Search

Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the $\mathrm{AUROC}$ in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, interpretability, and flexibility, and show how current approaches fail to meet them. We propose the Area under the Generalized Risk Coverage curve ($\mathrm{AUGRC}$), which meets all requirements and can be directly interpreted as the average risk of undetected failures. We empirically demonstrate the relevance of $\mathrm{AUGRC}$ on a comprehensive benchmark spanning 6 data sets and 13 confidence scoring functions. We find that the proposed metric substantially changes metric rankings on 5 out of the 6 data sets.

In the presence of unmeasured heterogeneity, the hazard ratio for exposure has a complex causal interpretation. To address this, accelerated failure time (AFT) models, which assess the effect on the survival time ratio scale, are often suggested as a better alternative. AFT models also allow for straightforward confounder adjustment. In this work, we formalize the causal interpretation of the acceleration factor in AFT models using structural causal models and data under independent censoring. We prove that the acceleration factor is a valid causal effect measure, even in the presence of frailty and treatment effect heterogeneity. Through simulations, we show that the acceleration factor better captures the causal effect than the hazard ratio when both AFT and proportional hazards models apply. Additionally, we extend the interpretation to systems with time-dependent acceleration factors, revealing the challenge of distinguishing between a time-varying homogeneous effect and unmeasured heterogeneity. While the causal interpretation of acceleration factors is promising, we caution practitioners about potential challenges in estimating these factors in the presence of effect heterogeneity.

In realistic medical settings, the data are often inherently long-tailed, with most samples concentrated in a few classes and a long tail of rare classes, usually containing just a few samples. This distribution presents a significant challenge because rare conditions are critical to detect and difficult to classify due to limited data. In this paper, rather than attempting to classify rare classes, we aim to detect these as out-of-distribution data reliably. We leverage low-rank adaption (LoRA) and diffusion guidance to generate targeted synthetic data for the detection problem. We significantly improve the OOD detection performance on a challenging histopathological task with only ten samples per tail class without losing classification accuracy on the head classes.

Medical image classification in radiology faces significant challenges, particularly in generalizing to unseen pathologies. In contrast, CLIP offers a promising solution by leveraging multimodal learning to improve zero-shot classification performance. However, in the medical domain, lesions can be small and might not be well represented in the embedding space. Therefore, in this paper, we explore the potential of visual prompt engineering to enhance the capabilities of Vision Language Models (VLMs) in radiology. Leveraging BiomedCLIP, trained on extensive biomedical image-text pairs, we investigate the impact of embedding visual markers directly within radiological images to guide the model's attention to critical regions. Our evaluation on the JSRT dataset, focusing on lung nodule malignancy classification, demonstrates that incorporating visual prompts $\unicode{x2013}$ such as arrows, circles, and contours $\unicode{x2013}$ significantly improves classification metrics including AUROC, AUPRC, F1 score, and accuracy. Moreover, the study provides attention maps, showcasing enhanced model interpretability and focus on clinically relevant areas. These findings underscore the efficacy of visual prompt engineering as a straightforward yet powerful approach to advance VLM performance in medical image analysis., Comment: Accepted at ECCV 2024 Workshop on Emergent Visual Abilities and Limits of Foundation Models

Robust semantic segmentation of intraoperative image data holds promise for enabling automatic surgical scene understanding and autonomous robotic surgery. While model development and validation are primarily conducted on idealistic scenes, geometric domain shifts, such as occlusions of the situs, are common in real-world open surgeries. To close this gap, we (1) present the first analysis of state-of-the-art (SOA) semantic segmentation models when faced with geometric out-of-distribution (OOD) data, and (2) propose an augmentation technique called "Organ Transplantation", to enhance generalizability. Our comprehensive validation on six different OOD datasets, comprising 600 RGB and hyperspectral imaging (HSI) cubes from 33 pigs, each annotated with 19 classes, reveals a large performance drop in SOA organ segmentation models on geometric OOD data. This performance decline is observed not only in conventional RGB data (with a dice similarity coefficient (DSC) drop of 46 %) but also in HSI data (with a DSC drop of 45 %), despite the richer spectral information content. The performance decline increases with the spatial granularity of the input data. Our augmentation technique improves SOA model performance by up to 67 % for RGB data and 90 % for HSI data, achieving performance at the level of in-distribution performance on real OOD test data. Given the simplicity and effectiveness of our augmentation method, it is a valuable tool for addressing geometric domain shifts in surgical scene segmentation, regardless of the underlying model. Our code and pre-trained models are publicly available at https://github.com/IMSY-DKFZ/htc., Comment: Silvia Seidlitz and Jan Sellner contributed equally

