![]() Arena, Giuseppe ![]() ![]() E-print/Working paper (2023) Background Parkinson's disease (PD) is the fastest growing neurodegenerative disorder, with affected individuals expected to double during the next 20 years. This raises the urgent need to better ... [more ▼] Background Parkinson's disease (PD) is the fastest growing neurodegenerative disorder, with affected individuals expected to double during the next 20 years. This raises the urgent need to better understand the genetic architecture and downstream cellular alterations underlying PD pathogenesis, in order to identify more focused therapeutic targets. While only ~10\% of PD cases can be clearly attributed to monogenic causes, there is mounting evidence that additional genetic factors could play a role in idiopathic PD (iPD). In particular, common variants with low to moderate effect size in multiple genes regulating key neuroprotective activities may act as risk factors for PD. In light of the well-established involvement of mitochondrial dysfunction in PD, we hypothesized that a fraction of iPD cases may harbour a pathogenic combination of common variants in nuclear-encoded mitochondrial genes, ultimately resulting in neurodegeneration.Methods: To capture this mitochondria-related 'missing heritability', we leveraged on existing data from previous genome-wide association studies (GWAS) i.e., the large PD GWAS from Nalls and colleagues. We then used computational approaches based on mitochondria-specific polygenic risk scores (mitoPRSs) for imputing the genotype data obtained from different iPD case-control datasets worldwide, including the Luxembourg Parkinson\textquoterights Study (412 iPD patients and 576 healthy controls) and the COURAGE-PD cohorts (7270 iPD cases and 6819 healthy controls).Results: Applying this approach to gene sets controlling mitochondrial pathways potentially relevant for neurodegeneration in PD, we demonstrated that common variants in genes regulating Oxidative Phosphorylation (OXPHOS-PRS) were significantly associated with a higher PD risk both in the Luxembourg Parkinson\textquoterights Study (odds ratio, OR=1.31[1.14-1.50], p=5.4e-04) and in COURAGE-PD (OR=1.23[1.18-1.27], p=1.5e-29). Functional analyses in primary skin fibroblasts and in the corresponding induced pluripotent stem cells-derived neuronal progenitor cells from Luxembourg Parkinson's Study iPD patients stratified according to the OXPHOS-PRS, revealed significant differences in mitochondrial respiration between high and low risk groups (p < 0.05). Finally, we also demonstrated that iPD patients with high OXPHOS-PRS have a significantly earlier age at disease onset compared to low-risk patients.Conclusions: Our findings suggest that OXPHOS-PRS may represent a promising strategy to stratify iPD patients into pathogenic subgroups in which the underlying neurodegeneration is due to a genetically defined mitochondrial burden potentially eligible for future, more tailored mitochondrially targeted treatments. [less ▲] Detailed reference viewed: 108 (4 UL)![]() Smajic, Semra ![]() ![]() in Brain : a journal of neurology (2022), 145(3), 964-978 Idiopathic Parkinson's disease is characterized by a progressive loss of dopaminergic neurons, but the exact disease etiology remains largely unknown. To date, Parkinson's disease research has mainly ... [more ▼] Idiopathic Parkinson's disease is characterized by a progressive loss of dopaminergic neurons, but the exact disease etiology remains largely unknown. To date, Parkinson's disease research has mainly focused on nigral dopaminergic neurons, although recent studies suggest disease-related changes also in non-neuronal cells and in midbrain regions beyond the substantia nigra. While there is some evidence for glial involvement in Parkinson's disease, the molecular mechanisms remain poorly understood. The aim of this study was to characterize the contribution of all cell types of the midbrain to Parkinson's disease pathology by single-nuclei RNA sequencing and to assess the cell type-specific risk for Parkinson's disease employing the latest genome-wide association study. We profiled >41 000 single-nuclei transcriptomes of postmortem midbrain from six idiopathic Parkinson's disease patients and five age-/sex-matched