In our paper, we present a performance evaluation of image segmentation algorithms on microscopic image data. In spite of the existence of many algorithms for image data partitioning, there is no universal and 'the best' method yet. Moreover, images of microscopic samples can be of various character and quality which can negatively influence the performance of image segmentation algorithms. Thus, the issue of selecting suitable method for a given set of image data is of big interest. We carried out a large number of experiments with a variety of segmentation methods to evaluate the behaviour of individual approaches on the testing set of microscopic images (cross-section images taken in three different modalities from the field of art restoration). The segmentation results were assessed by several indices used for measuring the output quality of image segmentation algorithms. In the end, the benefit of segmentation combination approach is studied and applicability of achieved results on another representatives of microscopic data category - biological samples - is shown.

• Keywords
• Image analysis, image segmentation, microscopic images, performance evaluation,
• MeSH
• Algorithms * MeSH
• Microscopy * methods   MeSH
• Mice MeSH
• Image Processing, Computer-Assisted methods   standards   MeSH
• Animals MeSH
• Check Tag
• Mice MeSH
• Animals MeSH
• Publication type
• Journal Article MeSH
• Evaluation Study MeSH
• Research Support, Non-U.S. Gov't MeSH

To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic (EM) images of the brain. Participants submitted boundary maps predicted for a test set of images, and were scored based on their agreement with a consensus of human expert annotations. The winning team had no prior experience with EM images, and employed a convolutional network. This "deep learning" approach has since become accepted as a standard for segmentation of EM images. The challenge has continued to accept submissions, and the best so far has resulted from cooperation between two teams. The challenge has probably saturated, as algorithms cannot progress beyond limits set by ambiguities inherent in 2D scoring and the size of the test dataset. Retrospective evaluation of the challenge scoring system reveals that it was not sufficiently robust to variations in the widths of neurite borders. We propose a solution to this problem, which should be useful for a future 3D segmentation challenge.

• Keywords
• connectomics, electron microscopy, image segmentation, machine learning, reconstruction,
• Publication type
• Journal Article MeSH

Computer Tomography (CT) is an imaging procedure that combines many X-ray measurements taken from different angles. The segmentation of areas in the CT images provides a valuable aid to physicians and radiologists in order to better provide a patient diagnose. The CT scans of a body torso usually include different neighboring internal body organs. Deep learning has become the state-of-the-art in medical image segmentation. For such techniques, in order to perform a successful segmentation, it is of great importance that the network learns to focus on the organ of interest and surrounding structures and also that the network can detect target regions of different sizes. In this paper, we propose the extension of a popular deep learning methodology, Convolutional Neural Networks (CNN), by including deep supervision and attention gates. Our experimental evaluation shows that the inclusion of attention and deep supervision results in consistent improvement of the tumor prediction accuracy across the different datasets and training sizes while adding minimal computational overhead.

• Keywords
• CNN, UNet, VNet, attention gates, deep supervision, medical image segmentation, organ segmentation, tumor segmentation,
• Publication type
• Journal Article MeSH

The analysis and segmentation of articular cartilage magnetic resonance (MR) images belongs to one of the most commonly routine tasks in diagnostics of the musculoskeletal system of the knee area. Conventional regional segmentation methods, which are based either on the histogram partitioning (e.g., Otsu method) or clustering methods (e.g., K-means), have been frequently used for the task of regional segmentation. Such methods are well known as fast and well working in the environment, where cartilage image features are reliably recognizable. The well-known fact is that the performance of these methods is prone to the image noise and artefacts. In this context, regional segmentation strategies, driven by either genetic algorithms or selected evolutionary computing strategies, have the potential to overcome these traditional methods such as Otsu thresholding or K-means in the context of their performance. These optimization strategies consecutively generate a pyramid of a possible set of histogram thresholds, of which the quality is evaluated by using the fitness function based on Kapur's entropy maximization to find the most optimal combination of thresholds for articular cartilage segmentation. On the other hand, such optimization strategies are often computationally demanding, which is a limitation of using such methods for a stack of MR images. In this study, we publish a comprehensive analysis of the optimization methods based on fuzzy soft segmentation, driven by artificial bee colony (ABC), particle swarm optimization (PSO), Darwinian particle swarm optimization (DPSO), and a genetic algorithm for an optimal thresholding selection against the routine segmentations Otsu and K-means for analysis and the features extraction of articular cartilage from MR images. This study objectively analyzes the performance of the segmentation strategies upon variable noise with dynamic intensities to report a segmentation's robustness in various image conditions for a various number of segmentation classes (4, 7, and 10), cartilage features (area, perimeter, and skeleton) extraction preciseness against the routine segmentation strategies, and lastly the computing time, which represents an important factor of segmentation performance. We use the same settings on individual optimization strategies: 100 iterations and 50 population. This study suggests that the combination of fuzzy thresholding with an ABC algorithm gives the best performance in the comparison with other methods as from the view of the segmentation influence of additive dynamic noise influence, also for cartilage features extraction. On the other hand, using genetic algorithms for cartilage segmentation in some cases does not give a good performance. In most cases, the analyzed optimization strategies significantly overcome the routine segmentation methods except for the computing time, which is normally lower for the routine algorithms. We also publish statistical tests of significance, showing differences in the performance of individual optimization strategies against Otsu and K-means method. Lastly, as a part of this study, we publish a software environment, integrating all the methods from this study.