Competing risks models can involve more than one time scale. A relevant example is the study of mortality after a cancer diagnosis, where time since diagnosis but also age may jointly determine the hazards of death due to different causes. Multiple time scales have rarely been explored in the context of competing events. Here, we propose a model in which the cause-specific hazards vary smoothly over two times scales. It is estimated by two-dimensional $P$-splines, exploiting the equivalence between hazard smoothing and Poisson regression. The data are arranged on a grid so that we can make use of generalized linear array models for efficient computations. The R-package TwoTimeScales implements the model. As a motivating example we analyse mortality after diagnosis of breast cancer and we distinguish between death due to breast cancer and all other causes of death. The time scales are age and time since diagnosis. We use data from the Surveillance, Epidemiology and End Results (SEER) program. In the SEER data, age at diagnosis is provided with a last open-ended category, leading to coarsely grouped data. We use the two-dimensional penalised composite link model to ungroup the data before applying the competing risks model with two time scales., Comment: 36 pages, 9 figures, 2 tables

Accurate assessment of lymph node size in 3D CT scans is crucial for cancer staging, therapeutic management, and monitoring treatment response. Existing state-of-the-art segmentation frameworks in medical imaging often rely on fully annotated datasets. However, for lymph node segmentation, these datasets are typically small due to the extensive time and expertise required to annotate the numerous lymph nodes in 3D CT scans. Weakly-supervised learning, which leverages incomplete or noisy annotations, has recently gained interest in the medical imaging community as a potential solution. Despite the variety of weakly-supervised techniques proposed, most have been validated only on private datasets or small publicly available datasets. To address this limitation, the Mediastinal Lymph Node Quantification (LNQ) challenge was organized in conjunction with the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023). This challenge aimed to advance weakly-supervised segmentation methods by providing a new, partially annotated dataset and a robust evaluation framework. A total of 16 teams from 5 countries submitted predictions to the validation leaderboard, and 6 teams from 3 countries participated in the evaluation phase. The results highlighted both the potential and the current limitations of weakly-supervised approaches. On one hand, weakly-supervised approaches obtained relatively good performance with a median Dice score of $61.0\%$. On the other hand, top-ranked teams, with a median Dice score exceeding $70\%$, boosted their performance by leveraging smaller but fully annotated datasets to combine weak supervision and full supervision. This highlights both the promise of weakly-supervised methods and the ongoing need for high-quality, fully annotated data to achieve higher segmentation performance., Comment: Submitted to MELBA

With sepsis remaining a leading cause of mortality, early identification of septic patients and those at high risk of death is a challenge of high socioeconomic importance. The driving hypothesis of this study was that hyperspectral imaging (HSI) could provide novel biomarkers for sepsis diagnosis and treatment management due to its potential to monitor microcirculatory alterations. We conducted a comprehensive study involving HSI data of the palm and fingers from more than 480 patients on the day of their intensive care unit (ICU) admission. The findings demonstrate that HSI measurements can predict sepsis with an area under the receiver operating characteristic curve (AUROC) of 0.80 (95 % confidence interval (CI) [0.76; 0.84]) and mortality with an AUROC of 0.72 (95 % CI [0.65; 0.79]). The predictive performance improves substantially when additional clinical data is incorporated, leading to an AUROC of up to 0.94 (95 % CI [0.92; 0.96]) for sepsis and 0.84 (95 % CI [0.78; 0.89]) for mortality. We conclude that HSI presents novel imaging biomarkers for the rapid, non-invasive prediction of sepsis and mortality, suggesting its potential as an important modality for guiding diagnosis and treatment., Comment: Markus A. Weigand, Lena Maier-Hein and Maximilian Dietrich contributed equally

Measuring the similarity of different representations of neural architectures is a fundamental task and an open research challenge for the machine learning community. This paper presents the first comprehensive benchmark for evaluating representational similarity measures based on well-defined groundings of similarity. The representational similarity (ReSi) benchmark consists of (i) six carefully designed tests for similarity measures, (ii) 23 similarity measures, (iii) eleven neural network architectures, and (iv) six datasets, spanning over the graph, language, and vision domains. The benchmark opens up several important avenues of research on representational similarity that enable novel explorations and applications of neural architectures. We demonstrate the utility of the ReSi benchmark by conducting experiments on various neural network architectures, real world datasets and similarity measures. All components of the benchmark are publicly available and thereby facilitate systematic reproduction and production of research results. The benchmark is extensible, future research can build on and further expand it. We believe that the ReSi benchmark can serve as a sound platform catalyzing future research that aims to systematically evaluate existing and explore novel ways of comparing representations of neural architectures., Comment: Feedback welcome! Code and data at https://github.com/mklabunde/resi

The application of machine learning in medicine and healthcare has led to the creation of numerous diagnostic and prognostic models. However, despite their success, current approaches generally issue predictions using data from a single modality. This stands in stark contrast with clinician decision-making which employs diverse information from multiple sources. While several multimodal machine learning approaches exist, significant challenges in developing multimodal systems remain that are hindering clinical adoption. In this paper, we introduce a multimodal framework, AutoPrognosis-M, that enables the integration of structured clinical (tabular) data and medical imaging using automated machine learning. AutoPrognosis-M incorporates 17 imaging models, including convolutional neural networks and vision transformers, and three distinct multimodal fusion strategies. In an illustrative application using a multimodal skin lesion dataset, we highlight the importance of multimodal machine learning and the power of combining multiple fusion strategies using ensemble learning. We have open-sourced our framework as a tool for the community and hope it will accelerate the uptake of multimodal machine learning in healthcare and spur further innovation.

