Search

Your search keyword '"Ghidoni, A"' showing total 4,273 results
Start Over Author "Ghidoni, A"
4,273 results on '"Ghidoni, A"'

1. WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks

Author

Bacchin, Alberto, Barcellona, Leonardo, Terreran, Matteo, Ghidoni, Stefano, Menegatti, Emanuele, and Kiyokawa, Takuya

Subjects
Computer Science - Robotics, Computer Science - Computer Vision and Pattern Recognition
Abstract

Robotic waste sorting poses significant challenges in both perception and manipulation, given the extreme variability of objects that should be recognized on a cluttered conveyor belt. While deep learning has proven effective in solving complex tasks, the necessity for extensive data collection and labeling limits its applicability in real-world scenarios like waste sorting. To tackle this issue, we introduce a data augmentation method based on a novel GAN architecture called wasteGAN. The proposed method allows to increase the performance of semantic segmentation models, starting from a very limited bunch of labeled examples, such as few as 100. The key innovations of wasteGAN include a novel loss function, a novel activation function, and a larger generator block. Overall, such innovations helps the network to learn from limited number of examples and synthesize data that better mirrors real-world distributions. We then leverage the higher-quality segmentation masks predicted from models trained on the wasteGAN synthetic data to compute semantic-aware grasp poses, enabling a robotic arm to effectively recognizing contaminants and separating waste in a real-world scenario. Through comprehensive evaluation encompassing dataset-based assessments and real-world experiments, our methodology demonstrated promising potential for robotic waste sorting, yielding performance gains of up to 5.8\% in picking contaminants. The project page is available at https://github.com/bach05/wasteGAN.git, Comment: Accepted at 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)

Published
2024

2. SOOD-ImageNet: a Large-Scale Dataset for Semantic Out-Of-Distribution Image Classification and Semantic Segmentation

Author

Bacchin, Alberto, Allegro, Davide, Ghidoni, Stefano, and Menegatti, Emanuele

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Out-of-Distribution (OOD) detection in computer vision is a crucial research area, with related benchmarks playing a vital role in assessing the generalizability of models and their applicability in real-world scenarios. However, existing OOD benchmarks in the literature suffer from two main limitations: (1) they often overlook semantic shift as a potential challenge, and (2) their scale is limited compared to the large datasets used to train modern models. To address these gaps, we introduce SOOD-ImageNet, a novel dataset comprising around 1.6M images across 56 classes, designed for common computer vision tasks such as image classification and semantic segmentation under OOD conditions, with a particular focus on the issue of semantic shift. We ensured the necessary scalability and quality by developing an innovative data engine that leverages the capabilities of modern vision-language models, complemented by accurate human checks. Through extensive training and evaluation of various models on SOOD-ImageNet, we showcase its potential to significantly advance OOD research in computer vision. The project page is available at https://github.com/bach05/SOODImageNet.git., Comment: Accepeted as long paper at "The 3rd Workshop for Out-of-Distribution Generalization in Computer Vision Foundation Models", ECCV 2024

Published
2024

3. Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose Estimation

Author

Bragagnolo, Laura, Terreran, Matteo, Allegro, Davide, and Ghidoni, Stefano

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Robotics
Abstract

Robust 3D human pose estimation is crucial to ensure safe and effective human-robot collaboration. Accurate human perception,however, is particularly challenging in these scenarios due to strong occlusions and limited camera viewpoints. Current 3D human pose estimation approaches are rather vulnerable in such conditions. In this work we present a novel approach for robust 3D human pose estimation in the context of human-robot collaboration. Instead of relying on noisy 2D features triangulation, we perform multi-view fusion on 3D skeletons provided by absolute monocular methods. Accurate 3D pose estimation is then obtained via reprojection error optimization, introducing limbs length symmetry constraints. We evaluate our approach on the public dataset Human3.6M and on a novel version Human3.6M-Occluded, derived adding synthetic occlusions on the camera views with the purpose of testing pose estimation algorithms under severe occlusions. We further validate our method on real human-robot collaboration workcells, in which we strongly surpass current 3D human pose estimation methods. Our approach outperforms state-of-the-art multi-view human pose estimation techniques and demonstrates superior capabilities in handling challenging scenarios with strong occlusions, representing a reliable and effective solution for real human-robot collaboration setups., Comment: ECCV workshops 2024

Published
2024

4. Multi-Camera Hand-Eye Calibration for Human-Robot Collaboration in Industrial Robotic Workcells

Author

Allegro, Davide, Terreran, Matteo, and Ghidoni, Stefano

Subjects
Computer Science - Robotics, Computer Science - Computer Vision and Pattern Recognition
Abstract

In industrial scenarios, effective human-robot collaboration relies on multi-camera systems to robustly monitor human operators despite the occlusions that typically show up in a robotic workcell. In this scenario, precise localization of the person in the robot coordinate system is essential, making the hand-eye calibration of the camera network critical. This process presents significant challenges when high calibration accuracy should be achieved in short time to minimize production downtime, and when dealing with extensive camera networks used for monitoring wide areas, such as industrial robotic workcells. Our paper introduces an innovative and robust multi-camera hand-eye calibration method, designed to optimize each camera's pose relative to both the robot's base and to each other camera. This optimization integrates two types of key constraints: i) a single board-to-end-effector transformation, and ii) the relative camera-to-camera transformations. We demonstrate the superior performance of our method through comprehensive experiments employing the METRIC dataset and real-world data collected on industrial scenarios, showing notable advancements over state-of-the-art techniques even using less than 10 images. Additionally, we release an open-source version of our multi-camera hand-eye calibration algorithm at https://github.com/davidea97/Multi-Camera-Hand-Eye-Calibration.git.

Published
2024

5. Genome-wide analyses reveal a potential role for the MAPT, MOBP, and APOE loci in sporadic frontotemporal dementia.

Author

Manzoni, Claudia, Kia, Demis, Ferrari, Raffaele, Leonenko, Ganna, Costa, Beatrice, Saba, Valentina, Jabbari, Edwin, Tan, Manuela, Albani, Diego, Alvarez, Victoria, Alvarez, Ignacio, Andreassen, Ole, Angiolillo, Antonella, Arighi, Andrea, Baker, Matt, Benussi, Luisa, Bessi, Valentina, Binetti, Giuliano, Blackburn, Daniel, Boada, Merce, Boeve, Bradley, Borrego-Ecija, Sergi, Borroni, Barbara, Bråthen, Geir, Brooks, William, Bruni, Amalia, Caroppo, Paola, Bandres-Ciga, Sara, Clarimon, Jordi, Colao, Rosanna, Cruchaga, Carlos, Danek, Adrian, de Boer, Sterre, de Rojas, Itziar, di Costanzo, Alfonso, Dickson, Dennis, Diehl-Schmid, Janine, Dobson-Stone, Carol, Dols-Icardo, Oriol, Donizetti, Aldo, Dopper, Elise, Durante, Elisabetta, Ferrari, Camilla, Forloni, Gianluigi, Frangipane, Francesca, Fratiglioni, Laura, Kramberger, Milica, Galimberti, Daniela, Gallucci, Maurizio, García-González, Pablo, Ghidoni, Roberta, Giaccone, Giorgio, Graff, Caroline, Graff-Radford, Neill, Grafman, Jordan, Halliday, Glenda, Hernandez, Dena, Hjermind, Lena, Hodges, John, Holloway, Guy, Huey, Edward, Illán-Gala, Ignacio, Josephs, Keith, Knopman, David, Kristiansen, Mark, Kwok, John, Leber, Isabelle, Leonard, Hampton, Libri, Ilenia, Lleo, Alberto, Mackenzie, Ian, Madhan, Gaganjit, Maletta, Raffaele, Marquié, Marta, Maver, Ales, Menendez-Gonzalez, Manuel, Milan, Graziella, Miller, Bruce, Morris, Christopher, Morris, Huw, Nacmias, Benedetta, Newton, Judith, Nielsen, Jørgen, Nilsson, Christer, Novelli, Valeria, Padovani, Alessandro, Pal, Suvankar, Pasquier, Florence, Pastor, Pau, Perneczky, Robert, Peterlin, Borut, Petersen, Ronald, Piguet, Olivier, Pijnenburg, Yolande, Puca, Annibale, Rademakers, Rosa, Rainero, Innocenzo, Reus, Lianne, Richardson, Anna, and Riemenschneider, Matthias

Subjects
Humans, Frontotemporal Dementia, tau Proteins, Genome-Wide Association Study, Apolipoproteins E, Male, Female, Genetic Predisposition to Disease, Aged, Polymorphism, Single Nucleotide, Genetic Loci, Middle Aged, Case-Control Studies, Myelin Proteins
Abstract

