In the field of computer vision, object detection consists of automatically finding objects in images by giving their positions. The most common fields of application are safety systems (pedestrian detection, identification of behavior) and control systems. Another important application is head/person detection, which is the primary material for road safety, rescue, surveillance, etc. In this study, we developed a new approach based on two parallel Deeplapv3+ to improve the performance of the person detection system. For the implementation of our semantic segmentation model, a working methodology with two types of ground truths extracted from the bounding boxes given by the original ground truths was established. The approach has been implemented in our two private datasets as well as in a public dataset. To show the performance of the proposed system, a comparative analysis was carried out on two deep learning semantic segmentation state-of-art models: SegNet and U-Net. By achieving 99.14% of global accuracy, the result demonstrated that the developed strategy could be an efficient way to build a deep neural network model for semantic segmentation. This strategy can be used, not only for the detection of the human head but also be applied in several semantic segmentation applications.

• Klíčová slova
• DeepLabv3+, head counting, head detection, parallel networks, safety systems, semantic segmentation,
• MeSH
• chodci * MeSH
• lidé MeSH
• neuronové sítě MeSH
• počítačové zpracování obrazu MeSH
• sémantika * MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH

Decellularized tissue is an important source for biological tissue engineering. Evaluation of the quality of decellularized tissue is performed using scanned images of hematoxylin-eosin stained (H&E) tissue sections and is usually dependent on the observer. The first step in creating a tool for the assessment of the quality of the liver scaffold without observer bias is the automatic segmentation of the whole slide image into three classes: the background, intralobular area, and extralobular area. Such segmentation enables to perform the texture analysis in the intralobular area of the liver scaffold, which is crucial part in the recellularization procedure. Existing semi-automatic methods for general segmentation (i.e., thresholding, watershed, etc.) do not meet the quality requirements. Moreover, there are no methods available to solve this task automatically. Given the low amount of training data, we proposed a two-stage method. The first stage is based on classification of simple hand-crafted descriptors of the pixels and their neighborhoods. This method is trained on partially annotated data. Its outputs are used for training of the second-stage approach, which is based on a convolutional neural network (CNN). Our architecture inspired by U-Net reaches very promising results, despite a very low amount of the training data. We provide qualitative and quantitative data for both stages. With the best training setup, we reach 90.70% recognition accuracy.

• Klíčová slova
• H&E, convolutional neural networks, decellularization, liver, semantic segmentation, tissue engineering,
• MeSH
• játra * diagnostické zobrazování   MeSH
• neuronové sítě MeSH
• počítačové zpracování obrazu * MeSH
• sémantika * MeSH
• Publikační typ
• dopisy MeSH

To determine the appropriate treatment plan for patients, radiologists must reliably detect brain tumors. Despite the fact that manual segmentation involves a great deal of knowledge and ability, it may sometimes be inaccurate. By evaluating the size, location, structure, and grade of the tumor, automatic tumor segmentation in MRI images aids in a more thorough analysis of pathological conditions. Due to the intensity differences in MRI images, gliomas may spread out, have low contrast, and are therefore difficult to detect. As a result, segmenting brain tumors is a challenging process. In the past, several methods for segmenting brain tumors in MRI scans were created. However, because of their susceptibility to noise and distortions, the usefulness of these approaches is limited. Self-Supervised Wavele- based Attention Network (SSW-AN), a new attention module with adjustable self-supervised activation functions and dynamic weights, is what we suggest as a way to collect global context information. In particular, this network's input and labels are made up of four parameters produced by the two-dimensional (2D) Wavelet transform, which makes the training process simpler by neatly segmenting the data into low-frequency and high-frequency channels. To be more precise, we make use of the channel attention and spatial attention modules of the self-supervised attention block (SSAB). As a result, this method may more easily zero in on crucial underlying channels and spatial patterns. The suggested SSW-AN has been shown to outperform the current state-of-the-art algorithms in medical image segmentation tasks, with more accuracy, more promising dependability, and less unnecessary redundancy.