Inverse problems, such as accelerated MRI reconstruction, are ill-posed and an infinite amount of possible and plausible solutions exist. This may not only lead to uncertainty in the reconstructed image but also in downstream tasks such as semantic segmentation. This uncertainty, however, is mostly not analyzed in the literature, even though probabilistic reconstruction models are commonly used. These models can be prone to ignore plausible but unlikely solutions like rare pathologies. Building on MRI reconstruction approaches based on diffusion models, we add guidance to the diffusion process during inference, generating two meaningfully diverse reconstructions corresponding to an upper and lower bound segmentation. The reconstruction uncertainty can then be quantified by the difference between these bounds, which we coin the 'uncertainty boundary'. We analyzed the behavior of the upper and lower bound segmentations for a wide range of acceleration factors and found the uncertainty boundary to be both more reliable and more accurate compared to repeated sampling. Code is available at https://github.com/NikolasMorshuis/SGR, Comment: Accepted at DGM4MICCAI 2024

This paper does not describe a novel method. Instead, it studies an essential foundation for reliable benchmarking and ultimately real-world application of AI-based image analysis: generating high-quality reference annotations. Previous research has focused on crowdsourcing as a means of outsourcing annotations. However, little attention has so far been given to annotation companies, specifically regarding their internal quality assurance (QA) processes. Therefore, our aim is to evaluate the influence of QA employed by annotation companies on annotation quality and devise methodologies for maximizing data annotation efficacy. Based on a total of 57,648 instance segmented images obtained from a total of 924 annotators and 34 QA workers from four annotation companies and Amazon Mechanical Turk (MTurk), we derived the following insights: (1) Annotation companies perform better both in terms of quantity and quality compared to the widely used platform MTurk. (2) Annotation companies' internal QA only provides marginal improvements, if any. However, improving labeling instructions instead of investing in QA can substantially boost annotation performance. (3) The benefit of internal QA depends on specific image characteristics. Our work could enable researchers to derive substantially more value from a fixed annotation budget and change the way annotation companies conduct internal QA., Comment: Accepted at ECCV 2024, preprint, Computer Vision, Data Annotation

Coherent phonons, light-induced coherent lattice vibrations in solids, provide a powerful route to engineer structural and electronic degrees of freedom using light. In this manuscript, we formulate an ab initio theory of the displacive excitation of coherent phonons (DECP), the primary mechanism for light-induced structural control in semimetals. Our study - based on the ab initio simulations of the ultrafast electron and coherent-phonon dynamics in presence of electron-phonon interactions - establishes a predictive computational framework for describing the emergence of light-induced structural changes and the ensuing transient band-structure renormalization arising from the DECP mechanism. We validate this framework via a combined theoretical and experimental investigation of coherent phonons in the elemental semimetal antimony. Via a Fourier analysis of time- and angle-resolved photoemission spectroscopy (tr-ARPES) measurements, we retrieve information about transient spectral features and quasiparticle renormalization arising from the coherent A1g phonon as a function of momentum, energy, time, and fluence. The qualitative and quantitative agreement between experiment and theory corroborates the first-principles approach formulated in this study. Besides advancing the fundamental understanding of electron-phonon interactions mediated by coherent phonons, this study opens new opportunities for predictively engineering structural and electronic degrees of freedom in semimetals via the DECP mechanism.

The upcoming 6G mobile communication standard will offer a revolutionary new feature: Integrated sensing and communication (ISAC) reuses mobile communication signals to realize multi-static radar for various applications including localization. Consequently, applied ISAC propagation research necessitates to evolve from classical monostatic radar cross section (RCS) measurement of static targets on to bistatic radar reflectivity characterization of dynamic objects. Here, we introduce our "Bistatic Radar" (BIRA) and antenna measurement facility for bistatic spherical positioning with sub-millimeter accuracy on a diameter of up to 7 m and with almost continuous frequency coverage from 0.7 up to 260 GHz. Currently, BIRA is the only bistatic measurement facility capable of unrestricted ISAC research: In addition to vector network analysis, BIRA employs advanced wideband transceiver technology with an instantaneous bandwidth of up to 4 GHz. These transceivers grant BIRA the unique ability to characterize dynamic targets in both Doppler and range, while also significantly accelerating RCS measurements of static objects., Comment: 9 pages, 8 figures

