Today, unmanned aerial vehicles (UAVs) are heavily dependent on Global Navigation Satellite Systems (GNSSs) for positioning and navigation. However, GNSS signals are vulnerable to jamming and spoofing attacks. This poses serious security risks, especially for military operations and critical civilian missions. In order to solve this problem, an image-based geolocation system has been developed that eliminates GNSS dependency. The proposed system estimates the geographical location of the UAV by matching the aerial images taken by the UAV with previously georeferenced high-resolution satellite images. For this purpose, common visual features were determined between satellite and UAV images and matching operations were carried out using methods based on the homography matrix. Thanks to image processing, a significant relationship has been established between the area where the UAV is located and the geographical coordinates, and reliable positioning is ensured even in cases where GNSS signals cannot be used. Within the scope of the study, traditional methods such as SIFT, AKAZE, and Multiple Template Matching were compared with learning-based methods including SuperPoint, SuperGlue, and LoFTR. The results showed that deep learning-based approaches can make successful matches, especially at high altitudes.

Chagas disease, caused by the Trypanosoma cruzi parasite, poses a significant health threat, particularly in Latin America, with millions affected globally. This research introduces a novel approach using deep learning techniques for the automated detection of Trypanosoma cruzi in blood smear images provided by Zoonoses Laboratory (CIR) in Mexico. Advanced deep learning architectures like Faster RCNN, RetinaNet, YOLOv8, and FCOS have been adapted, trained, and compared with each other in terms of the detection accuracy of each image. Our selection of those models is based on their ability to swiftly and accurately detect anomalies, measured through rigorous assessment using pivotal metrics like Mean Average Precision (mAP) across varying Intersection over Union (IoU) thresholds. Notably, the YOLOv8 model has showcased outstanding performance, boasting a remarkable mAP score of 0.951 for parasite detection and localisation. Specifically, YOLOv8 outperforms with a leading mAP of 0.951 at 50

This paper describes a methodology to analyse the complexity of HeLa cells as observed with electron microscopy, in particular the relationship between mitochondria and the roughness of the nuclear envelope as reflected by the invaginations of the surface. For this purpose, several mitochondria segmentation algorithms were quantitatively compared, namely: Topology, Image Processing, Topology and Image Processing, and Deep Learning, which provided the highest accuracy. The invaginations were successfully segmented with one image processing algorithm. Metrics were extracted for both structures and correlations between the mitochondria and invaginations were explored for 25 segmented cells. It was found that there was a positive correlation between the volume of invaginations and the volume of mitochondria, and negative correlations between the number and the mean volume of mitochondria, and between the volume of the cytoplasm and the aspect ratio of mitochondria. These results suggest that there is a relationship between the shape of a cell, its nucleus and its mitochondria; as well as a relationship between the number of mitochondria and their shapes. Whilst these results were obtained from a single cell line and a relatively small number of cells, they encourage further study as the methodology proposed can be easily applied to other cells and settings. Code and data are freely available. HeLa images are available from http://dx.doi.org/10.6019/EMPIAR-10094, code from https://github.com/reyesaldasoro/MitoEM, and segmented nuclei, cells, invaginations and mitochondria from https://github.com/reyesaldasoro/HeLa_Cell Data.

Staining of histological slides with Hematoxylin and Eosin is widely used in clinical and laboratory settings as these dyes reveal nuclear structures as well as cytoplasm and collagen. For cancer diagnosis, these slides are used to recognize tissues and morphological changes. Tissue semantic segmentation is therefore important and at the same time a challenging and time-consuming task. This paper describes a UNet-like deep learning architecture called DRD-UNet, which adds a novel processing block called DRD (Dilation, Residual, and Dense block) to a UNet architecture. DRD is formed by the combination of dilated convolutions (D), residual connections (R), and dense layers (D). DRD-UNet was applied to the multi-class (tumor, stroma, inflammatory, necrosis, and other) semantic segmentation of histological images from breast cancer samples stained with Hematoxylin and Eosin. The histological images were released through the Breast Cancer Semantic Segmentation (BCSS) Challenge. DRD-UNet outperformed the original UNet architecture and 15 other UNet-based architectures on the segmentation of 12,930 image patches extracted from regions of interest that ranged in size between 1036 x 1222 to 6813 x 7360 pixels. DRD-UNet obtained the best performance as measured with Jaccard similarity index, Dice coefficient, in a per-class comparison and accuracy for overall segmentation.