• Klíčová slova
• Wavelet transform, attention mechanisms, self-supervised attention block (SSAB), self-supervised wavelet-based attention network (SSW-AN), semantic image segmentation,
• MeSH
• algoritmy MeSH
• lidé MeSH
• magnetická rezonanční tomografie metody   MeSH
• nádory mozku * MeSH
• počítačové zpracování obrazu metody   MeSH
• sémantika * MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH

Wall segmentation is a special case of semantic segmentation, and the task is to classify each pixel into one of two classes: wall and no-wall. The segmentation model returns a mask showing where objects like windows and furniture are located, as well as walls. This article proposes the module's structure for semantic segmentation of walls in 2D images, which can effectively address the problem of wall segmentation. The proposed model achieved higher accuracy and faster execution than other solutions. An encoder-decoder architecture of the segmentation module was used. Dilated ResNet50/101 network was used as an encoder, representing ResNet50/101 network in which dilated convolutional layers replaced the last convolutional layers. The ADE20K dataset subset containing only interior images, was used for model training, while only its subset was used for model evaluation. Three different approaches to model training were analyzed in the research. On the validation dataset, the best approach based on the proposed structure with the ResNet101 network resulted in an average accuracy at the pixel level of 92.13% and an intersection over union (IoU) of 72.58%. Moreover, all proposed approaches can be applied to recognize other objects in the image to solve specific tasks.

• Klíčová slova
• ADE20K, Encoder-decoder, PSPNet, Semantic segmentation, Wall segmentation,
• Publikační typ
• časopisecké články MeSH

BACKGROUND: Analysis of structures contained in tissue samples and the relevant contextual information is of utmost importance to histopathologists during diagnosis. Cardiac biopsies require in-depth analysis of the relationships between biological structures. Statistical measures are insufficient for determining a model's viability and applicability in the diagnostic process. A deeper understanding of predictions is necessary in order to support histopathologists. METHODS: We propose a method for providing supporting information in the form of segmentation of histological structures to histopathologists based on these principles. The proposed method utilizes nuclei type and density information in addition to standard image input provided at two different zoom levels for the semantic segmentation of blood vessels, inflammation, and endocardium in heart tissue. RESULTS: The proposed method was able to reach state-of-the-art segmentation results. The overall quality and viability of the predictions was qualitatively evaluated by two pathologists and a histotechnologist. CONCLUSIONS: The decision process of the proposed deep learning model utilizes the provided information sources correctly and simulates the decision process of histopathologists via the usage of a custom-designed attention gate that provides a combination of spatial and encoder attention mechanisms. The implementation is available at https://github.com/mathali/IEDL-segmentation-of-heart-tissue.

• Klíčová slova
• Computer vision, Computer-aided diagnosis, Deep learning, Digital pathology,
• MeSH
• deep learning * MeSH
• lidé MeSH
• myokard patologie   cytologie   MeSH
• počítačové zpracování obrazu metody   MeSH
• sémantika MeSH
• srdce diagnostické zobrazování   anatomie a histologie   MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

BACKGROUND: Manual analysis of (mini-)rhizotron (MR) images is tedious. Several methods have been proposed for semantic root segmentation based on homogeneous, single-source MR datasets. Recent advances in deep learning (DL) have enabled automated feature extraction, but comparisons of segmentation accuracy, false positives and transferability are virtually lacking. Here we compare six state-of-the-art methods and propose two improved DL models for semantic root segmentation using a large MR dataset with and without augmented data. We determine the performance of the methods on a homogeneous maize dataset, and a mixed dataset of > 8 species (mixtures), 6 soil types and 4 imaging systems. The generalisation potential of the derived DL models is determined on a distinct, unseen dataset. RESULTS: The best performance was achieved by the U-Net models; the more complex the encoder the better the accuracy and generalisation of the model. The heterogeneous mixed MR dataset was a particularly challenging for the non-U-Net techniques. Data augmentation enhanced model performance. We demonstrated the improved performance of deep meta-architectures and feature extractors, and a reduction in the number of false positives. CONCLUSIONS: Although correction factors are still required to match human labelled root lengths, neural network architectures greatly reduce the time required to compute the root length. The more complex architectures illustrate how future improvements in root segmentation within MR images can be achieved, particularly reaching higher segmentation accuracies and model generalisation when analysing real-world datasets with artefacts-limiting the need for model retraining.

• Klíčová slova
• Automatic image segmentation, Data augmentation, Deep learning, False positives, Fine roots, Image processing, Minirhizotron, Neural networks, Root segmentation, U-Net,
• Publikační typ
• časopisecké články 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.