This paper explores the use of model-based offline reinforcement learning with long model rollouts. While some literature criticizes this approach due to compounding errors, many practitioners have found success in real-world applications. The paper aims to demonstrate that long rollouts do not necessarily result in exponentially growing errors and can actually produce better Q-value estimates than model-free methods. These findings can potentially enhance reinforcement learning techniques., Comment: Accepted at ESANN 2024

Physics-inspired Generative Models (GMs), in particular Diffusion Models (DMs) and Poisson Flow Models (PFMs), enhance Bayesian methods and promise great utility in medical imaging. This review examines the transformative role of such generative methods. First, a variety of physics-inspired GMs, including Denoising Diffusion Probabilistic Models (DDPMs), Score-based Diffusion Models (SDMs), and Poisson Flow Generative Models (PFGMs and PFGM++), are revisited, with an emphasis on their accuracy, robustness as well as acceleration. Then, major applications of physics-inspired GMs in medical imaging are presented, comprising image reconstruction, image generation, and image analysis. Finally, future research directions are brainstormed, including unification of physics-inspired GMs, integration with Vision-Language Models (VLMs), and potential novel applications of GMs. Since the development of generative methods has been rapid, this review will hopefully give peers and learners a timely snapshot of this new family of physics-driven generative models and help capitalize their enormous potential for medical imaging.

Neural networks typically generalize well when fitting the data perfectly, even though they are heavily overparameterized. Many factors have been pointed out as the reason for this phenomenon, including an implicit bias of stochastic gradient descent (SGD) and a possible simplicity bias arising from the neural network architecture. The goal of this paper is to disentangle the factors that influence generalization stemming from optimization and architectural choices by studying random and SGD-optimized networks that achieve zero training error. We experimentally show, in the low sample regime, that overparameterization in terms of increasing width is beneficial for generalization, and this benefit is due to the bias of SGD and not due to an architectural bias. In contrast, for increasing depth, overparameterization is detrimental for generalization, but random and SGD-optimized networks behave similarly, so this can be attributed to an architectural bias. For more information, see https://bias-sgd-or-architecture.github.io ., Comment: Accepted at ICML 2024

In the field of space exploration, floating platforms play a crucial role in scientific investigations and technological advancements. However, controlling these platforms in zero-gravity environments presents unique challenges, including uncertainties and disturbances. This paper introduces an innovative approach that combines Proximal Policy Optimization (PPO) with Model Predictive Control (MPC) in the zero-gravity laboratory (Zero-G Lab) at the University of Luxembourg. This approach leverages PPO's reinforcement learning power and MPC's precision to navigate the complex control dynamics of floating platforms. Unlike traditional control methods, this PPO-MPC approach learns from MPC predictions, adapting to unmodeled dynamics and disturbances, resulting in a resilient control framework tailored to the zero-gravity environment. Simulations and experiments in the Zero-G Lab validate this approach, showcasing the adaptability of the PPO agent. This research opens new possibilities for controlling floating platforms in zero-gravity settings, promising advancements in space exploration., Comment: Pre-print version submitted to 2024 International Conference on Robotics and Automation (ICRA)

Neutrinoless double beta decay is one of the most sensitive probes for new physics beyond the Standard Model of particle physics. One of the isotopes under investigation is $^{136}$Xe, which would double beta decay into $^{136}$Ba. Detecting the single $^{136}$Ba daughter provides a sort of ultimate tool in the discrimination against backgrounds. Previous work demonstrated the ability to perform single atom imaging of Ba atoms in a single-vacancy site of a solid xenon matrix. In this paper, the effort to identify signal from individual barium atoms is extended to Ba atoms in a hexa-vacancy site in the matrix and is achieved despite increased photobleaching in this site. Abrupt fluorescence turn-off of a single Ba atom is also observed. Significant recovery of fluorescence signal lost through photobleaching is demonstrated upon annealing of Ba deposits in the Xe ice. Following annealing, it is observed that Ba atoms in the hexa-vacancy site exhibit antibleaching while Ba atoms in the tetra-vacancy site exhibit bleaching. This may be evidence for a matrix site transfer upon laser excitation. Our findings offer a path of continued research toward tagging of Ba daughters in all significant sites in solid xenon., Comment: 9 pages, 8 figures

Processing histopathological Whole Slide Images (WSI) leads to massive storage requirements for clinics worldwide. Even after lossy image compression during image acquisition, additional lossy compression is frequently possible without substantially affecting the performance of deep learning-based (DL) downstream tasks. In this paper, we show that the commonly used JPEG algorithm is not best suited for further compression and we propose Stain Quantized Latent Compression (SQLC ), a novel DL based histopathology data compression approach. SQLC compresses staining and RGB channels before passing it through a compression autoencoder (CAE ) in order to obtain quantized latent representations for maximizing the compression. We show that our approach yields superior performance in a classification downstream task, compared to traditional approaches like JPEG, while image quality metrics like the Multi-Scale Structural Similarity Index (MS-SSIM) is largely preserved. Our method is online available.

