References of "Jarazo, Javier 50002037"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailFrom tech to bench: Deep Learning pipeline for image segmentation of high-throughput high-content microscopy data
Garcia Santa Cruz, Beatriz UL; Jarazo, Javier UL; Saraiva, Claudia UL et al

Poster (2019, November 29)

Automation of biological image analysis is essential to boost biomedical research. The study of complex diseases such as neurodegenerative diseases calls for big amounts of data to build models towards ... [more ▼]

Automation of biological image analysis is essential to boost biomedical research. The study of complex diseases such as neurodegenerative diseases calls for big amounts of data to build models towards precision medicine. Such data acquisition is feasible in the context of high-throughput screening in which the quality of the results relays on the accuracy of image analysis. Although the state-of-the-art solutions for image segmentation employ deep learning approaches, the high cost of manual data curation is hampering the real use in current biomedical research laboratories. Here, we propose a pipeline that employs deep learning not only to conduct accurate segmentation but also to assist with the creation of high-quality datasets in a less time-consuming solution for the experts. Weakly-labelled datasets are becoming a common alternative as a starting point to develop real-world solutions. Traditional approaches based on classical multimedia signal processing were employed to generate a pipeline specifically optimized for the high-throughput screening images of iPSC fused with rosella biosensor. Such pipeline produced good segmentation results but with several inaccuracies. We employed the weakly-labelled masks produced in this pipeline to train a multiclass semantic segmentation CNN solution based on U-net architecture. Since a strong class imbalance was detected between the classes, we employed a class sensitive cost function: Dice coe!cient. Next, we evaluated the accuracy between the weakly-labelled data and the trained network segmentation using double-blind tests conducted by experts in cell biology with experience in this type of images; as well as traditional metrics to evaluate the quality of the segmentation using manually curated segmentations by cell biology experts. In all the evaluations the prediction of the neural network overcomes the weakly-labelled data quality segmentation. Another big handicap that complicates the use of deep learning solutions in wet lab environments is the lack of user-friendly tools for non-computational experts such as biologists. To complete our solution, we integrated the trained network on a GUI built on MATLAB environment with non-programming requirements for the user. This integration allows conducting semantic segmentation of microscopy images in a few seconds. In addition, thanks to the patch-based approach it can be employed in images with different sizes. Finally, the human-experts can correct the potential inaccuracies of the prediction in a simple interactive way which can be easily stored and employed to re-train the network to improve its accuracy. In conclusion, our solution focuses on two important bottlenecks to translate leading-edge technologies in computer vision to biomedical research: On one hand, the effortless obtention of high-quality datasets with expertise supervision taking advantage of the proven ability of our CNN solution to generalize from weakly-labelled inaccuracies. On the other hand, the ease of use provided by the GUI integration of our solution to both segment images and interact with the predicted output. Overall this approach looks promising for fast adaptability to new scenarios. [less ▲]

Detailed reference viewed: 63 (11 UL)
Full Text
Peer Reviewed
See detailDeep Learning Quality Control for High-Throughput High-Content Screening Microscopy Images
Garcia Santa Cruz, Beatriz UL; Jarazo, Javier UL; Schwamborn, Jens Christian UL et al

Poster (2019, October 10)

Automation of biological image analysis is essential to boost biomedical research. The study of complex diseases such as neurodegenerative diseases calls for big amounts of data to build models towards ... [more ▼]

Automation of biological image analysis is essential to boost biomedical research. The study of complex diseases such as neurodegenerative diseases calls for big amounts of data to build models towards precision medicine. Such data acquisition is feasible in the context of high-throughput high-content screening (HTHCS) in which the quality of the results relays on the accuracy of image analysis. Deep learning (DL) yields great performance in image analysis tasks especially with big amounts of data such as the produced in HTHCS contexts. Such DL and HTHCS strength is also their biggest weakness since DL solutions are highly sensitive to bad quality datasets. Hence, accurate Quality Control (QC) for microscopy HTHCS becomes an essential step to obtain reliable pipelines for HTHCS analysis. Usually, artifacts found on these platforms are the consequence of out-of-focus and undesirable density variations. The importance of accurate outlier detection becomes essential for both the training process of generic ML solutions (i.e. segmentation or classification) and the QC of the input data such solution will predict on. Moreover, during the QC of the input dataset, we aim not only to discard unsuitable images but to report the user on the quality of its dataset giving the user the choice to keep or discard the bad images. To build the QC solution we employed fluorescent microscopy images of rosella biosensor generated in the HTHCS platform. A total of 15 planes ranging from -6z to +7z steps to the two optimum planes. We evaluated 27 known focus measure operators and concluded that they have low sensitivity in noisy conditions. We propose a CNN solution which predicts the focus error based on the distance to the optimal plane, outperforming the evaluated focus operators. This QC allows for better results in cell segmentation models based on U-Net architecture as well as promising improvements in image classification tasks. [less ▲]

Detailed reference viewed: 45 (3 UL)
Full Text
Peer Reviewed
See detailAutomated microfluidic cell culture of stem cell derived dopaminergic neurons
Kane, Khalid; Lucumi Moreno, Edinson; Hachi, Siham et al

in Scientific Reports (2019)

