Obtained Segmentation Results Research Articles

#439 Nephron number determination in whole slide mice kidney specimens using a deep learning assisted disector/fractionator approach

Abstract Background and Aims Nephron number highly varies between different species and within species, ranging in humans from 200 000 to 2 000 000 nephrons per kidney. Low nephron numbers can promote early onset of end-stage kidney disease. Nephron assessment is highly needed for better diagnosis and more targeted treatment. However, its assessment in vivo is not established in clinical practice yet. Pioneer studies suggest nephron number estimation in vivo through a combination of glomerular densities in kidney biopsies together with medical imaging. In contrast, post-mortem nephron assessment either using optical clearing or by exhaustive kidney sectioning is well studied but remains laborious. Here, we propose a new semi-automated nephron counting approach using serial PAS-stained whole slide kidney sections, deep learning segmentation and slide registration. Method Mice were sacrificed, kidneys harvested, measured, halved in the coronary plane and then opposingly embedded in paraffin. Subsequently, the entire kidney was sectioned with 10 µm thickness per slide. Tissue was stained with PAS and slides were digitalized using Aperio GT 450 DX scanner (Leica, Wetzlar, Germany) (Fig. a). Deep learning segmentation of glomeruli was performed in the first and every 10th (reference) section and subsequent (look-up) section using Tensorflow. Obtained segmentation results were manually quality controlled and adjusted, if necessary, in QuPath (Fig. b). Final segmentations of the look-up slides were registered to the reference slides in ImageJ using manual landmarks with the ImageJ BigWarp plugin (Fig. c). Glomeruli being present either in the look-up slide, or in the reference slide were counted as disector particles (Q-). Kidney areas on every examined slide were measured. Total number of glomeruli and total kidney area were determined as previously described (Fig. d). Results A kidney from a 12-week-old mouse suffering chronic kidney disease (mouse line Alb-creERT2 (ki/ki); Glut9 (fl/fl)) was used. Kidney weight was 162 mg, length 11 mm, width 6 mm, depth 4 mm and kidney volume 260 mm³. In total the kidney was sectioned in 95 slices. 20 reference sections and its respective look-up sections were stained and digitalized. In total 5981 glomeruli were segmented in 40 kidney slices using the deep learning algorithm. Glomerular segmentation quality was verified by two independent observers (mean dice score 0.79). Inaccuracies, if any, where manually corrected. For image registration in average 18.1 landmarks per slide were created within the ImageJ BigWarp plugin. Registration took in average 5 minutes per slide. Glomeruli without match (disector particles, Q-) were automatically counted. Number of disector particles (Q-) ranged from 32 to 244 per slide. Total nephron number was 11.085 and kidney area 210 mm³. The differences to the manual measured volume (260 mm³) might be explained by discard of small kidney fractions for the used sectioning technique. Conclusion We report, to our knowledge, the first deep learning assisted disector/fractionator approach to determine nephron number in whole slide kidney specimens. This method requires no physical disector setup, is scalable, cheap, time efficient, and unbiased. The method was so far validated in a mouse model of chronic kidney disease. The method will further be validated on different animal models. Additionally, occurrence of atubular glomeruli will be considered in nephron number determination. Furthermore, the integration of GFR measurements might allow the calculation of mean single nephron GFR and might together with automated glomerular area measurements unravel pathophysiologic processes in kidney ageing and disease.

DCCaps-UNet: A U-Shaped Hyperspectral Semantic Segmentation Model Based on the Depthwise Separable and Conditional Convolution Capsule Network