Frontotemporal dementia (FTD) is the second most common cause of early-onset dementia after Alzheimer disease (AD). Efforts in the field mainly focus on familial forms of disease (fFTDs), while studies of the genetic etiology of sporadic FTD (sFTD) have been less common. In the current work, we analyzed 4,685 sFTD cases and 15,308 controls looking for common genetic determinants for sFTD. We found a cluster of variants at the MAPT (rs199443; p = 2.5 × 10-12, OR = 1.27) and APOE (rs6857; p = 1.31 × 10-12, OR = 1.27) loci and a candidate locus on chromosome 3 (rs1009966; p = 2.41 × 10-8, OR = 1.16) in the intergenic region between RPSA and MOBP, contributing to increased risk for sFTD through effects on expression and/or splicing in brain cortex of functionally relevant in-cis genes at the MAPT and RPSA-MOBP loci. The association with the MAPT (H1c clade) and RPSA-MOBP loci may suggest common genetic pleiotropy across FTD and progressive supranuclear palsy (PSP) (MAPT and RPSA-MOBP loci) and across FTD, AD, Parkinson disease (PD), and cortico-basal degeneration (CBD) (MAPT locus). Our data also suggest population specificity of the risk signals, with MAPT and APOE loci associations mainly driven by Central/Nordic and Mediterranean Europeans, respectively. This study lays the foundations for future work aimed at further characterizing population-specific features of potential FTD-discriminant APOE haplotype(s) and the functional involvement and contribution of the MAPT H1c haplotype and RPSA-MOBP loci to pathogenesis of sporadic forms of FTD in brain cortex.

Published
2024

6. Show and Grasp: Few-shot Semantic Segmentation for Robot Grasping through Zero-shot Foundation Models

Author

Barcellona, Leonardo, Bacchin, Alberto, Terreran, Matteo, Menegatti, Emanuele, and Ghidoni, Stefano

Subjects
Computer Science - Robotics, Computer Science - Artificial Intelligence
Abstract

The ability of a robot to pick an object, known as robot grasping, is crucial for several applications, such as assembly or sorting. In such tasks, selecting the right target to pick is as essential as inferring a correct configuration of the gripper. A common solution to this problem relies on semantic segmentation models, which often show poor generalization to unseen objects and require considerable time and massive data to be trained. To reduce the need for large datasets, some grasping pipelines exploit few-shot semantic segmentation models, which are capable of recognizing new classes given a few examples. However, this often comes at the cost of limited performance and fine-tuning is required to be effective in robot grasping scenarios. In this work, we propose to overcome all these limitations by combining the impressive generalization capability reached by foundation models with a high-performing few-shot classifier, working as a score function to select the segmentation that is closer to the support set. The proposed model is designed to be embedded in a grasp synthesis pipeline. The extensive experiments using one or five examples show that our novel approach overcomes existing performance limitations, improving the state of the art both in few-shot semantic segmentation on the Graspnet-1B (+10.5% mIoU) and Ocid-grasp (+1.6% AP) datasets, and real-world few-shot grasp synthesis (+21.7% grasp accuracy). The project page is available at: https://leobarcellona.github.io/showandgrasp.github.io/

Published
2024

7. Mechanical power ratio threshold for ventilator-induced lung injury

Author

D’Albo, Rosanna, Pozzi, Tommaso, Nicolardi, Rosmery V., Galizia, Mauro, Catozzi, Giulia, Ghidoni, Valentina, Donati, Beatrice, Romitti, Federica, Herrmann, Peter, Busana, Mattia, Gattarello, Simone, Collino, Francesca, Sonzogni, Aurelio, Camporota, Luigi, Marini, John J., Moerer, Onnen, Meissner, Konrad, and Gattinoni, Luciano

Published
2024
Full Text
View/download PDF

8. A systematic review of progranulin concentrations in biofluids in over 7,000 people—assessing the pathogenicity of GRN mutations and other influencing factors

Author

Swift, Imogen J., Rademakers, Rosa, Finch, NiCole, Baker, Matt, Ghidoni, Roberta, Benussi, Luisa, Binetti, Giuliano, Rossi, Giacomina, Synofzik, Matthis, Wilke, Carlo, Mengel, David, Graff, Caroline, Takada, Leonel T., Sánchez-Valle, Raquel, Antonell, Anna, Galimberti, Daniela, Fenoglio, Chiara, Serpente, Maria, Arcaro, Marina, Schreiber, Stefanie, Vielhaber, Stefan, Arndt, Philipp, Santana, Isabel, Almeida, Maria Rosario, Moreno, Fermín, Barandiaran, Myriam, Gabilondo, Alazne, Stubert, Johannes, Gómez-Tortosa, Estrella, Agüero, Pablo, Sainz, M. José, Gohda, Tomohito, Murakoshi, Maki, Kamei, Nozomu, Kittel-Schneider, Sarah, Reif, Andreas, Weigl, Johannes, Jian, Jinlong, Liu, Chuanju, Serrero, Ginette, Greither, Thomas, Theil, Gerit, Lohmann, Ebba, Gazzina, Stefano, Bagnoli, Silvia, Coppola, Giovanni, Bruni, Amalia, Quante, Mirja, Kiess, Wieland, Hiemisch, Andreas, Jurkutat, Anne, Block, Matthew S., Carlson, Aaron M., Bråthen, Geir, Sando, Sigrid Botne, Grøntvedt, Gøril Rolfseng, Lauridsen, Camilla, Heslegrave, Amanda, Heller, Carolin, Abel, Emily, Gómez-Núñez, Alba, Puey, Roger, Arighi, Andrea, Rotondo, Enmanuela, Jiskoot, Lize C., Meeter, Lieke H. H., Durães, João, Lima, Marisa, Tábuas-Pereira, Miguel, Lemos, João, Boeve, Bradley, Petersen, Ronald C., Dickson, Dennis W., Graff-Radford, Neill R., LeBer, Isabelle, Sellami, Leila, Lamari, Foudil, Clot, Fabienne, Borroni, Barbara, Cantoni, Valentina, Rivolta, Jasmine, Lleó, Alberto, Fortea, Juan, Alcolea, Daniel, Illán-Gala, Ignacio, Andres-Cerezo, Lucie, Van Damme, Philip, Clarimon, Jordi, Steinacker, Petra, Feneberg, Emily, Otto, Markus, van der Ende, Emma L., van Swieten, John C., Seelaar, Harro, Zetterberg, Henrik, Sogorb-Esteve, Aitana, and Rohrer, Jonathan D.

Published
2024
Full Text
View/download PDF

9. Mechanical power ratio threshold for ventilator-induced lung injury

Author

Rosanna D’Albo, Tommaso Pozzi, Rosmery V. Nicolardi, Mauro Galizia, Giulia Catozzi, Valentina Ghidoni, Beatrice Donati, Federica Romitti, Peter Herrmann, Mattia Busana, Simone Gattarello, Francesca Collino, Aurelio Sonzogni, Luigi Camporota, John J. Marini, Onnen Moerer, Konrad Meissner, and Luciano Gattinoni

Subjects
Medical emergencies. Critical care. Intensive care. First aid, RC86-88.9
Abstract

Abstract Rationale Mechanical power (MP) is a summary variable incorporating all causes of ventilator-induced-lung-injury (VILI). We expressed MP as the ratio between observed and normal expected values (MPratio). Objective To define a threshold value of MPratio leading to the development of VILI. Methods In a population of 82 healthy pigs, a threshold of MPratio for VILI, as assessed by histological variables and confirmed by using unsupervised cluster analysis was 4.5. The population was divided into two groups with MPratio above or below the threshold. Measurements and main results We measured physiological variables every six hours. At the end of the experiment, we measured lung weight and wet-to-dry ratio to quantify edema. Histological samples were analyzed for alveolar ruptures, inflammation, alveolar edema, atelectasis. An MPratio threshold of 4.5 was associated with worse injury, lung weight, wet-to-dry ratio and fluid balance (all p 4.5 MPratio in healthy lungs subjected to 48 h of mechanical ventilation appears to be a threshold for the development of ventilator-induced lung injury, as indicated by the convergence of histological, physiological, and anatomical alterations. In humans and in lungs that are already injured, this threshold is likely to be different.

