Constantino Carlos Reyes-Aldasoro

• PhD, MSc, DIC, BSEE, SM IEEE
• Senior Lecturer at City, University of London

Medical image analysis has experienced significant advances with the integration of machine learning, deep learning, and other mathematical and computational methodologies into the pipelines of data analysis. One methodology that has received less attention is Persistent Homology (PH), which comes from the growing field of Topological Data Analysis...

The extracellular matrix (ECM) controls tumour dissemination. We characterise ECM organization in human and mouse tumours, identifying three regions: tumour body, proximal invasive front and distal invasive front. Invasive areas show increased matrix density, fibre thickness, length, and alignment, with unique radial fibre orientation at the distal...

This study investigated lateral asymmetry in the linguopalatal speech sounds of British English by means of electropalatography. This instrumental technique visualizes tongue–palate contact during speech production and allows for the quantification of contact patterns. The first and main objective of the study was to establish a method of measuring...

Affect recognition in a real-world, less constrained environment is the principal prerequisite of the industrial-level usefulness of this technology. Monitoring the psychological profile using smart, wearable electroencephalogram (EEG) sensors during daily activities without external stimuli, such as memory-induced emotions, is a challenging resear...

The International Classification of Diseases (ICD) serves as a widely employed framework for assigning diagnosis codes to electronic health records of patients. These codes facilitate the encapsulation of diagnoses and procedures conducted during a patient’s hospitalisation. This study aims to devise a predictive model for ICD codes based on the MI...

Obtaining the traces and the characteristics of elongated structures is an important task in computer vision pipelines. In biomedical applications, the analysis of traces of vasculature, nerves or fibres of the extracellular matrix can help characterise processes like angiogenesis or the effect of a certain treatment. This paper presents an objecti...

This paper describes the advantages and disadvantages of adapting the U-Net architecture from a traditional GPU to a 4f free-space optical environment. The implementation is based on an optical-based acceleration called FatNet and thus this adaption is called Fat-U-Net. Fat-U-Net neglects the pooling operations in UNet, but maintains a similar numb...

Class I PI3kinases coordinate the delivery of microbicidal effectors to the phagosome by forming the phosphoinositide lipid second messenger, phosphatidylinositol (3, 4, 5)-trisphosphate (PIP3). However, the dynamics of PIP3 in neutrophils during a bacterial infection are unknown. We have therefore developed an in vivo, live zebrafish infection mod...

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...

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 segmentation mitochondria algorithms were quantitatively compared,...

The Oxford English Dictionary includes 17 definitions for the word “model” as a noun and another 11 as a verb. Therefore, context is necessary to understand the meaning of the word model. For instance, “model railways” refer to replicas of railways and trains at a smaller scale and a “model student” refers to an exemplary individual. In some cases,...

The Oxford English Dictionary includes 17 definitions for the word “model” as a noun and other 11 as a verb. Therefore, context is necessary to understand the meaning of the word model. For in-stance, “model railways” refer to replicas of railways and trains at a smaller scale and a “model student” refers to an exemplar individual. In some cases, a...

The inspection and maintenance of electrical power lines (PL) via unmanned aerial vehicles (UAV) require fast and accurate PL detection to ensure smooth and secure electrical operations. However, the detection of PLs from aerial images is a highly challenging task due to the thin nature of PLs and the inherent noisy image backgrounds. Traditional l...

A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image seeks to explain an image’s classification probability by contrasting the image with a representative contrast image, such as an auto-generat...

Early detection of Alzheimer’s disease (AD) has been a major focus of current research efforts to guide interventions at the earliest stages of the disease. Subtle changes to the brain might be observed with neuroimaging techniques, even before symptoms surface. We interrogated brain images obtained with Magnetic Resonance Imaging (MRI) from two la...

This paper describes the transformation of a traditional in silico classification network into an optical fully convolutional neural network with high-resolution feature maps and kernels. When using the free-space 4f system to accelerate the inference speed of neural networks, higher resolutions of feature maps and kernels can be used without the l...

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 dime...