controls. To validate our findings in a spatial context, we utilized immunolabeling of the same tissues. Moreover, we analyzed Parkinson's disease-associated risk enrichment in genes with cell type-specific expression patterns. We discovered a neuronal cell cluster characterized by CADPS2 overexpression and low TH levels, which was exclusively present in IPD midbrains. Validation analyses in laser-microdissected neurons suggest that this cluster represents dysfunctional dopaminergic neurons. With regard to glial cells, we observed an increase in nigral microglia in Parkinson's disease patients. Moreover, nigral idiopathic Parkinson's disease microglia were more amoeboid, indicating an activated state. We also discovered a reduction in idiopathic Parkinson's disease oligodendrocyte numbers with the remaining cells being characterized by a stress-induced upregulation of S100B. Parkinson's disease risk variants were associated with glia- and neuron-specific gene expression patterns in idiopathic Parkinson's disease cases. Furthermore, astrocytes and microglia presented idiopathic Parkinson's disease-specific cell proliferation and dysregulation of genes related to unfolded protein response and cytokine signaling. While reactive patient astrocytes showed CD44 overexpression, idiopathic Parkinson's disease-microglia revealed a pro-inflammatory trajectory characterized by elevated levels of IL1B, GPNMB, and HSP90AA1. Taken together, we generated the first single-nuclei RNA sequencing dataset from the idiopathic Parkinson's disease midbrain, which highlights a disease-specific neuronal cell cluster as well as 'pan-glial' activation as a central mechanism in the pathology of the movement disorder. This finding warrants further research into inflammatory signaling and immunomodulatory treatments in Parkinson's disease. [less ▲] Detailed reference viewed: 124 (22 UL)![]() ; Smajic, Semra ![]() ![]() in Movement disorders : official journal of the Movement Disorder Society (2022) BACKGROUND: Mutations in the E3 ubiquitin ligase parkin cause autosomal recessive Parkinson's disease (PD). Together with PTEN-induced kinase 1 (PINK1), parkin regulates the clearance of dysfunctional ... [more ▼] BACKGROUND: Mutations in the E3 ubiquitin ligase parkin cause autosomal recessive Parkinson's disease (PD). Together with PTEN-induced kinase 1 (PINK1), parkin regulates the clearance of dysfunctional mitochondria. New mitochondria are generated through an interplay of nuclear- and mitochondrial-encoded proteins, and recent studies suggest that parkin influences this process at both levels. In addition, parkin was shown to prevent mitochondrial membrane permeability, impeding mitochondrial DNA (mtDNA) escape and subsequent neuroinflammation. However, parkin's regulatory roles independent of mitophagy are not well described in patient-derived neurons. OBJECTIVES: We sought to investigate parkin's role in preventing neuronal mtDNA dyshomeostasis, release, and glial activation at the endogenous level. METHODS: We generated induced pluripotent stem cell (iPSC)-derived midbrain neurons from PD patients with parkin (PRKN) mutations and healthy controls. Live-cell imaging, proteomic, mtDNA integrity, and gene expression analyses were employed to investigate mitochondrial biogenesis and genome maintenance. To assess neuroinflammation, we performed single-nuclei RNA sequencing in postmortem tissue and quantified interleukin expression in mtDNA/lipopolysaccharides (LPS)-treated iPSC-derived neuron-microglia co-cultures. RESULTS: Neurons from patients with PRKN mutations revealed deficits in the mitochondrial biogenesis pathway, resulting in mtDNA dyshomeostasis. Moreover, the energy sensor sirtuin 1, which controls mitochondrial biogenesis and clearance, was downregulated in parkin-deficient cells. Linking mtDNA disintegration to neuroinflammation, in postmortem midbrain with PRKN mutations, we confirmed mtDNA dyshomeostasis and detected an upregulation of microglia overexpressing proinflammatory cytokines. Finally, parkin-deficient neuron-microglia co-cultures elicited an enhanced immune response when exposed to mtDNA/LPS. CONCLUSIONS: Our findings suggest that parkin coregulates mitophagy, mitochondrial biogenesis, and mtDNA maintenance pathways, thereby protecting midbrain neurons from neuroinflammation and degeneration. