使用Kellgren-Lawence分级系统在放射线照片中评估放射性骨关节炎的严重程度评估放射科医生的表现，是放射学家的表现。根据Kellgren-Lawence分级系统，开发一种自动化的基于深度学习的算法，该算法使用膝盖X光片的后侧（PA）和侧面（LAT）视图来评估膝关节骨关节炎的严重程度。我们使用了来自多中心骨关节炎研究的2802名患者的9739例检查的数据集（大多数）。该数据集分为2040名患者的训练集，259例患者的验证和503例患者的测试组。一种新型的基于深度学习的方法用于评估膝关节OA分为两个步骤：（1）图像中膝关节的定位，（2）根据KL分级系统进行分类。我们的方法同时使用PA和LAT视图作为模型的输入。将算法生成的分数与整个测试集的最多数据集中提供的等级以及我们机构中5位放射科医生提供的成绩进行了比较。与大多数数据集中提供的评分相比，该模型在整个测试集上获得了71.90％的多级准确性。该组的二次加权KAPPA系数为0.9066。我们机构的所有放射科医生对研究的平均二次加权Kappa为0.748。我们机构的算法和放射科医生之间的平均二次加权Kappa为0.769。所提出的模型表明，KL分类与MSK放射科医生的等效性，但显然可重复性。我们的模型还与我们机构的放射科医生同意与放射科医生相同的程度。该算法可用于提供膝关节炎严重程度的可重复评估。

膝关节X射线上的膝盖骨关节炎（KOA）的评估是使用总膝关节置换术的中心标准。但是，该评估遭受了不精确的标准，并且读取器间的可变性非常高。对KOA严重性的算法，自动评估可以通过提高其使用的适当性来改善膝盖替代程序的总体结果。我们提出了一种基于深度学习的新型五步算法，以自动从X光片后验（PA）视图对KOA进行评级：（1）图像预处理（2）使用Yolo V3-tiny模型，图像在图像中定位膝关节， （3）使用基于卷积神经网络的分类器对骨关节炎的严重程度进行初步评估，（4）关节分割和关节空间狭窄（JSN）的计算（JSN）和（5），JSN和最初的结合评估确定最终的凯尔格伦法律（KL）得分。此外，通过显示用于进行评估的分割面具，我们的算法与典型的“黑匣子”深度学习分类器相比表现出更高的透明度。我们使用我们机构的两个公共数据集和一个数据集进行了全面的评估，并表明我们的算法达到了最先进的性能。此外，我们还从机构中的多个放射科医生那里收集了评分，并表明我们的算法在放射科医生级别进行。该软件已在https://github.com/maciejmazurowowski/osteoarthitis-classification上公开提供。

Due to the environmental impacts caused by the construction industry, repurposing existing buildings and making them more energy-efficient has become a high-priority issue. However, a legitimate concern of land developers is associated with the buildings' state of conservation. For that reason, infrared thermography has been used as a powerful tool to characterize these buildings' state of conservation by detecting pathologies, such as cracks and humidity. Thermal cameras detect the radiation emitted by any material and translate it into temperature-color-coded images. Abnormal temperature changes may indicate the presence of pathologies, however, reading thermal images might not be quite simple. This research project aims to combine infrared thermography and machine learning (ML) to help stakeholders determine the viability of reusing existing buildings by identifying their pathologies and defects more efficiently and accurately. In this particular phase of this research project, we've used an image classification machine learning model of Convolutional Neural Networks (DCNN) to differentiate three levels of cracks in one particular building. The model's accuracy was compared between the MSX and thermal images acquired from two distinct thermal cameras and fused images (formed through multisource information) to test the influence of the input data and network on the detection results.

Rapid advancements in collection and dissemination of multi-platform molecular and genomics data has resulted in enormous opportunities to aggregate such data in order to understand, prevent, and treat human diseases. While significant improvements have been made in multi-omic data integration methods to discover biological markers and mechanisms underlying both prognosis and treatment, the precise cellular functions governing these complex mechanisms still need detailed and data-driven de-novo evaluations. We propose a framework called Functional Integrative Bayesian Analysis of High-dimensional Multiplatform Genomic Data (fiBAG), that allows simultaneous identification of upstream functional evidence of proteogenomic biomarkers and the incorporation of such knowledge in Bayesian variable selection models to improve signal detection. fiBAG employs a conflation of Gaussian process models to quantify (possibly non-linear) functional evidence via Bayes factors, which are then mapped to a novel calibrated spike-and-slab prior, thus guiding selection and providing functional relevance to the associations with patient outcomes. Using simulations, we illustrate how integrative methods with functional calibration have higher power to detect disease related markers than non-integrative approaches. We demonstrate the profitability of fiBAG via a pan-cancer analysis of 14 cancer types to identify and assess the cellular mechanisms of proteogenomic markers associated with cancer stemness and patient survival.