• Keywords
• ABC, DPSO, K-means clustering, Otsu thresholding, PSO, articular cartilage, medical image segmentation, regional segmentation,
• MeSH
• Algorithms MeSH
• Artifacts MeSH
• Cartilage, Articular * diagnostic imaging   MeSH
• Magnetic Resonance Imaging methods   MeSH
• Image Processing, Computer-Assisted methods   MeSH
• Cluster Analysis MeSH
• Publication type
• Journal Article MeSH

This paper describes an evaluation framework that allows a standardized and quantitative comparison of IVUS lumen and media segmentation algorithms. This framework has been introduced at the MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop, comparing the results of eight teams that participated. We describe the available data-base comprising of multi-center, multi-vendor and multi-frequency IVUS datasets, their acquisition, the creation of the reference standard and the evaluation measures. The approaches address segmentation of the lumen, the media, or both borders; semi- or fully-automatic operation; and 2-D vs. 3-D methodology. Three performance measures for quantitative analysis have been proposed. The results of the evaluation indicate that segmentation of the vessel lumen and media is possible with an accuracy that is comparable to manual annotation when semi-automatic methods are used, as well as encouraging results can be obtained also in case of fully-automatic segmentation. The analysis performed in this paper also highlights the challenges in IVUS segmentation that remains to be solved.

• Keywords
• Algorithm comparison, Evaluation framework, IVUS (intravascular ultrasound), Image segmentation,
• MeSH
• Databases, Factual standards   MeSH
• Internationality MeSH
• Image Interpretation, Computer-Assisted methods   standards   MeSH
• Ultrasonography, Interventional methods   standards   MeSH
• Humans MeSH
• Coronary Artery Disease diagnostic imaging   MeSH
• Reference Values MeSH
• Reproducibility of Results MeSH
• Sensitivity and Specificity MeSH
• Practice Guidelines as Topic * MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH
• Research Support, N.I.H., Extramural MeSH
• Research Support, U.S. Gov't, Non-P.H.S. MeSH

Image segmentation using bi-level thresholds works well for straightforward scenarios; however, dealing with complex images that contain multiple objects or colors presents considerable computational difficulties. Multi-level thresholding is crucial for these situations, but it also introduces a challenging optimization problem. This paper presents an improved Reptile Search Algorithm (RSA) that includes a Gbest operator to enhance its performance. The proposed method determines optimal threshold values for both grayscale and color images, utilizing entropy-based objective functions derived from the Otsu and Kapur techniques. Experiments were carried out on 16 benchmark images, which included COVID-19 scans along with standard color and grayscale images. A thorough evaluation was conducted using metrics such as the fitness function, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and the Friedman ranking test. The results indicate that the proposed algorithm seems to surpass existing state-of-the-art methods, demonstrating its effectiveness and robustness in multi-level thresholding tasks.