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society. [less ▲] Detailed reference viewed: 115 (10 UL)![]() ; Ohnmacht, Jochen ![]() in Scientific Reports (2021), 11 Parkinson’s disease (PD) is characterised by the degeneration of A9 dopaminergic neurons and the pathological accumulation of alpha-synuclein. The p.A30P SNCA mutation generates the pathogenic form of the ... [more ▼] Parkinson’s disease (PD) is characterised by the degeneration of A9 dopaminergic neurons and the pathological accumulation of alpha-synuclein. The p.A30P SNCA mutation generates the pathogenic form of the alpha-synuclein protein causing an autosomal-dominant form of PD. There are limited studies assessing pathogenic SNCA mutations in patient-derived isogenic cell models. Here we provide a functional assessment of dopaminergic neurons derived from a patient harbouring the p.A30P SNCA mutation. Using two clonal gene-corrected isogenic cell lines we identified image-based phenotypes showing impaired neuritic processes. The pathological neurons displayed impaired neuronal activity, reduced mitochondrial respiration, an energy deficit, vulnerability to rotenone, and transcriptional alterations in lipid metabolism. Our data describes for the first time the mutation-only effect of the p.A30P SNCA mutation on neuronal function, supporting the use of isogenic cell lines in identifying image-based pathological phenotypes that can serve as an entry point for future disease-modifying compound screenings and drug discovery strategies. [less ▲] Detailed reference viewed: 49 (1 UL)![]() Bolognin, Silvia ![]() ![]() ![]() in Biomedical Science and Engineering (2021) Detailed reference viewed: 200 (25 UL)![]() ; Boussaad, Ibrahim ![]() ![]() in Scientific Reports (2021) Detailed reference viewed: 114 (5 UL)![]() ; Bolognin, Silvia ![]() in Cell Reports (2021) Detailed reference viewed: 99 (11 UL)![]() Boussaad, Ibrahim ![]() ![]() ![]() in Scientific Reports (2021) Detailed reference viewed: 148 (5 UL)![]() Badanjak, Katja ![]() ![]() ![]() in Frontiers in cell and developmental biology (2021), 9 Parkinson's disease (PD) is a neurodegenerative disease with unknown cause in the majority of patients, who are therefore considered "idiopathic" (IPD). PD predominantly affects dopaminergic neurons in ... [more ▼] Parkinson's disease (PD) is a neurodegenerative disease with unknown cause in the majority of patients, who are therefore considered "idiopathic" (IPD). PD predominantly affects dopaminergic neurons in the substantia nigra pars compacta (SNpc), yet the pathology is not limited to this cell type. Advancing age is considered the main risk factor for the development of IPD and greatly influences the function of microglia, the immune cells of the brain. With increasing age, microglia become dysfunctional and release pro-inflammatory factors into the extracellular space, which promote neuronal cell death. Accordingly, neuroinflammation has also been described as a feature of PD. So far, studies exploring inflammatory pathways in IPD patient samples have primarily focused on blood-derived immune cells or brain sections, but rarely investigated patient microglia in vitro. Accordingly, we decided to explore the contribution of microglia to IPD in a comparative manner using, both, iPSC-derived cultures and postmortem tissue. Our meta-analysis of published RNAseq datasets indicated an upregulation of IL10 and IL1B in nigral tissue from IPD patients. We observed increased expression levels of these cytokines in microglia compared to neurons using our single-cell midbrain atlas. Moreover, IL10 and IL1B were upregulated in IPD compared to control microglia. Next, to validate these findings in vitro, we generated IPD patient microglia from iPSCs using an established differentiation protocol. IPD microglia were more readily primed as indicated by elevated IL1B and IL10 gene expression and higher mRNA and protein levels of NLRP3 after LPS treatment. In addition, IPD microglia had higher phagocytic capacity under basal conditions-a phenotype that was further exacerbated upon stimulation with LPS, suggesting an aberrant microglial function. Our results demonstrate the significance of