Published
2024
Full Text
View/download PDF

10. A systematic review of progranulin concentrations in biofluids in over 7,000 people—assessing the pathogenicity of GRN mutations and other influencing factors

Author

Imogen J. Swift, Rosa Rademakers, NiCole Finch, Matt Baker, Roberta Ghidoni, Luisa Benussi, Giuliano Binetti, Giacomina Rossi, Matthis Synofzik, Carlo Wilke, David Mengel, Caroline Graff, Leonel T. Takada, Raquel Sánchez-Valle, Anna Antonell, Daniela Galimberti, Chiara Fenoglio, Maria Serpente, Marina Arcaro, Stefanie Schreiber, Stefan Vielhaber, Philipp Arndt, Isabel Santana, Maria Rosario Almeida, Fermín Moreno, Myriam Barandiaran, Alazne Gabilondo, Johannes Stubert, Estrella Gómez-Tortosa, Pablo Agüero, M. José Sainz, Tomohito Gohda, Maki Murakoshi, Nozomu Kamei, Sarah Kittel-Schneider, Andreas Reif, Johannes Weigl, Jinlong Jian, Chuanju Liu, Ginette Serrero, Thomas Greither, Gerit Theil, Ebba Lohmann, Stefano Gazzina, Silvia Bagnoli, Giovanni Coppola, Amalia Bruni, Mirja Quante, Wieland Kiess, Andreas Hiemisch, Anne Jurkutat, Matthew S. Block, Aaron M. Carlson, Geir Bråthen, Sigrid Botne Sando, Gøril Rolfseng Grøntvedt, Camilla Lauridsen, Amanda Heslegrave, Carolin Heller, Emily Abel, Alba Gómez-Núñez, Roger Puey, Andrea Arighi, Enmanuela Rotondo, Lize C. Jiskoot, Lieke H. H. Meeter, João Durães, Marisa Lima, Miguel Tábuas-Pereira, João Lemos, Bradley Boeve, Ronald C. Petersen, Dennis W. Dickson, Neill R. Graff-Radford, Isabelle LeBer, Leila Sellami, Foudil Lamari, Fabienne Clot, Barbara Borroni, Valentina Cantoni, Jasmine Rivolta, Alberto Lleó, Juan Fortea, Daniel Alcolea, Ignacio Illán-Gala, Lucie Andres-Cerezo, Philip Van Damme, Jordi Clarimon, Petra Steinacker, Emily Feneberg, Markus Otto, Emma L. van der Ende, John C. van Swieten, Harro Seelaar, Henrik Zetterberg, Aitana Sogorb-Esteve, and Jonathan D. Rohrer

Subjects
Frontotemporal dementia, Progranulin, Neurosciences. Biological psychiatry. Neuropsychiatry, RC321-571, Neurology. Diseases of the nervous system, RC346-429
Abstract

Abstract Background Pathogenic heterozygous mutations in the progranulin gene (GRN) are a key cause of frontotemporal dementia (FTD), leading to significantly reduced biofluid concentrations of the progranulin protein (PGRN). This has led to a number of ongoing therapeutic trials aiming to treat this form of FTD by increasing PGRN levels in mutation carriers. However, we currently lack a complete understanding of factors that affect PGRN levels and potential variation in measurement methods. Here, we aimed to address this gap in knowledge by systematically reviewing published literature on biofluid PGRN concentrations. Methods Published data including biofluid PGRN concentration, age, sex, diagnosis and GRN mutation were collected for 7071 individuals from 75 publications. The majority of analyses (72%) had focused on plasma PGRN concentrations, with many of these (56%) measured with a single assay type (Adipogen) and so the influence of mutation type, age at onset, sex, and diagnosis were investigated in this subset of the data. Results We established a plasma PGRN concentration cut-off between pathogenic mutation carriers and non-carriers of 74.8 ng/mL using the Adipogen assay based on 3301 individuals, with a CSF concentration cut-off of 3.43 ng/mL. Plasma PGRN concentration varied by GRN mutation type as well as by clinical diagnosis in those without a GRN mutation. Plasma PGRN concentration was significantly higher in women than men in GRN mutation carriers (p = 0.007) with a trend in non-carriers (p = 0.062), and there was a significant but weak positive correlation with age in both GRN mutation carriers and non-carriers. No significant association was seen with weight or with TMEM106B rs1990622 genotype. However, higher plasma PGRN levels were seen in those with the GRN rs5848 CC genotype in both GRN mutation carriers and non-carriers. Conclusions These results further support the usefulness of PGRN concentration for the identification of the large majority of pathogenic mutations in the GRN gene. Furthermore, these results highlight the importance of considering additional factors, such as mutation type, sex and age when interpreting PGRN concentrations. This will be particularly important as we enter the era of trials for progranulin-associated FTD.

Published
2024
Full Text
View/download PDF

12. SlideTiler: A dataset creator software for boosting deep learning on histological whole slide images

Author

Leonardo Barcellona, Lorenzo Nicolè, Rocco Cappellesso, Angelo Paolo Dei Tos, and Stefano Ghidoni

Subjects
Digital pathology, Deep learning, Image preprocessing, Tissue classifier, TCGA, Computer applications to medicine. Medical informatics, R858-859.7, Pathology, RB1-214
Abstract

The introduction of deep learning caused a significant breakthrough in digital pathology. Thanks to its capability of mining hidden data patterns in digitised histological slides to resolve diagnostic tasks and extract prognostic and predictive information. However, the high performance achieved in classification tasks depends on the availability of large datasets, whose collection and preprocessing are still time-consuming processes. Therefore, strategies to make these steps more efficient are worth investigation. This work introduces SlideTiler, an open-source software with a user-friendly graphical interface. SlideTiler can manage several image preprocessing phases through an intuitive workflow that does not require specific coding skills. The software was designed to provide direct access to virtual slides, allowing custom tiling of specific regions of interest drawn by the user, tile labelling, quality assessment, and direct export to dataset directories. To illustrate the functions and the scalability of SlideTiler, a deep learning-based classifier was implemented to classify 4 different tumour histotypes available in the TCGA repository. The results demonstrate the effectiveness of SlideTiler in facilitating data preprocessing and promoting accessibility to digitised pathology images for research purposes. Considering the increasing interest in deep learning applications of digital pathology, SlideTiler has a positive impact on this field. Moreover, SlideTiler has been conceived as a dynamic tool in constant evolution, and more updated and efficient versions will be released in the future.

Published
2024
Full Text
View/download PDF

14. Correction: Mechanical power ratio threshold for ventilator-induced lung injury

Author

Rosanna D’Albo, Tommaso Pozzi, Rosmery V. Nicolardi, Mauro Galizia, Giulia Catozzi, Valentina Ghidoni, Beatrice Donati, Federica Romitti, Peter Herrmann, Mattia Busana, Simone Gattarello, Francesca Collino, Aurelio Sonzogni, Luigi Camporota, John J. Marini, Onnen Moerer, Konrad Meissner, and Luciano Gattinoni

Subjects
Medical emergencies. Critical care. Intensive care. First aid, RC86-88.9
Published
2024
Full Text
View/download PDF

