Jorge Cardoso

Petru-Daniel Tudosiu, Walter Hugo Lopez Pinaya, Mark S. Graham et al.

Human anatomy, morphology, and associated diseases can be studied using medical imaging data. However, access to medical imaging data is restricted by governance and privacy concerns, data ownership, and the cost of acquisition, thus limiting our ability to understand the human body. A possible solution to this issue is the creation of a model able to learn and then generate synthetic images of the human body conditioned on specific characteristics of relevance (e.g., age, sex, and disease status). Deep generative models, in the form of neural networks, have been recently used to create synthetic 2D images of natural scenes. Still, the ability to produce high-resolution 3D volumetric imaging data with correct anatomical morphology has been hampered by data scarcity and algorithmic and computational limitations. This work proposes a generative model that can be scaled to produce anatomically correct, high-resolution, and realistic images of the human brain, with the necessary quality to allow further downstream analyses. The ability to generate a potentially unlimited amount of data not only enables large-scale studies of human anatomy and pathology without jeopardizing patient privacy, but also significantly advances research in the field of anomaly detection, modality synthesis, learning under limited data, and fair and ethical AI. Code and trained models are available at: https://github.com/AmigoLab/SynthAnatomy.

Jasmin Bogatinovski, Sasho Nedelkoski, Alexander Acker et al.

In the current IT world, developers write code while system operators run the code mostly as a black box. The connection between both worlds is typically established with log messages: the developer provides hints to the (unknown) operator, where the cause of an occurred issue is, and vice versa, the operator can report bugs during operation. To fulfil this purpose, developers write log instructions that are structured text commonly composed of a log level (e.g., "info", "error"), static text ("IP {} cannot be reached"), and dynamic variables (e.g. IP {}). However, as opposed to well-adopted coding practices, there are no widely adopted guidelines on how to write log instructions with good quality properties. For example, a developer may assign a high log level (e.g., "error") for a trivial event that can confuse the operator and increase maintenance costs. Or the static text can be insufficient to hint at a specific issue. In this paper, we address the problem of log quality assessment and provide the first step towards its automation. We start with an in-depth analysis of quality log instruction properties in nine software systems and identify two quality properties: 1) correct log level assignment assessing the correctness of the log level, and 2) sufficient linguistic structure assessing the minimal richness of the static text necessary for verbose event description. Based on these findings, we developed a data-driven approach that adapts deep learning methods for each of the two properties. An extensive evaluation on large-scale open-source systems shows that our approach correctly assesses log level assignments with an accuracy of 0.88, and the sufficient linguistic structure with an F1 score of 0.99, outperforming the baselines. Our study shows the potential of the data-driven methods in assessing instructions quality and aid developers in comprehending and writing better code.

Virginia Fernandez, Pedro Sanchez, Walter Hugo Lopez Pinaya et al.

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model without exposing it to identifiable data. Here, we are interested in the privacy issue faced by a data provider who wishes to share their data via a multimodal generative model. A question that immediately arises is ``How can a data provider ensure that the generative model is not leaking identifiable information about a patient?''. Our solution consists of (1) training a first diffusion model on real data (2) generating a synthetic dataset using this model and filtering it to exclude images with a re-identifiability risk (3) training a second diffusion model on the filtered synthetic data only. We showcase that datasets sampled from models trained with privacy distillation can effectively reduce re-identification risk whilst maintaining downstream performance.

Jasmin Bogatinovski, Sasho Nedelkoski, Li Wu et al.

The reliability of cloud platforms is of significant relevance because society increasingly relies on complex software systems running on the cloud. To improve it, cloud providers are automating various maintenance tasks, with failure identification frequently being considered. The precondition for automation is the availability of observability tools, with system logs commonly being used. The focus of this paper is log-based failure identification. This problem is challenging because of the instability of the log data and the incompleteness of the explicit logging failure coverage within the code. To address the two challenges, we present CLog as a method for failure identification. The key idea presented herein based is on our observation that by representing the log data as sequences of subprocesses instead of sequences of log events, the effect of the unstable log data is reduced. CLog introduces a novel subprocess extraction method that uses context-aware neural network and clustering methods to extract meaningful subprocesses. The direct modeling of log event contexts allows the identification of failures with respect to the abrupt context changes, addressing the challenge of insufficient logging failure coverage. Our experimental results demonstrate that the learned subprocesses representations reduce the instability in the input, allowing CLog to outperform the baselines on the failure identification subproblems - 1) failure detection by 9-24% on F1 score and 2) failure type identification by 7% on the macro averaged F1 score. Further analysis shows the existent negative correlation between the instability in the input event sequences and the detection performance in a model-agnostic manner.