This paper describes the transformation of a traditional in-silico classification network into an optical fully convolutional neural network with high-resolution feature maps and kernels. When using the free-space 4f system to accelerate the inference speed of neural networks, higher resolutions of feature maps and kernels can be used without the l...

In this work, the performance of five deep learning architectures in classifying COVID-19 in a multi-class set-up is evaluated. The classifiers were built on pretrained ResNet-50, ResNet-50r (with kernel size 5×5 in the first convolutional layer), DenseNet-121, MobileNet-v3 and the state-of-the-art CaiT-24-XXS-224 (CaiT) transformer. The cross entr...

This paper describes a multiclass semantic segmentation of breast cancer images into the following classes: Tumour, Stroma, Inflammatory, Necrosis and Other. The images were stained with Haematoxilin and Eosin and acquired from the Cancer Genome Atlas through the Breast Cancer Semantic Segmentation Challenge. Over 12,000 patches of data and classes...

Background: Cancer-related research, as indicated by the number of entries in Medline, the National Library of Medicine of the USA, has dominated the medical literature. An important component of this research is based on the use of computational techniques to analyse the data produced by the many acquisition modalities. This paper presents a revie...

A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image’s classification probability by contrasting the image with a corresponding image generated automatically via adversarial le...

This paper describes the quantitative and qualitative evaluation of training data, ground truth and the variability of the shape of HeLa cells as observed with electron microscopy in the process of semantic segmentation. HeLa cells are a widely used immortal cell line, but the principles described here could apply to other cells. From a data set of...

Background Cancer-related research, as indicated by the number of entries in Medline, the National Library of Medicine of the USA, has dominated the medical literature. An important component of this research is based on the use of computational techniques to analyse the data produced by the many acquisition modalities. This paper presents a review...

This paper presents a computer-vision-based methodology for automatic image-based classification of 2042 training images and 284 unseen (test) images divided into 68 categories of gemstones. A series of feature extraction techniques (33 including colour histograms in the RGB, HSV and CIELAB space, local binary pattern, Haralick texture and grey-lev...

This work describes a non-invasive, automated software framework to discriminate between individuals with a genetic disorder, Pitt–Hopkins syndrome (PTHS), and healthy individuals through the identification of morphological facial features. The input data consist of frontal facial photographs in which faces are located using histograms of oriented...

Modern Electron Microscopes (EM) can acquire very high-resolution images and a core facility can produce tens of thousands of data sets that can easily exceed gigabytes of data every month. The identification of individual cells, and the shape of the cell are of great interest to scientists, as the structure of the cell may reveal some conditions o...

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 Musculos...

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 Musculos...

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...

In this work, the unsupervised volumetric semantic 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 8, 192 × 8, 192 pixels each. The background was used to create a dist...

Efficient detection of thin objects, from stationary or moving images, is significant in a variety of research areas. These research areas include but are not limited to electric power line detection systems, sperm tail detection for clinical sperm research, mooring lines detection, road-lane line detection for autonomous vehicles, and cracks detec...

The segmentation of power lines (PLs) from aerial images is a crucial task for the safe navigation of unmanned aerial vehicles (UAVs) operating at low altitudes. Despite the advances in deep learning-based approaches for PL segmentation, these models are still vulnerable to the class imbalance present in the data. The PLs occupy only a minimal port...

This work describe an algorithm for the automatic analysis of the waggle dance of honeybees. The algorithm analyses a video of a beehive with 13,624 frames, acquired at 25 frames/second. The algorithm employs the following traditional image processing steps: conversion to grayscale, low pass filtering, background subtraction, thresholding, tracking...

Accurate measurements of cell morphology and behaviour are fundamentally important for understanding how disease, molecules and drugs affect cell function in vivo . Here, by using muscle stem cell (muSC) responses to injury in zebrafish as our biological paradigm, we established a ‘ground truth’ for muSC behaviour. This revealed that segmentation a...

