EPDiff: Erasure Perception Diffusion Model for Unsupervised Anomaly Detection in Preoperative Multimodal Images.

Objectives:To investigate trends observed in a decade of published research on multimodality PET(/CT)+MR imaging in abdominal oncology, and to explore how these trends are reflected by the use of multimodality imaging performed at our institution.Methods:First, we performed a literature search (2009–2018) including all papers published on the multimodality combination of PET(/CT) and MRI in abdominal oncology. Retrieved papers were categorized according to a structured labelling system, including study design and outcome, cancer and lesion type under investigation and PET-tracer type. Results were analysed using descriptive statistics and evolutions over time were plotted graphically. Second, we performed a descriptive analysis of the numbers of MRI, PET/CT and multimodality PET/CT+MRI combinations (performed within a ≤14 days interval) performed during a similar time span at our institution.Results:Published research papers involving multimodality PET(/CT)+MRI combinations showed an impressive increase in numbers, both for retrospective combinations of PET/CT and MRI, as well as hybrid PET/MRI. Main areas of research included new PET-tracers, visual PET(/CT)+MRI assessment for staging, and (semi-)quantitative analysis of PET-parameters compared to or combined with MRI-parameters as predictive biomarkers. In line with literature, we also observed a vast increase in numbers of multimodality PET/CT+MRI imaging in our institutional data.Conclusions:The tremendous increase in published literature on multimodality imaging, reflected by our institutional data, shows the continuously growing interest in comprehensive multivariable imaging evaluations to guide oncological practice.Advances in knowledge:The role of multimodality imaging in oncology is rapidly evolving. This paper summarizes the main applications and recent developments in multimodality imaging, with a specific focus on the combination of PET+MRI in abdominal oncology.

Anomaly detection is the process of identifying unexpected items or events in datasets, which differ from the norm. In contrast to standard classification tasks, anomaly detection is often applied on unlabeled data, taking only the internal structure of the dataset into account. This challenge is known as unsupervised anomaly detection and is addressed in many practical applications, for example in network intrusion detection, fraud detection as well as in the life science and medical domain. Dozens of algorithms have been proposed in this area, but unfortunately the research community still lacks a comparative universal evaluation as well as common publicly available datasets. These shortcomings are addressed in this study, where 19 different unsupervised anomaly detection algorithms are evaluated on 10 different datasets from multiple application domains. By publishing the source code and the datasets, this paper aims to be a new well-funded basis for unsupervised anomaly detection research. Additionally, this evaluation reveals the strengths and weaknesses of the different approaches for the first time. Besides the anomaly detection performance, computational effort, the impact of parameter settings as well as the global/local anomaly detection behavior is outlined. As a conclusion, we give an advise on algorithm selection for typical real-world tasks.

This review examines the recent developments in deep learning (DL) techniques applied to multimodal fusion image segmentation for liver cancer. Hepatocellular carcinoma is a highly dangerous malignant tumor that requires accurate image segmentation for effective treatment and disease monitoring. Multimodal image fusion has the potential to offer more comprehensive information and more precise segmentation, and DL techniques have achieved remarkable progress in this domain. This paper starts with an introduction to liver cancer, then explains the preprocessing and fusion methods for multimodal images, then explores the application of DL methods in this area. Various DL architectures such as convolutional neural networks (CNN) and U-Net are discussed and their benefits in multimodal image fusion segmentation. Furthermore, various evaluation metrics and datasets currently used to measure the performance of segmentation models are reviewed. While reviewing the progress, the challenges of current research, such as data imbalance, model generalization, and model interpretability, are emphasized and future research directions are suggested. The application of DL in multimodal image segmentation for liver cancer is transforming the field of medical imaging and is expected to further enhance the accuracy and efficiency of clinical decision making. This review provides useful insights and guidance for medical practitioners.

Unsupervised anomaly detection (UAD) attracts a lot of research interest and drives widespread applications, where only anomaly-free samples are available for training. Some UAD applications intend to locate the anomalous regions further even without any anomaly information. Although the absence of anomalous samples and annotations deteriorates the UAD performance, an inconspicuous, yet powerful statistics model, the normalizing flows, is appropriate for anomaly detection (AD) and localization in an unsupervised fashion. The flow-based probabilistic models, only trained on anomaly-free data, can efficiently distinguish unpredictable anomalies by assigning them much lower likelihoods than normal data. Nevertheless, the size variation of unpredictable anomalies introduces another inconvenience to the flow-based methods for high-precision AD and localization. To generalize the anomaly size variation, we propose a novel multiscale flow-based framework (MSFlow) composed of asymmetrical parallel flows followed by a fusion flow to exchange multiscale perceptions. Moreover, different multiscale aggregation strategies are adopted for image-wise AD and pixel-wise anomaly localization according to the discrepancy between them. The proposed MSFlow is evaluated on three AD datasets, significantly outperforming existing methods. Notably, on the challenging MVTec AD benchmark, our MSFlow achieves a new state-of-the-art (SOTA) with a detection AUORC score of up to 99.7%, localization AUCROC score of 98.8% and PRO score of 97.1%.

