Logo: to the web site of Uppsala University

Computed tomography has revolutionised the study of the internal three-dimensional structure of fossils. Historically, fossils typically spent years in preparation to be freed from the enclosing rock. Now, X-ray and synchrotron tomography reveal structures that are otherwise invisible, and data acquisition can be fast. However, manual segmentation of these 3D volumes can still take months to years. This is especially challenging for resource-poor teams, as scanning may be free, but the computing power and (AI-assisted) segmentation software required to handle the resulting large data sets are complex to use and expensive.

Here we present a free, browser-based segmentation tool that reduces computational overhead by splitting volumes into small chunks, allowing processing on low-memory, inexpensive hardware. Our tool also speeds up collaborative ground-truth generation and 3D visualisation, all in-browser. We developed and evaluated our pipeline on various open-data scans of differing contrast, resolution, textural complexity, and size. Our tool successfully isolated the Thrinaxodon and Broomistega pair from an Early Triassic burrow. It isolated cranial bones from the Cretaceous acipenseriform Parapsephurus willybemisi on both 45.53 µm and 13.67 µm resolution (voxel size) scanning data. We also isolated bones of the Middle Triassic sauropterygian Nothosaurus and a challenging scan of a squamate embryo inside an egg dating back to the Early Cretaceous. Our tool reliably reproduces expert-supervised segmentation at a fraction of the time and cost, offering greater accessibility than existing tools. Beyond the online tool, all our code is open source, enabling contributions from the palaeontology community to further this emerging machine-learning ecosystem.

Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden properties of the observations. System identification learns mathematical descriptions of dynamic systems from input-output data and can thus benefit from the advances of deep neural networks to enrich the possible range of models to choose from. For this reason, we provide a survey of deep learning from a system identification perspective. We cover a wide spectrum of topics to enable researchers to understand the methods, providing rigorous practical and theoretical insights into the benefits and challenges of using them. The main aim of the identified model is to predict new data from previous observations. This can be achieved with different deep learning-based modelling techniques and we discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks. Their parameters have to be estimated from past data to optimize the prediction performance. For this purpose, we discuss a specific set of first-order optimization tools that have emerged as efficient. The survey then draws connections to the well-studied area of kernel-based methods. They control the data fit by regularization terms that penalize models not in line with prior assumptions. We illustrate how to cast them in deep architectures to obtain deep kernel-based methods. The success of deep learning also resulted in surprising empirical observations, like the counter-intuitive behaviour of models with many parameters. We discuss the role of overparameterized models, including their connection to kernels, as well as implicit regularization mechanisms which affect generalization, specifically the interesting phenomena of benign overfitting and double-descent. Finally, we highlight numerical, computational and software aspects in the area with the help of applied examples.

Universitet och högskolor spelar en viktig roll i samhällsutvecklingen, inte minst i samspel med näringslivet. Samverkan mellan akademi och näringsliv innebär en möjlighet för företag att ta del av den senaste forskningen och utveckla sina verksamheter genom forskningsbaserad kunskap. På samma sätt kan universitetens forskning bli mer relevant i samarbete med näringslivet. En vanlig form för samverkan av detta slag är företagsdoktorander, ibland också kallade industridoktorander, det vill säga att en anställd vid ett företag blir doktorand vid ett lärosäte.

Idag utgör företagsdoktorander en stor del av de forskare som har en fot både i näringslivet och i akademin. Andelen företagsdoktorander har ökat under de senaste 15 åren. Många företag och lärosäten skulle dock vilja öka omfattningen av programmen samverkansprogrammen ytterligare, men hindras till följd av brist på finansiering och komplexa avtal. av juridiska svårigheter i avtalsförhandlingarna. En viktig förutsättning för samverkan är att den är varaktig och organiserad. Det är därför problematiskt att det finns svårigheter med upprättande av anställningsavtal, både vad gäller gemensamma regelverk för hur avtalen bör reglerasatt få avtal och hur finansieringen ska lösasfinansiering på plats.

The current state-of-the art motion planners for mobile robots typically do not consider the future movement of moving obstacles. Instead they work by rapid replanning, which makes them reactively adapt to any changes in the environment. This can result in a sub-optimal behavior, which we address in this work by proposing a predictive motion planner that integrates motion predictions into all planning steps. We demonstrate the validity of our approach by evaluating our proposed planner in a dynamic environment where the robot moves slower than the moving obstacles. We benchmark our predictive planner with a reactive planning approach and observe better performance, both in avoiding collisions and maintaining the robots position in the goal region.

