Supervised Tractogram Filtering using Geometric Deep Learning
Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）；Istituto Italiano di Tecnologia（意大利技术研究院）；University of Trento（特伦托大学）；CNRS（法国国家科学研究中心）；CEA（法国原子能和替代能源委员会）；Université de Bordeaux（波尔多大学）；Azienda Provinciale per i Servizi Sanitari（省卫生服务局）；NNAISENSE
Pietro Astolfi, Ruben Verhagen, Laurent Petit, Emanuele Olivetti, Silvio Sarubbo, Jonathan Masci, Davide Boscaini, Paolo Avesani
A tractogram is a virtual representation of the brain white matter. It is composed of millions of virtual fibers, encoded as 3D polylines, which approximate the white matter axonal pathways. To date, tractograms are the most accurate white matter representation and thus are used for tasks like presurgical planning and investigations of neuroplasticity, brain disorders, or brain networks. However, it is a well-known issue that a large portion of tractogram fibers is not anatomically plausible and can be considered artifacts of the tracking procedure. With Verifyber, we tackle the problem of filtering out such non-plausible fibers using a novel fully-supervised learning approach. Differently from other approaches based on signal reconstruction and/or brain topology regularization, we guide our method with the existing anatomical knowledge of the white matter. Using tractograms annotated according to anatomical principles, we train our model, Verifyber, to classify fibers as either anatomically plausible or non-plausible. The proposed Verifyber model is an original Geometric Deep Learning method that can deal with variable size fibers, while being invariant to fiber orientation. Our model considers each fiber as a graph of points, and by learning features of the edges between consecutive points via the proposed sequence Edge Convolution, it can capture the underlying anatomical properties. The output filtering results highly accurate and robust across an extensive set of experiments, and fast; with a 12GB GPU, filtering a tractogram of 1M fibers requires less than a minute. Verifyber implementation and trained models are available at https://github.com/FBK-NILab/verifyber.
Assessing Streamline Plausibility Through Randomized Iterative Spherical-Deconvolution Informed Tractogram Filtering
Saarland University（萨尔大学）；Krembil Research Institute（克伦比尔研究所）；Toronto Western Hospital（多伦多西部医院）；University Health Network（大学健康网络）；KTH Royal Institute of Technology（KTH皇家理工学院）
Multi-temporal speckle reduction with self-supervised deep neural networks
LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院 LTCI 实验室）；Univ Lyon, UJM-Saint-Etienne（里昂大学圣艾蒂安让·莫内大学）；CNRS（法国国家科学研究中心）；Laboratoire Hubert Curien UMR 5516（于贝尔·居里安实验室（UMR 5516））；Laboratoire MAP5, UMR CNRS 8145（MAP5 实验室（法国国家科学研究中心 UMR 8145））；Université Paris Cité（巴黎西岱大学）
LMLCC-Net: A Semi-Supervised Deep Learning Model for Lung Nodule Malignancy Prediction from CT Scans using a Novel Hounsfield Unit-Based Intensity Filtering
mHealth Lab, Department of Biomedical Engineering, Bangladesh University of Engineering and Technology（孟加拉国工程与技术大学生物医学工程系mHealth实验室）
FIESTA: Autoencoders for accurate fiber segmentation in tractography
Université de Sherbrooke, Canada（舍布鲁克大学，加拿大）；Sherbrooke Connectivity Imaging Lab (SCIL)（舍布鲁克连接成像实验室（SCIL））；Videos & Images Theory and Analytics Lab (VITAL)（视频与图像理论及分析实验室（VITAL））；Department of Computer Science（计算机科学系）；Department of Radiology（放射科）；Brigham and Women’s Hospital（布莱根妇女医院）；Mass General Brigham/Harvard Medical School, USA（麻省总医院布莱根联合/哈佛医学院，美国）；Centre de Calcul Scientifique（科学计算中心）；Medical Imaging and Neuroinformatic (MINi) Lab（医学成像与神经信息学（MINi）实验室）；Groupe d’Imagerie Neurofonctionnelle (GIN)（神经功能成像小组（GIN））；CNRS, CEA, IMN, GIN, UMR 5293, F-33000 Bordeaux（法国国家科学研究中心、法国原子能委员会、神经影像研究所、神经功能成像小组、5293号联合研究单位，波尔多）；Université de Bordeaux, France（波尔多大学，法国）；Pharma Research and Early Development（制药研究与早期开发）；Neuroscience and Rare Diseases（神经科学与罕见病）；Roche Innovation Center Basel（巴塞尔罗氏创新中心）；F. Hoffmann-La Roche Ltd., Basel, Switzerland（F.霍夫曼-罗氏有限公司，巴塞尔，瑞士）
Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Liangzhu Laboratory and WeDoctor Cloud（良渚实验室和微医云）；Shanghai Innovation Institute（上海创新研究院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；State Key Laboratory of Transvascular Implantation Devices and TIDRI（经血管植入器械全国重点实验室和TIDRI）；Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室）
