined by means of benchmark Mini-MIAS dataset and DDSM dataset. The experimental values obtained highlights the superior performance of the OMLTS-DLCN model with a higher accuracy of 98.50 and 97.55% on the Mini-MIAS dataset and DDSM dataset, respectively.

B-PO05-076 REPRODUCIBILITY OF LEFT ATRIAL ENDO AND EPICARDIAL WALL EXTRACTION FROM CTA

LA wall thickness (LAWT) is a major determinant of lesion transmurality in AF ablation. Computed tomography angiography (CTA) provides sub-millimetric resolution allowing reliable 3D LAWT segmentation. To analyze the intra and inter-user reproducibility of 3D CTA LAWT segmentations. Three observers with different levels of expertise performed, using ADAS 3D, complete LAWT segmentation of CTA (0.5x0.5x0.6mm) once for thirty patients and twice for ten. The endocardial layer was generated by a semi-automatic threshold-based segmentation. The epicardial, by manual contouring of key transverse slices followed by automatic interpolation. Finally, the user adjusted the 3D reconstructions. LAWT, presented as a discretized color map, was generated assigning at each point of the endocardium the distance to the epicardium. Reproducibility was calculated as the point to surface distance between different analyses of the same patient. Pulmonary veins, LAA and mitral annulus were excluded from analysis. Endocardial segmentations were closer than 1mm in 99.38%±0.86 of the vertices for intra and 95.12%±5.07 for inter-user variability, with a mean distance between meshes of 0.17mm±0.08 and 0.30mm±0.18, respectively. For the epicardium, mean distances between meshes were 0.54mm±0.17 for intra and 0.72mm±0.16 for inter-observer, and closer than 1 mm in 82.38%±9.89 of points for intra and 77.68%±7.16 for inter-user analyses. Reproducibility improved significantly (p<0.05) with user expertise. Obtaining reliable CTA-derived 3D LAWT maps by means of endo and epicardial segmentation of the LA wall is feasible with high reproducibility.

Tissue segmentation in histologic images of intracranial aneurysm wall

We qualitatively compare three image segmentation techniques (filter and threshold-based segmentation, texture-based clustering and deep learning) for histologic images of intracranial aneurysms. Due to remodeling of the vessel wall and aneurysm formation, the tissue is highly diverse. Only the deep learning segmentation provided semantic information about the segmented tissue. The other segmentation techniques were designed to segment areas of different textures and tissues, respectively. Therefore, in contrast to the deep learning approach, they did not require knowledge of all tissue types possible occurring in intracranial aneurysms. Rare tissue classes were missed by the deep learning segmentation, but the resolution of the deep learning segmentation was better than the ground truth segmentation. Overall, the deep learning segmentation of ten classes achieved a test accuracy of 60.68%.

Entropy-Aided Assessment of Amla (Emblica officinalis) Quality Using Principal Component Analysis

The texture analysis-based scheme for identifying non-consumable amla fruit (Emblica officinalis) samples is proposed here. The method uses entropy analysis to detect wrinkles and irregularities developed on the fruit surface with progression in time. Since entropy is one of the major tools used to detect the randomness of data, it is used here to identify these surface irregularities, which are almost absent in fresh samples. Based on these features, the edibility of the samples is predicted. Principal component analysis (PCA) further analyzes these entropy features to enhance the most important directions of variations, followed by a threshold-based segmentation scheme to detect rotten samples. The method possesses less computational burden as it applies PCA and entropy only; it is highly efficient to yield a high detection accuracy of 93.33%; hence, it is easy for real-life implementation.

Image Analysis of Sauvola and Niblack Thresholding Techniques

Image segmentation is a critical problem in computer vision and other image processing applications. Image segmentation has become quite challenging over the years due to its widespread use in a variety of applications. Image thresholding is a popular image segmentation technique. The segmented image quality is determined by the techniques used to determine the threshold value.A locally adaptive thresholding method based on neighborhood processing is presented in this paper. The performance of locally thresholding methods like Niblack and Sauvola was demonstrated using real-world images, printed text, and handwritten text images. Threshold-based segmentation methods were investigated using misclassification error, MSE and PSNR. Experiments have shown that the Sauvola method outperforms real-world images, printed and handwritten text images in terms of misclassification error, PSNR, and MSE.