Traditional hyperspectral image semantic segmentation algorithms can not fully utilize the spatial information or realize efficient segmentation with less sample data. In order to solve the above problems, a U-shaped hyperspectral semantic segmentation model (DCCaps-UNet) based on the depthwise separable and conditional convolution capsule network was proposed in this study. The whole network is an encoding–decoding structure. In the encoding part, image features are firstly fully extracted and fused. In the decoding part, images are then reconstructed by upsampling. In the encoding part, a dilated convolutional capsule block is proposed to fully acquire spatial information and deep features and reduce the calculation cost of dynamic routes using a conditional sliding window. A depthwise separable block is constructed to replace the common convolution layer in the traditional capsule network and efficiently reduce network parameters. After principal component analysis (PCA) dimension reduction and patch preprocessing, the proposed model was experimentally tested with Indian Pines and Pavia University public hyperspectral image datasets. The obtained segmentation results of various ground objects were analyzed and compared with those obtained with other semantic segmentation models. The proposed model performed better than other semantic segmentation methods and achieved higher segmentation accuracy with the same samples. Dice coefficients reached 0.9989 and 0.9999. The OA value can reach 99.92% and 100%, respectively, thus, verifying the effectiveness of the proposed model.

A Novel Interval Iterative Multi-Thresholding Algorithm Based on Hybrid Spatial Filter and Region Growing for Medical Brain MR Images

Medical image segmentation is widely used in clinical medicine, and the accuracy of the segmentation algorithm will affect the diagnosis results and treatment plans. However, manual segmentation of medical images requires extensive experience and knowledge, and it is both time-consuming and labor-intensive. To overcome the problems above, we propose a novel interval iterative multi-thresholding segmentation algorithm based on hybrid spatial filter and region growing for medical brain MR images. First, a hybrid spatial filter is designed to perform on the original image, which can make full use of the spatial information while denoising. Second, the interval iterative Otsu method based on region growing is proposed to segment the original image and its filtering layer. The initial thresholds can be quickly obtained by region growing algorithm, which can reduce the time complexity. The interval iterative algorithm is used to optimize the thresholds. Finally, a weighted strategy is used to refine the segmentation results. The segmentation results of our proposed algorithm outperform other comparison algorithms in both subjective and objective evaluations. Subjectively, the obtained segmentation results have clear edges, complete and consistent regions. We use the uniformity measure (U) for objective evaluation, and the U value is significantly higher than other comparison algorithms. The proposed algorithm achieved an average U value of 0.9854 across all test images. The proposed algorithm can segment medical images well and expand the doctor’s ability to utilize medical images.

Deep learning approach to skin layers segmentation in inflammatory dermatoses

Monitoring skin layers with medical imaging is critical to diagnosing and treating patients with chronic inflammatory skin diseases. The high-frequency ultrasound (HFUS) makes it possible to monitor skin condition in different dermatoses. Accurate and reliable segmentation of skin layers in patients with atopic dermatitis or psoriasis enables the assessment of the treatment effect by the layer thickness measurements. The epidermis and the subepidermal low echogenic band (SLEB) are the most important for further diagnosis since their appearance is an indicator of different skin problems. In medical practice, the analysis, including segmentation, is usually performed manually by the physician with all drawbacks of such an approach, e.g., extensive time consumption and lack of repeatability. Recently, HFUS becomes common in dermatological practice, yet it is barely supported by the development of automated analysis tools. To meet the need for skin layer segmentation and measurement, we developed an automated segmentation method of both epidermis and SLEB layers. It consists of a fuzzy c-means clustering-based preprocessing step followed by a U-shaped convolutional neural network. The network employs batch normalization layers adjusting and scaling the activation to make the segmentation more robust. The obtained segmentation results are verified and compared to the current state-of-the-art methods addressing the skin layer segmentation. The obtained Dice coefficient equal to 0.87 and 0.83 for the epidermis and SLEB, respectively, proves the developed framework’s efficiency, outperforming the other approaches.