microglia as the key player in the neuroinflammation process in IPD. While our study highlights the importance of microglia-mediated inflammatory signaling in IPD, further investigations will be needed to explore particular disease mechanisms in these cells. [less ▲] Detailed reference viewed: 162 (20 UL)![]() Jarazo, Javier ![]() ![]() in Movement Disorders (2021) Detailed reference viewed: 135 (25 UL)![]() ; ; Antony, Paul ![]() in NPJ systems biology and applications (2020), 6(1), 38 Mitochondrial dysfunction is linked to pathogenesis of Parkinson's disease (PD). However, individual mitochondria-based analyses do not show a uniform feature in PD patients. Since mitochondria interact ... [more ▼] Mitochondrial dysfunction is linked to pathogenesis of Parkinson's disease (PD). However, individual mitochondria-based analyses do not show a uniform feature in PD patients. Since mitochondria interact with each other, we hypothesize that PD-related features might exist in topological patterns of mitochondria interaction networks (MINs). Here we show that MINs formed nonclassical scale-free supernetworks in colonic ganglia both from healthy controls and PD patients; however, altered network topological patterns were observed in PD patients. These patterns were highly correlated with PD clinical scores and a machine-learning approach based on the MIN features alone accurately distinguished between patients and controls with an area-under-curve value of 0.989. The MINs of midbrain dopaminergic neurons (mDANs) derived from several genetic PD patients also displayed specific changes. CRISPR/CAS9-based genome correction of alpha-synuclein point mutations reversed the changes in MINs of mDANs. Our organelle-interaction network analysis opens another critical dimension for a deeper characterization of various complex diseases with mitochondrial dysregulation. [less ▲] Detailed reference viewed: 67 (1 UL)![]() Hanss, Zoé ![]() ![]() ![]() in Movement Disorders (2020) Background: VPS35 is part of the retromer complex and is responsible for the trafficking and recycling of proteins implicated in autophagy and lysosomal degradation, but also takes part in the degradation ... [more ▼] Background: VPS35 is part of the retromer complex and is responsible for the trafficking and recycling of proteins implicated in autophagy and lysosomal degradation, but also takes part in the degradation of mitochondrial proteins via mitochondria-derived vesicles. The p.D620N mutation of VPS35 causes an autosomal-dominant form of Parkinson’s disease (PD), clinically representing typical PD. Objective: Most of the studies on p.D620N VPS35 were performed on human tumor cell lines, rodent models overexpressing mutant VPS35, or in patient-derived fibroblasts. Here, based on identified target proteins, we investigated the implication of mutant VPS35 in autophagy, lysosomal degradation, and mitochondrial function in induced pluripotent stem cell-derived neurons from a patient harboring the p.D620N mutation. Methods: We reprogrammed fibroblasts from a PD patient carrying the p.D620N mutation in the VPS35 gene and from two healthy donors in induced pluripotent stem cells. These were subsequently differentiated into neuronal precursor cells to finally generate midbrain dopaminergic neurons. Results: We observed a decreased autophagic flux and lysosomal mass associated with an accumulation of α-synuclein in patient-derived neurons compared to controls. Moreover, patient-derived neurons presented a mitochondrial dysfunction with decreased membrane potential, impaired mitochondrial respiration, and increased production of reactive oxygen species associated with a defect in mitochondrial quality control via mitophagy. Conclusion: We describe for the first time the impact of the p.D620N VPS35 mutation on autophago-lysosome pathway and mitochondrial function in stem cell-derived neurons from an affected p.D620N carrier and define neuronal phenotypes for future pharmacological interventions [less ▲] Detailed reference viewed: 99 (10 UL)![]() ; May, Patrick ![]() ![]() in Molecular Psychiatry (2020), 25(3), 629-639 Common variants of about 20 genes contributing to AD risk have so far been identified through genome-wide association studies (GWAS). However, there is