A Hybrid CNN-SVM Threshold Segmentation Approach for Tumor Detection and Classification of MRI Brain Images

ObjectiveIn this research paper, the brain MRI images are going to classify by considering the excellence of CNN on a public dataset to classify Benign and Malignant tumors. Materials and MethodsDeep learning (DL) methods due to good performance in the last few years have become more popular for Image classification. Convolution Neural Network (CNN), with several methods, can extract features without using handcrafted models, and eventually, show better accuracy of classification. The proposed hybrid model combined CNN and support vector machine (SVM) in terms of classification and with threshold-based segmentation in terms of detection. ResultThe findings of previous studies are based on different models with their accuracy as Rough Extreme Learning Machine (RELM)-94.233%, Deep CNN (DCNN)-95%, Deep Neural Network (DNN) and Discrete Wavelet Autoencoder (DWA)-96%, k-nearest neighbors (kNN)-96.6%, CNN-97.5%. The overall accuracy of the hybrid CNN-SVM is obtained as 98.4959%. ConclusionIn today's world, brain cancer is one of the most dangerous diseases with the highest death rate, detection and classification of brain tumors due to abnormal growth of cells, shapes, orientation, and the location is a challengeable task in medical imaging. Magnetic resonance imaging (MRI) is a typical method of medical imaging for brain tumor analysis. Conventional machine learning (ML) techniques categorize brain cancer based on some handicraft property with the radiologist specialist choice. That can lead to failure in the execution and also decrease the effectiveness of an Algorithm. With a brief look came to know that the proposed hybrid model provides more effective and improvement techniques for classification.

A Kriging-Based Magnetic Flux Leakage Method for Fast Defect Detection in Massive Pipelines

Abstract Systems in service continue to degrade with the passage of time. Pipelines are among the most common systems that wear away with usage. For public safety, it is of utmost importance to monitor pipelines. Magnetic flux leakage (MFL) testing is a widely used nondestructive evaluation (NDE) technique for defect detections within the pipelines, particularly those composed of ferromagnetic materials. Pipeline inspection gauge (PIG) procedure based on line scans can collect accurate MFL readings for defect detection. However, in real world, applications involving large pipe sectors such as extensive scanning techniques are extremely time consuming and costly. In this article, we develop a fast and cheap methodology that does not need MFL readings at all the points used in traditional PIG procedures but conducts defect detection with similar accuracy. We consider an under-sampling based scheme that collects MFL at uniformly chosen random scan points over large lattices instead of extensive PIG scans over all lattice points. On the basis of readings from the chosen random scan points, we use kriging to reconstruct MFL readings. Thereafter, we use thresholding-based segmentation on the reconstructed data for detecting defective areas. We demonstrate the applicability of our methodology on synthetic data generated using finite element models and on MFL data collected via laboratory experiments. In these experiments, spanning a wide range of defect types, our proposed novel MFL-based NDE methodology is witnessed to have operating characteristics within the acceptable threshold of PIG-based traditional methods and thus provide an extremely cost-effective, fast procedure with competing error rates.

Efficient Segmentation of Lymphoblast in Acute Lymphocytic Leukemia

Microscopic examination of peripheral blood smears and bone marrow is the preliminary step for the diagnosis of several life-threatening diseases. Acute lymphocytic leukemia (ALL) is the most common disease in children that also needs an early diagnosis for on-time treatment as it spreads rapidly in the blood and forms immature lymphocytes. This might cause death in some weeks if left untreated. Manual methods in clinical laboratory being applied for the diagnosis of these diseases are inefficient and expensive, and the results are less accurate. A computer-aided system is the need of the day in which the most important step is segmenting the region of interest in blood or bone marrow for the detection and cure of the diseases which is the most challenging task. This study aims to propose a simple threshold-based segmentation technique by processing the S component of the HSV color space to segment the lymphoblasts in the bone marrow images of ALL patients. The technique was applied to 230 RGB bone marrow images having all the three types of ALL, i.e., L1, L2, and L3 resulted in the overall accuracy of 96.8%.