PURPOSE: To apply quantitative imaging analysis for noninvasive classification of the most frequent subtypes of Non-Hodgkin Lymphoma (NHL) as a basis for a clinical imaging genomic model to support therapeutic monitoring and clinical decision making. MATERIALS AND METHODS: In this single-center study, 201 treatment-naïve patients with biopsy-proven NHL (50 diffuse large B-cell lymphoma [DLBCL], 51 mantle cell lymphoma [MCL], 49 follicular lymphoma [FL], and 51 chronic lymphocytic leukemia [CLL]) and 39 treatment-naïve non-small cell lung cancer patients with positron emission tomography (PET)/computed tomography (CT)-confirmed healthy axillary lymph nodes (LNs) were retrospectively analyzed. Three-dimensional (3D) segmentation and radiomic analysis of pathologically enlarged nodes (n = 1,628) were performed on contrast-enhanced CT scans, including healthy LNs as references. Feature selection was performed using a random forest (RF) classifier. Multiclass Classifier was performed using a Light Gradient Boosting Machine (LGBM) classifier for lymphoma subtype classification. RESULTS: Performance to classify lymphoma from non-lymphoma and lymphoma subtypes was as follows: lymphoma vs. non-lymphoma: area under the curve (AUC) = 0.999; MCL vs. other NHL: AUC = 0.997; DLBCL vs. other NHL: AUC = 0.971; CLL vs. other NHL: AUC = 0.956; FL vs. other NHL: AUC = 0.892. CONCLUSION: Radiomics combined with multiclass machine learning enables highly accurate, non-invasive differentiation of the major NHL subtypes on routine contrast-enhanced CT. By reliably separating indolent from aggressive phenotypes, this approach lays the groundwork for imaging-genomic models that could streamline biopsy guidance, enhance therapeutic monitoring, and advance precision oncology in lymphoma care.Conducted as a single-centre, retrospective proof-of-concept with internal patient-level cross-validation, these results are promising and form the basis for a prospective multicentre study to confirm generalisability and clinical utility. CLINICAL RELEVANCE STATEMENT: Accurate lymphoma classification is essential for predicting clinical behavior and guiding treatment. Imaging aids in disease staging, with quantitative analysis showing promise in predicting pathology and outcome. We explored machine learning on imaging features for lymphoma classification, thus enhancing clinical decisions.

Automated vehicles need to not only perceive their environment, but also predict the possible future behavior of all detected traffic participants in order to safely navigate in complex scenarios and avoid critical situations, ranging from merging on highways to crossing urban intersections. Due to the availability of datasets with large numbers of recorded trajectories of traffic participants, deep learning based approaches can be used to model the behavior of road users. This paper proposes a convolutional network that operates on rasterized actor-centric images which encode the static and dynamic actor-environment. We predict multiple possible future trajectories for each traffic actor, which include position, velocity, acceleration, orientation, yaw rate and position uncertainty estimates. To make better use of the past movement of the actor, we propose to employ temporal convolutional networks (TCNs) and rely on uncertainties estimated from the previous object tracking stage. We evaluate our approach on the public "Argoverse Motion Forecasting" dataset, on which it won the first prize at the Argoverse Motion Forecasting Challenge, as presented on the NeurIPS 2019 workshop on "Machine Learning for Autonomous Driving".

Abstract In connection with the work of Anscombe, Macpherson, Steinhorn and the present author in [1] we investigate the notion of a multidimensional exact class (R-mec), a special kind of multidimensional asymptotic class (R-mac) with measuring functions that yield the exact sizes of definable sets, not just approximations. We use results about smooth approximation [24] and Lie coordinatization [13] to prove the following result (Theorem 4.6.4), as conjectured by Macpherson: For any countable language $\mathcal {L}$ and any positive integerdthe class $\mathcal {C}(\mathcal {L},d)$ of all finite $\mathcal {L}$ -structures with at mostd4-types is a polynomial exact class in $\mathcal {L}$ , where a polynomial exact class is a multidimensional exact class with polynomial measuring functions.

In this article, we present results obtained from field trials with the Hobbit robotic platform, an assistive, social service robot aiming at enabling prolonged independent living of older adults in their own homes. Our main contribution lies within the detailed results on perceived safety, usability, and acceptance from field trials with autonomous robots in real homes of older users. In these field trials, we studied how 16 older adults (75 plus) lived with autonomously interacting service robots over multiple weeks. Robots have been employed for periods of months previously in home environments for older people, and some have been tested with manipulation abilities, but this is the first time a study has tested a robot in private homes that provided the combination of manipulation abilities, autonomous navigation, and non-scheduled interaction for an extended period of time. This article aims to explore how older adults interact with such a robot in their private homes. Our results show that all users interacted with Hobbit daily, rated most functions as well working, and reported that they believe that Hobbit will be part of future elderly care. We show that Hobbit’s adaptive behavior approach towards the user increasingly eased the interaction between the users and the robot. Our trials reveal the necessity to move into actual users’ homes, as only there, we encounter real-world challenges and demonstrate issues such as misinterpretation of actions during non-scripted human-robot interaction.

Applications that provide location related services need to understand the environment in which humans live such that verbal references and human interaction are possible. We formulate this semantic labelling task as the problem of learning the semantic labels from the perceived 3D structure. In this contribution we propose a batch approach and a novel multi-view frame fusion technique to exploit multiple views for improving the semantic labelling results. The batch approach works offline and is the direct application of an existing single-view method to scene reconstructions with multiple views. The multi-view frame fusion works in an incremental fashion accumulating the single-view results, hence allowing the online multi-view semantic segmentation of single frames and the offline reconstruction of semantic maps. Our experiments show the superiority of the approaches based on our fusion scheme, which leads to a more accurate semantic labelling.

In this paper, we present an efficient semantic segmentation framework for indoor scenes operating on 3D point clouds. We use the results of a Random Forest Classifier to initialize the unary potentials of a densely interconnected Conditional Random Field, for which we learn the parameters for the pairwise potentials from training data. These potentials capture and model common spatial relations between class labels, which can often be observed in indoor scenes. We evaluate our approach on the popular NYU Depth datasets, for which it achieves superior results compared to the current state of the art. Exploiting parallelization and applying an efficient CRF inference method based on mean field approximation, our framework is able to process full resolution Kinect point clouds in half a second on a regular laptop, more than twice as fast as comparable methods.

While navigation based on 2D laser data is well understood, the application of robots at home environments requires seeing more than a slice of the world. RGB-D cameras have been used to perceive the full scenes and solutions exist consuming extensive computing power. We propose a setup with two RGB-D cameras that covers the need for conflicting requirements regarding localization, obstacle avoidance, object search and recognition, and gesture recognition. We show that this setup provides sufficient data to enable navigation at homes and we present how ROS modules can be configured to use virtual RGB-D scans instead of laser data for operation in real-time (10Hz). Finally, we present first results of exploiting this versatile setup for a home service robot that picks up things from the floor to prevent potential falls of its future users.

We generalize the network flow formulation for multiobject tracking to multi-camera setups. In the past, reconstruction of multi-camera data was done as a separate extension. In this work, we present a combined maximum a posteriori (MAP) formulation, which jointly models multicamera reconstruction as well as global temporal data association. A flow graph is constructed, which tracks objects in 3D world space. The multi-camera reconstruction can be efficiently incorporated as additional constraints on the flow graph without making the graph unnecessarily large. The final graph is efficiently solved using binary linear programming. On the PETS 2009 dataset we achieve results that significantly exceed the current state of the art.