Automatic Pancreas Segmentation Using Double Adversarial Networks With Pyramidal Pooling Module

Owing to the irregular shape and high anatomical variability of the pancreas in abdominal CT images, pancreas segmentation is regarded as a challenging task. To address this issue, we propose an automatic segmentation model using double adversarial networks with a pyramidal pooling module. First, we introduce double adversarial networks that double-check whether the obtained segmentation results are similar to their ground truths owing to the special competing mechanism of adversarial learning, which contributes to the capturing of spatial information for segmentation and prompts the obtained samples to be more realistic, to improve the network segmentation performance. Second, we design a pyramidal pooling module to collect multi-level features and retain substantial information for segmentation in order to further boost the network performance. Finally, to assess the segmentation performance of our model, we use several indexes, namely the Dice similarity coefficient (DSC), Jaccard index, precision, and recall, as evaluation indicators. Experimental results show that the proposed model outperforms most existing pancreas segmentation methods.

Automatic detection and segmentation of lumbar vertebrae from X-ray images for compression fracture evaluation

For compression fracture detection and evaluation, an automatic X-ray image segmentation technique that combines deep-learning and level-set methods is proposed. Automatic segmentation is much more difficult for X-ray images than for CT or MRI images because they contain overlapping shadows of thoracoabdominal structures including lungs, bowel gases, and other bony structures such as ribs. Additional difficulties include unclear object boundaries, the complex shape of the vertebra, inter-patient variability, and variations in image contrast. Accordingly, a structured hierarchical segmentation method is presented that combines the advantages of two deep-learning methods. Pose-driven learning is used to selectively identify the five lumbar vertebrae in an accurate and robust manner. With knowledge of the vertebral positions, M-net is employed to segment the individual vertebra. Finally, fine-tuning segmentation is applied by combining the level-set method with the previously obtained segmentation results. The performance of the proposed method was validated by 160 lumbar X-ray images, resulting in a mean Dice similarity metric of 91.60±2.22%. The results show that the proposed method achieves accurate and robust identification of each lumbar vertebra and fine segmentation of individual vertebra.

Towards a computer aided diagnosis (CAD) for brain MRI glioblastomas tumor exploration based on a deep convolutional neuronal networks (D-CNN) architectures

Manuel brain glioblastomas tumor exploration through MRI modalities is time-consuming. It is considered as a harmful and critical task due to highly inhomogeneous tumor regions composition. For this reason, clinicians recommend the Computer-Aided Diagnosis (CAD) tools to ensure a more accurate diagnostic. Based on convolutional Deep-Learning algorithms, this paper investigates a fully automatic CAD for brain Glioblastomas tumors exploration including three steps: pre-processing, segmentation, and finally classification. A denoising and an automatic contrast enhancement method have been applied to preprocess the MRI scans. A Multi-Modal Cascaded U-net architecture, based on Fully Convolutional deep Network (FCN), has been adopted for the Region of Interest (ROI) extraction and finally, Deep Convolutional Neural Network (D-CNN) architecture has been used to classify brain glioblastomas tumor into High-Grade (HG) and Low-Grade (LG). Experiments were performed on the Multimodal Brain Tumor Segmentation Challenge BraTS-2018 datasets benchmark. Several validations metric have been adopted to assess the CAD’s performances. The Dice Metric (DM) parameter has been calculated between the obtained segmentation results and the available ground truth data. The accuracy parameter has been computed for classification performance evaluation. The higher DM and accuracy values could attest the performance and the efficiency of the proposed CAD tool.

DeepSeg: deep neural network framework for automatic brain tumor segmentation using magnetic resonance FLAIR images

PurposeGliomas are the most common and aggressive type of brain tumors due to their infiltrative nature and rapid progression. The process of distinguishing tumor boundaries from healthy cells is still a challenging task in the clinical routine. Fluid-attenuated inversion recovery (FLAIR) MRI modality can provide the physician with information about tumor infiltration. Therefore, this paper proposes a new generic deep learning architecture, namely DeepSeg, for fully automated detection and segmentation of the brain lesion using FLAIR MRI data.MethodsThe developed DeepSeg is a modular decoupling framework. It consists of two connected core parts based on an encoding and decoding relationship. The encoder part is a convolutional neural network (CNN) responsible for spatial information extraction. The resulting semantic map is inserted into the decoder part to get the full-resolution probability map. Based on modified U-Net architecture, different CNN models such as residual neural network (ResNet), dense convolutional network (DenseNet), and NASNet have been utilized in this study.ResultsThe proposed deep learning architectures have been successfully tested and evaluated on-line based on MRI datasets of brain tumor segmentation (BraTS 2019) challenge, including s336 cases as training data and 125 cases for validation data. The dice and Hausdorff distance scores of obtained segmentation results are about 0.81 to 0.84 and 9.8 to 19.7 correspondingly.ConclusionThis study showed successful feasibility and comparative performance of applying different deep learning models in a new DeepSeg framework for automated brain tumor segmentation in FLAIR MR images. The proposed DeepSeg is open source and freely available at https://github.com/razeineldin/DeepSeg/.