This paper investigates the impact of the amount of training data and the shape variability on the segmentation provided by the deep learning architecture U-Net. Further, the correctness of ground truth (GT) was also evaluated. The input data consisted of a three-dimensional set of images of HeLa cells observed with an electron microscope with dimensions 8192×8192×517. From there, a smaller region of interest (ROI) of 2000×2000×300 was cropped and manually delineated to obtain the ground truth necessary for a quantitative evaluation. A qualitative evaluation was performed on the 8192×8192 slices due to the lack of ground truth. Pairs of patches of data and labels for the classes nucleus, nuclear envelope, cell and background were generated to train U-Net architectures from scratch. Several training strategies were followed, and the results were compared against a traditional image processing algorithm. The correctness of GT, that is, the inclusion of one or more nuclei within the region of interest was also evaluated. The impact of the extent of training data was evaluated by comparing results from 36,000 pairs of data and label patches extracted from the odd slices in the central region, to 135,000 patches obtained from every other slice in the set. Then, 135,000 patches from several cells from the 8192×8192 slices were generated automatically using the image processing algorithm. Finally, the two sets of 135,000 pairs were combined to train once more with 270,000 pairs. As would be expected, the accuracy and Jaccard similarity index improved as the number of pairs increased for the ROI. This was also observed qualitatively for the 8192×8192 slices. When the 8192×8192 slices were segmented with U-Nets trained with 135,000 pairs, the architecture trained with automatically generated pairs provided better results than the architecture trained with the pairs from the manually segmented ground truths. This suggests that the pairs that were extracted automatically from many cells provided a better representation of the four classes of the various cells in the 8192×8192 slice than those pairs that were manually segmented from a single cell. Finally, the two sets of 135,000 pairs were combined, and the U-Net trained with these provided the best results.

In this work, an unsupervised volumetric semantic instance segmentation of the plasma membrane of HeLa cells as observed with serial block face scanning electron microscopy is described. The resin background of the images was segmented at different slices of a 3D stack of 518 slices with 8192 × 8192 pixels each. The background was used to create a distance map, which helped identify and rank the cells by their size at each slice. The centroids of the cells detected at different slices were linked to identify them as a single cell that spanned a number of slices. A subset of these cells, i.e., the largest ones and those not close to the edges were selected for further processing. The selected cells were then automatically cropped to smaller regions of interest of 2000 × 2000 × 300 voxels that were treated as cell instances. Then, for each of these volumes, the nucleus was segmented, and the cell was separated from any neighbouring cells through a series of traditional image processing steps that followed the plasma membrane. The segmentation process was repeated for all the regions of interest previously selected. For one cell for which the ground truth was available, the algorithm provided excellent results in Accuracy (AC) and the Jaccard similarity Index (JI): nucleus: JI =0.9665, AC =0.9975, cell including nucleus JI =0.8711, AC =0.9655, cell excluding nucleus JI =0.8094, AC =0.9629. A limitation of the algorithm for the plasma membrane segmentation was the presence of background. In samples with tightly packed cells, this may not be available. When tested for these conditions, the segmentation of the nuclear envelope was still possible. All the code and data were released openly through GitHub, Zenodo and EMPIAR.