Simple Summary The appearance of histology images stained with H&E can vary a lot as a consequence of changes in the reagents, staining conditions, preparation procedure and acquisition system. In this work we investigated whether color preprocessing—specifically color deconvolution and color normalization—could be used to correct such variability...

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 seman...

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 t...

Fractures of the wrist are common in Emergency Departments, where some patients are treated with a procedure called Manipulation under Anaesthesia. In some cases, this procedure is unsuccessful and patients need to revisit the hospital where they undergo surgery to treat the fracture. This work describes a geometric semi-automatic image analysis al...

Wrist fractures (e.g. Colles’ fracture) are the most common injuries in the upper extremity treated in Emergency Departments. Treatment for most patients is an intervention called Manipulation under Anaesthesia (MUA). Surgical treatment would be needed for complex fractures or if the wrist stability is not restored. In addition, an unsuccessful tre...

In this paper, a novel method for interaction detection is presented to compare the contact dynamics of macrophages in the Drosophila embryo. The study is carried out by a framework called macrosight, which analyses the movement and interaction of migrating macrophages. The framework incorporates a segmentation and tracking algorithm into analysing...

Centrosome separation in late G2/ early prophase requires precise spatial coordination that is determined by a balance of forces promoting and antagonizing separation. The major effector of centrosome separation is the kinesin Eg5. However, the identity and regulation of Eg5-antagonizing forces is less well characterized. By manipulating candidate...

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 a...

This paper experiments with the number of fully-connected layers in a deep convolutional neural network as applied to the classification of fundus retinal images. The images analysed corresponded to the ODIR 2019 (Peking University International Competition on Ocular Disease Intelligent Recognition) [9], which included images of various eye disease...

This paper describes a methodology that extracts morphological features from histological breast cancer images stained for Hematoxilyn and Eosin (H&E). Cellularity was estimated and the correlation between features and the residual tumour size cellularity after a Neo-Adjuvant treatment (NAT) was examined. Images from whole slide imaging (WSI) were...

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...

Electropalatography is a technique that employs a custom-made artificial palate to measure the contact established between the tongue and the hard palate. This technique is widely used in treatment of articulation disorders and studies of speech. In order to evaluate the accuracy of the electropalate, the device needs to be separated from the volum...

This paper compares the contact-repulsion movement of mutant and wild-type macrophages using a novel interaction detection mechanism. The migrating macrophages are observed in Drosophila embryos. The study is carried out by a framework called macrosight, which analyses the movement and interaction of migrating macrophages. The framework incorporate...

This work describes an automatic methodology to discriminate between individuals with the genetic disorder Pitt-Hopkins syndrome (PTHS), and healthy individuals. As input data, the methodology accepts unconstrained frontal facial photographs, from which faces are located with Histograms of Oriented Gradients features descriptors. Pre-processing ste...

In this work, images of a HeLa cancer cell were semantically segmented with one traditional image-processing algorithm and three deep learning architectures: VGG16, ResNet18 and Inception-ResNet-v2. Three hundred slices, each 2000 × 2000 pixels, of a HeLa Cell were acquired with Serial Block Face Scanning Electron Microscopy. The deep learning arch...

Wrist fractures (e.g. Colles’ fracture) are the most common injuries in the upper extremity treated in Emergency Departments. Most patients are treated with a procedure called Manipulation under Anaesthesia. Surgical treatment may still be needed in complex fractures or if the wrist stability is not restored. This can lead to inefficiency in constr...

Fractures of the wrist are common in Emergency Departments, where some patients are treated with a procedure called Manipulation under Anaesthesia. In some cases this procedure is unsuccessful and patients need to visit the hospital again where they undergo surgery to treat the fracture. This work describes a geometric semi-automatic image analysis...

This paper presents a preliminary study on macrophages migration in Drosophila embryos, comparing two types of cells. The study is carried out by a framework called macrosight which analyses the movement and interaction of migrating macrophages. The framework incorporates a segmentation and tracking algorithm into analysing motion characteristics o...