Epithelium segmentation and automated Gleason grading of prostate cancer via deep learning in label-free multiphoton microscopic images.

In the current clinical care practice, Gleason grading system is one of the most powerful prognostic predictors for prostate cancer (PCa). The grading system is based on the architectural pattern of cancerous epithelium in histological images. However, the standard procedure of histological examination often involves complicated tissue fixation and staining, which are time-consuming and may delay the diagnosis and surgery. In this study, label-free multiphoton microscopy (MPM) was used to acquire subcellular-resolution images of unstained prostate tissues. Then, a deep learning architecture (U-net) was introduced for epithelium segmentation of prostate tissues in MPM images. The obtained segmentation results were then merged with the original MPM images to train a classification network (AlexNet) for automated Gleason grading. The developed method achieved an overall pixel accuracy of 92.3% with a mean F1 score of 0.839 for epithelium segmentation. By merging the segmentation results with the MPM images, the accuracy of Gleason grading was improved from 72.42% to 81.13% in hold-out test set. Our results suggest that MPM in combination with deep learning holds the potential to be used as a fast and powerful clinical tool for PCa diagnosis.

Strong target constrained video saliency detection

Aiming at the problem of video saliency detection, a strong target constrained video saliency detection method is proposed in this paper. In order to detect the salient region fast and effectively, strong target constraints forcing by the location, scale and color model are introduced into the video saliency detection. First, a target locating strategy for obtaining the location and scale information is proposed by correcting the result of video tracking with the optical flow result and the segmentation result of the last frame. Second, the estimated color model of the target is also calculated by the obtained segmentation results. Finally, the strong target constraints are integrated into the saliency model in the way of extending the significance hypothesis, and a high quality saliency map is obtained, where segmentation is employed for constrained parameters updating. In details, Densecut is initialized by the obtained saliency map to calculate the segmentation result of the last frame. Compared with some state-of-art saliency detection methods, our proposed method performs outstandingly, and the results on DAVIS dataset are significantly improved in terms of accuracy and robustness.

Selecting geomorphic variables for automatic river segmentation: Trade-offs between information gained and effort required

Identifying river segments with apparently distinct geomorphic characteristics but relatively homogeneous internal features may be critically helpful in designing network analysis for characterization, environmental assessment and river management. Automatic segmentation procedures using geographic tools and statistical methods provide objective and replicable results. In particular, multivariate procedures may be appropriated for different purposes such as coping with the multiple dimensionality of river systems. Although there is an increasing number of studies dealing with segmentation using different sets of morphological variables, the influence that the selected variables have on segmentation results is rarely assessed. In this context, we defined five combinations of frequently used geomorphic variables (i.e., channel slope, active channel width, valley bottom width, channel confinement and specific stream power), and compared the obtained segmentation results. We study the upper Esla River network, covering a total length of 294 km, with the largest two rivers regulated by large dams. Variables were measured at successive river sections 200 m apart. Five segmentation results were obtained in which we compared the number and characteristics of the segments, and the internal variability and the suitability of predicting river dynamics (i.e., occurrence of bare and vegetated gravel bars). The number of segments per kilometer of river and their average length were different among segmentations but varied much more across rivers than across segmentations. In general, segmentations including channel slope and active channel width performed better in predicting the occurrence of bare gravel bars than segmentations based on stream power or valley confinement. When splitting the initial data set into regulated and non-regulated segments, differences in predicting the occurrence of gravel bars were found, with better results in the case of non-regulated rivers. Channel slope and active channel width showed a reduced explanatory power for the regulated reaches. Finally, we conclude that primary geomorphic variables such as channel slope and active channel width were more efficient than secondary variables such as stream power, which may encompass more information but needed additional data and the use of empirical models, with greater effort and much uncertainty. In the case of regulated rivers, automatic segmentation including the affected variables (e.g., active channel width) may help in detecting differences in geomorphic sensitivity to river adjustments across the resulting segments downstream from the dams. Our results offer valuable insights into the selection of geomorphic variables for river segmentation analysis, in which trade-offs between the information gained and the effort required must be considered according to the respective research targets.