Jasmin Bogatinovski, Gjorgji Madjarov, Sasho Nedelkoski et al.

Artificial Intelligence for IT Operations (AIOps) describes the process of maintaining and operating large IT systems using diverse AI-enabled methods and tools for, e.g., anomaly detection and root cause analysis, to support the remediation, optimization, and automatic initiation of self-stabilizing IT activities. The core step of any AIOps workflow is anomaly detection, typically performed on high-volume heterogeneous data such as log messages (logs), metrics (e.g., CPU utilization), and distributed traces. In this paper, we propose a method for reliable and practical anomaly detection from system logs. It overcomes the common disadvantage of related works, i.e., the need for a large amount of manually labeled training data, by building an anomaly detection model with log instructions from the source code of 1000+ GitHub projects. The instructions from diverse systems contain rich and heterogenous information about many different normal and abnormal IT events and serve as a foundation for anomaly detection. The proposed method, named ADLILog, combines the log instructions and the data from the system of interest (target system) to learn a deep neural network model through a two-phase learning procedure. The experimental results show that ADLILog outperforms the related approaches by up to 60% on the F1 score while satisfying core non-functional requirements for industrial deployments such as unsupervised design, efficient model updates, and small model sizes.

Zi Yang, Haojin Yang, Soumajit Majumder et al.

Previous studies have demonstrated that not each sample in a dataset is of equal importance during training. Data pruning aims to remove less important or informative samples while still achieving comparable results as training on the original (untruncated) dataset, thereby reducing storage and training costs. However, the majority of data pruning methods are applied to image classification tasks. To our knowledge, this work is the first to explore the feasibility of these pruning methods applied to object re-identification (ReID) tasks, while also presenting a more comprehensive data pruning approach. By fully leveraging the logit history during training, our approach offers a more accurate and comprehensive metric for quantifying sample importance, as well as correcting mislabeled samples and recognizing outliers. Furthermore, our approach is highly efficient, reducing the cost of importance score estimation by 10 times compared to existing methods. Our approach is a plug-and-play, architecture-agnostic framework that can eliminate/reduce 35%, 30%, and 5% of samples/training time on the VeRi, MSMT17 and Market1501 datasets, respectively, with negligible loss in accuracy (< 0.1%). The lists of important, mislabeled, and outlier samples from these ReID datasets are available at https://github.com/Zi-Y/data-pruning-reid.

Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez et al.

Deep learning holds immense promise for transforming medical image analysis, yet its clinical generalization remains profoundly limited. A major barrier is data heterogeneity. This is particularly true in Magnetic Resonance Imaging, where scanner hardware differences, diverse acquisition protocols, and varying sequence parameters introduce substantial domain shifts that obscure underlying biological signals. Data harmonization methods aim to reduce these instrumental and acquisition variability, but existing approaches remain insufficient. When applied to imaging data, image-based harmonization approaches are often restricted by the need for target images, while existing text-guided methods rely on simplistic labels that fail to capture complex acquisition details or are typically restricted to datasets with limited variability, failing to capture the heterogeneity of real-world clinical environments. To address these limitations, we propose DIST-CLIP (Disentangled Style Transfer with CLIP Guidance), a unified framework for MRI harmonization that flexibly uses either target images or DICOM metadata for guidance. Our framework explicitly disentangles anatomical content from image contrast, with the contrast representations being extracted using pre-trained CLIP encoders. These contrast embeddings are then integrated into the anatomical content via a novel Adaptive Style Transfer module. We trained and evaluated DIST-CLIP on diverse real-world clinical datasets, and showed significant improvements in performance when compared against state-of-the-art methods in both style translation fidelity and anatomical preservation, offering a flexible solution for style transfer and standardizing MRI data. Our code and weights will be made publicly available upon publication.

Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez et al.