Detailed reference viewed: 153 (10 UL)
Full Text
Peer Reviewed
See detailImpaired serine metabolism complements LRRK2-G2019S pathogenicity in PD patients
Nickels, Sarah UL; Walter, Jonas; Bolognin, Silvia UL et al

in Parkinsonism and Related Disorders (2019)

Detailed reference viewed: 92 (4 UL)
Full Text
Peer Reviewed
See detailAutomated high-throughput highcontent autophagy and mitophagy analysis platform
Arias-Fuenzalida, Jonathan; Jarazo, Javier UL; Walter, Jonas et al

in Scientific Reports (2019)

Detailed reference viewed: 84 (8 UL)
Full Text
Peer Reviewed
See detail3D Cultures of Parkinson's Disease‐Specific Dopaminergic Neurons for High Content Phenotyping and Drug Testing
Bolognin, Silvia UL; Fossépré, Marie; Qing, Xiaobing et al

in Advanced Science (2018)

Parkinson's disease (PD)‐specific neurons, grown in standard 2D cultures, typically only display weak endophenotypes. The cultivation of PD patient‐specific neurons, derived from induced pluripotent stem ... [more ▼]

Parkinson's disease (PD)‐specific neurons, grown in standard 2D cultures, typically only display weak endophenotypes. The cultivation of PD patient‐specific neurons, derived from induced pluripotent stem cells carrying the LRRK2‐G2019S mutation, is optimized in 3D microfluidics. The automated image analysis algorithms are implemented to enable pharmacophenomics in disease‐relevant conditions. In contrast to 2D cultures, this 3D approach reveals robust endophenotypes. High‐content imaging data show decreased dopaminergic differentiation and branching complexity, altered mitochondrial morphology, and increased cell death in LRRK2‐G2019S neurons compared to isogenic lines without using stressor agents. Treatment with the LRRK2 inhibitor 2 (Inh2) rescues LRRK2‐G2019S‐dependent dopaminergic phenotypes. Strikingly, a holistic analysis of all studied features shows that the genetic background of the PD patients, and not the LRRK2‐G2019S mutation, constitutes the strongest contribution to the phenotypes. These data support the use of advanced in vitro models for future patient stratification and personalized drug development. [less ▲]

Detailed reference viewed: 228 (35 UL)
Full Text
See detailTHE PARKINSON’S DISEASE ASSOCIATED PINK1-PARKIN PATHWAY IN PATHOLOGY AND DEVELOPMENT
Jarazo, Javier UL

Doctoral thesis (2018)

Parkinson’s disease (PD) has an aetiology not completely understood. One of the hypothesis in the field is that many neurodegenerative diseases are influenced by developmental disorders. The underlying ... [more ▼]

Parkinson’s disease (PD) has an aetiology not completely understood. One of the hypothesis in the field is that many neurodegenerative diseases are influenced by developmental disorders. The underlying concept is that already during brain development some processes are deregulated producing a higher degree of susceptibility for neurodegeneration during aging. Two hereditary early onset forms of PD are caused by recessive mutations in PTEN-induced putative kinase 1 (PINK1) and Parkin genes that regulate mitochondrial function and morphology, quarantining damaged mitochondria before their degradation as well as triggering the process of mitophagy. Our hypothesis is that alterations of the Pink1-Parkin pathway have an impact in mitochondrial physiology tempering the differentiation ability of neuroepithelial stem cells into dopaminergic neurons. For evaluating this hypothesis we reprogramed patients’ fibroblasts carrying PINK1 mutations, as well as from healthy individuals, to human induced pluripotent stem cells. We developed a streamlined technique of gene editing (FACE) by using the CRISPR/Cas9 system combined with a composite of fluorescent proteins in the donor template for biallelic gene targeting. Isogenic controls were generated using this technique that allowed us to analyze the contribution of corrected patients’ mutations in the cellular defects observed. Human iPSCs were differentiated into a neuroepithelial stem cell state (NESC) from where the cells were further differentiated into neurons. We established different algorithms for pattern recognition and applied them for image analysis of different features such as mitochondrial morphology, proliferation capacity, apoptosis and differentiation. Patient’s derived cells presented an impaired differentiation efficiency into dopaminergic neurons as well as an imbalanced cell renewal that can be linked to the mitochondrial differences. Using 3D cultures, such as microfluidics and organoids, we were able to recapitulate this differentiation impairment in a system that mimics better the context of an in vivo environment. We evaluated the energetic capabilities of the NESCs and the firing activity of differentiated neurons, which also showed a dysregulation in patient cells. We introduced a new system for large-scale analysis of the autophagy and mitophagy pathways by the combination of stably integrated Rosella constructs in different patients’ lines and an image analysis script for classification of the different subcellular structures involved in these pathways activities. This revealed that the basal activity as well as the response against stressors of these pathways are altered in cells derived from patients having different mutations causative of PD. We performed a screen of repurposed drugs as well as of novel compounds to evaluate their impact in this altered developmental transition identifying a potential candidate to be further analysed in an in vivo context. [less ▲]

Detailed reference viewed: 140 (26 UL)