Regenerative Semi-Supervised Bidirectional W-Network-Based Knee Bone Tumor Classification on Radiographs Guided by Three-Region Bone Segmentation

The objective of this study is to develop and evaluate a new deep learning architecture, namely regenerative semi-supervised bidirectional W-network (RSS-BW), to predict the tumor state of the knee bone from radiographic images. First, we constructed an autoencoder model, called Bidirectional W-network (BW), for segmenting three-region (i.e., femur, tibia, and fibula) of knee bone. Using these regions as input data, RSS-BW architecture consisting of the autoencoding model for regenerating the bone structures, the backbone model for extracting features with pretrained ImageNet, and the predicting model for knee bone tumor classification are established. The developed scheme rapidly obtained segmentation results of the three-region of knee bone with a mean dice score of 98.06 ± 0.08%. Moreover, two types of classification are conducted: single-step and double-step. The single-step classifies the bone images into normal, benign, and malignant states. The mean values of accuracy, precision, recall and F-beta score obtained from the segmented images were 85.23±3.91%, 82.23±3.22%, 82.15±3.31%, and 82.21±3.25%, respectively. For the double-step of bone tumor classification, the images are classified first as normal versus abnormal. The second classification is conducted for abnormal images as benign versus malignant. The double-step classification shows an improvement of the mean accuracy by 1.7% compared to the single-step classification. In conclusion, the RSS-BW model presents higher accuracy than conventional models, indicating its potential clinical decision support for bone tumor classification.

Decreasing Respondent Heterogeneity by Likert Scales Adjustment via Multipoles

A description of Likert scales can be given using the multipoles technique known in quantum physics and applied to behavioral sciences data. This paper considers decomposition of Likert scales by the multipoles for the application of decreasing the respondents’ heterogeneity. Due to cultural and language differences, different respondents habitually use the lower end, the mid-scale, or the upper end of the Likert scales which can lead to distortion and inconsistency in data across respondents. A big impact of different kinds of respondent is well known, for instance, in international studies, and it is called the problem of high and low raters. Application of a multipoles technique to the row-data smoothing via prediction of individual rates by the histogram of the Likert scale tiers produces better results than standard row-centering in data. A numerical example by marketing research data shows that the results are encouraging: while a standard row-centering produces a poor outcome, the dipole-adjustment noticeably improves the obtained segmentation results.

A target image–oriented dictionary learning–based method for fully automated latent fingerprint forensic

AbstractSeveral fully automated latent print forensic techniques have been reported. In this paper, we propose a fully automated latent print segmentation module for the partition of the fingerprint region in a query latent image, which can help find a corresponding match of the suspect reliably. Being different from the existing methods that build the prelearned dictionary from the high‐quality fingerprint image patches, the proposed dictionary learning procedure is conducted on the target images. The advantages of the proposed method are the following: (i) it does not require a large number of high‐quality “ridge‐valley” atoms and (ii) not only the structure similarity but also the pattern scale has been kept consistent between the target image patches and learned dictionary atoms. Because no commercial latent fingerprint matcher is publicly available and the latent matcher reported in the literature is not accessible to the public either, a latent fingerprint matching platform is implemented to evaluate the obtained segmentation results and automated latent fingerprint matching performance. On the basis of this platform, experimental comparisons are conducted to assess closeness to the system performance upper bound when different segmentation modules are deployed. Moreover, matcher‐independent criteria such as genuine minutiae preservation rate and the segmented region of interest's accuracy are used. All the experimental results demonstrate that the proposed segmentation approach outperforms state‐of‐the‐art techniques in terms of finding the correct fingerprint of the suspect subject.