Recent increases in the computational demands of deep neural networks (DNNs) have sparked interest in efficient deep learning mechanisms, e.g., quantization or pruning. These mechanisms enable the construction of a small, efficient version of commercial-scale models with comparable accuracy, accelerating their deployment to resource-constrained devices. In this paper, we study the security considerations of publishing on-device variants of large-scale models. We first show that an adversary can exploit on-device models to make attacking the large models easier. In evaluations across 19 DNNs, by exploiting the published on-device models as a transfer prior, the adversarial vulnerability of the original commercial-scale models increases by up to 100x. We then show that the vulnerability increases as the similarity between a full-scale and its efficient model increase. Based on the insights, we propose a defense, $similarity$-$unpairing$, that fine-tunes on-device models with the objective of reducing the similarity. We evaluated our defense on all the 19 DNNs and found that it reduces the transferability up to 90% and the number of queries required by a factor of 10-100x. Our results suggest that further research is needed on the security (or even privacy) threats caused by publishing those efficient siblings.

The highest grossing media franchise of all times, with over \$90 billion in total revenue, is Pokemon. The video games belong to the class of Japanese Role Playing Games (J-RPG). Developing a powerful AI agent for these games is very hard because they present big challenges to MinMax, Monte Carlo Tree Search and statistical Machine Learning, as they are vastly different from the well explored in AI literature games. An AI agent for one of these games means significant progress in AI agents for the entire class. Further, the key principles of such work can hopefully inspire approaches to several domains that require excellent teamwork under conditions of extreme uncertainty, including managing a team of doctors, robots or employees in an ever changing environment, like a pandemic stricken region or a war-zone. In this paper we first explain the mechanics of the game and we perform a game analysis. We continue by proposing unique AI algorithms based on our understanding that the two biggest challenges in the game are keeping a balanced team and dealing with three sources of uncertainty. Later on, we describe why evaluating the performance of such agents is challenging and we present the results of our approach. Our AI agent performed significantly better than all previous attempts and peaked at the 33rd place in the world, in one of the most popular battle formats, while running on only 4 single socket servers.

Unlike tabular data, features in network data are interconnected within a domain-specific graph. Examples of this setting include gene expression overlaid on a protein interaction network (PPI) and user opinions in a social network. Network data is typically high-dimensional (large number of nodes) and often contains outlier snapshot instances and noise. In addition, it is often non-trivial and time-consuming to annotate instances with global labels (e.g., disease or normal). How can we jointly select discriminative subnetworks and representative instances for network data without supervision? We address these challenges within an unsupervised framework for joint subnetwork and instance selection in network data, called UISS, via a convex self-representation objective. Given an unlabeled network dataset, UISS identifies representative instances while ignoring outliers. It outperforms state-of-the-art baselines on both discriminative subnetwork selection and representative instance selection, achieving up to 10% accuracy improvement on all real-world data sets we use for evaluation. When employed for exploratory analysis in RNA-seq network samples from multiple studies it produces interpretable and informative summaries.

In this paper we present TruFor, a forensic framework that can be applied to a large variety of image manipulation methods, from classic cheapfakes to more recent manipulations based on deep learning. We rely on the extraction of both high-level and low-level traces through a transformer-based fusion architecture that combines the RGB image and a learned noise-sensitive fingerprint. The latter learns to embed the artifacts related to the camera internal and external processing by training only on real data in a self-supervised manner. Forgeries are detected as deviations from the expected regular pattern that characterizes each pristine image. Looking for anomalies makes the approach able to robustly detect a variety of local manipulations, ensuring generalization. In addition to a pixel-level localization map and a whole-image integrity score, our approach outputs a reliability map that highlights areas where localization predictions may be error-prone. This is particularly important in forensic applications in order to reduce false alarms and allow for a large scale analysis. Extensive experiments on several datasets show that our method is able to reliably detect and localize both cheapfakes and deepfakes manipulations outperforming state-of-the-art works. Code will be publicly available at https://grip-unina.github.io/TruFor/

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large version, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model's inferences in question answering. We then test this notion by observing a model's behavior on answering questions about a story after performing two novel semantic interventions -- deletion intervention and negation intervention. While transformer models achieve high performance on standard question answering tasks, we show that they fail to be semantically faithful once we perform these interventions for a significant number of cases (~50% for deletion intervention, and ~20% drop in accuracy for negation intervention). We then propose an intervention-based training regime that can mitigate the undesirable effects for deletion intervention by a significant margin (from ~50% to ~6%). We analyze the inner-workings of the models to better understand the effectiveness of intervention-based training for deletion intervention. But we show that this training does not attenuate other aspects of semantic unfaithfulness such as the models' inability to deal with negation intervention or to capture the predicate-argument structure of texts. We also test InstructGPT, via prompting, for its ability to handle the two interventions and to capture predicate-argument structure. While InstructGPT models do achieve very high performance on predicate-argument structure task, they fail to respond adequately to our deletion and negation interventions.

From smoothly pursuing moving objects to rapidly shifting gazes during visual search, humans employ a wide variety of eye movement strategies in different contexts. While eye movements provide a rich window into mental processes, building generative models of eye movements is notoriously difficult, and to date the computational objectives guiding eye movements remain largely a mystery. In this work, we tackled these problems in the context of a canonical spatial planning task, maze-solving. We collected eye movement data from human subjects and built deep generative models of eye movements using a novel differentiable architecture for gaze fixations and gaze shifts. We found that human eye movements are best predicted by a model that is optimized not to perform the task as efficiently as possible but instead to run an internal simulation of an object traversing the maze. This not only provides a generative model of eye movements in this task but also suggests a computational theory for how humans solve the task, namely that humans use mental simulation.