This paper investigates the classification of radiographic images with eleven convolutional neural network (CNN) architectures ( GoogleNet, VGG-19, AlexNet, SqueezeNet, ResNet-18, Inception-v3, ResNet-50, VGG-16, ResNet-101, DenseNet-201 and Inception-ResNet-v2 ). The CNNs were used to classify a series of wrist radiographs from the Stanford Musculoskeletal Radiographs (MURA) dataset into two classes - normal and abnormal. The architectures were compared for different hyper-parameters against accuracy and Cohen’s kappa coefficient. The best two results were then explored with data augmentation. Without the use of augmentation, the best results were provided by Inception-Resnet-v2 (Mean accuracy = 0.723 , Mean kappa = 0.506 ). These were significantly improved with augmentation to Inception-Resnet-v2 (Mean accuracy = 0.857 , Mean kappa = 0.703 ). Finally, Class Activation Mapping was applied to interpret activation of the network against the location of an anomaly in the radiographs.

This is a data set that contains 300 labelled HeLa cell images, indicating the five different classes: nuclear envelope, nucleus, other cells, background and cell. The ground truth is based on a data set previously released in Zenodo (https://doi.org/10.5281/zenodo.3874949), which contained four classes, nuclear envelope, nucleus, cells, background. For this data set the class cell was divided to contain other cells and the cell that corresponds to the nucleus. Each image corresponds to a 3D stack of images acquired with Electron Microscopy and are released as tif images and Matlab files. Details of the imaging, preparation and analysis of the Electron Microscopy images and have been published in: Cefa Karabağ, Martin L. Jones, Christopher J. Peddie, Anne E. Weston, Lucy M. Collinson, Constantino Carlos Reyes-Aldasoro. Segmentation and Modelling of the Nuclear Envelope of HeLa Cells Imaged with Serial Block Face Scanning Electron Microscopy. J. Imaging 2019, 5(9), 75; https://doi.org/10.3390/jimaging5090075 Karabağ C, Jones ML, Peddie CJ, Weston AE, Collinson LM, Reyes-Aldasoro, CC., Semantic segmentation of HeLa cells: An objective comparison between one traditional algorithm and four deep-learning architectures (2020). PLOS ONE 15(10): e0230605. https://doi.org/10.1371/journal.pone.0230605 The Electron Microscope images are freely available through EMPIAR: http://dx.doi.org/10.6019/EMPIAR-10094 EMPIAR.

In this work, the geometrical characteristics of two different types of cells observed with Electron Microscopy were analysed. The nuclear envelope of Wild-type HeLa cells and Chlamydia trachomatis-infected HeLa cells were automatically segmented and then modelled against a spheroid and converted to a two-dimensional surface. Geometric measurements from this surface and the volumetric nuclear envelope were extracted to compare the two types of cells. The measurements included the nuclear volume, the sphericity of the nucleus, its flatness or spikiness. In total 13 different cells were segmented: 7 Wild-type and 6 Chlamydia trachomatis-infected. The cells were statistically different in the following measurements. Wild-type HeLa cells have greater volumes than that of Chlamydia trachomatis-infected HeLa cells and they are more spherical as Jaccard index suggests. Standard deviation (), and range of values for the nuclear envelope, which shows the distance of the highest peaks and deepest valleys from the spheroid, were also extracted from the modelling against a spheroid and these metrics were used to compare two different data sets in order to draw conclusions.

This is a data set that contains labeled HeLa cell images, generated in MATLAB® Image Labeler, indicating the four different classes - nuclear envelope, nucleus, rest of the cell, and background for deep learning architecture training. Details of the imaging and preparation have been published in: Cefa Karabağ, Martin L. Jones, Christopher J. Peddie, Anne E. Weston, Lucy M. Collinson, Constantino Carlos Reyes-Aldasoro. Segmentation and Modelling of the Nuclear Envelope of HeLa Cells Imaged with Serial Block Face Scanning Electron Microscopy. J. Imaging 2019, 5(9), 75; https://doi.org/10.3390/jimaging5090075 and The data sets are freely available through EMPIAR: http://dx.doi.org/10.6019/EMPIAR-10094 EMPIAR. Details on the segmentation and analysis of HeLa cells have been published in: Cefa Karabağ, Martin L. Jones, Christopher J. Peddie, Anne E. Weston, Lucy M. Collinson, Constantino Carlos Reyes-Aldasoro. Semantic Segmentation of HeLa Cells: An Objective Comparison between one Traditional Algorithm and Three Deep-Learning Architectures, BioRxiv, https://doi.org/10.1101/2020.03.05.978478 and Cefa Karabağ, Martin L. Jones, Christopher J. Peddie, Anne E. Weston, Lucy M. Collinson, Constantino Carlos Reyes-Aldasoro. Segmentation and Modelling of the Nuclear Envelope of HeLa Cells Imaged with Serial Block Face Scanning Electron Microscopy. J. Imaging 2019, 5(9), 75; https://doi.org/10.3390/jimaging5090075