Automatic segmentation of seismic signal with support of innovative filtering

The paper presents a new algorithm for automatic segmentation of seismic signal. This segmentation relies on the observation of changes in the signal spectrum structure based exclusively on second-order signals statistics. The starting point of the proposed method are time-varying reflection coefficients of adaptive innovation filter. Schur's algorithm, performing the estimation of the reflection coefficients, is known as a fast, accurate and stable algorithm capable of quickly tracking the changes in signal statistics. Signal segmentation is a necessary stage for further processing of the signals, their interpretation, modelling or automatic classification. The issue of automatic segmentation is known in literature for its many applications (diagnostics of machinery, speech analysis, medicine etc.). There have also been a few proposals for segmentation of seismic signals. Unfortunately, segmentation of seismic signals is very difficult because of their variability. The purpose of the authors' work was to design an algorithm, which could be used in automatic processing of seismic signals in a deep underground copper mine. The paper presents the algorithm structure, defines its properties, specifies the values of parameters and presents the results of the effectiveness of the detection process. The obtained segmentation results are satisfactory.

Statistical textural feature and deformable model based brain tumor segmentation and volume estimation

Segmentation and precise volume estimation of abnormalities is one of the main focus in medical image processing field for the purpose of diagnosis and treatment planning. The precise estimation of volume of the abnormality aids better prognosis, treatment planning and dose estimation. The work put forth in this paper has proposed and implemented a semi-automatic technique that yields appropriate segmented regions from MR brain images. The Segmentation technique here utilizes fusion of information beyond human perception from MR images to develop a fused feature map. The information beyond human perception include second order derivatives that are computed from an image which are discussed in detail in relevant section of this paper. This obtained feature map acts as a stopping function for the initialized curve in the framework of an active contour model to obtain a well segmented region of interest. The segmentation is carried out in all the slices of a particular dataset with initialization of the active contour required only on the first slice which makes this method fast. The obtained segmentation results are compared with ground truth segmentation results obtained from experts manually using Jackard's Co-efficient of Similarity and Overlap index. The boundaries of the segmented regions are utilized in surveyor's algorithm to compute the volume of the tumors with high accuracy. The efficacy of this volume estimation technique is illustrated with comparison to mostly used ABC/2 method and cavalieri method. The results obtained on various case studies like Craniophryngioma, High grade Glioma and Microadenoma show a good efficacy of the overall method.

3D cerebral MR image segmentation using multiple-classifier system.

The three soft brain tissues white matter (WM), gray matter (GM), and cerebral spinal fluid (CSF) identified in a magnetic resonance (MR) image via image segmentation techniques can aid in structural and functional brain analysis, brain's anatomical structures measurement and visualization, neurodegenerative disorders diagnosis, and surgical planning and image-guided interventions, but only if obtained segmentation results are correct. This paper presents a multiple-classifier-based system for automatic brain tissue segmentation from cerebral MR images. The developed system categorizes each voxel of a given MR image as GM, WM, and CSF. The algorithm consists of preprocessing, feature extraction, and supervised classification steps. In the first step, intensity non-uniformity in a given MR image is corrected and then non-brain tissues such as skull, eyeballs, and skin are removed from the image. For each voxel, statistical features and non-statistical features were computed and used a feature vector representing the voxel. Three multilayer perceptron (MLP) neural networks trained using three different datasets were used as the base classifiers of the multiple-classifier system. The output of the base classifiers was fused using majority voting scheme. Evaluation of the proposed system was performed using Brainweb simulated MR images with different noise and intensity non-uniformity and internet brain segmentation repository (IBSR) real MR images. The quantitative assessment of the proposed method using Dice, Jaccard, and conformity coefficient metrics demonstrates improvement (around 5% for CSF) in terms of accuracy as compared to single MLP classifier and the existing methods and tools such FSL-FAST and SPM. As accurately segmenting a MR image is of paramount importance for successfully promoting the clinical application of MR image segmentation techniques, the improvement obtained by using multiple-classifier-based system is encouraging.