Assessing tumor response to systemic therapies is one of the main applications of PET/CT. Routinely, only a small subset of index lesions out of multiple lesions is analyzed. However, this operator dependent selection may bias the results due to possible significant inter-metastatic heterogeneity of response to therapy. Automated, AI based approaches for lesion tracking hold promise in enabling the analysis of many more lesions and thus providing a better assessment of tumor response. This work introduces a Siamese CNN approach for lesion tracking between PET/CT scans. Our approach is applied on the laborious task of tracking a high number of bone lesions in full-body baseline and follow-up [68Ga]Ga- or [18F]F-PSMA PET/CT scans after two cycles of [177Lu]Lu-PSMA therapy of metastatic castration resistant prostate cancer patients. Data preparation includes lesion segmentation and affine registration. Our algorithm extracts suitable lesion patches and forwards them into a Siamese CNN trained to classify the lesion patch pairs as corresponding or non-corresponding lesions. Experiments have been performed with different input patch types and a Siamese network in 2D and 3D. The CNN model successfully learned to classify lesion assignments, reaching a lesion tracking accuracy of 83 % in its best configuration with an AUC = 0.91. For remaining lesions the pipeline accomplished a re-identification rate of 89 %. We proved that a CNN may facilitate the tracking of multiple lesions in PSMA PET/CT scans. Future clinical studies are necessary if this improves the prediction of the outcome of therapies., Comment: 25 pages, 9 figures, 3 tables

Semantic segmentation is an essential component of medical image analysis research, with recent deep learning algorithms offering out-of-the-box applicability across diverse datasets. Despite these advancements, segmentation failures remain a significant concern for real-world clinical applications, necessitating reliable detection mechanisms. This paper introduces a comprehensive benchmarking framework aimed at evaluating failure detection methodologies within medical image segmentation. Through our analysis, we identify the strengths and limitations of current failure detection metrics, advocating for the risk-coverage analysis as a holistic evaluation approach. Utilizing a collective dataset comprising five public 3D medical image collections, we assess the efficacy of various failure detection strategies under realistic test-time distribution shifts. Our findings highlight the importance of pixel confidence aggregation and we observe superior performance of the pairwise Dice score (Roy et al., 2019) between ensemble predictions, positioning it as a simple and robust baseline for failure detection in medical image segmentation. To promote ongoing research, we make the benchmarking framework available to the community., Comment: This work has been submitted for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Identifying predictive biomarkers, which forecast individual treatment effectiveness, is crucial for personalized medicine and informs decision-making across diverse disciplines. These biomarkers are extracted from pre-treatment data, often within randomized controlled trials, and have to be distinguished from prognostic biomarkers, which are independent of treatment assignment. Our study focuses on the discovery of predictive imaging biomarkers, aiming to leverage pre-treatment images to unveil new causal relationships. Previous approaches relied on labor-intensive handcrafted or manually derived features, which may introduce biases. In response, we present a new task of discovering predictive imaging biomarkers directly from the pre-treatment images to learn relevant image features. We propose an evaluation protocol for this task to assess a model's ability to identify predictive imaging biomarkers and differentiate them from prognostic ones. It employs statistical testing and a comprehensive analysis of image feature attribution. We explore the suitability of deep learning models originally designed for estimating the conditional average treatment effect (CATE) for this task, which previously have been primarily assessed for the precision of CATE estimation, overlooking the evaluation of imaging biomarker discovery. Our proof-of-concept analysis demonstrates promising results in discovering and validating predictive imaging biomarkers from synthetic outcomes and real-world image datasets., Comment: 19 pages, 12 figures

Electron-neutrino charged-current interactions with xenon nuclei were modeled in the nEXO neutrinoless double-beta decay detector (~5-tonne, 90% ${}^{136}$Xe, 10% ${}^{134}$Xe) to evaluate its sensitivity to supernova neutrinos. Predictions for event rates and detectable signatures were modeled using the MARLEY event generator. We find good agreement between MARLEY's predictions and existing theoretical calculations of the inclusive cross sections at supernova neutrino energies. The interactions modeled by MARLEY were simulated within the nEXO simulation framework and were run through an example reconstruction algorithm to determine the detector's efficiency for reconstructing these events. The simulated data, incorporating the detector response, were used to study the ability of nEXO to reconstruct the incident electron-neutrino spectrum and these results were extended to a larger xenon detector of the same isotope enrichment. We estimate that nEXO will be able to observe electron-neutrino interactions with xenon from supernovae as far as 5 to 8 kpc from earth, while the ability to reconstruct incident electron-neutrino spectrum parameters from observed interactions in nEXO is limited to closer supernovae., Comment: 17 pages, 16 figures

