Stride

D. Turner, A. Ricciuto, Ayanna E. Lewis, F. D'amico, J. Dhaliwal, A. Griffiths, D. Bettenworth, W. Sandborn, B. Sands, W. Reinisch, J. Schölmerich, W. Bemelman, S. Danese, J. Mary, D. Rubin, J. Colombel, L. Peyrin-Biroulet, I. Dotan, M. Abreu, A. Dignass

BACKGROUND The Selecting Therapeutic Targets in Inflammatory Bowel Disease (STRIDE) initiative of the International Organization for the Study of Inflammatory Bowel Diseases (IOIBD) has proposed treatment-targets in 2015 for adult IBD patients. We aimed to update the original STRIDE statements for incorporating treatment targets in both adult and pediatric IBD. METHODS Based on a systematic review of the literature and iterative surveys of 89 IOIBD members, recommendations were drafted and modified in two surveys and two voting rounds. Consensus was reached if ≥75% of participants scored the recommendation as 7-10 on a 10-point rating scale. RESULTS In the systematic-review, 11,278 manuscripts were screened, of which 435 were included. The first IOIBD survey (n=39 on Crohn's Disease (CD) and n=36 on ulcerative colitis (UC)) identified the following targets as most important: clinical response and remission, endoscopic healing, and normalization of C-reactive protein/erythrocyte sedimentation rate and calprotectin. Fifteen recommendations were identified, of which 13 were endorsed (n=70). STRIDE-II confirmed STRIDE-I long-term targets of clinical remission and endoscopic healing and added absence of disability, restoration of quality of life and normal growth in children. Symptomatic relief and normalization of serum and fecal markers have been determined as short-term targets. Transmural healing in CD and histological healing in UC are not formal targets but should be assessed as measures of the remission depth. CONCLUSIONS STRIDE-II encompasses evidence- and consensus-based recommendations for treat-to-target strategies in adults and children with IBD. This framework should be adapted to individual patients and local resources to improve outcomes.

L. Peyrin-Biroulet, W. Sandborn, B. Sands, W. Reinisch, W. Reinisch, W. Bemelman, R. Bryant, G. D'Haens, I. Dotan, M. Dubinsky, B. Feagan, G. Fiorino, R. Gearry, S. Krishnareddy, P. Lakatos, E. Loftus, P. Marteau, P. Munkholm, T. Murdoch, I. Ordás, R. Panaccione, R. Riddell, J. Ruel, D. Rubin, M. Samaan, C. Siegel, M. Silverberg, J. Stoker, S. Schreiber, S. Travis, G. V. Assche, G. V. Assche, S. Danese, J. Panés, G. Bouguen, S. O’Donnell, B. Pariente, S. Winer, S. Hanauer, J. Colombel

Lue Fan, Ziqi Pang, Tianyuan Zhang, Yu-Xiong Wang, Hang Zhao, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Over-looking this difference, many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. In this paper, we start by rethinking how such multi-stride stereotype affects the LiDAR-based 3D object detectors. Our experiments point out that the downsampling operations bring few advantages, and lead to inevitable information loss. To remedy this issue, we propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network. Armed with transformers, our method addresses the problem of insufficient receptive field in single-stride architectures. It also cooperates well with the sparsity of point clouds and naturally avoids expensive computation. Eventually, our SST achieves state-of-the-art results on the large-scale Waymo Open Dataset. It is worth mentioning that our method can achieve exciting performance (83.8 LEVEL_1 AP on validation split) on small object (pedestrian) detection due to the characteristic of single stride. Our codes will be public soon.

Dongqing Sun, Zhaoyang Liu, Taiwen Li, Qiu Wu, Chenfei Wang

The recent advances in spatial transcriptomics have brought unprecedented opportunities to understand the cellular heterogeneity in the spatial context. However, the current limitations of spatial technologies hamper the exploration of cellular localizations and interactions at single-cell level. Here, we present spatial transcriptomics deconvolution by topic modeling (STRIDE), a computational method to decompose cell types from spatial mixtures by leveraging topic profiles trained from single-cell transcriptomics. STRIDE accurately estimated the cell-type proportions and showed balanced specificity and sensitivity compared to existing methods. We demonstrate STRIDE’s utility by applying it to different spatial platforms and biological systems. Deconvolution by STRIDE not only mapped rare cell types to spatial locations but also improved the identification of spatial localized genes and domains. Moreover, topics discovered by STRIDE were associated with cell-type-specific functions, and could be further used to integrate successive sections and reconstruct the three-dimensional architecture of tissues. Taken together, STRIDE is a versatile and extensible tool for integrated analysis of spatial and single-cell transcriptomics and is publicly available at https://github.com/wanglabtongji/STRIDE.

Lara Mauri, E. Damiani

The application of emerging technologies, such as Artificial Intelligence (AI), entails risks that need to be addressed to ensure secure and trustworthy socio-technical infrastructures. Machine Learning (ML), the most developed subfield of AI, allows for improved decision-making processes. However, ML models exhibit specific vulnerabilities that conventional IT systems are not subject to. As systems incorporating ML components become increasingly pervasive, the need to provide security practitioners with threat modeling tailored to the specific AI-ML pipeline is of paramount importance. Currently, there exist no well-established approach accounting for the entire ML life-cycle in the identification and analysis of threats targeting ML techniques. In this paper, we propose an asset-centered methodology—STRIDE-AI—for assessing the security of AI-ML-based systems. We discuss how to apply the FMEA process to identify how assets generated and used at different stages of the ML life-cycle may fail. By adapting Microsoft’s STRIDE approach to the AI-ML domain, we map potential ML failure modes to threats and security properties these threats may endanger. The proposed methodology can assist ML practitioners in choosing the most effective security controls to protect ML assets. We illustrate STRIDE-AI with the help of a real-world use case selected from the TOREADOR H2020 project.