Processing Pipeline of Sugarcane Spectral Response to Characterize the Fallen Plants Phenomenon

Nowadays, in agronomic systems it is possible to make a variable management of inputs to improve the efficiency of agronomic industry and optimize the logistics of the harvesting process. In this way, it was proposed for sugarcane culture the use of remote sensing tools and computational methods to identify useful areas in the cultivated lands. The objective was to use these areas to make variable management of the crop. When at the moment of harvesting the sugarcane there are fallen stalks, together with them some strange material (vegetal or mineral) is collected. This strange material is not millable and when it enters onto the sugar mill it causes important looses of efficiency in the sugar extraction processes and affects its quality. Considering this issue, the spectral response of sugarcane plants in aerial multispectral images was studied. The spectral response was analyzed in different bands of the electromagnetic spectrum. Then, the aerial images were segmented to obtain homogeneous regions useful for producers to make decisions related to the use of inputs and resources according to the variability of the system (existence of fallen cane and standing cane). The obtained segmentation results were satisfactory. It was possible to identify regions with fallen cane and regions with standing cane with high precision rates.

A Novel Method for the Separation of Overlapping Pollen Species for Automated Detection and Classification.

The identification of pollen in an automated way will accelerate different tasks and applications of palynology to aid in, among others, climate change studies, medical allergies calendar, and forensic science. The aim of this paper is to develop a system that automatically captures a hundred microscopic images of pollen and classifies them into the 12 different species from Lagunera Region, Mexico. Many times, the pollen is overlapping on the microscopic images, which increases the difficulty for its automated identification and classification. This paper focuses on a method to segment the overlapping pollen. First, the proposed method segments the overlapping pollen. Second, the method separates the pollen based on the mean shift process (100% segmentation) and erosion by H-minima based on the Fibonacci series. Thus, pollen is characterized by its shape, color, and texture for training and evaluating the performance of three classification techniques: random tree forest, multilayer perceptron, and Bayes net. Using the newly developed system, we obtained segmentation results of 100% and classification on top of 96.2% and 96.1% in recall and precision using multilayer perceptron in twofold cross validation.

Color image segmentation based on multiobjective artificial bee colony optimization

This paper presents a new color image segmentation method based on a multiobjective optimization algorithm, named improved bee colony algorithm for multi-objective optimization (IBMO). Segmentation is posed as a clustering problem through grouping image features in this approach, which combines IBMO with seeded region growing (SRG). Since feature extraction has a crucial role for image segmentation, the presented method is firstly focused on this manner. The main features of an image: color, texture and gradient magnitudes are measured by using the local homogeneity, Gabor filter and color spaces. Then SRG utilizes the extracted feature vector to classify the pixels spatially. It starts running from centroid points called as seeds. IBMO determines the coordinates of the seed points and similarity difference of each region by optimizing a set of cluster validity indices simultaneously in order to improve the quality of segmentation. Finally, segmentation is completed by merging small and similar regions. The proposed method was applied on several natural images obtained from Berkeley segmentation database. The robustness of the proposed ideas was showed by comparison of hand-labeled and experimentally obtained segmentation results. Besides, it has been seen that the obtained segmentation results have better values than the ones obtained from fuzzy c-means which is one of the most popular methods used in image segmentation, non-dominated sorting genetic algorithm II which is a state-of-the-art algorithm, and non-dominated sorted PSO which is an adapted algorithm of PSO for multi-objective optimization.