Magnetic Resonance Imaging suffers from substantial data heterogeneity and the absence of standardized contrast labels across scanners, protocols, and institutions, which severely limits large-scale automated analysis. A unified representation of MRI contrast would enable a wide range of downstream utilities, from automatic sequence recognition to harmonization and quality control, without relying on manual annotations. To this end, we introduce MR-CLIP, a metadata-guided framework that learns MRI contrast representations by aligning volumetric images with their DICOM acquisition parameters. The resulting embeddings shows distinct clusters of MRI sequences and outperform supervised 3D baselines under data scarcity in few-shot sequence classification. Moreover, MR-CLIP enables unsupervised data quality control by identifying corrupted or inconsistent metadata through image-metadata embedding distances. By transforming routinely available acquisition metadata into a supervisory signal, MR-CLIP provides a scalable foundation for label-efficient MRI analysis across diverse clinical datasets.

Mehmet Yigit Avci, Pedro Borges, Paul Wright et al.

Accurate interpretation of Magnetic Resonance Imaging scans in clinical systems is based on a precise understanding of image contrast. This contrast is primarily governed by acquisition parameters, such as echo time and repetition time, which are stored in the DICOM metadata. To simplify contrast identification, broad labels such as T1-weighted or T2-weighted are commonly used, but these offer only a coarse approximation of the underlying acquisition settings. In many real-world datasets, such labels are entirely missing, leaving raw acquisition parameters as the only indicators of contrast. Adding to this challenge, the available metadata is often incomplete, noisy, or inconsistent. The lack of reliable and standardized metadata complicates tasks such as image interpretation, retrieval, and integration into clinical workflows. Furthermore, robust contrast-aware representations are essential to enable more advanced clinical applications, such as achieving modality-invariant representations and data harmonization. To address these challenges, we propose MR-CLIP, a multimodal contrastive learning framework that aligns MR images with their DICOM metadata to learn contrast-aware representations, without relying on manual labels. Trained on a diverse clinical dataset that spans various scanners and protocols, MR-CLIP captures contrast variations across acquisitions and within scans, enabling anatomy-invariant representations. We demonstrate its effectiveness in cross-modal retrieval and contrast classification, highlighting its scalability and potential for further clinical applications. The code and weights are publicly available at https://github.com/myigitavci/MR-CLIP.

Sasho Nedelkoski, Jasmin Bogatinovski, Alexander Acker et al.

Logs are extensively used during the development and maintenance of software systems. They collect runtime events and allow tracking of code execution, which enables a variety of critical tasks such as troubleshooting and fault detection. However, large-scale software systems generate massive volumes of semi-structured log records, posing a major challenge for automated analysis. Parsing semi-structured records with free-form text log messages into structured templates is the first and crucial step that enables further analysis. Existing approaches rely on log-specific heuristics or manual rule extraction. These are often specialized in parsing certain log types, and thus, limit performance scores and generalization. We propose a novel parsing technique called NuLog that utilizes a self-supervised learning model and formulates the parsing task as masked language modeling (MLM). In the process of parsing, the model extracts summarizations from the logs in the form of a vector embedding. This allows the coupling of the MLM as pre-training with a downstream anomaly detection task. We evaluate the parsing performance of NuLog on 10 real-world log datasets and compare the results with 12 parsing techniques. The results show that NuLog outperforms existing methods in parsing accuracy with an average of 99% and achieves the lowest edit distance to the ground truth templates. Additionally, two case studies are conducted to demonstrate the ability of the approach for log-based anomaly detection in both supervised and unsupervised scenario. The results show that NuLog can be successfully used to support troubleshooting tasks. The implementation is available at https://github.com/nulog/nulog.

Mehmet Yigit Avci, Akshit Achara, Andrew King et al.

Demographic attributes such as age, sex, and race can be predicted from medical images, raising concerns about bias in clinical AI systems. In brain MRI, this signal may arise from anatomical variation, acquisition-dependent contrast differences, or both, yet these sources remain entangled in conventional analyses. Without disentangling them, mitigation strategies risk failing to address the underlying causes. We propose a controlled framework based on disentangled representation learning, decomposing brain MRI into anatomy-focused representations that suppress acquisition influence and contrast embeddings that capture acquisition-dependent characteristics. Training predictive models for age, sex, and race on full images, anatomical representations, and contrast-only embeddings allows us to quantify the relative contributions of structure and acquisition to the demographic signal. Across three datasets and multiple MRI sequences, we find that demographic predictability is primarily rooted in anatomical variation: anatomy-focused representations largely preserve the performance of models trained on raw images. Contrast-only embeddings retain a weaker but systematic signal that is dataset-specific and does not generalise across sites. These findings suggest that effective mitigation must explicitly account for the distinct anatomical and acquisition-dependent origins of the demographic signal, ensuring that any bias reduction generalizes robustly across domains.