The Fine-Gray model for the subdistribution hazard is commonly used for estimating associations between covariates and competing risks outcomes. When there are missing values in the covariates included in a given model, researchers may wish to multiply impute them. Assuming interest lies in estimating the risk of only one of the competing events, this paper develops a substantive-model-compatible multiple imputation approach that exploits the parallels between the Fine-Gray model and the standard (single-event) Cox model. In the presence of right-censoring, this involves first imputing the potential censoring times for those failing from competing events, and thereafter imputing the missing covariates by leveraging methodology previously developed for the Cox model in the setting without competing risks. In a simulation study, we compared the proposed approach to alternative methods, such as imputing compatibly with cause-specific Cox models. The proposed method performed well (in terms of estimation of both subdistribution log hazard ratios and cumulative incidences) when data were generated assuming proportional subdistribution hazards, and performed satisfactorily when this assumption was not satisfied. The gain in efficiency compared to a complete-case analysis was demonstrated in both the simulation study and in an applied data example on competing outcomes following an allogeneic stem cell transplantation. For individual-specific cumulative incidence estimation, assuming proportionality on the correct scale at the analysis phase appears to be more important than correctly specifying the imputation procedure used to impute the missing covariates.

The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to preserve features from all training data during FL is an active area of research. To explore FL methodology, the breast density classification FL challenge was hosted in partnership with the American College of Radiology, Harvard Medical School's Mass General Brigham, University of Colorado, NVIDIA, and the National Institutes of Health National Cancer Institute. Challenge participants were able to submit docker containers capable of implementing FL on three simulated medical facilities, each containing a unique large mammography dataset. The breast density FL challenge ran from June 15 to September 5, 2022, attracting seven finalists from around the world. The winning FL submission reached a linear kappa score of 0.653 on the challenge test data and 0.413 on an external testing dataset, scoring comparably to a model trained on the same data in a central location., Comment: 16 pages, 9 figures

VisionTransformers have been shown to be powerful out-of-distribution detectors for ImageNet-scale settings when finetuned from publicly available checkpoints, often outperforming other model types on popular benchmarks. In this work, we investigate the impact of both the pretraining and finetuning scheme on the performance of ViTs on this task by analyzing a large pool of models. We find that the exact type of pretraining has a strong impact on which method works well and on OOD detection performance in general. We further show that certain training schemes might only be effective for a specific type of out-distribution, but not in general, and identify a best-practice training recipe., Comment: arXiv admin note: text overlap with arXiv:2306.00826

Objective: Federated Learning (FL) enables collaborative model training while keeping data locally. Currently, most FL studies in radiology are conducted in simulated environments due to numerous hurdles impeding its translation into practice. The few existing real-world FL initiatives rarely communicate specific measures taken to overcome these hurdles, leaving behind a significant knowledge gap. Minding efforts to implement real-world FL, there is a notable lack of comprehensive assessment comparing FL to less complex alternatives. Materials & Methods: We extensively reviewed FL literature, categorizing insights along with our findings according to their nature and phase while establishing a FL initiative, summarized to a comprehensive guide. We developed our own FL infrastructure within the German Radiological Cooperative Network (RACOON) and demonstrated its functionality by training FL models on lung pathology segmentation tasks across six university hospitals. We extensively evaluated FL against less complex alternatives in three distinct evaluation scenarios. Results: The proposed guide outlines essential steps, identified hurdles, and proposed solutions for establishing successful FL initiatives conducting real-world experiments. Our experimental results show that FL outperforms less complex alternatives in all evaluation scenarios, justifying the effort required to translate FL into real-world applications. Discussion & Conclusion: Our proposed guide aims to aid future FL researchers in circumventing pitfalls and accelerating translation of FL into radiological applications. Our results underscore the value of efforts needed to translate FL into real-world applications by demonstrating advantageous performance over alternatives, and emphasize the importance of strategic organization, robust management of distributed data and infrastructure in real-world settings.

We consider the K\"ahler-Ricci flow on compact K\"ahler manifolds with semiample canonical bundle and intermediate Kodaira dimension, and show that the flow collapses to a canonical metric on the base of the Iitaka fibration in the locally smooth topology and with bounded Ricci curvature away from the singular fibers. This follows from an asymptotic expansion for the evolving metrics, in the spirit of recent work of the first and third-named authors on collapsing Calabi-Yau metrics, and proves two conjectures of Song and Tian., Comment: 89 pages

Objective Hospitals register information in the electronic health records (EHR) continuously until discharge or death. As such, there is no censoring for in-hospital outcomes. We aimed to compare different dynamic regression modeling approaches to predict central line-associated bloodstream infections (CLABSI) in EHR while accounting for competing events precluding CLABSI. Materials and Methods We analyzed data from 30,862 catheter episodes at University Hospitals Leuven from 2012 and 2013 to predict 7-day risk of CLABSI. Competing events are discharge and death. Static models at catheter onset included logistic, multinomial logistic, Cox, cause-specific hazard, and Fine-Gray regression. Dynamic models updated predictions daily up to 30 days after catheter onset (i.e. landmarks 0 to 30 days), and included landmark supermodel extensions of the static models, separate Fine-Gray models per landmark time, and regularized multi-task learning (RMTL). Model performance was assessed using 100 random 2:1 train-test splits. Results The Cox model performed worst of all static models in terms of area under the receiver operating characteristic curve (AUC) and calibration. Dynamic landmark supermodels reached peak AUCs between 0.741-0.747 at landmark 5. The Cox landmark supermodel had the worst AUCs (<=0.731) and calibration up to landmark 7. Separate Fine-Gray models per landmark performed worst for later landmarks, when the number of patients at risk was low. Discussion and Conclusion Categorical and time-to-event approaches had similar performance in the static and dynamic settings, except Cox models. Ignoring competing risks caused problems for risk prediction in the time-to-event framework (Cox), but not in the categorical framework (logistic regression)., Comment: 3388 words; 3 figures; 4 tables