• Keywords
• Image segmentation, Medical images, Multi-level threshold, Otsu method, Kapur method, Reptile search algorithm,
• MeSH
• Algorithms * MeSH
• COVID-19 * diagnostic imaging   virology   MeSH
• Humans MeSH
• Image Processing, Computer-Assisted * methods   MeSH
• Signal-To-Noise Ratio MeSH
• SARS-CoV-2 isolation & purification   MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH

Accurate and efficient medical image segmentation is a critical yet challenging task due to issues like intensity inhomogeneity, poor contrast, noise, and blur. In this paper, we introduce a novel framework that addresses these challenges by leveraging adaptive level set evolution, enhanced with a unique edge indication function. Unlike prior edge-based algorithms, which frequently fail with noisy images and have large computing costs, our method incorporates an improved edge indicator term into the level set architecture, considerably improving performance on degraded images. The efficiency of proposed model depends on the optimization and implementation of proximal alternating direction technique of multipliers ([Formula: see text]). Our findings were validated using qualitative and quantitative methods such as dice coefficient assessment, sensitivity, accuracy, and mean absolute distance (MAD). Experimental findings show that the model successfully detects boundaries of objects within noisy and blurred visual data. The algorithm showed exceptional precision through its average dice coefficient of 0.96 which matched the ground truth data measurement standards. The system runs efficiently for only 0.90 seconds on average as a performance result. The framework achieved standout performance metrics that included 0.9552 accuracy together with 0.8854 sensitivity and 0.0796 MAD. The framework demonstrates robust capabilities in medical image evaluation which makes it an optimistic instrument for advancing the field.

• Keywords
• [Formula: see text] optimization, Edge indication function, Intensity inhomogeneity, Level-set evaluation, Medical image segmentation,
• Publication type
• Journal Article MeSH

Automatic detection and segmentation of biological objects in 2D and 3D image data is central for countless biomedical research questions to be answered. While many existing computational methods are used to reduce manual labeling time, there is still a huge demand for further quality improvements of automated solutions. In the natural image domain, spatial embedding-based instance segmentation methods are known to yield high-quality results, but their utility to biomedical data is largely unexplored. Here we introduce EmbedSeg, an embedding-based instance segmentation method designed to segment instances of desired objects visible in 2D or 3D biomedical image data. We apply our method to four 2D and seven 3D benchmark datasets, showing that we either match or outperform existing state-of-the-art methods. While the 2D datasets and three of the 3D datasets are well known, we have created the required training data for four new 3D datasets, which we make publicly available online. Next to performance, also usability is important for a method to be useful. Hence, EmbedSeg is fully open source (https://github.com/juglab/EmbedSeg), offering (i) tutorial notebooks to train EmbedSeg models and use them to segment object instances in new data, and (ii) a napari plugin that can also be used for training and segmentation without requiring any programming experience. We believe that this renders EmbedSeg accessible to virtually everyone who requires high-quality instance segmentations in 2D or 3D biomedical image data.

• Keywords
• Embeddings, Instance Segmentation, Microscopy,
• MeSH
• Algorithms * MeSH
• Humans MeSH
• Microscopy * methods   MeSH
• Image Processing, Computer-Assisted methods   MeSH
• Imaging, Three-Dimensional methods   MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.

• Keywords
• Labelling, Segmentation, Spine, Vertebrae,
• MeSH
• Algorithms MeSH
• Benchmarking * MeSH
• Humans MeSH
• Spine diagnostic imaging   MeSH
• Tomography, X-Ray Computed * MeSH
• Image Processing, Computer-Assisted MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH

Living cell segmentation from bright-field light microscopy images is challenging due to the image complexity and temporal changes in the living cells. Recently developed deep learning (DL)-based methods became popular in medical and microscopy image segmentation tasks due to their success and promising outcomes. The main objective of this paper is to develop a deep learning, U-Net-based method to segment the living cells of the HeLa line in bright-field transmitted light microscopy. To find the most suitable architecture for our datasets, a residual attention U-Net was proposed and compared with an attention and a simple U-Net architecture. The attention mechanism highlights the remarkable features and suppresses activations in the irrelevant image regions. The residual mechanism overcomes with vanishing gradient problem. The Mean-IoU score for our datasets reaches 0.9505, 0.9524, and 0.9530 for the simple, attention, and residual attention U-Net, respectively. The most accurate semantic segmentation results was achieved in the Mean-IoU and Dice metrics by applying the residual and attention mechanisms together. The watershed method applied to this best - Residual Attention - semantic segmentation result gave the segmentation with the specific information for each cell.

• Keywords
• Cell detection, Deep learning, Microscopy image segmentation, Neural network, Semantic segmentation, Tissue segmentation, Watershed segmentation,
• MeSH
• Benchmarking MeSH
• Microscopy * MeSH
• Neural Networks, Computer MeSH
• Image Processing, Computer-Assisted * methods   MeSH
• Semantics MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH