Capítols de llibre
http://hdl.handle.net/2117/3337
2024-03-28T23:53:03ZMRI brain tumor segmentation and uncertainty estimation using 3D-UNet architectures
http://hdl.handle.net/2117/360072
MRI brain tumor segmentation and uncertainty estimation using 3D-UNet architectures
Mora Ballestar, Laura; Vilaplana Besler, Verónica
Automation of brain tumor segmentation in 3D magnetic resonance images (MRIs) is key to assess the diagnostic and treatment of the disease. In recent years, convolutional neural networks (CNNs) have shown improved results in the task. However, high memory consumption is still a problem in 3D-CNNs. Moreover, most methods do not include uncertainty information, which is especially critical in medical diagnosis. This work studies 3D encoder-decoder architectures trained with patch-based techniques to reduce memory consumption and decrease the effect of unbalanced data. The different trained models are then used to create an ensemble that leverages the properties of each model, thus increasing the performance. We also introduce voxel-wise uncertainty information, both epistemic and aleatoric using test-time dropout (TTD) and data-augmentation (TTA) respectively. In addition, a hybrid approach is proposed that helps increase the accuracy of the segmentation. The model and uncertainty estimation measurements proposed in this work have been used in the BraTS’20 Challenge for task 1 and 3 regarding tumor segmentation and uncertainty estimation.
2022-01-20T08:46:18ZMora Ballestar, LauraVilaplana Besler, VerónicaAutomation of brain tumor segmentation in 3D magnetic resonance images (MRIs) is key to assess the diagnostic and treatment of the disease. In recent years, convolutional neural networks (CNNs) have shown improved results in the task. However, high memory consumption is still a problem in 3D-CNNs. Moreover, most methods do not include uncertainty information, which is especially critical in medical diagnosis. This work studies 3D encoder-decoder architectures trained with patch-based techniques to reduce memory consumption and decrease the effect of unbalanced data. The different trained models are then used to create an ensemble that leverages the properties of each model, thus increasing the performance. We also introduce voxel-wise uncertainty information, both epistemic and aleatoric using test-time dropout (TTD) and data-augmentation (TTA) respectively. In addition, a hybrid approach is proposed that helps increase the accuracy of the segmentation. The model and uncertainty estimation measurements proposed in this work have been used in the BraTS’20 Challenge for task 1 and 3 regarding tumor segmentation and uncertainty estimation.Enhancing online knowledge graph population with semantic knowledge
http://hdl.handle.net/2117/332082
Enhancing online knowledge graph population with semantic knowledge
Fernández Cañellas, Dèlia; Rimmek, Joan Marco; Espadaler Rodés, Joan; Garolera Huguet, Blai; Barja Romero, Adrià; Codina, Marc; Sastre Rienitz, Marc; Giró Nieto, Xavier; Riveiro, Juan Carlos; Bou Balust, Elisenda
Knowledge Graphs (KG) are becoming essential to organize, represent and store the world’s knowledge, but they still rely heavily on humanly-curated structured data. Information Extraction (IE) tasks, like disambiguating entities and relations from unstructured text, are key to automate KG population. However, Natural Language Processing (NLP) methods alone can not guarantee the validity of the facts extracted and may introduce erroneous information into the KG. This work presents an end-to-end system that combines Semantic Knowledge and Validation techniques with NLP methods, to provide KG population of novel facts from clustered news events. The contributions of this paper are two-fold: First, we present a novel method for including entity-type knowledge into a Relation Extraction model, improving F1-Score over the baseline with TACRED and TypeRE datasets. Second, we increase the precision by adding data validation on top of the Relation Extraction method. These two contributions are combined in an industrial pipeline for automatic KG population over aggregated news, demonstrating increased data validity when performing online learning from unstructured web data. Finally, the TypeRE and AggregatedNewsRE datasets build to benchmark these results are also published to foster future research in this field.
2020-11-12T16:33:47ZFernández Cañellas, DèliaRimmek, Joan MarcoEspadaler Rodés, JoanGarolera Huguet, BlaiBarja Romero, AdriàCodina, MarcSastre Rienitz, MarcGiró Nieto, XavierRiveiro, Juan CarlosBou Balust, ElisendaKnowledge Graphs (KG) are becoming essential to organize, represent and store the world’s knowledge, but they still rely heavily on humanly-curated structured data. Information Extraction (IE) tasks, like disambiguating entities and relations from unstructured text, are key to automate KG population. However, Natural Language Processing (NLP) methods alone can not guarantee the validity of the facts extracted and may introduce erroneous information into the KG. This work presents an end-to-end system that combines Semantic Knowledge and Validation techniques with NLP methods, to provide KG population of novel facts from clustered news events. The contributions of this paper are two-fold: First, we present a novel method for including entity-type knowledge into a Relation Extraction model, improving F1-Score over the baseline with TACRED and TypeRE datasets. Second, we increase the precision by adding data validation on top of the Relation Extraction method. These two contributions are combined in an industrial pipeline for automatic KG population over aggregated news, demonstrating increased data validity when performing online learning from unstructured web data. Finally, the TypeRE and AggregatedNewsRE datasets build to benchmark these results are also published to foster future research in this field.Unsupervised GRN Ensemble
http://hdl.handle.net/2117/176898
Unsupervised GRN Ensemble
Bellot, Pau; Salembier Clairon, Philippe Jean; Pham, Ngoc C.; Meyer, Patrick E.
Inferring gene regulatory networks from expression data is a very challenging problem that has raised the interest of the scientific community. Different algorithms have been proposed to try to solve this issue, but it has been shown that different methods have some particular biases and strengths, and none of them is the best across all types of data and datasets. As a result, the idea of aggregating various network inferences through a consensus mechanism naturally arises. In this chapter, a common framework to standardize already proposed consensus methods is presented, and based on this framework different proposals are introduced and analyzed in two different scenarios: Homogeneous and Heterogeneous. The first scenario reflects situations where the networks to be aggregated are rather similar because they are obtained with inference algorithms working on the same data, whereas the second scenario deals with very diverse networks because various sources of data are used to generate the individual networks. A procedure for combining multiple network inference algorithms is analyzed in a systematic way. The results show that there is a very significant difference between these two scenarios, and that the best way to combine networks in the Heterogeneous scenario is not the most commonly used. We show in particular that aggregation in the Heterogeneous scenario can be very beneficial if the individual networks are combined with our new proposed method ScaleLSum.
2020-02-05T18:40:37ZBellot, PauSalembier Clairon, Philippe JeanPham, Ngoc C.Meyer, Patrick E.Inferring gene regulatory networks from expression data is a very challenging problem that has raised the interest of the scientific community. Different algorithms have been proposed to try to solve this issue, but it has been shown that different methods have some particular biases and strengths, and none of them is the best across all types of data and datasets. As a result, the idea of aggregating various network inferences through a consensus mechanism naturally arises. In this chapter, a common framework to standardize already proposed consensus methods is presented, and based on this framework different proposals are introduced and analyzed in two different scenarios: Homogeneous and Heterogeneous. The first scenario reflects situations where the networks to be aggregated are rather similar because they are obtained with inference algorithms working on the same data, whereas the second scenario deals with very diverse networks because various sources of data are used to generate the individual networks. A procedure for combining multiple network inference algorithms is analyzed in a systematic way. The results show that there is a very significant difference between these two scenarios, and that the best way to combine networks in the Heterogeneous scenario is not the most commonly used. We show in particular that aggregation in the Heterogeneous scenario can be very beneficial if the individual networks are combined with our new proposed method ScaleLSum.Cascaded V-Net using ROI masks for brain tumor segmentation
http://hdl.handle.net/2117/120811
Cascaded V-Net using ROI masks for brain tumor segmentation
Casamitjana Díaz, Adrià; Catà, Marcel; Sanchez Muriana, Irina; Combalia, Marc; Vilaplana Besler, Verónica
This book constitutes revised selected papers from the Third International MICCAI Brainlesion Workshop, BrainLes 2017, as well as the International Multimodal Brain Tumor Segmentation, BraTS, and White Matter Hyperintensities, WMH, segmentation challenges, which were held jointly at the Medical Image computing for Computer Assisted Intervention Conference, MICCAI, in Quebec City, Canada, in September 2017.
2018-09-04T10:11:37ZCasamitjana Díaz, AdriàCatà, MarcelSanchez Muriana, IrinaCombalia, MarcVilaplana Besler, VerónicaThis book constitutes revised selected papers from the Third International MICCAI Brainlesion Workshop, BrainLes 2017, as well as the International Multimodal Brain Tumor Segmentation, BraTS, and White Matter Hyperintensities, WMH, segmentation challenges, which were held jointly at the Medical Image computing for Computer Assisted Intervention Conference, MICCAI, in Quebec City, Canada, in September 2017.Hierarchical object detection with deep reinforcement learning
http://hdl.handle.net/2117/113093
Hierarchical object detection with deep reinforcement learning
Bellver, Míriam; Giró Nieto, Xavier; Marqués Acosta, Fernando; Torres Viñals, Jordi
Deep learning and image processing are two areas of great interest to academics and industry professionals alike. The areas of application of these two disciplines range widely, encompassing fields such as medicine, robotics, and security and surveillance.
The aim of this book, ‘Deep Learning for Image Processing Applications’, is to offer concepts from these two areas in the same platform, and the book brings together the shared ideas of professionals from academia and research about problems and solutions relating to the multifaceted aspects of the two disciplines. The first chapter provides an introduction to deep learning, and serves as the basis for much of what follows in the subsequent chapters, which cover subjects including: the application of deep neural networks for image classification; hand gesture recognition in robotics; deep learning techniques for image retrieval; disease detection using deep learning techniques; and the comparative analysis of deep data and big data.
The book will be of interest to all those whose work involves the use of deep learning and image processing techniques.
2018-01-23T10:37:10ZBellver, MíriamGiró Nieto, XavierMarqués Acosta, FernandoTorres Viñals, JordiDeep learning and image processing are two areas of great interest to academics and industry professionals alike. The areas of application of these two disciplines range widely, encompassing fields such as medicine, robotics, and security and surveillance.
The aim of this book, ‘Deep Learning for Image Processing Applications’, is to offer concepts from these two areas in the same platform, and the book brings together the shared ideas of professionals from academia and research about problems and solutions relating to the multifaceted aspects of the two disciplines. The first chapter provides an introduction to deep learning, and serves as the basis for much of what follows in the subsequent chapters, which cover subjects including: the application of deep neural networks for image classification; hand gesture recognition in robotics; deep learning techniques for image retrieval; disease detection using deep learning techniques; and the comparative analysis of deep data and big data.
The book will be of interest to all those whose work involves the use of deep learning and image processing techniques.Object retrieval with deep convolutional features
http://hdl.handle.net/2117/113092
Object retrieval with deep convolutional features
Mohedano, Eva; Salvador Aguilera, Amaia; McGuinness, Kevin; Giró Nieto, Xavier; O'Connor, Noel; Marqués Acosta, Fernando
Deep learning and image processing are two areas of great interest to academics and industry professionals alike. The areas of application of these two disciplines range widely, encompassing fields such as medicine, robotics, and security and surveillance.
The aim of this book, ‘Deep Learning for Image Processing Applications’, is to offer concepts from these two areas in the same platform, and the book brings together the shared ideas of professionals from academia and research about problems and solutions relating to the multifaceted aspects of the two disciplines. The first chapter provides an introduction to deep learning, and serves as the basis for much of what follows in the subsequent chapters, which cover subjects including: the application of deep neural networks for image classification; hand gesture recognition in robotics; deep learning techniques for image retrieval; disease detection using deep learning techniques; and the comparative analysis of deep data and big data.
The book will be of interest to all those whose work involves the use of deep learning and image processing techniques.
2018-01-23T10:28:21ZMohedano, EvaSalvador Aguilera, AmaiaMcGuinness, KevinGiró Nieto, XavierO'Connor, NoelMarqués Acosta, FernandoDeep learning and image processing are two areas of great interest to academics and industry professionals alike. The areas of application of these two disciplines range widely, encompassing fields such as medicine, robotics, and security and surveillance.
The aim of this book, ‘Deep Learning for Image Processing Applications’, is to offer concepts from these two areas in the same platform, and the book brings together the shared ideas of professionals from academia and research about problems and solutions relating to the multifaceted aspects of the two disciplines. The first chapter provides an introduction to deep learning, and serves as the basis for much of what follows in the subsequent chapters, which cover subjects including: the application of deep neural networks for image classification; hand gesture recognition in robotics; deep learning techniques for image retrieval; disease detection using deep learning techniques; and the comparative analysis of deep data and big data.
The book will be of interest to all those whose work involves the use of deep learning and image processing techniques.3D convolutional neural networks for brain tumor segmentation: a comparison of multi-resolution architectures
http://hdl.handle.net/2117/108071
3D convolutional neural networks for brain tumor segmentation: a comparison of multi-resolution architectures
Casamitjana Díaz, Adrià; Puch Giner, Santi; Aduriz Saiz, Asier; Vilaplana Besler, Verónica
The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-55524-9 15
2017-09-27T11:55:36ZCasamitjana Díaz, AdriàPuch Giner, SantiAduriz Saiz, AsierVilaplana Besler, VerónicaTime-consistent estimation of end-effectors from RGB-D data
http://hdl.handle.net/2117/101150
Time-consistent estimation of end-effectors from RGB-D data
Lin, Xiao; Pardàs Feliu, Montse; Casas Pla, Josep Ramon
End-effectors are usually related to the location of the free end of a kinematic chain. Each of them contains rich structure information about the entity. Hence, estimating stable end-effectors of different entities enables robust tracking as well as a generic representation. In this paper, we present a system for end-effector estimation from RGB-D stream data. Instead of relying on a specific
pose or configuration for initialization, we exploit time coherence without making any assumption with respect to the prior knowledge. This makes the estimation process more robust in a predict-update framework. Qualitative and quantitative experiments are performed against the reference method with promising results.
2017-02-16T14:19:30ZLin, XiaoPardàs Feliu, MontseCasas Pla, Josep RamonEnd-effectors are usually related to the location of the free end of a kinematic chain. Each of them contains rich structure information about the entity. Hence, estimating stable end-effectors of different entities enables robust tracking as well as a generic representation. In this paper, we present a system for end-effector estimation from RGB-D stream data. Instead of relying on a specific
pose or configuration for initialization, we exploit time coherence without making any assumption with respect to the prior knowledge. This makes the estimation process more robust in a predict-update framework. Qualitative and quantitative experiments are performed against the reference method with promising results.3D point cloud video segmentation based on interaction analysis
http://hdl.handle.net/2117/101141
3D point cloud video segmentation based on interaction analysis
Lin, Xiao; Casas Pla, Josep Ramon; Pardàs Feliu, Montse
Given the widespread availability of point cloud data from consumer depth sensors, 3D segmentation becomes a promising building block for high level applications such as scene understanding and interaction analysis. It benefits from the richer information contained in actual world 3D data compared to apparent (projected) data in 2D images. This also implies that the classical color segmentation challenges have recently shifted to RGBD data, whereas new emerging challenges are added as 3D information from depth measurements is usually noisy, sparse and unorganized. We present a novel segmentation approach for 3D point cloud video based on low level features and oriented to the analysis of object interactions. A hierarchical representation of the input point cloud is proposed to efficiently segment 3D data at the finer level, and to temporally establish the correspondence between segments, while dynamically managing the object split and merge at the coarser level. Experiments illustrate promising results and its potential application in object interaction analysis.
2017-02-16T12:08:27ZLin, XiaoCasas Pla, Josep RamonPardàs Feliu, MontseGiven the widespread availability of point cloud data from consumer depth sensors, 3D segmentation becomes a promising building block for high level applications such as scene understanding and interaction analysis. It benefits from the richer information contained in actual world 3D data compared to apparent (projected) data in 2D images. This also implies that the classical color segmentation challenges have recently shifted to RGBD data, whereas new emerging challenges are added as 3D information from depth measurements is usually noisy, sparse and unorganized. We present a novel segmentation approach for 3D point cloud video based on low level features and oriented to the analysis of object interactions. A hierarchical representation of the input point cloud is proposed to efficiently segment 3D data at the finer level, and to temporally establish the correspondence between segments, while dynamically managing the object split and merge at the coarser level. Experiments illustrate promising results and its potential application in object interaction analysis.Neighborhood filters and the recovery of 3D information
http://hdl.handle.net/2117/83350
Neighborhood filters and the recovery of 3D information
Digne, Julie; Dimiccoli, Mariella; Sabater, Neus; Salembier Clairon, Philippe Jean
2016-02-23T19:14:51ZDigne, JulieDimiccoli, MariellaSabater, NeusSalembier Clairon, Philippe Jean