Multi-modal foundation models such as CLIP have showcased impressive zero-shot capabilities. However, their applicability in resource-constrained environments is limited due to their large number of parameters and high inference time. While existing approaches have scaled down the entire CLIP architecture, we focus on training smaller variants of the image encoder, which suffices for efficient zero-shot classification. The use of synthetic data has shown promise in distilling representations from larger teachers, resulting in strong few-shot and linear probe performance. However, we find that this approach surprisingly fails in true zero-shot settings when using contrastive losses. We identify the exploitation of spurious features as being responsible for poor generalization between synthetic and real data. However, by using the image feature-based L2 distillation loss, we mitigate these problems and train students that achieve zero-shot performance which on four domain-specific datasets is on-par with a ViT-B/32 teacher model trained on DataCompXL, while featuring up to 92% fewer parameters.

Despite considerable strides in developing deep learning models for 3D medical image segmentation, the challenge of effectively generalizing across diverse image distributions persists. While domain generalization is acknowledged as vital for robust application in clinical settings, the challenges stemming from training with a limited Field of View (FOV) remain unaddressed. This limitation leads to false predictions when applied to body regions beyond the FOV of the training data. In response to this problem, we propose a novel loss function that penalizes predictions in implausible body regions, applicable in both single-dataset and multi-dataset training schemes. It is realized with a Body Part Regression model that generates axial slice positional scores. Through comprehensive evaluation using a test set featuring varying FOVs, our approach demonstrates remarkable improvements in generalization capabilities. It effectively mitigates false positive tumor predictions up to 85% and significantly enhances overall segmentation performance.

Cybersecurity faces challenges in identifying and mitigating ransomware, which is important for protecting critical infrastructures. The absence of datasets for distinguishing normal versus abnormal network behaviour hinders the development of proactive detection strategies against ransomware. An obstacle in proactive prevention methods is the absence of comprehensive datasets for contrasting normal versus abnormal network behaviours. The dataset enabling such contrasts would significantly expedite threat anomaly mitigation. In this study, we introduce UGRansome2024, an optimised dataset for ransomware detection in network traffic. This dataset is derived from the UGRansome data using an intuitionistic feature engineering approach that considers only relevant patterns in network behaviour analysis. The study presents an analysis of ransomware detection using the UGRansome2024 dataset and the Random Forest algorithm. Through encoding and feature relevance determination, the Random Forest achieved a classification accuracy of 96% and effectively identified unusual ransomware transactions. Findings indicate that certain ransomware variants, such as those utilising Encrypt Decrypt Algorithms (EDA) and Globe ransomware, have the highest financial impact. These insights have significant implications for real-world cybersecurity practices, highlighting the importance of machine learning in ransomware detection and mitigation. Further research is recommended to expand datasets, explore alternative detection methods, and address limitations in current approaches.

With the wealth of medical image data, efficient curation is essential. Assigning the sequence type to magnetic resonance images is necessary for scientific studies and artificial intelligence-based analysis. However, incomplete or missing metadata prevents effective automation. We therefore propose a deep-learning method for classification of prostate cancer scanning sequences based on a combination of image data and DICOM metadata. We demonstrate superior results compared to metadata or image data alone, and make our code publicly available at https://github.com/deepakri201/DICOMScanClassification.

The release of nnU-Net marked a paradigm shift in 3D medical image segmentation, demonstrating that a properly configured U-Net architecture could still achieve state-of-the-art results. Despite this, the pursuit of novel architectures, and the respective claims of superior performance over the U-Net baseline, continued. In this study, we demonstrate that many of these recent claims fail to hold up when scrutinized for common validation shortcomings, such as the use of inadequate baselines, insufficient datasets, and neglected computational resources. By meticulously avoiding these pitfalls, we conduct a thorough and comprehensive benchmarking of current segmentation methods including CNN-based, Transformer-based, and Mamba-based approaches. In contrast to current beliefs, we find that the recipe for state-of-the-art performance is 1) employing CNN-based U-Net models, including ResNet and ConvNeXt variants, 2) using the nnU-Net framework, and 3) scaling models to modern hardware resources. These results indicate an ongoing innovation bias towards novel architectures in the field and underscore the need for more stringent validation standards in the quest for scientific progress., Comment: Accepted at MICCAI 2024

This paper presents the first algorithm for model-based offline quantum reinforcement learning and demonstrates its functionality on the cart-pole benchmark. The model and the policy to be optimized are each implemented as variational quantum circuits. The model is trained by gradient descent to fit a pre-recorded data set. The policy is optimized with a gradient-free optimization scheme using the return estimate given by the model as the fitness function. This model-based approach allows, in principle, full realization on a quantum computer during the optimization phase and gives hope that a quantum advantage can be achieved as soon as sufficiently powerful quantum computers are available.