Qiao Yu, Wengui Zhang, Jorge Cardoso et al.

In large-scale datacenters, memory failure is a common cause of server crashes, with Uncorrectable Errors (UEs) being a major indicator of Dual Inline Memory Module (DIMM) defects. Existing approaches primarily focus on predicting UEs using Correctable Errors (CEs), without fully considering the information provided by error bits. However, error bit patterns have a strong correlation with the occurrence of UEs. In this paper, we present a comprehensive study on the correlation between CEs and UEs, specifically emphasizing the importance of spatio-temporal error bit information. Our analysis reveals a strong correlation between spatio-temporal error bits and UE occurrence. Through evaluations using real-world datasets, we demonstrate that our approach significantly improves prediction performance by 15% in F1-score compared to the state-of-the-art algorithms. Overall, our approach effectively reduces the number of virtual machine interruptions caused by UEs by approximately 59%.

Chris Foulon, Robert Gray, James K. Ruffle et al.

Ischaemic stroke, a leading cause of death and disability, critically relies on neuroimaging for characterising the anatomical pattern of injury. Diffusion-weighted imaging (DWI) provides the highest expressivity in ischemic stroke but poses substantial challenges for automated lesion segmentation: susceptibility artefacts, morphological heterogeneity, age-related comorbidities, time-dependent signal dynamics, instrumental variability, and limited labelled data. Current U-Net-based models therefore underperform, a problem accentuated by inadequate evaluation metrics that focus on mean performance, neglecting anatomical, subpopulation, and acquisition-dependent variability. Here, we present a high-performance DWI lesion segmentation tool addressing these challenges through optimized vision transformer-based architectures, integration of 3563 annotated lesions from multi-site data, and algorithmic enhancements, achieving state-of-the-art results. We further propose a novel evaluative framework assessing model fidelity, equity (across demographics and lesion subtypes), anatomical precision, and robustness to instrumental variability, promoting clinical and research utility. This work advances stroke imaging by reconciling model expressivity with domain-specific challenges and redefining performance benchmarks to prioritize equity and generalizability, critical for personalized medicine and mechanistic research.

Paolo Notaro, Soroush Haeri, Jorge Cardoso et al.

To protect large-scale computing environments necessary to meet increasing computing demand, cloud providers have implemented security measures to monitor Operations and Maintenance (O&M) activities and therefore prevent data loss and service interruption. Command interception systems are used to intercept, assess, and block dangerous Command-line Interface (CLI) commands before they can cause damage. Traditional solutions for command risk assessment include rule-based systems, which require expert knowledge and constant human revision to account for unseen commands. To overcome these limitations, several end-to-end learning systems have been proposed to classify CLI commands. These systems, however, have several other limitations, including the adoption of general-purpose text classifiers, which may not adapt to the language characteristics of scripting languages such as Bash or PowerShell, and may not recognize dangerous commands in the presence of an unbalanced class distribution. In this paper, we propose a transformer-based command risk classification system, which leverages the generalization power of Large Language Models (LLM) to provide accurate classification and the ability to identify rare dangerous commands effectively, by exploiting the power of transfer learning. We verify the effectiveness of our approach on a realistic dataset of production commands and show how to apply our model for other security-related tasks, such as dangerous command interception and auditing of existing rule-based systems.

Qiao Yu, Wengui Zhang, Min Zhou et al.

Large-scale datacenters often experience memory failures, where Uncorrectable Errors (UEs) highlight critical malfunction in Dual Inline Memory Modules (DIMMs). Existing approaches primarily utilize Correctable Errors (CEs) to predict UEs, yet they typically neglect how these errors vary between different CPU architectures, especially in terms of Error Correction Code (ECC) applicability. In this paper, we investigate the correlation between CEs and UEs across different CPU architectures, including X86 and ARM. Our analysis identifies unique patterns of memory failure associated with each processor platform. Leveraging Machine Learning (ML) techniques on production datasets, we conduct the memory failure prediction in different processors' platforms, achieving up to 15% improvements in F1-score compared to the existing algorithm. Finally, an MLOps (Machine Learning Operations) framework is provided to consistently improve the failure prediction in the production environment.

Reuben Dorent, Aaron Kujawa, Marina Ivory et al.

Domain Adaptation (DA) has recently raised strong interests in the medical imaging community. While a large variety of DA techniques has been proposed for image segmentation, most of these techniques have been validated either on private datasets or on small publicly available datasets. Moreover, these datasets mostly addressed single-class problems. To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2021). CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality DA. The challenge's goal is to segment two key brain structures involved in the follow-up and treatment planning of vestibular schwannoma (VS): the VS and the cochleas. Currently, the diagnosis and surveillance in patients with VS are performed using contrast-enhanced T1 (ceT1) MRI. However, there is growing interest in using non-contrast sequences such as high-resolution T2 (hrT2) MRI. Therefore, we created an unsupervised cross-modality segmentation benchmark. The training set provides annotated ceT1 (N=105) and unpaired non-annotated hrT2 (N=105). The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137). A total of 16 teams submitted their algorithm for the evaluation phase. The level of performance reached by the top-performing teams is strikingly high (best median Dice - VS:88.4%; Cochleas:85.7%) and close to full supervision (median Dice - VS:92.5%; Cochleas:87.7%). All top-performing methods made use of an image-to-image translation approach to transform the source-domain images into pseudo-target-domain images. A segmentation network was then trained using these generated images and the manual annotations provided for the source image.

Guilherme Pombo, Robert Gray, Jorge Cardoso et al.

We describe Countersynth, a conditional generative model of diffeomorphic deformations that induce label-driven, biologically plausible changes in volumetric brain images. The model is intended to synthesise counterfactual training data augmentations for downstream discriminative modelling tasks where fidelity is limited by data imbalance, distributional instability, confounding, or underspecification, and exhibits inequitable performance across distinct subpopulations. Focusing on demographic attributes, we evaluate the quality of synthesized counterfactuals with voxel-based morphometry, classification and regression of the conditioning attributes, and the Fréchet inception distance. Examining downstream discriminative performance in the context of engineered demographic imbalance and confounding, we use UK Biobank magnetic resonance imaging data to benchmark CounterSynth augmentation against current solutions to these problems. We achieve state-of-the-art improvements, both in overall fidelity and equity. The source code for CounterSynth is available online.

Anshul Jindal, Ilya Shakhat, Jorge Cardoso et al.

Server virtualization in the form of virtual machines (VMs) with the use of a hypervisor or a Virtual Machine Monitor (VMM) is an essential part of cloud computing technology to provide infrastructure-as-a-service (IaaS). A fault or an anomaly in the VMM can propagate to the VMs hosted on it and ultimately affect the availability and reliability of the applications running on those VMs. Therefore, identifying and eventually resolving it quickly is highly important. However, anomalous VMM detection is a challenge in the cloud environment since the user does not have access to the VMM. This paper addresses this challenge of anomalous VMM detection in the cloud-based environment without having any knowledge or data from VMM by introducing a novel machine learning-based algorithm called IAD: Indirect Anomalous VMMs Detection. This algorithm solely uses the VM's resources utilization data hosted on those VMMs for the anomalous VMMs detection. The developed algorithm's accuracy was tested on four datasets comprising the synthetic and real and compared against four other popular algorithms, which can also be used to the described problem. It was found that the proposed IAD algorithm has an average F1-score of 83.7% averaged across four datasets, and also outperforms other algorithms by an average F1-score of 11\%.

Henry Watkins, Robert Gray, Adam Julius et al.

Radiological reports typically summarize the content and interpretation of imaging studies in unstructured form that precludes quantitative analysis. This limits the monitoring of radiological services to throughput undifferentiated by content, impeding specific, targeted operational optimization. Here we present Neuradicon, a natural language processing (NLP) framework for quantitative analysis of neuroradiological reports. Our framework is a hybrid of rule-based and artificial intelligence models to represent neurological reports in succinct, quantitative form optimally suited to operational guidance. We demonstrate the application of Neuradicon to operational phenotyping of a corpus of 336,569 reports, and report excellent generalizability across time and two independent healthcare institutions.

Anshul Jindal, Paul Staab, Jorge Cardoso et al.

A memory leak in an application deployed on the cloud can affect the availability and reliability of the application. Therefore, to identify and ultimately resolve it quickly is highly important. However, in the production environment running on the cloud, memory leak detection is a challenge without the knowledge of the application or its internal object allocation details. This paper addresses this challenge of online detection of memory leaks in cloud-based infrastructure without having any internal application knowledge by introducing a novel machine learning based algorithm Precog. This algorithm solely uses one metric i.e the system's memory utilization on which the application is deployed for the detection of a memory leak. The developed algorithm's accuracy was tested on 60 virtual machines manually labeled memory utilization data provided by our industry partner Huawei Munich Research Center and it was found that the proposed algorithm achieves the accuracy score of 85\% with less than half a second prediction time per virtual machine.

João Caldeira, Fernando Brito e Abreu, Jorge Cardoso et al.

Context: Profiling developers is challenging since many factors, such as their skills, experience, development environment and behaviors, may influence a detailed analysis and the delivery of coherent interpretations. Objective: We aim at profiling software developers by mining their software development process. To do so, we performed a controlled experiment where, in the realm of a Python programming contest, a group of developers had the same well-defined set of requirements specifications and a well-defined sprint schedule. Events were collected from the PyCharm IDE, and from the Mooshak automatic jury where subjects checked-in their code. Method: We used n-gram language models and text mining to characterize developers' profiles, and process mining algorithms to discover their overall workflows and extract the correspondent metrics for further evaluation. Results: Findings show that we can clearly characterize with a coherent rationale most developers, and distinguish the top performers from the ones with more challenging behaviors. This approach may lead ultimately to the creation of a catalog of software development process smells. Conclusions: The profile of a developer provides a software project manager a clue for the selection of appropriate tasks he/she should be assigned. With the increasing usage of low and no-code platforms, where coding is automatically generated from an upper abstraction layer, mining developer's actions in the development platforms is a promising approach to early detect not only behaviors but also assess project complexity and model effort.

Jasmin Bogatinovski, Sasho Nedelkoski, Alexander Acker et al.

Artificial Intelligence for IT Operations (AIOps) is an emerging interdisciplinary field arising in the intersection between the research areas of machine learning, big data, streaming analytics, and the management of IT operations. AIOps, as a field, is a candidate to produce the future standard for IT operation management. To that end, AIOps has several challenges. First, it needs to combine separate research branches from other research fields like software reliability engineering. Second, novel modelling techniques are needed to understand the dynamics of different systems. Furthermore, it requires to lay out the basis for assessing: time horizons and uncertainty for imminent SLA violations, the early detection of emerging problems, autonomous remediation, decision making, support of various optimization objectives. Moreover, a good understanding and interpretability of these aiding models are important for building trust between the employed tools and the domain experts. Finally, all this will result in faster adoption of AIOps, further increase the interest in this research field and contribute to bridging the gap towards fully-autonomous operating IT systems. The main aim of the AIOPS workshop is to bring together researchers from both academia and industry to present their experiences, results, and work in progress in this field. The workshop aims to strengthen the community and unite it towards the goal of joining the efforts for solving the main challenges the field is currently facing. A consensus and adoption of the principles of openness and reproducibility will boost the research in this emerging area significantly.

Paolo Notaro, Jorge Cardoso, Michael Gerndt

IT systems of today are becoming larger and more complex, rendering their human supervision more difficult. Artificial Intelligence for IT Operations (AIOps) has been proposed to tackle modern IT administration challenges thanks to AI and Big Data. However, past AIOps contributions are scattered, unorganized and missing a common terminology convention, which renders their discovery and comparison impractical. In this work, we conduct an in-depth mapping study to collect and organize the numerous scattered contributions to AIOps in a unique reference index. We create an AIOps taxonomy to build a foundation for future contributions and allow an efficient comparison of AIOps papers treating similar problems. We investigate temporal trends and classify AIOps contributions based on the choice of algorithms, data sources and the target components. Our results show a recent and growing interest towards AIOps, specifically to those contributions treating failure-related tasks (62%), such as anomaly detection and root cause analysis.

João Caldeira, Fernando Brito e Abreu, Jorge Cardoso et al.

Context : Software comprehension and maintenance activities, such as refactoring, are said to be negatively impacted by software complexity. The methods used to measure software product and processes complexity have been thoroughly debated in the literature. However, the discernment about the possible links between these two dimensions, particularly on the benefits of using the process perspective, has a long journey ahead. Objective: To improve the understanding of the liaison of developers' activities and software complexity within a refactoring task, namely by evaluating if process metrics gathered from the IDE, using process mining methods and tools, are suitable to accurately classify different refactoring practices and the resulting software complexity. Method: We mined source code metrics from a software product after a quality improvement task was given in parallel to (117) software developers, organized in (71) teams. Simultaneously, we collected events from their IDE work sessions (320) and used process mining to model their processes and extract the correspondent metrics. Results: Most teams using a plugin for refactoring (JDeodorant) reduced software complexity more effectively and with simpler processes than the ones that performed refactoring using only Eclipse native features. We were able to find moderate correlations (43%) between software cyclomatic complexity and process cyclomatic complexity. The best models found for the refactoring method and cyclomatic complexity level predictions, had an accuracy of 92.95% and 94.36%, respectively. Conclusions: Our approach agnostic to programming languages, geographic location, or development practices. Initial findings are encouraging, and lead us to suggest practitioners may use our method in other development tasks, such as, defect analysis and unit or integration tests.

Reuben Dorent, Thomas Booth, Wenqi Li et al.

Brain tissue segmentation from multimodal MRI is a key building block of many neuroimaging analysis pipelines. Established tissue segmentation approaches have, however, not been developed to cope with large anatomical changes resulting from pathology, such as white matter lesions or tumours, and often fail in these cases. In the meantime, with the advent of deep neural networks (DNNs), segmentation of brain lesions has matured significantly. However, few existing approaches allow for the joint segmentation of normal tissue and brain lesions. Developing a DNN for such a joint task is currently hampered by the fact that annotated datasets typically address only one specific task and rely on task-specific imaging protocols including a task-specific set of imaging modalities. In this work, we propose a novel approach to build a joint tissue and lesion segmentation model from aggregated task-specific hetero-modal domain-shifted and partially-annotated datasets. Starting from a variational formulation of the joint problem, we show how the expected risk can be decomposed and optimised empirically. We exploit an upper bound of the risk to deal with heterogeneous imaging modalities across datasets. To deal with potential domain shift, we integrated and tested three conventional techniques based on data augmentation, adversarial learning and pseudo-healthy generation. For each individual task, our joint approach reaches comparable performance to task-specific and fully-supervised models. The proposed framework is assessed on two different types of brain lesions: White matter lesions and gliomas. In the latter case, lacking a joint ground-truth for quantitative assessment purposes, we propose and use a novel clinically-relevant qualitative assessment methodology.

Sasho Nedelkoski, Jasmin Bogatinovski, Alexander Acker et al.

The detection of anomalies is essential mining task for the security and reliability in computer systems. Logs are a common and major data source for anomaly detection methods in almost every computer system. They collect a range of significant events describing the runtime system status. Recent studies have focused predominantly on one-class deep learning methods on predefined non-learnable numerical log representations. The main limitation is that these models are not able to learn log representations describing the semantic differences between normal and anomaly logs, leading to a poor generalization of unseen logs. We propose Logsy, a classification-based method to learn log representations in a way to distinguish between normal data from the system of interest and anomaly samples from auxiliary log datasets, easily accessible via the internet. The idea behind such an approach to anomaly detection is that the auxiliary dataset is sufficiently informative to enhance the representation of the normal data, yet diverse to regularize against overfitting and improve generalization. We propose an attention-based encoder model with a new hyperspherical loss function. This enables learning compact log representations capturing the intrinsic differences between normal and anomaly logs. Empirically, we show an average improvement of 0.25 in the F1 score, compared to the previous methods. To investigate the properties of Logsy, we perform additional experiments including evaluation of the effect of the auxiliary data size, the influence of expert knowledge, and the quality of the learned log representations. The results show that the learned representation boost the performance of the previous methods such as PCA with a relative improvement of 28.2%.