• Klíčová slova
• Cell detection, Deep learning, Microscopy image segmentation, Neural network, Semantic segmentation, Tissue segmentation, Watershed segmentation,
• MeSH
• benchmarking MeSH
• mikroskopie * MeSH
• neuronové sítě MeSH
• počítačové zpracování obrazu * metody   MeSH
• sémantika MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

It is now possible to generate large volumes of high-quality images of biomolecules at near-atomic resolution and in near-native states using cryogenic electron microscopy/electron tomography (Cryo-EM/ET). However, the precise annotation of structures like filaments and membranes remains a major barrier towards applying these methods in high-throughput. To address this, we present TARDIS (Transformer-based Rapid Dimensionless Instance Segmentation), a machine-learning framework for fast and accurate annotation of micrographs and tomograms. TARDIS combines deep learning for semantic segmentation with a novel geometric model for precise instance segmentation of various macromolecules. We develop pre-trained models within TARDIS for segmenting microtubules and membranes, demonstrating high accuracy across multiple modalities and resolutions, enabling segmentation of over 13,000 tomograms from the CZI Cryo-Electron Tomography data portal. As a modular framework, TARDIS can be extended to new structures and imaging modalities with minimal modification. TARDIS is open-source and freely available at https://github.com/SMLC-NYSBC/TARDIS, and accelerates analysis of high-resolution biomolecular structural imaging data.

• Klíčová slova
• CNN, Cryo-EM/ET, DIST, Filaments, Instance Segmentation, Membranes, Microtubules, Point Cloud, Segmentation, Semantic Segmentation, TARDIS, TEM EM/ET,
• Publikační typ
• časopisecké články MeSH
• preprinty MeSH

Liver volumetry is an important tool in clinical practice. The calculation of liver volume is primarily based on Computed Tomography. Unfortunately, automatic segmentation algorithms based on handcrafted features tend to leak segmented objects into surrounding tissues like the heart or the spleen. Currently, convolutional neural networks are widely used in various applications of computer vision including image segmentation, while providing very promising results. In our work, we utilize robustly segmentable structures like the spine, body surface, and sagittal plane. They are used as key points for position estimation inside the body. The signed distance fields derived from these structures are calculated and used as an additional channel on the input of our convolutional neural network, to be more specific U-Net, which is widely used in medical image segmentation tasks. Our work shows that this additional position information improves the results of the segmentation. We test our approach in two experiments on two public datasets of Computed Tomography images. To evaluate the results, we use the Accuracy, the Hausdorff distance, and the Dice coefficient. Code is publicly available at: https://gitlab.com/hachaf/liver-segmentation.git.

• Klíčová slova
• convolutional neural network, liver volumetry, machine learning, medical imaging, position features, semantic segmentation,
• Publikační typ
• časopisecké články MeSH

BACKGROUND: Agar plate analysis is vital for microbiological testing in industries like food, pharmaceuticals, and biotechnology. Manual inspection is slow, laborious, and error-prone, while existing automated systems struggle with the complexity of real-world agar plates. A shortage of diverse datasets hinders the development and evaluation of robust automated systems. METHODS: In this paper, two new annotated datasets and a novel methodology for synthetic agar plate generation are presented. The datasets comprise 854 images of cultivated agar plates and 1,588 images of empty agar plates, encompassing various agar plate types and microorganisms. These datasets are an extension of the publicly available BRUKERCOLONY dataset, collectively forming one of the largest publicly available annotated datasets for research. The methodology is based on an efficient image generation pipeline that also simulates cultivation-related phenomena such as haemolysis or chromogenic reactions. RESULTS: The augmentations significantly improved the Dice coefficient of trained U-Net models, increasing it from 0.671 to 0.721. Furthermore, training the U-Net model with a combination of real and 150% synthetic data demonstrated its efficacy, yielding a remarkable Dice coefficient of 0.729, a substantial improvement from the baseline of 0.518. UNet3+ exhibited the highest performance among the U-Net and Attention U-Net architectures, achieving a Dice coefficient of 0.767. CONCLUSIONS: Our experiments showed the methodology's applicability to real-world scenarios, even with highly variable agar plates. Our paper contributes to automating agar plate analysis by presenting a new dataset and effective methodology, potentially enhancing fully automated microbiological testing.

• Klíčová slova
• Agar plates, Deep learning, Semantic segmentation, Synthetic images generation,
• Publikační typ
• časopisecké články MeSH