The quantitative study of cell morphology is of great importance as the structure and condition of cells and their structures can be related to conditions of health or disease. The first step towards that, is the accurate segmentation of cell structures. In this work, we compare five approaches, one traditional and four deep-learning, for the semantic segmentation of the nuclear envelope of cervical cancer cells commonly known as HeLa cells. Images of a HeLa cancer cell were semantically segmented with one traditional image-processing algorithm and four three deep learning architectures: VGG16, ResNet18, Inception-ResNet-v2, and U-Net. Three hundred slices, each 2000 × 2000 pixels, of a HeLa Cell were acquired with Serial Block Face Scanning Electron Microscopy. The first three deep learning architectures were pre-trained with ImageNet and then fine-tuned with transfer learning. The U-Net architecture was trained from scratch with 36, 000 training images and labels of size 128 × 128. The image-processing algorithm followed a pipeline of several traditional steps like edge detection, dilation and morphological operators. The algorithms were compared by measuring pixel-based segmentation accuracy and Jaccard index against a labelled ground truth. The results indicated a superior performance of the traditional algorithm (Accuracy = 99%, Jaccard = 93%) over the deep learning architectures: VGG16 (93%, 90%), ResNet18 (94%, 88%), Inception-ResNet-v2 (94%, 89%), and U-Net (92%, 56%).

This paper describes a methodology that extracts key morphological features from histological breast cancer images in order to automatically assess Tumour Cellularity (TC) in Neo-Adjuvant treatment (NAT) patients. The response to NAT gives information on therapy efficacy and it is measured by the residual cancer burden index, which is composed of two metrics: TC and the assessment of lymph nodes. The data consist of whole slide images (WSIs) of breast tissue stained with Hematoxylin and Eosin (H&E) released in the 2019 SPIE Breast Challenge. The methodology proposed is based on traditional computer vision methods (K-means, watershed segmentation, Otsu’s binarisation, and morphological operations), implementing colour separation, segmentation, and feature extraction. Correlation between morphological features and the residual TC after a NAT treatment was examined. Linear regression and statistical methods were used and twenty-two key morphological parameters from the nuclei, epithelial region, and the full image were extracted. Subsequently, an automated TC assessment that was based on Machine Learning (ML) algorithms was implemented and trained with only selected key parameters. The methodology was validated with the score assigned by two pathologists through the intra-class correlation coefficient (ICC). The selection of key morphological parameters improved the results reported over other ML methodologies and it was very close to deep learning methodologies. These results are encouraging, as a traditionally-trained ML algorithm can be useful when limited training data are available preventing the use of deep learning approaches.

This paper describes a method for residual tumour cellularity (TC) estimation in Neoadjuvant treatment (NAT) of advanced breast cancer. This is determined manually by visual inspection by a radiologist, then an automated computation will contribute to reduce time workload and increase precision and accuracy. TC is estimated as the ratio of tumour area by total image area estimated after the NAT. The method proposed computes TC by using machine learning techniques trained with information on morphological parameters of segmented nuclei in order to classify regions of the image as tumour or normal. The data is provided by the 2019 SPIE Breast challenge, which was proposed to develop automated TC computation algorithms. Three algorithms were implemented: Support Vector Machines, Nearest K-means and Adaptive Boosting (AdaBoost) decision trees. Performance based on accuracy is compared and evaluated and the best result was obtained with Support Vector Machines. Results obtained by the methods implemented were submitted during ongoing challenge with a maximum of 0.76 of prediction probability of success.