Joao Caldeira, Fernando Brito e Abreu, Jorge Cardoso et al.

Context:Software Development Analytics is a research area concerned with providing insights to improve product deliveries and processes. Many types of studies, data sources and mining methods have been used for that purpose. Objective:This systematic literature review aims at providing an aggregate view of the relevant studies on Software Development Analytics in the past decade, with an emphasis on its application in practical settings. Method:Definition and execution of a search string upon several digital libraries, followed by a quality assessment criteria to identify the most relevant papers. On those, we extracted a set of characteristics (study type, data source, study perspective, development life-cycle activities covered, stakeholders, mining methods, and analytics scope) and classified their impact against a taxonomy. Results:Source code repositories, experimental case studies, and developers are the most common data sources, study types, and stakeholders, respectively. Product and project managers are also often present, but less than expected. Mining methods are evolving rapidly and that is reflected in the long list identified. Descriptive statistics are the most usual method followed by correlation analysis. Being software development an important process in every organization, it was unexpected to find that process mining was present in only one study. Most contributions to the software development life cycle were given in the quality dimension. Time management and costs control were lightly debated. The analysis of security aspects suggests it is an increasing topic of concern for practitioners. Risk management contributions are scarce. Conclusions:There is a wide improvement margin for software development analytics in practice. For instance, mining and analyzing the activities performed by software developers in their actual workbench, the IDE.

Thomas Booth, Matthew Williams, Aysha Luis et al.

Aim: To review how machine learning (ML) is applied to imaging biomarkers in neuro-oncology, in particular for diagnosis, prognosis, and treatment response monitoring. Materials and Methods: The PubMed and MEDLINE databases were searched for articles published before September 2018 using relevant search terms. The search strategy focused on articles applying ML to high-grade glioma biomarkers for treatment response monitoring, prognosis, and prediction. Results: Magnetic resonance imaging (MRI) is typically used throughout the patient pathway because routine structural imaging provides detailed anatomical and pathological information and advanced techniques provide additional physiological detail. Using carefully chosen image features, ML is frequently used to allow accurate classification in a variety of scenarios. Rather than being chosen by human selection, ML also enables image features to be identified by an algorithm. Much research is applied to determining molecular profiles, histological tumour grade, and prognosis using MRI images acquired at the time that patients first present with a brain tumour. Differentiating a treatment response from a post-treatment-related effect using imaging is clinically important and also an area of active study (described here in one of two Special Issue publications dedicated to the application of ML in glioma imaging). Conclusion: Although pioneering, most of the evidence is of a low level, having been obtained retrospectively and in single centres. Studies applying ML to build neuro-oncology monitoring biomarker models have yet to show an overall advantage over those using traditional statistical methods. Development and validation of ML models applied to neuro-oncology require large, well-annotated datasets, and therefore multidisciplinary and multi-centre collaborations are necessary.

Mauricio Orbes-Arteaga, Jorge Cardoso, Lauge Sørensen et al.

In the absence of sufficient data variation (e.g., scanner and protocol variability) in annotated data, deep neural networks (DNNs) tend to overfit during training. As a result, their performance is significantly lower on data from unseen sources compared to the performance on data from the same source as the training data. Semi-supervised domain adaptation methods can alleviate this problem by tuning networks to new target domains without the need for annotated data from these domains. Adversarial domain adaptation (ADA) methods are a popular choice that aim to train networks in such a way that the features generated are domain agnostic. However, these methods require careful dataset-specific selection of hyperparameters such as the complexity of the discriminator in order to achieve a reasonable performance. We propose to use knowledge distillation (KD) -- an efficient way of transferring knowledge between different DNNs -- for semi-supervised domain adaption of DNNs. It does not require dataset-specific hyperparameter tuning, making it generally applicable. The proposed method is compared to ADA for segmentation of white matter hyperintensities (WMH) in magnetic resonance imaging (MRI) scans generated by scanners that are not a part of the training set. Compared with both the baseline DNN (trained on source domain only and without any adaption to target domain) and with using ADA for semi-supervised domain adaptation, the proposed method achieves significantly higher WMH dice scores.

Patrick Bilic, Patrick Christ, Hongwei Bran Li et al.

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in \url{http://medicaldecathlon.com/}. In addition, both data and online evaluation are accessible via \url{www.lits-challenge.com}.