Behavioural immune landscapes of inflammation.

Transcriptional and proteomic profiling of individual cells have revolutionized interpretation of biological phenomena by providing cellular landscapes of healthy and diseased tissues1,2. These approaches, however, do not describe dynamic scenarios in which cells continuously change their biochemical properties and downstream 'behavioural' outputs3-5. Here we used 4D live imaging to record tens to hundreds of morpho-kinetic parameters describing the dynamics of individual leukocytes at sites of active inflammation. By analysing more than 100,000 reconstructions of cell shapes and tracks over time, we obtained behavioural descriptors of individual cells and used these high-dimensional datasets to build behavioural landscapes. These landscapes recognized leukocyte identities in the inflamed skin and trachea, and uncovered a continuum of neutrophil states inside blood vessels, including a large, sessile state that was embraced by the underlying endothelium and associated with pathogenic inflammation. Behavioural screening in 24 mouse mutants identified the kinase Fgr as a driver of this pathogenic state, and interference with Fgr protected mice from inflammatory injury. Thus, behavioural landscapes report distinct properties of dynamic environments at high cellular resolution.

URI-CADS: A Fully Automated Computer-Aided Diagnosis System for Ultrasound Renal Imaging.

Ultrasound is a widespread imaging modality, with special application in medical fields such as nephrology. However, automated approaches for ultrasound renal interpretation still pose some challenges: (1) the need for manual supervision by experts at various stages of the system, which prevents its adoption in primary healthcare, and (2) their limited considered taxonomy (e.g., reduced number of pathologies), which makes them unsuitable for training practitioners and providing support to experts. This paper proposes a fully automated computer-aided diagnosis system for ultrasound renal imaging addressing both of these challenges. Our system is based in a multi-task architecture, which is implemented by a three-branched convolutional neural network and is capable of segmenting the kidney and detecting global and local pathologies with no need of human interaction during diagnosis. The integration of different image perspectives at distinct granularities enhanced the proposed diagnosis. We employ a large (1985 images) and demanding ultrasound renal imaging database, publicly released with the system and annotated on the basis of an exhaustive taxonomy of two global and nine local pathologies (including cysts, lithiasis, hydronephrosis, angiomyolipoma), establishing a benchmark for ultrasound renal interpretation. Experiments show that our proposed method outperforms several state-of-the-art methods in both segmentation and diagnosis tasks and leverages the combination of global and local image information to improve the diagnosis. Our results, with a 87.41% of AUC in healthy-pathological diagnosis and 81.90% in multi-pathological diagnosis, support the use of our system as a helpful tool in the healthcare system.

An interpretable CNN-based CAD system for skin lesion diagnosis.

Recently, convolutional neural networks have greatly outperformed previous systems based on handcrafted features once the size of public databases has increased. However, these algorithms learn feature representations that are difficult to interpret and analyse. On the other hand, experts require automatic systems to explain their decisions according to clinical criteria which, in the field of melanoma diagnosis, are related to the analysis of dermoscopic features found in the lesions. In recent years, the interpretability of deep networks has been explored using methods that obtain visual features highlighted by neurones or analyse activations to extract more useful information. Following the latter approach, this study proposes a system for melanoma diagnosis that explicitly incorporates dermoscopic feature segmentations into a diagnosis network through a channel modulation scheme. Modulation weights control the influence of the detected visual patterns based on the lesion content. As shown in the experimental section, our design not only improves the system performance on the ISIC 2016 (average AUC of 86.6% vs. 85.8%) and 2017 (average AUC of 94.0% vs. 93.8%) datasets, but also notably enhances the interpretability of the diagnosis, providing useful and intuitive cues to clinicians.

The Homologous Recombination Deficiency Scar in Advanced Cancer: Agnostic Targeting of Damaged DNA Repair.

BRCA1 and BRCA2 are the most recognized tumor-suppressor genes involved in double-strand DNA break repair through the homologous recombination (HR) system. Widely known for its role in hereditary cancer, HR deficiency (HRD) has turned out to be critical beyond breast and ovarian cancer: for prostate and pancreatic cancer also. The relevance for the identification of these patients exceeds diagnostic purposes, since results published from clinical trials with poly-ADP ribose polymerase (PARP) inhibitors (PARPi) have shown how this type of targeted therapy can modify the long-term evolution of patients with HRD. Somatic aberrations in other HRD pathway genes, but also indirect genomic instability as a sign of this DNA repair impairment (known as HRD scar), have been reported to be relevant events that lead to more frequently than expected HR loss of function in several tumor types, and should therefore be included in the current diagnostic and therapeutic algorithm. However, the optimal strategy to identify HRD and potential PARPi responders in cancer remains undefined. In this review, we summarize the role and prevalence of HRD across tumor types and the current treatment landscape to guide the agnostic targeting of damaged DNA repair. We also discuss the challenge of testing patients and provide a special insight for new strategies to select patients who benefit from PARPi due to HRD scarring.

ACME: Automatic feature extraction for cell migration examination through intravital microscopy imaging.

Cell detection and tracking applied to in vivo fluorescence microscopy has become an essential tool in biomedicine to characterize 4D (3D space plus time) biological processes at the cellular level. Traditional approaches to cell motion analysis by microscopy imaging, although based on automatic frameworks, still require manual supervision at some points of the system. Hence, when dealing with a large amount of data, the analysis becomes incredibly time-consuming and typically yields poor biological information. In this paper, we propose a fully-automated system for segmentation, tracking and feature extraction of migrating cells within blood vessels in 4D microscopy imaging. Our system consists of a robust 3D convolutional neural network (CNN) for joint blood vessel and cell segmentation, a 3D tracking module with collision handling, and a novel method for feature extraction, which takes into account the particular geometry in the cell-vessel arrangement. Experiments on a large 4D intravital microscopy dataset show that the proposed system achieves a significantly better performance than the state-of-the-art tools for cell segmentation and tracking. Furthermore, we have designed an analytical method of cell behaviors based on the automatically extracted features, which supports the hypotheses related to leukocyte migration posed by expert biologists. This is the first time that such a comprehensive automatic analysis of immune cell migration has been performed, where the total population under study reaches hundreds of neutrophils and thousands of time instances.

DermaKNet: Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for Skin Lesion Diagnosis.

Traditional approaches to automatic diagnosis of skin lesions consisted of classifiers working on sets of hand-crafted features, some of which modeled lesion aspects of special importance for dermatologists. Recently, the broad adoption of convolutional neural networks (CNNs) in most computer vision tasks has brought about a great leap forward in terms of performance. Nevertheless, with this performance leap, the CNN-based computer-aided diagnosis (CAD) systems have also brought a notable reduction of the useful insights provided by hand-crafted features. This paper presents DermaKNet, a CAD system based on CNNs that incorporates specific subsystems modeling properties of skin lesions that are of special interest to dermatologists aiming to improve the interpretability of its diagnosis. Our results prove that the incorporation of these subsystems not only improves the performance, but also enhances the diagnosis by providing more interpretable outputs.