20. Author Correction: Common variants in Alzheimer’s disease and risk stratification by polygenic risk scores

Author

de Rojas, Itziar, Moreno-Grau, Sonia, Tesi, Niccolo, Grenier-Boley, Benjamin, Andrade, Victor, Jansen, Iris E., Pedersen, Nancy L., Stringa, Najada, Zettergren, Anna, Hernández, Isabel, Montrreal, Laura, Antúnez, Carmen, Antonell, Anna, Tankard, Rick M., Bis, Joshua C., Sims, Rebecca, Bellenguez, Céline, Quintela, Inés, González-Perez, Antonio, Calero, Miguel, Franco-Macías, Emilio, Macías, Juan, Blesa, Rafael, Cervera-Carles, Laura, Menéndez-González, Manuel, Frank-García, Ana, Royo, Jose Luís, Moreno, Fermin, Huerto Vilas, Raquel, Baquero, Miquel, Diez-Fairen, Mónica, Lage, Carmen, García-Madrona, Sebastián, García-González, Pablo, Alarcón-Martín, Emilio, Valero, Sergi, Sotolongo-Grau, Oscar, Ullgren, Abbe, Naj, Adam C., Lemstra, Afina W., Benaque, Alba, Pérez-Cordón, Alba, Benussi, Alberto, Rábano, Alberto, Padovani, Alessandro, Squassina, Alessio, de Mendonça, Alexandre, Arias Pastor, Alfonso, Kok, Almar A. L., Meggy, Alun, Pastor, Ana Belén, Espinosa, Ana, Corma-Gómez, Anaïs, Martín Montes, Angel, Sanabria, Ángela, DeStefano, Anita L., Schneider, Anja, Haapasalo, Annakaisa, Kinhult Ståhlbom, Anne, Tybjærg-Hansen, Anne, Hartmann, Annette M., Spottke, Annika, Corbatón-Anchuelo, Arturo, Rongve, Arvid, Borroni, Barbara, Arosio, Beatrice, Nacmias, Benedetta, Nordestgaard, Børge G., Kunkle, Brian W., Charbonnier, Camille, Abdelnour, Carla, Masullo, Carlo, Martínez Rodríguez, Carmen, Muñoz-Fernandez, Carmen, Dufouil, Carole, Graff, Caroline, Ferreira, Catarina B., Chillotti, Caterina, Reynolds, Chandra A., Fenoglio, Chiara, Van Broeckhoven, Christine, Clark, Christopher, Pisanu, Claudia, Satizabal, Claudia L., Holmes, Clive, Buiza-Rueda, Dolores, Aarsland, Dag, Rujescu, Dan, Alcolea, Daniel, Galimberti, Daniela, Wallon, David, Seripa, Davide, Grünblatt, Edna, Dardiotis, Efthimios, Düzel, Emrah, Scarpini, Elio, Conti, Elisa, Rubino, Elisa, Gelpi, Ellen, Rodriguez-Rodriguez, Eloy, Duron, Emmanuelle, Boerwinkle, Eric, Ferri, Evelyn, Tagliavini, Fabrizio, Küçükali, Fahri, Pasquier, Florence, Sanchez-Garcia, Florentino, Mangialasche, Francesca, Jessen, Frank, Nicolas, Gaël, Selbæk, Geir, Ortega, Gemma, Chêne, Geneviève, Hadjigeorgiou, Georgios, Rossi, Giacomina, Spalletta, Gianfranco, Giaccone, Giorgio, Grande, Giulia, Binetti, Giuliano, Papenberg, Goran, Hampel, Harald, Bailly, Henri, Zetterberg, Henrik, Soininen, Hilkka, Karlsson, Ida K., Alvarez, Ignacio, Appollonio, Ildebrando, Giegling, Ina, Skoog, Ingmar, Saltvedt, Ingvild, Rainero, Innocenzo, Rosas Allende, Irene, Hort, Jakub, Diehl-Schmid, Janine, Van Dongen, Jasper, Vidal, Jean-Sebastien, Lehtisalo, Jenni, Wiltfang, Jens, Thomassen, Jesper Qvist, Kornhuber, Johannes, Haines, Jonathan L., Vogelgsang, Jonathan, Pineda, Juan A., Fortea, Juan, Popp, Julius, Deckert, Jürgen, Buerger, Katharina, Morgan, Kevin, Fließbach, Klaus, Sleegers, Kristel, Molina-Porcel, Laura, Kilander, Lena, Weinhold, Leonie, Farrer, Lindsay A., Wang, Li-San, Kleineidam, Luca, Farotti, Lucia, Parnetti, Lucilla, Tremolizzo, Lucio, Hausner, Lucrezia, Benussi, Luisa, Froelich, Lutz, Ikram, M. Arfan, Deniz-Naranjo, M. Candida, Tsolaki, Magda, Rosende-Roca, Maitée, Löwenmark, Malin, Hulsman, Marc, Spallazzi, Marco, Pericak-Vance, Margaret A., Esiri, Margaret, Bernal Sánchez-Arjona, María, Dalmasso, Maria Carolina, Martínez-Larrad, María Teresa, Arcaro, Marina, Nöthen, Markus M., Fernández-Fuertes, Marta, Dichgans, Martin, Ingelsson, Martin, Herrmann, Martin J., Scherer, Martin, Vyhnalek, Martin, Kosmidis, Mary H., Yannakoulia, Mary, Schmid, Matthias, Ewers, Michael, Heneka, Michael T., Wagner, Michael, Scamosci, Michela, Kivipelto, Miia, Hiltunen, Mikko, Zulaica, Miren, Alegret, Montserrat, Fornage, Myriam, Roberto, Natalia, van Schoor, Natasja M., Seidu, Nazib M., Banaj, Nerisa, Armstrong, Nicola J., Scarmeas, Nikolaos, Scherbaum, Norbert, Goldhardt, Oliver, Hanon, Oliver, Peters, Oliver, Skrobot, Olivia Anna, Quenez, Olivier, Lerch, Ondrej, Bossù, Paola, Caffarra, Paolo, Dionigi Rossi, Paolo, Sakka, Paraskevi, Mecocci, Patrizia, Hoffmann, Per, Holmans, Peter A., Fischer, Peter, Riederer, Peter, Yang, Qiong, Marshall, Rachel, Kalaria, Rajesh N., Mayeux, Richard, Vandenberghe, Rik, Cecchetti, Roberta, Ghidoni, Roberta, Frikke-Schmidt, Ruth, Sorbi, Sandro, Hägg, Sara, Engelborghs, Sebastiaan, Helisalmi, Seppo, Botne Sando, Sigrid, Kern, Silke, Archetti, Silvana, Boschi, Silvia, Fostinelli, Silvia, Gil, Silvia, Mendoza, Silvia, Mead, Simon, Ciccone, Simona, Djurovic, Srdjan, Heilmann-Heimbach, Stefanie, Riedel-Heller, Steffi, Kuulasmaa, Teemu, del Ser, Teodoro, Lebouvier, Thibaud, Polak, Thomas, Ngandu, Tiia, Grimmer, Timo, Bessi, Valentina, Escott-Price, Valentina, Giedraitis, Vilmantas, Deramecourt, Vincent, Maier, Wolfgang, Jian, Xueqiu, Pijnenburg, Yolande A. L., Kehoe, Patrick Gavin, Garcia-Ribas, Guillermo, Sánchez-Juan, Pascual, Pastor, Pau, Pérez-Tur, Jordi, Piñol-Ripoll, Gerard, Lopez de Munain, Adolfo, García-Alberca, Jose María, Bullido, María J., Álvarez, Victoria, Lleó, Alberto, Real, Luis M., Mir, Pablo, Medina, Miguel, Scheltens, Philip, Holstege, Henne, Marquié, Marta, Sáez, María Eugenia, Carracedo, Ángel, Amouyel, Philippe, Schellenberg, Gerard D., Williams, Julie, Seshadri, Sudha, van Duijn, Cornelia M., Mather, Karen A., Sánchez-Valle, Raquel, Serrano-Ríos, Manuel, Orellana, Adelina, Tárraga, Lluís, Blennow, Kaj, Huisman, Martijn, Andreassen, Ole A., Posthuma, Danielle, Clarimón, Jordi, Boada, Mercè, van der Flier, Wiesje M., Ramirez, Alfredo, Lambert, Jean-Charles, van der Lee, Sven J., and Ruiz, Agustín

Published
2023
Full Text
View/download PDF

21. Deep Features for training Support Vector Machine

Author

Nanni, Loris, Ghidoni, Stefano, and Brahnam, Sheryl

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Features play a crucial role in computer vision. Initially designed to detect salient elements by means of handcrafted algorithms, features are now often learned by different layers in Convolutional Neural Networks (CNNs). This paper develops a generic computer vision system based on features extracted from trained CNNs. Multiple learned features are combined into a single structure to work on different image classification tasks. The proposed system was experimentally derived by testing several approaches for extracting features from the inner layers of CNNs and using them as inputs to SVMs that are then combined by sum rule. Dimensionality reduction techniques are used to reduce the high dimensionality of inner layers. The resulting vision system is shown to significantly boost the performance of standard CNNs across a large and diverse collection of image data sets. An ensemble of different topologies using the same approach obtains state-of-the-art results on a virus data set.

Published
2021
Full Text
View/download PDF

22. Serum Beta-Secretase 1 Activity Is a Potential Marker for the Differential Diagnosis between Alzheimer’s Disease and Frontotemporal Dementia: A Pilot Study

Author

Claudia Saraceno, Carlo Cervellati, Alessandro Trentini, Daniela Crescenti, Antonio Longobardi, Andrea Geviti, Natale Salvatore Bonfiglio, Sonia Bellini, Roland Nicsanu, Silvia Fostinelli, Gianmarco Mola, Raffaella Riccetti, Davide Vito Moretti, Orazio Zanetti, Giuliano Binetti, Giovanni Zuliani, and Roberta Ghidoni

Subjects
BACE1, Alzheimer’s disease, frontotemporal dementia, GFAP, NfL, serum, Biology (General), QH301-705.5, Chemistry, QD1-999
Abstract

Alzheimer’s disease (AD) and frontotemporal dementia (FTD) are the two major neurodegenerative diseases causing dementia. Due to similar clinical phenotypes, differential diagnosis is challenging without specific biomarkers. Beta-site Amyloid Precursor Protein cleaving enzyme 1 (BACE1) is a β-secretase pivotal in AD pathogenesis. In AD and mild cognitive impairment subjects, BACE1 activity is increased in brain/cerebrospinal fluid, and plasma levels appear to reflect those in the brain. In this study, we aim to evaluate serum BACE1 activity in FTD, since, to date, there is no evidence about its role. The serum of 30 FTD patients and 30 controls was analyzed to evaluate (i) BACE1 activity, using a fluorescent assay, and (ii) Glial Fibrillary Acid Protein (GFAP) and Neurofilament Light chain (NfL) levels, using a Simoa kit. As expected, a significant increase in GFAP and NfL levels was observed in FTD patients compared to controls. Serum BACE1 activity was not altered in FTD patients. A significant increase in serum BACE1 activity was shown in AD vs. FTD and controls. Our results support the hypothesis that serum BACE1 activity is a potential biomarker for the differential diagnosis between AD and FTD.

Published
2024
Full Text
View/download PDF

23. Unveiling New Genetic Variants Associated with Age at Onset in Alzheimer’s Disease and Frontotemporal Lobar Degeneration Due to C9orf72 Repeat Expansions

Author

Antonio Longobardi, Sonia Bellini, Roland Nicsanu, Andrea Pilotto, Andrea Geviti, Alessandro Facconi, Chiara Tolassi, Ilenia Libri, Claudia Saraceno, Silvia Fostinelli, Barbara Borroni, Alessandro Padovani, Giuliano Binetti, and Roberta Ghidoni

Subjects
Alzheimer’s disease, Frontotemporal lobar degeneration, GRN, C9orf72, age at onset, transferrin, Biology (General), QH301-705.5, Chemistry, QD1-999
Abstract

Alzheimer’s disease (AD) and Frontotemporal lobar degeneration (FTLD) represent the most common forms of neurodegenerative dementias with a highly phenotypic variability. Herein, we investigated the role of genetic variants related to the immune system and inflammation as genetic modulators in AD and related dementias. In patients with sporadic AD/FTLD (n = 300) and GRN/C9orf72 mutation carriers (n = 80), we performed a targeted sequencing of 50 genes belonging to the immune system and inflammation, selected based on their high expression in brain regions and low tolerance to genetic variation. The linear regression analyses revealed two genetic variants: (i) the rs1049296 in the transferrin (TF) gene, shown to be significantly associated with age at onset in the sporadic AD group, anticipating the disease onset of 4 years for each SNP allele with respect to the wild-type allele, and (ii) the rs7550295 in the calsyntenin-1 (CLSTN1) gene, which was significantly associated with age at onset in the C9orf72 group, delaying the disease onset of 17 years in patients carrying the SNP allele. In conclusion, our data support the role of genetic variants in iron metabolism (TF) and in the modulation of the calcium signalling/axonal anterograde transport of vesicles (CLSTN1) as genetic modulators in AD and FTLD due to C9orf72 expansions.

Published
2024
Full Text
View/download PDF

26. Mutational Landscape of Alzheimer’s Disease and Frontotemporal Dementia: Regional Variances in Northern, Central, and Southern Italy

Author

Claudia Saraceno, Lorenzo Pagano, Valentina Laganà, Andrea Geviti, Silvia Bagnoli, Assunta Ingannato, Salvatore Mazzeo, Antonio Longobardi, Silvia Fostinelli, Sonia Bellini, Alberto Montesanto, Giuliano Binetti, Raffaele Maletta, Benedetta Nacmias, and Roberta Ghidoni

Subjects
Alzheimer’s Disease, Frontotemporal Dementia, gene, mutation, APP, PSEN1, Biology (General), QH301-705.5, Chemistry, QD1-999
Abstract

Alzheimer’s Disease (AD) and Frontotemporal Dementia (FTD) are the two major neurodegenerative diseases with distinct clinical and neuropathological profiles. The aim of this report is to conduct a population-based investigation in well-characterized APP, PSEN1, PSEN2, MAPT, GRN, and C9orf72 mutation carriers/pedigrees from the north, the center, and the south of Italy. We retrospectively analyzed the data of 467 Italian individuals. We identified 21 different GRN mutations, 20 PSEN1, 11 MAPT, 9 PSEN2, and 4 APP. Moreover, we observed geographical variability in mutation frequencies by looking at each cohort of participants, and we observed a significant difference in age at onset among the genetic groups. Our study provides evidence that age at onset is influenced by the genetic group. Further work in identifying both genetic and environmental factors that modify the phenotypes in all groups is needed. Our study reveals Italian regional differences among the most relevant AD/FTD causative genes and emphasizes how the collaborative studies in rare diseases can provide new insights to expand knowledge on genetic/epigenetic modulators of age at onset.

Published
2024
Full Text
View/download PDF

27. Comparisons among different stochastic selection of activation layers for convolutional neural networks for healthcare

Author

Nanni, Loris, Lumini, Alessandra, Ghidoni, Stefano, and Maguolo, Gianluca

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

Classification of biological images is an important task with crucial application in many fields, such as cell phenotypes recognition, detection of cell organelles and histopathological classification, and it might help in early medical diagnosis, allowing automatic disease classification without the need of a human expert. In this paper we classify biomedical images using ensembles of neural networks. We create this ensemble using a ResNet50 architecture and modifying its activation layers by substituting ReLUs with other functions. We select our activations among the following ones: ReLU, leaky ReLU, Parametric ReLU, ELU, Adaptive Piecewice Linear Unit, S-Shaped ReLU, Swish , Mish, Mexican Linear Unit, Gaussian Linear Unit, Parametric Deformable Linear Unit, Soft Root Sign (SRS) and others. As a baseline, we used an ensemble of neural networks that only use ReLU activations. We tested our networks on several small and medium sized biomedical image datasets. Our results prove that our best ensemble obtains a better performance than the ones of the naive approaches. In order to encourage the reproducibility of this work, the MATLAB code of all the experiments will be shared at https://github.com/LorisNanni.

Published
2020

32. Performance Evaluation of Depth Completion Neural Networks for Various RGB-D Camera Technologies in Indoor Scenarios

Author

Castellano, Rino, Terreran, Matteo, Ghidoni, Stefano, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Basili, Roberto, editor, Lembo, Domenico, editor, Limongelli, Carla, editor, and Orlandini, Andrea, editor

Published
2023
Full Text
View/download PDF

33. Assessment of a Wall Distance Free Transition Model Based on the Laminar Kinetic Energy in a Discontinuous Galerkin Solver

Author

Colombo, Alessandro, Ghidoni, Antonio, Noventa, Gianmaria, Barth, Timothy J., Series Editor, Griebel, Michael, Series Editor, Keyes, David E., Series Editor, Nieminen, Risto M., Series Editor, Roose, Dirk, Series Editor, Schlick, Tamar, Series Editor, Melenk, Jens M., editor, Perugia, Ilaria, editor, Schöberl, Joachim, editor, and Schwab, Christoph, editor

Published
2023
Full Text
View/download PDF

34. Clustering-Based Refinement for 3D Human Body Parts Segmentation

Author

Barcellona, Leonardo, Terreran, Matteo, Evangelista, Daniele, Ghidoni, Stefano, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Petrovic, Ivan, editor, Menegatti, Emanuele, editor, and Marković, Ivan, editor

Published
2023
Full Text
View/download PDF

35. Skeleton-Based Action and Gesture Recognition for Human-Robot Collaboration

Author

Terreran, Matteo, Lazzaretto, Margherita, Ghidoni, Stefano, Kacprzyk, Janusz, Series Editor, Gomide, Fernando, Advisory Editor, Kaynak, Okyay, Advisory Editor, Liu, Derong, Advisory Editor, Pedrycz, Witold, Advisory Editor, Polycarpou, Marios M., Advisory Editor, Rudas, Imre J., Advisory Editor, Wang, Jun, Advisory Editor, Petrovic, Ivan, editor, Menegatti, Emanuele, editor, and Marković, Ivan, editor

Published
2023
Full Text
View/download PDF

37. Risk and protective factors associated with mental health status in an Italian sample of students during the fourth wave of COVID-19 pandemic

Author

Mariangela Lanfredi, Jessica Dagani, Andrea Geviti, Federica Di Cosimo, Maria Bussolati, Luciana Rillosi, Donatella Albini, Marina Pizzi, Roberta Ghidoni, Elisa Fazzi, Antonio Vita, and Roberta Rossi

Subjects
COVID-19, Mental health, Adolescents, Young adults, Psychological distress, Pediatrics, RJ1-570, Psychiatry, RC435-571
Abstract

Abstract Background It is well known that the COVID-19 pandemic has caused a global health crisis, especially for young people. However, most studies were conducted during the first waves of the pandemic. Few Italian studies specifically attempted to broadly assess young people’s mental health status during the fourth wave of the pandemic. Methods This study aimed at evaluating the mental health status among a group of Italian adolescents and young adults during the fourth wave of the COVID-19 pandemic. 11,839 high school students and 15,000 university students (age range 14–25) were asked to complete a multidimensional online survey, of which 7,146 (26,6%) agreed to participate. The survey also included standardized measures for depression, anxiety, anger, somatic symptoms, resilience, loneliness and post-traumatic growth. Two separate clusters were identified through cluster analysis. Random forest, classification tree and logistic regressions analyses were applied to identify factors associated to a good or a poor level of mental health and, thus, to define students’ mental health profiles. Results Overall, the students in our sample showed high levels of psychopathology. The clustering methods performed identified two separate clusters reflecting groups of students with different psychological features, that we further defined as "poor mental health" and "good mental health". The random forest and the logistic regressions found that the most discriminating variables among those two groups were: UCLA Loneliness Scale score, self-harm behaviors, Connor-Davidson Resilience Scale-10 score, satisfaction with family relationships, Fear of COVID-19 Scale score, gender and binge eating behaviors. The classification tree analysis identified students’ profiles, showing that, globally, poor mental health was defined by higher scores of loneliness and self-harm, followed by being of female gender, presenting binge eating behaviors and, finally, having unsatisfying family relationships. Conclusions The results of this study confirmed the major psychological distress caused by the COVID-19 pandemic in a large sample of Italian students, and provided further insights regarding those factors associated with a good or poor mental health status. Our findings suggest the importance of implementing programs targeting aspects that have been found to be associated to a good mental health.

Published
2023
Full Text
View/download PDF

38. Incidence of young‐onset dementia in Italy: The Brescia register study

Author

Barbara Borroni, Ilenia Libri, Matteo Rota, Giuliano Binetti, Luisa Benussi, Roberta Ghidoni, Maria Sofia Cotelli, Silvia Fostinelli, Fabio Guerini, Stefano Boffelli, Eugenio Magni, Marta Pengo, Michele Gennuso, Marta Bianchi, Beatrice Cossu, Vincenzo Palomba, Andrea Crucitti, Angelo Bianchetti, Giancarlo Logroscino, and Alessandro Padovani

Subjects
Alzheimer's disease, frontotemporal dementia, incidence, population‐based study, young‐onset dementia, Neurology. Diseases of the nervous system, RC346-429, Geriatrics, RC952-954.6
Abstract

Abstract INTRODUCTION The goal of the present work was to assess the incidence of dementia with onset before the age of 65 years (i.e., young‐onset dementia [YOD]) and define the frequencies of young‐onset Alzheimer's disease (AD), frontotemporal lobar degeneration (FTLD), and dementia with Lewy bodies (DLB) in the general population. METHODS The study was conducted from January 1, 2019 to December 31, 2019 in Brescia province (population: 1,268,455). During the study period, all new YOD cases (incident YOD) were counted, and all patients’ records reviewed. The incidence was standardized to the Italian general population in 2019. RESULTS A total of 29 YOD patients were diagnosed. The age‐sex standardized incidence rate was 4.58 (95% confidence interval, 3.07–6.58) per 100,000 person‐years. No difference in incidence rate between YOD due to AD or FTLD (P = 0.83) and between sexes (P = 0.81) was observed. YOD incidence increased with age, reaching its peak after 60 years. DISCUSSION Presenting neurodegenerative YOD phenotypes encompasses both AD and FTLD. Improved knowledge on YOD epidemiology is essential to adequately plan and organize health services.

Published
2024
Full Text
View/download PDF

39. Distribution of the C9orf72 hexanucleotide repeat expansion in healthy subjects: a multicenter study promoted by the Italian IRCCS network of neuroscience and neurorehabilitation

Author

Emiliano Giardina, Paola Mandich, Roberta Ghidoni, Nicola Ticozzi, Giacomina Rossi, Chiara Fenoglio, Francesco Danilo Tiziano, Federica Esposito, Sabina Capellari, Benedetta Nacmias, Rossana Mineri, Rosa Campopiano, Luana Di Pilla, Federica Sammarone, Stefania Zampatti, Cristina Peconi, Flavio De Angelis, Ilaria Palmieri, Caterina Galandra, Eleonora Nicodemo, Paola Origone, Fabio Gotta, Clarissa Ponti, Roland Nicsanu, Luisa Benussi, Silvia Peverelli, Antonia Ratti, Martina Ricci, Giuseppe Di Fede, Stefania Magri, Maria Serpente, Serena Lattante, Teuta Domi, Paola Carrera, Elisa Saltimbanco, Silvia Bagnoli, Assunta Ingannato, Alberto Albanese, Fabrizio Tagliavini, Raffaele Lodi, Carlo Caltagirone, Stefano Gambardella, Enza Maria Valente, and Vincenzo Silani

Subjects
C9orf72, GGGGCC hexanucleotide repeat, amyotrophic lateral sclerosis, frontotemporal dementia, allele distribution, Neurology. Diseases of the nervous system, RC346-429
Abstract

IntroductionHigh repeat expansion (HRE) alleles in C9orf72 have been linked to both amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD); ranges for intermediate allelic expansions have not been defined yet, and clinical interpretation of molecular data lacks a defined genotype–phenotype association. In this study, we provide results from a large multicenter epidemiological study reporting the distribution of C9orf72 repeats in healthy elderly from the Italian population.MethodsA total of 967 samples were collected from neurologically evaluated healthy individuals over 70 years of age in the 13 institutes participating in the RIN (IRCCS Network of Neuroscience and Neurorehabilitation) based in Italy. All samples were genotyped using the AmplideXPCR/CE C9orf72 Kit (Asuragen, Inc.), using standardized protocols that have been validated through blind proficiency testing.ResultsAll samples carried hexanucleotide G4C2 expansion alleles in the normal range. All samples were characterized by alleles with less than 25 repeats. In particular, 93.7% of samples showed a number of repeats ≤10, 99.9% ≤20 repeats, and 100% ≤25 repeats.ConclusionThis study describes the distribution of hexanucleotide G4C2 expansion alleles in an Italian healthy population, providing a definition of alleles associated with the neurological healthy phenotype. Moreover, this study provides an effective model of federation between institutes, highlighting the importance of sharing genomic data and standardizing analysis techniques, promoting translational research. Data derived from the study may improve genetic counseling and future studies on ALS/FTD.

Published
2024
Full Text
View/download PDF

40. Robotic Arm Control and Task Training through Deep Reinforcement Learning

Author

Franceschetti, Andrea, Tosello, Elisa, Castaman, Nicola, and Ghidoni, Stefano

Subjects
Computer Science - Robotics, Computer Science - Artificial Intelligence
Abstract

This paper proposes a detailed and extensive comparison of the Trust Region Policy Optimization and DeepQ-Network with Normalized Advantage Functions with respect to other state of the art algorithms, namely Deep Deterministic Policy Gradient and Vanilla Policy Gradient. Comparisons demonstrate that the former have better performances then the latter when asking robotic arms to accomplish manipulation tasks such as reaching a random target pose and pick &placing an object. Both simulated and real-world experiments are provided. Simulation lets us show the procedures that we adopted to precisely estimate the algorithms hyper-parameters and to correctly design good policies. Real-world experiments let show that our polices, if correctly trained on simulation, can be transferred and executed in a real environment with almost no changes., Comment: Submitted to IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2018

Published
2020

43. The ship timbers from the Islamic site of al-Balid : a case study of sewn-plank technology in the Indian Ocean

Author

Ghidoni, A., Cooper, J., and Insoll, T.

Subjects
Sewn-plank construction, Indian Ocean, Medieval watercraft, Oman
Abstract

The sewn-plank ships that sailed the Indian Ocean during the medieval Islamic period (10th-15th centuries) carried people, goods, and ideas between East Africa, Arabia, India, and China. Yet, despite the crucial role such vessels played in the history of this remarkably disparate and expansive region, we know relatively little about them. To date, the archaeological work related to sewn boats in the region has been relatively limited, while the few textual references to sewn-plank vessels generally lack crucial details regarding their design, structure, and operation. Thus, archaeological evidence such as the ship timbers recently discovered at al-Balid, southern Oman, provides us with an invaluable opportunity to deepen our understanding of these watercraft and the material culture they represent. In this thesis, I undertake the most comprehensive and interdisciplinary analysis of Islamic era sewn-boat technology in the Indian Ocean to date, with a particular emphasis on the sewn-planks of al-Balid This study provides a technical analysis of the al-Balid timbers in a comparative context. First, the pieces are examined from a material perspective by analyzing the technical details of each plank and identifying their material composition. Second, the timbers are then compared with extant textual, iconographic, ethnographic, archaeological, and experimental archaeological evidence. Finally, this study contextualizes the al-Balid timbers within the broader material networks in the Indian Ocean during the medieval Islamic period. In doing so, it increases our knowledge of Indian Ocean maritime technology and of the people who built these historically important vessels.

Published
2021

44. Gene Expression Imputation Across Multiple Tissue Types Provides Insight Into the Genetic Architecture of Frontotemporal Dementia and Its Clinical Subtypes

Author

Reus, Lianne M, Pasaniuc, Bogdan, Posthuma, Danielle, Boltz, Toni, Consortium, International FTD-Genomics, Ferrari, Raffaele, Hernandez, Dena G, Nalls, Michael A, Rohrer, Jonathan D, Ramasamy, Adaikalavan, Kwok, John BJ, Dobson-Stone, Carol, Brooks, William S, Schofield, Peter R, Halliday, Glenda M, Hodges, John R, Piguet, Olivier, Bartley, Lauren, Thompson, Elizabeth, Hernández, Isabel, Ruiz, Agustín, Boada, Mercè, Borroni, Barbara, Padovani, Alessandro, Cruchaga, Carlos, Cairns, Nigel J, Benussi, Luisa, Binetti, Giuliano, Ghidoni, Roberta, Forloni, Gianluigi, Galimberti, Daniela, Fenoglio, Chiara, Serpente, Maria, Scarpini, Elio, Clarimón, Jordi, Lleó, Alberto, Blesa, Rafael, Waldö, Maria Landqvist, Nilsson, Karin, Nilsson, Christer, Mackenzie, Ian RA, Hsiung, Ging-Yuek R, Mann, David MA, Grafman, Jordan, Morris, Christopher M, Attems, Johannes, Griffiths, Timothy D, McKeith, Ian G, Thomas, Alan J, Pietrini, Pietro, Huey, Edward D, Wassermann, Eric M, Baborie, Atik, Jaros, Evelyn, Tierney, Michael C, Pastor, Pau, Razquin, Cristina, Ortega-Cubero, Sara, Alonso, Elena, Perneczky, Robert, Diehl-Schmid, Janine, Alexopoulos, Panagiotis, Kurz, Alexander, Rainero, Innocenzo, Rubino, Elisa, Pinessi, Lorenzo, Rogaeva, Ekaterina, St. George-Hyslop, Peter, Rossi, Giacomina, Tagliavini, Fabrizio, Giaccone, Giorgio, Rowe, James B, Schlachetzki, Johannes CM, Uphill, James, Collinge, John, Mead, Simon, Danek, Adrian, Van Deerlin, Vivianna M, Grossman, Murray, Trojanowski, John Q, van der Zee, Julie, Van Broeckhoven, Christine, Cappa, Stefano F, Le Ber, Isabelle, Hannequin, Didier, Golfier, Véronique, Vercelletto, Martine, Brice, Alexis, Nacmias, Benedetta, Sorbi, Sandro, Bagnoli, Silvia, Piaceri, Irene, Nielsen, Jørgen E, Hjermind, Lena E, Riemenschneider, Matthias, Mayhaus, Manuel, Ibach, Bernd, Gasparoni, Gilles, Pichler, Sabrina, and Gu, Wei

Subjects
Biological Sciences, Genetics, Acquired Cognitive Impairment, Frontotemporal Dementia (FTD), Aging, Dementia, Neurodegenerative, Neurosciences, Alzheimer's Disease including Alzheimer's Disease Related Dementias (AD/ADRD), Brain Disorders, Prevention, Alzheimer's Disease Related Dementias (ADRD), Rare Diseases, Aetiology, 2.1 Biological and endogenous factors, Neurological, Frontotemporal Dementia, Gene Expression, Humans, International FTD-Genomics Consortium, 17q21.31 inversion region, Dorsolateral prefrontal cortex, Expression quantitative trait loci, Frontotemporal dementia, SEC22B, Transcriptome-wide association study, Medical and Health Sciences, Psychology and Cognitive Sciences, Psychiatry, Biological sciences, Biomedical and clinical sciences, Psychology
Abstract

BackgroundThe etiology of frontotemporal dementia (FTD) is poorly understood. To identify genes with predicted expression levels associated with FTD, we integrated summary statistics with external reference gene expression data using a transcriptome-wide association study approach.MethodsFUSION software was used to leverage FTD summary statistics (all FTD: n = 2154 cases, n = 4308 controls; behavioral variant FTD: n = 1337 cases, n = 2754 controls; semantic dementia: n = 308 cases, n = 616 controls; progressive nonfluent aphasia: n = 269 cases, n = 538 controls; FTD with motor neuron disease: n = 200 cases, n = 400 controls) from the International FTD-Genomics Consortium with 53 expression quantitative loci tissue type panels (n = 12,205; 5 consortia). Significance was assessed using a 5% false discovery rate threshold.ResultsWe identified 73 significant gene-tissue associations for FTD, representing 44 unique genes in 34 tissue types. Most significant findings were derived from dorsolateral prefrontal cortex splicing data (n = 19 genes, 26%). The 17q21.31 inversion locus contained 23 significant associations, representing 6 unique genes. Other top hits included SEC22B (a gene involved in vesicle trafficking), TRGV5, and ZNF302. A single gene finding (RAB38) was observed for behavioral variant FTD. For other clinical subtypes, no significant associations were observed.ConclusionsWe identified novel candidate genes (e.g., SEC22B) and previously reported risk regions (e.g., 17q21.31) for FTD. Most significant associations were observed in dorsolateral prefrontal cortex splicing data despite the modest sample size of this reference panel. This suggests that our findings are specific to FTD and are likely to be biologically relevant highlights of genes at different FTD risk loci that are contributing to the disease pathology.

Published
2021

45. Pathogenic Huntingtin Repeat Expansions in Patients with Frontotemporal Dementia and Amyotrophic Lateral Sclerosis

Author

Dewan, Ramita, Chia, Ruth, Ding, Jinhui, Hickman, Richard A, Stein, Thor D, Abramzon, Yevgeniya, Ahmed, Sarah, Sabir, Marya S, Portley, Makayla K, Tucci, Arianna, Ibáñez, Kristina, Shankaracharya, FNU, Keagle, Pamela, Rossi, Giacomina, Caroppo, Paola, Tagliavini, Fabrizio, Waldo, Maria L, Johansson, Per M, Nilsson, Christer F, Rowe, James B, Benussi, Luisa, Binetti, Giuliano, Ghidoni, Roberta, Jabbari, Edwin, Viollet, Coralie, Glass, Jonathan D, Singleton, Andrew B, Silani, Vincenzo, Ross, Owen A, Ryten, Mina, Torkamani, Ali, Tanaka, Toshiko, Ferrucci, Luigi, Resnick, Susan M, Pickering-Brown, Stuart, Brady, Christopher B, Kowal, Neil, Hardy, John A, Van Deerlin, Vivianna, Vonsattel, Jean Paul, Harms, Matt, Morris, Christopher M, Ferrari, Raffaele, Landers, John E, Chiò, Adriano, Gibbs, Jesse Raphael, Dalgard, Clifton L, Scholz, Sonja W, Traynor, Bryan J, Adeleye, Adelani, Alba, Camille, Bacikova, Dagmar, Hupalo, Daniel N, Martinez, Elisa McGrath, Pollard, Harvey B, Sukumar, Gauthaman, Soltis, Anthony R, Tuck, Meila, Zhang, Xijun, Wilkerson, Matthew D, Smith, Bradley N, Ticozzi, Nicola, Fallini, Claudia, Gkazi, Athina Soragia, Topp, Simon D, Kost, Jason, Scotter, Emma L, Kenna, Kevin P, Miller, Jack W, Tiloca, Cinzia, Vance, Caroline, Danielson, Eric W, Troakes, Claire, Colombrita, Claudia, Al-Sarraj, Safa, Lewis, Elizabeth A, King, Andrew, Calini, Daniela, Pensato, Viviana, Castellotti, Barbara, de Belleroche, Jacqueline, Baas, Frank, Asbroek, Anneloor LMA ten, Sapp, Peter C, McKenna-Yasek, Diane, McLaughlin, Russell L, Polak, Meraida, Asress, Seneshaw, Esteban-Pérez, Jesús, Muñoz-Blanco, José Luis, Stevic, Zorica, D’Alfonso, Sandra, Mazzini, Letizia, Comi, Giacomo P, Del Bo, Roberto, Ceroni, Mauro, Gagliardi, Stella, Querin, Giorgia, Bertolin, Cinzia, and van Rheenen, Wouter

Subjects
Genetics, Alzheimer's Disease including Alzheimer's Disease Related Dementias (AD/ADRD), Clinical Research, Neurodegenerative, Acquired Cognitive Impairment, Dementia, Frontotemporal Dementia (FTD), Alzheimer's Disease Related Dementias (ADRD), ALS, Rare Diseases, Brain Disorders, Neurosciences, Huntington's Disease, 2.1 Biological and endogenous factors, Aetiology, Neurological, Amyotrophic Lateral Sclerosis, DNA Repeat Expansion, Frontotemporal Dementia, Humans, Huntingtin Protein, Mutation, Whole Genome Sequencing, American Genome Center, FALS Sequencing Consortium, Genomics England Research Consortium, International ALS/FTD Genomics Consortium, International FTD Genetics Consortium, International LBD Genomics Consortium, NYGC ALS Consortium, PROSPECT Consortium, amyotrophic lateral sclerosis, frontotemporal dementia, huntingtin, repeat expansions, whole-genome sequencing, Psychology, Cognitive Sciences, Neurology & Neurosurgery
Abstract

We examined the role of repeat expansions in the pathogenesis of frontotemporal dementia (FTD) and amyotrophic lateral sclerosis (ALS) by analyzing whole-genome sequence data from 2,442 FTD/ALS patients, 2,599 Lewy body dementia (LBD) patients, and 3,158 neurologically healthy subjects. Pathogenic expansions (range, 40-64 CAG repeats) in the huntingtin (HTT) gene were found in three (0.12%) patients diagnosed with pure FTD/ALS syndromes but were not present in the LBD or healthy cohorts. We replicated our findings in an independent collection of 3,674 FTD/ALS patients. Postmortem evaluations of two patients revealed the classical TDP-43 pathology of FTD/ALS, as well as huntingtin-positive, ubiquitin-positive aggregates in the frontal cortex. The neostriatal atrophy that pathologically defines Huntington's disease was absent in both cases. Our findings reveal an etiological relationship between HTT repeat expansions and FTD/ALS syndromes and indicate that genetic screening of FTD/ALS patients for HTT repeat expansions should be considered.