still a large proportion of heritability that might ... [more ▼] Common variants of about 20 genes contributing to AD risk have so far been identified through genome-wide association studies (GWAS). However, there is still a large proportion of heritability that might be explained by rare but functionally important variants. One of the so far identified genes with rare AD causing variants is ADAM10. Using whole-genome sequencing we now identified a single rare nonsynonymous variant (SNV) rs142946965 [p.R215I] in ADAM17 co-segregating with an autosomal-dominant pattern of late-onset AD in one family. Subsequent genotyping and analysis of available whole-exome sequencing data of additional case/control samples from Germany, the UK and the USA identified five variant carriers among AD patients only. The mutation inhibits pro-protein cleavage and the formation of the active enzyme, thus leading to loss-of-function of ADAM17 α-secretase. Further, we identified a strong negative correlation between ADAM17 and APP gene expression in human brain and present in vitro evidence that ADAM17 negatively controls the expression of APP. As a consequence, p.R215I mutation of ADAM17 leads to elevated Aß formation in vitro. Together our data supports a causative association of the identified ADAM17 variant in the pathogenesis of AD. [less ▲] Detailed reference viewed: 361 (31 UL)![]() Krüger, Rejko ![]() ![]() ![]() in Scientific Reports (2020) Mitochondrial dysfunction is a hallmark in idiopathic Parkinson’s disease (IPD). Here, we established screenable phenotypes of mitochondrial morphology and function in primary fibroblasts derived from ... [more ▼] Mitochondrial dysfunction is a hallmark in idiopathic Parkinson’s disease (IPD). Here, we established screenable phenotypes of mitochondrial morphology and function in primary fibroblasts derived from patients with IPD. Upper arm punch skin biopsy was performed in 41 patients with mid-stage IPD and 21 age-matched healthy controls. At the single-cell level, the basal mitochondrial membrane potential (Ψm) was higher in patients with IPD than in controls. Similarly, under carbonyl cyanide 4-(trifluoromethoxy)phenylhydrazone (FCCP) stress, the remaining Ψm was increased in patients with IPD. Analysis of mitochondrial morphometric parameters revealed significantly decreased mitochondrial connectivity in patients with IPD, with 9 of 14 morphometric mitochondrial parameters differing from those in controls. Significant morphometric mitochondrial changes included the node degree, mean volume, skeleton size, perimeter, form factor, node count, erosion body count, endpoints, and mitochondria count (all P-values < 0.05). These functional data reveal that resistance to depolarization was increased by treatment with the protonophore FCCP in patients with IPD, whereas morphometric data revealed decreased mitochondrial connectivity and increased mitochondrial fragmentation. [less ▲] Detailed reference viewed: 173 (10 UL)![]() Barbuti, Peter ![]() ![]() ![]() in Cells (2020), 9(9), The generation of isogenic induced pluripotent stem cell (iPSC) lines using CRISPR-Cas9 technology is a technically challenging, time-consuming process with variable efficiency. Here we use fluorescence ... [more ▼] The generation of isogenic induced pluripotent stem cell (iPSC) lines using CRISPR-Cas9 technology is a technically challenging, time-consuming process with variable efficiency. Here we use fluorescence-activated cell sorting (FACS) to sort biallelic CRISPR-Cas9 edited single-cell iPSC clones into high-throughput 96-well microtiter plates. We used high-content screening (HCS) technology and generated an in-house developed algorithm to select the correctly edited isogenic clones for continued expansion and validation. In our model we have gene-corrected the iPSCs of a Parkinson's disease (PD) patient carrying the autosomal dominantly inherited heterozygous c.88G>C mutation in the SNCA gene, which leads to the pathogenic p.A30P form of the alpha-synuclein protein. Undertaking a PCR restriction-digest mediated clonal selection strategy prior to sequencing, we were able to post-sort validate each isogenic clone using a quadruple screening strategy prior to generating footprint-free isogenic iPSC lines, retaining