The monotonous routine of medical image analysis under tight time constraints has always led to work fatigue for many medical practitioners. Medical image interpretation can be error-prone and this can increase the risk of an incorrect procedure being recommended. While the advancement of complex deep learning models has achieved performance beyond...

Accurate measurements of cell morphology and behaviour are fundamentally important for understanding how disease, molecules and drugs affect cell function in vivo. Using muscle stem cell (muSC) responses to injury in zebrafish as our biological paradigm we have established a ground truth for muSC cell behaviour. This revealed that variability in se...

A high-speed camera has been used to produce unique time-resolved images of high quality to describe the dynamics of the lubricant flow and cavitation characteristics in a sliding optical liner over a fixed single piston-ring lubricant assembly for three lubricants with different viscosities to establish their impact on cavitation formation and dev...

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-l...

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 proc...

The initial host response to fungal pathogen invasion is critical to infection establishment and outcome. However, the diversity of leukocyte–pathogen interactions is only recently being appreciated. We describe a new form of interleukocyte conidial exchange called “shuttling.” In Talaromyces marneffei and Aspergillus fumigatus zebrafish in vivo in...

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 Hus{\o}y were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a dee...

This paper compares the effects of colour pre-processing on the classification performance of H&E-stained images. Variations in the tissue preparation procedures, acquisition systems, stain conditions and reagents are all source of artifacts that can affect negatively computer-based classification. Pre-processing methods such as colour constancy, t...

The process of speech production, i.e., the compression of air in the lungs, the vibration activity of the larynx, and the movement of the articulators, is of great interest in phonetics, phonology, and psychology. One technique by which speech production is analysed is electropalatography, in which an artificial palate, moulded to the speaker's ha...

Background For virtually every patient with colorectal cancer (CRC), hematoxylin–eosin (HE)–stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract...

OS in the TCGA and DACHS cohort, stratified by UICC stage I, II, III, and IV (cleanstage). Log rank p < 0.0001 for panels A and B. DACHS, Darmkrebs: Chancen der Verhütung durch Screening; OS, overall survival; TCGA, The Cancer Genome Atlas; UICC, Union Internationale Contre le Cancer. (TIF)

TRIPOD compliance statement. (DOCX)

Flowchart of the study. (A) First, we used an image set of 100,000 histological images to find the best neural network model among three candidates. VGG19 achieved the best classification accuracy in an internal test set. (B) We then trained a VGG19 model on the full set of 100,000 images and tested the prediction accuracy in an external test set o...

ROC curves of classification performance in an external validation set. The external validation set consisted of 7,180 images in nine tissue classes (CRC-VAL-HE-7K data set) and was randomly split into k = 25 subsets. The classifier was applied to each of these subsets. For each tissue class and each subset, the ROC curve is plotted, and the AUC is...

Categorical variables of the TCGA cohort. (DOCX)

All layers in the final modified VGG19 CNN model. (DOCX)

Comparison of three CNN architectures. The image data set with 100,000 images in nine classes was divided into 70% training set, 15% validation set, and 15% testing set. Five different networks (alexnet, googlenet, resnet50, squeezenet, and vgg19) were trained on this data set. VGG19 achieved the best classification accuracy (98.7%) in this interna...

Clustering of stromal and tumoral phenotypes. Deep neuron activation (fc7 layer in the VGG19 model) from the training set NCT-CRC-HE-100K were extracted for all images in the classes STR and TUM. These activation vectors were visualized using tSNE. Representative images from four regions (top, bottom, left, right) are shown. (A) tSNE for class STR,...

Genes used for the CAF signature, established by Isella et al. (35). CAF, cancer-associated fibroblast. (DOCX)

Continuous variables of the TCGA cohort. (DOCX)

Softmax layer activations for larger images in the DACHS cohort. (A–M) Representative images from this data set; left: HE after color normalization; right: output neuron activations (softmax layer [layer 46]). DACHS, Darmkrebs: Chancen der Verhütung durch Screening; HE, hematoxylin–eosin. (TIF)

Categorical variables of the DACHS cohort. (DOCX)

Continuous variables of the DACHS cohort. (DOCX)