This paper describes an algorithm to segment the 3D nuclear envelope of HeLa cancer cells from electron microscopy images and model the volumetric shape of the nuclear envelope against an ellipsoid. The algorithm was trained on a single cell and then tested in six separate cells. To assess the algorithm, Jaccard similarity index and Hausdorff distance against a manually-delineated gold standard were calculated on two cells. The mean Jaccard value and Hausdorff distance that the segmentation achieved for central slices were 98% and 4 pixels for the first cell and 94% and 13 pixels for the second cell and outperformed segmentation with active contours. The modelling projects a 3D to a 2D surface that summarises the complexity of the shape in an intuitive result. Measurements extracted from the modelled surface may be useful to correlate shape with biological characteristics. The algorithm is unsupervised, fully automatic, fast and processes one image in less than 10 seconds. Code and data are freely available at https://github.com/reyesaldasoro/Hela-Cell-Segmentation and http://dx.doi.org/10.6019/EMPIAR-10094.

This paper compares a series of traditional and deep learning methodologies for the segmentation of textures. Six well-known texture composites first published by Randen and Husøy were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a deep-learning approach based on the U-Net architecture. For the latter, the effects of depth of the network, number of epochs and different optimisation algorithms were investigated. Overall, the best results were provided by the deep-learning approach. However, the best results were distributed within the parameters, and many configurations provided results well below the traditional techniques.

This paper describes an unsupervised algorithm, which segments the nuclear envelope of HeLa cells imaged by Serial Block Face Scanning Electron Microscopy. The algorithm exploits the variations of pixel intensity in different cellular regions by calculating edges, which are then used to generate superpixels. The superpixels are morphologically processed and those that correspond to the nuclear region are selected through the analysis of size, position, and correspondence with regions detected in neighbouring slices. The nuclear envelope is segmented from the nuclear region. The three-dimensional segmented nuclear envelope is then modelled against a spheroid to create a two-dimensional (2D) surface. The 2D surface summarises the complex 3D shape of the nuclear envelope and allows the extraction of metrics that may be relevant to characterise the nature of cells. The algorithm was developed and validated on a single cell and tested in six separate cells, each with 300 slices of 2000 × 2000 pixels. Ground truth was available for two of these cells, i.e., 600 hand-segmented slices. The accuracy of the algorithm was evaluated with two similarity metrics: Jaccard Similarity Index and Mean Hausdorff distance. Jaccard values of the first/second segmentation were 93%/90% for the whole cell, and 98%/94% between slices 75 and 225, as the central slices of the nucleus are more regular than those on the extremes. Mean Hausdorff distances were 9/17 pixels for the whole cells and 4/13 pixels for central slices. One slice was processed in approximately 8 s and a whole cell in 40 min. The algorithm outperformed active contours in both accuracy and time.

This paper describes a framework for the automatic segmentation of the nuclear envelope of cancerous HeLa cells and the modelling of the volumetric shape against an ellipsoid. The framework is automatic and unsupervised and reported a Jaccard Similarity Index of 0.968 against a manual segmentation. The modelling of the surface provides a visual display of the variations, both smooth and rugged over the surface, and measurements can be extracted with the expectation that they can correlate with the biological characteristics of the cells.

AbstractThis paper describes a framework for the automatic segmentation of the nuclear envelope of cancerous HeLa cells and the modelling of the volumetric shape against an ellipsoid. The framework is automatic and unsupervised and reported a Jaccard Similarity Index of 0.968 against a manual segmentation. The modelling of the surface provides a visual display of the variations, both smooth and rugged over the surface, and measurements can be extracted with the expectation that they can correlate with the biological characteristics of the cells.

This paper describes an image-processing pipeline for the automatic segmentation of the nuclear envelope of HeLa cells observed through Electron Microscopy. The pipeline was applied to a 3D stack of 300 images. The intermediate results of neighbouring slices are further combined to improve the final results. Comparison with a hand-segmented ground truth reported Jaccard similarity values between 94–98 https://github.com/reyesaldasoro/HeLa-Cell-Segmentation .