Many safety-critical applications, especially in autonomous driving, require reliable object detectors. They can be very effectively assisted by a method to search for and identify potential failures and systematic errors before these detectors are deployed. Systematic errors are characterized by combinations of attributes such as object location, scale, orientation, and color, as well as the composition of their respective backgrounds. To identify them, one must rely on something other than real images from a test set because they do not account for very rare but possible combinations of attributes. To overcome this limitation, we propose a pipeline for generating realistic synthetic scenes with fine-grained control, allowing the creation of complex scenes with multiple objects. Our approach, BEV2EGO, allows for a realistic generation of the complete scene with road-contingent control that maps 2D bird's-eye view (BEV) scene configurations to a first-person view (EGO). In addition, we propose a benchmark for controlled scene generation to select the most appropriate generative outpainting model for BEV2EGO. We further use it to perform a systematic analysis of multiple state-of-the-art object detection models and discover differences between them.

Many blockchain platforms use committee-based consensus for scalability, finality, and security. In this consensus scheme, a committee decides which blocks get appended to the chain, typically through several voting phases. Platforms typically leverage the committee members' recorded votes to reward, punish, or detect failures. A common approach is to let the block proposer decide which votes to include, opening the door to possible attacks. For example, a malicious proposer can omit votes from targeted committee members, resulting in lost profits and, ultimately, their departure from the system. This paper presents Iniva, an inclusive and incentive-compatible vote aggregation scheme that prevents such vote omission attacks. Iniva relies on a tree overlay with carefully selected fallback paths, making it robust against process failures without needing reconfiguration or additional redundancy. Our analysis shows that Iniva significantly reduces the chance to omit individual votes while ensuring that omitting many votes incurs a significant cost. In addition, our experimental results show that Iniva enjoys robustness, scalability, and reasonable throughput., Comment: Committee-based blockchains, Vote omission attack, Vote inclusion, Signature aggregation, Incentive-compatible

Accurately segmenting thin tubular structures, such as vessels, nerves, roads or concrete cracks, is a crucial task in computer vision. Standard deep learning-based segmentation loss functions, such as Dice or Cross-Entropy, focus on volumetric overlap, often at the expense of preserving structural connectivity or topology. This can lead to segmentation errors that adversely affect downstream tasks, including flow calculation, navigation, and structural inspection. Although current topology-focused losses mark an improvement, they introduce significant computational and memory overheads. This is particularly relevant for 3D data, rendering these losses infeasible for larger volumes as well as increasingly important multi-class segmentation problems. To mitigate this, we propose a novel Skeleton Recall Loss, which effectively addresses these challenges by circumventing intensive GPU-based calculations with inexpensive CPU operations. It demonstrates overall superior performance to current state-of-the-art approaches on five public datasets for topology-preserving segmentation, while substantially reducing computational overheads by more than 90%. In doing so, we introduce the first multi-class capable loss function for thin structure segmentation, excelling in both efficiency and efficacy for topology-preservation., Comment: Accepted at ECCV 2024

Instance segmentation of neurons in volumetric light microscopy images of nervous systems enables groundbreaking research in neuroscience by facilitating joint functional and morphological analyses of neural circuits at cellular resolution. Yet said multi-neuron light microscopy data exhibits extremely challenging properties for the task of instance segmentation: Individual neurons have long-ranging, thin filamentous and widely branching morphologies, multiple neurons are tightly inter-weaved, and partial volume effects, uneven illumination and noise inherent to light microscopy severely impede local disentangling as well as long-range tracing of individual neurons. These properties reflect a current key challenge in machine learning research, namely to effectively capture long-range dependencies in the data. While respective methodological research is buzzing, to date methods are typically benchmarked on synthetic datasets. To address this gap, we release the FlyLight Instance Segmentation Benchmark (FISBe) dataset, the first publicly available multi-neuron light microscopy dataset with pixel-wise annotations. In addition, we define a set of instance segmentation metrics for benchmarking that we designed to be meaningful with regard to downstream analyses. Lastly, we provide three baselines to kick off a competition that we envision to both advance the field of machine learning regarding methodology for capturing long-range data dependencies, and facilitate scientific discovery in basic neuroscience., Comment: CVPR2024, Project page: https://kainmueller-lab.github.io/fisbe