Published
2021

46. C9orf72, age at onset, and ancestry help discriminate behavioral from language variants in FTLD cohorts

Author

Costa, Beatrice, Manzoni, Claudia, Bernal-Quiros, Manuel, Kia, Demis A, Aguilar, Miquel, Alvarez, Ignacio, Alvarez, Victoria, Andreassen, Ole, Anfossi, Maria, Bagnoli, Silvia, Benussi, Luisa, Bernardi, Livia, Binetti, Giuliano, Blackburn, Daniel, Boada, Mercè, Borroni, Barbara, Bowns, Lucy, Bråthen, Geir, Bruni, Amalia C, Chiang, Huei-Hsin, Clarimon, Jordi, Colville, Shuna, Conidi, Maria E, Cope, Tom E, Cruchaga, Carlos, Cupidi, Chiara, Di Battista, Maria Elena, Diehl-Schmid, Janine, Diez-Fairen, Monica, Dols-Icardo, Oriol, Durante, Elisabetta, Flisar, Dušan, Frangipane, Francesca, Galimberti, Daniela, Gallo, Maura, Gallucci, Maurizio, Ghidoni, Roberta, Graff, Caroline, Grafman, Jordan H, Grossman, Murray, Hardy, John, Hernández, Isabel, Holloway, Guy JT, Huey, Edward D, Illán-Gala, Ignacio, Karydas, Anna, Khoshnood, Behzad, Kramberger, Milica G, Kristiansen, Mark, Lewis, Patrick A, Lleó, Alberto, Madhan, Gaganjit K, Maletta, Raffaele, Maver, Aleš, Menendez-Gonzalez, Manuel, Milan, Graziella, Miller, Bruce, Mol, Merel O, Momeni, Parastoo, Moreno-Grau, Sonia, Morris, Chris M, Nacmias, Benedetta, Nilsson, Christer, Novelli, Valeria, Öijerstedt, Linn, Padovani, Alessandro, Pal, Suvankar, Panchbhaya, Yasmin, Pastor, Pau, Peterlin, Borut, Piaceri, Irene, Pickering-Brown, Stuart, Pijnenburg, Yolande AL, Puca, Annibale A, Rainero, Innocenzo, Rendina, Antonella, Richardson, Anna MT, Rogaeva, Ekaterina, Rogelj, Boris, Rollinson, Sara, Rossi, Giacomina, Rossmeier, Carola, Rowe, James B, Rubino, Elisa, Ruiz, Agustín, Sanchez-Valle, Raquel, Sando, Sigrid B, Santillo, Alexander F, Saxon, Jennifer, Scarpini, Elio, Serpente, Maria, Smirne, Nicoletta, Sorbi, Sandro, Suh, EunRan, Tagliavini, Fabrizio, Thompson, Jennifer C, Trojanowski, John Q, Van Deerlin, Vivianna M, Van der Zee, Julie, and Van Broeckhoven, Christine

Subjects
Biomedical and Clinical Sciences, Neurosciences, Clinical Sciences, Rare Diseases, Acquired Cognitive Impairment, Alzheimer's Disease Related Dementias (ADRD), Brain Disorders, Alzheimer's Disease including Alzheimer's Disease Related Dementias (AD/ADRD), Neurodegenerative, Frontotemporal Dementia (FTD), Genetics, Clinical Research, Dementia, Neurological, Age of Onset, Aged, Aged, 80 and over, Aphasia, Primary Progressive, C9orf72 Protein, Cohort Studies, DNA Repeat Expansion, Europe, Female, Frontotemporal Dementia, Frontotemporal Lobar Degeneration, Geography, Humans, Male, Mediterranean Region, Middle Aged, Principal Component Analysis, Scandinavian and Nordic Countries, Syndrome, International FTD-Genetics Consortium, Cognitive Sciences, Neurology & Neurosurgery, Clinical sciences
Abstract

ObjectiveWe sought to characterize C9orf72 expansions in relation to genetic ancestry and age at onset (AAO) and to use these measures to discriminate the behavioral from the language variant syndrome in a large pan-European cohort of frontotemporal lobar degeneration (FTLD) cases.MethodsWe evaluated expansions frequency in the entire cohort (n = 1,396; behavioral variant frontotemporal dementia [bvFTD] [n = 800], primary progressive aphasia [PPA] [n = 495], and FTLD-motor neuron disease [MND] [n = 101]). We then focused on the bvFTD and PPA cases and tested for association between expansion status, syndromes, genetic ancestry, and AAO applying statistical tests comprising Fisher exact tests, analysis of variance with Tukey post hoc tests, and logistic and nonlinear mixed-effects model regressions.ResultsWe found C9orf72 pathogenic expansions in 4% of all cases (56/1,396). Expansion carriers differently distributed across syndromes: 12/101 FTLD-MND (11.9%), 40/800 bvFTD (5%), and 4/495 PPA (0.8%). While addressing population substructure through principal components analysis (PCA), we defined 2 patients groups with Central/Northern (n = 873) and Southern European (n = 523) ancestry. The proportion of expansion carriers was significantly higher in bvFTD compared to PPA (5% vs 0.8% [p = 2.17 × 10-5; odds ratio (OR) 6.4; confidence interval (CI) 2.31-24.99]), as well as in individuals with Central/Northern European compared to Southern European ancestry (4.4% vs 1.8% [p = 1.1 × 10-2; OR 2.5; CI 1.17-5.99]). Pathogenic expansions and Central/Northern European ancestry independently and inversely correlated with AAO. Our prediction model (based on expansions status, genetic ancestry, and AAO) predicted a diagnosis of bvFTD with 64% accuracy.ConclusionsOur results indicate correlation between pathogenic C9orf72 expansions, AAO, PCA-based Central/Northern European ancestry, and a diagnosis of bvFTD, implying complex genetic risk architectures differently underpinning the behavioral and language variant syndromes.

Published
2020

48. Real-time Tracking-by-Detection of Human Motion in RGB-D Camera Networks

Author

Malaguti, Alessandro, Carraro, Marco, Guidolin, Mattia, Tagliapietra, Luca, Menegatti, Emanuele, and Ghidoni, Stefano

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

This paper presents a novel real-time tracking system capable of improving body pose estimation algorithms in distributed camera networks. The first stage of our approach introduces a linear Kalman filter operating at the body joints level, used to fuse single-view body poses coming from different detection nodes of the network and to ensure temporal consistency between them. The second stage, instead, refines the Kalman filter estimates by fitting a hierarchical model of the human body having constrained link sizes in order to ensure the physical consistency of the tracking. The effectiveness of the proposed approach is demonstrated through a broad experimental validation, performed on a set of sequences whose ground truth references are generated by a commercial marker-based motion capture system. The obtained results show how the proposed system outperforms the considered state-of-the-art approaches, granting accurate and reliable estimates. Moreover, the developed methodology constrains neither the number of persons to track, nor the number, position, synchronization, frame-rate, and manufacturer of the RGB-D cameras used. Finally, the real-time performances of the system are of paramount importance for a large number of real-world applications., Comment: Accepted to IEEE SMC 2019

Published
2019

49. Proprioceptive Robot Collision Detection through Gaussian Process Regression

Author

Alberto, Dalla Libera, Elisa, Tosello, Gianluigi, Pillonetto, Stefano, Ghidoni, and Ruggero, Carli

Subjects
Computer Science - Robotics
Abstract

This paper proposes a proprioceptive collision detection algorithm based on Gaussian Regression. Compared to sensor-based collision detection and other proprioceptive algorithms, the proposed approach has minimal sensing requirements, since only the currents and the joint configurations are needed. The algorithm extends the standard Gaussian Process models adopted in learning the robot inverse dynamics, using a more rich set of input locations and an ad-hoc kernel structure to model the complex and non-linear behaviors due to frictions in quasi-static configurations. Tests performed on a Universal Robots UR10 show the effectiveness of the proposed algorithm to detect when a collision has occurred., Comment: Published at ACC 2019

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results