Vision-language models such as CLIP have shown great impact on diverse downstream tasks for zero-shot or label-free predictions. However, when it comes to low-level vision such as image restoration their performance deteriorates dramatically due to corrupted inputs. In this paper, we present a degradation-aware vision-language model (DA-CLIP) to better transfer pretrained vision-language models to low-level vision tasks as a universal framework for image restoration. More specifically, DA-CLIP trains an additional controller that adapts the fixed CLIP image encoder to predict high-quality feature embeddings. By integrating the embedding into an image restoration network via cross-attention, we are able to pilot the model to learn a high-fidelity image reconstruction. The controller itself will also output a degradation feature that matches the real corruptions of the input, yielding a natural classifier for different degradation types. In addition, we construct a mixed degradation dataset with synthetic captions for DA-CLIP training. Our approach advances state-of-the-art performance on both degradation-specific and unified image restoration tasks, showing a promising direction of prompting image restoration with large-scale pretrained vision-language models. Our code is available at https://github. com/Algolzw/daclip-uir.

Imbalances in electrolyte concentrations can have severe consequences, but accurate and accessible measurements could improve patient outcomes. The current measurement method based on blood tests is accurate but invasive and time-consuming and is often unavailable for example in remote locations or an ambulance setting. In this paper, we explore the use of deep neural networks (DNNs) for regression tasks to accurately predict continuous electrolyte concentrations from electrocardiograms (ECGs), a quick and widely adopted tool. We analyze our DNN models on a novel dataset of over 290,000 ECGs across four major electrolytes and compare their performance with traditional machine learning models. For improved understanding, we also study the full spectrum from continuous predictions to a binary classification of extreme concentration levels. Finally, we investigate probabilistic regression approaches and explore uncertainty estimates for enhanced clinical usefulness. Our results show that DNNs outperform traditional models but model performance varies significantly across different electrolytes. While discretization leads to good classification performance, it does not address the original problem of continuous concentration level prediction. Probabilistic regression has practical potential, but our uncertainty estimates are not perfectly calibrated. Our study is therefore a first step towards developing an accurate and reliable ECG-based method for electrolyte concentration level prediction—a method with high potential impact within multiple clinical scenarios.

Uncertainty estimation is a necessary component when implementing AI in high-risk settings, such as autonomous cars, medicine, or insurances. Large Language Models (LLMs) have seen a surge in popularity in recent years, but they are subject to hallucinations, which may cause serious harm in high-risk settings. Despite their success, LLMs are expensive to train and run: they need a large amount of computations and memory, preventing the use of ensembling methods in practice. In this work, we present a novel method that allows for fast and memory-friendly training of LLM ensembles. We show that the resulting ensembles can detect hallucinations and are a viable approach in practice as only one GPU is needed for training and inference.

Background

In neurointensive care, increased intracranial pressure (ICP) is a feared secondary brain insult in traumatic brain injury (TBI). A system that predicts ICP insults before they emerge may facilitate early optimization of the physiology, which may in turn lead to stopping the predicted ICP insult from occurring. The aim of this study was to evaluate the performance of different artificial intelligence models in predicting the risk of ICP insults.

Methods

The models were trained to predict risk of ICP insults starting within 30 min, using the Uppsala high frequency TBI dataset. A restricted dataset consisting of only monitoring data were used, and an unrestricted dataset using monitoring data as well as clinical data, demographic data, and radiological evaluations was used. Four different model classes were compared: Gaussian process regression, logistic regression, random forest classifier, and Extreme Gradient Boosted decision trees (XGBoost).

Results

Six hundred and two patients with TBI were included (total monitoring 138,411 h). On the task of predicting upcoming ICP insults, the Gaussian process regression model performed similarly on the Uppsala high frequency TBI dataset (sensitivity 93.2%, specificity 93.9%, area under the receiver operating characteristic curve [AUROC] 98.3%), as in earlier smaller studies. Using a more flexible model (XGBoost) resulted in a comparable performance (sensitivity 93.8%, specificity 94.6%, AUROC 98.7%). Adding more clinical variables and features further improved the performance of the models slightly (XGBoost: sensitivity 94.1%, specificity of 94.6%, AUROC 98.8%).

Conclusions

Artificial intelligence models have potential to become valuable tools for predicting ICP insults in advance during neurointensive care. The fact that common off-the-shelf models, such as XGBoost, performed well in predicting ICP insults opens new possibilities that can lead to faster advances in the field and earlier clinical implementations.