a normal molecular karyotype, pluripotency and three germ-layer differentiation potential. Directed differentiation into midbrain dopaminergic neurons revealed that SNCA expression is reduced in the gene-corrected clones, which was validated by a reduction at the alpha-synuclein protein level. The generation of single-cell isogenic clones facilitates new insights in the role of alpha-synuclein in PD and furthermore is applicable across patient-derived disease models. [less ▲] Detailed reference viewed: 141 (5 UL)![]() Monzel, Anna Sophia ![]() ![]() in Parkinsonism and Related Disorders (2020) Detailed reference viewed: 131 (21 UL)![]() ; ; Antony, Paul ![]() in Human Molecular Genetics (2020) Detailed reference viewed: 405 (27 UL)![]() Smajic, Semra ![]() ![]() E-print/Working paper (2020) Parkinson’s disease (PD) etiology is associated with genetic and environmental factors that lead to a loss of dopaminergic neurons. However, the functional interpretation of PD-associated risk variants ... [more ▼] Parkinson’s disease (PD) etiology is associated with genetic and environmental factors that lead to a loss of dopaminergic neurons. However, the functional interpretation of PD-associated risk variants and how other midbrain cells contribute to this neurodegenerative process are poorly understood. Here, we profiled >41,000 single-nuclei transcriptomes of postmortem midbrain tissue from 6 idiopathic PD (IPD) patients and 5 matched controls. We show that PD-risk variants are associated with glia- and neuron-specific gene expression patterns. Furthermore, Microglia and astrocytes presented IPD-specific cell proliferation and dysregulation of genes related to unfolded protein response and cytokine signalling. IPD-microglia revealed a specific pro-inflammatory trajectory. Finally, we discovered a neuronal cell cluster exclusively present in IPD midbrains characterized by CADPS2 overexpression and a high proportion of cycling cells. We conclude that elevated CADPS2 expression is specific to dysfunctional dopaminergic neurons, which have lost their dopaminergic identity and unsuccessful attempt to re-enter the cell cycle. [less ▲] Detailed reference viewed: 66 (9 UL)![]() Berenguer, Clara ![]() ![]() in Journal of Clinical Medicine (2019) Background: Although most cases of Parkinson´s disease (PD) are idiopathic with unknown cause, an increasing number of genes and genetic risk factors have been discovered that play a role in PD ... [more ▼] Background: Although most cases of Parkinson´s disease (PD) are idiopathic with unknown cause, an increasing number of genes and genetic risk factors have been discovered that play a role in PD pathogenesis. Many of the PD‐associated proteins are involved in mitochondrial quality control, e.g., PINK1, Parkin, and LRRK2, which were recently identified as regulators of mitochondrial‐endoplasmic reticulum (ER) contact sites (MERCs) linking mitochondrial homeostasis to intracellular calcium handling. In this context, Miro1 is increasingly recognized to play a role in PD pathology. Recently, we identified the first PD patients carrying mutations in RHOT1, the gene coding for Miro1. Here, we describe two novel RHOT1 mutations identified in two PD patients and the characterization of the cellular phenotypes. Methods: Using whole exome sequencing we identified two PD patients carrying heterozygous mutations leading to the amino acid exchanges T351A and T610A in Miro1. We analyzed calcium homeostasis and MERCs in detail by live cell imaging and immunocytochemistry in patient‐derived fibroblasts. Results: We show that fibroblasts expressing mutant T351A or T610A Miro1 display impaired calcium homeostasis and a reduced amount of MERCs. All fibroblast lines from patients with pathogenic variants in Miro1, revealed alterations of the structure of MERCs. Conclusion: Our data suggest that Miro1 is important for the regulation of the structure and function of MERCs. Moreover, our study supports the role of MERCs in the pathogenesis of PD and further establishes variants in RHOT1 as rare genetic risk factors for neurodegeneration. [less ▲] Detailed reference viewed: 166 (13 UL)![]() Garcia Santa Cruz, Beatriz ![]() ![]() ![]() 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: 1135 (44 UL) |
||