Supervised deep learning approaches provide state-of-the-art performance on medical image classification tasks for disease screening. However, these methods require large labeled datasets that involve resource-intensive expert annotation. Further, disease screening applications have low prevalence of abnormal samples; this class imbalance makes the task more akin to anomaly detection. While the machine learning community has proposed unsupervised deep learning methods for anomaly detection, they have yet to be characterized on medical images where normal vs. anomaly distinctions may be more subtle and variable. In this work, we characterize existing unsupervised anomaly detection methods on retinal fundus images, and find that they require significant fine tuning and offer unsatisfactory performance. We thus propose an efficient and effective transfer-learning based approach for unsupervised anomaly detection. Our method employs a deep convolutional neural network trained on ImageNet as a feature extractor, and subsequently feeds the learned feature representations into an existing unsupervised anomaly detection method. We show that our approach significantly outperforms baselines on two natural image datasets and two retinal fundus image datasets, all with minimal fine-tuning. We further show the ability to leverage very small numbers of labelled anomalies to improve performance. Our work establishes a strong unsupervised baseline for image-based anomaly detection, alongside a flexible and scalable approach for screening applications.

Existing fusion algorithms often struggle to maintain modality features, leading to issues like color distortion and halo artifacts in fusion results. To address these challenges, this paper proposes a multimodal image fusion method based on diffusion models. Specifically, the proposed approach formulates the multimodal fusion task as a conditional generation problem within a DDPM sampling framework. It utilizes multi-scale modality features to guide the iterative generation of fusion images. Our proposed method consists of two key modules: a feature extraction module and a diffusion generation module. The former employs a Swin Transformer network to extract complementary modality features from multimodal images, while the latter implements a denoising network with forward and reverse diffusion processes in pixel space to facilitate data distribution learning. To maintain the original spectral characteristics of objects, enhance modal information integration, and preserve color fidelity, gradient consistency loss and intensity consistency loss are introduced. Extensive experiments validate that our method outperforms some state-of-the-art fusion techniques, especially in terms of color fidelity.

Erdheim-Chester disease (ECD) is an extremely rare histiocytic neoplasm with a highly variable and often unpredictable clinical course and prognosis. Multiple organs can be affected mimicking other systemic diseases both clinically and radiologically. This makes timely diagnosis more challenging. We report the case of a 39-year-old male presented with a 15-day history of fever and retrosternal chest pain. Ha has a long history of diabetes insipidus, hypogonadism of unknown aetiology. On exploration, computed tomography revealed retroperitoneal fibrosis and "hairy" kidney appearance. Subsequent multimodality imaging studies showed the extensive multisystemic involvement including the skeletal system, retroperitoneum, pituitary, retroperitoneum, kidneys, heart, central nervous system, myocardium, pleura, lymph nodes and GI tract. Histopathology confirmed CD68+/CD1a- histiocytosis. Molecular analysis for BRAF mutation is currently pending. Pegylated interferon α and corticosteroids induced rapid clinical and biochemical improvement. Therapeutic response using a follow-up 18F-FDG PET scan revealed subsequent improved systemic lesions. A prolonged history of unexplained endocrine abnormalities in the context of fever of unknown origin should evoke the diagnosis of ECD. Multimodal imaging is essential for diagnosis and for monitoring treatment response. This case highlights the importance of the multidisciplinary approach that integrates clinical evaluation, histological analysis, and imaging studies for the optimal the management of this disease. Early initiation of immunomodulatory therapy can lead to better outcomes, even prior to confirmation of molecular findings.

Multimodality imaging for prosthetic valves evaluation: Current understanding and future directions

Sinus of Valsalva aneurysm is a rare defect that can present with fatal complications in case of rupture. Heart failure symptoms are common due to high fraction of the resultant shunt. Multimodality imaging and invasive hemodynamic assessment is essential for comprehensive evaluation of the defect and guiding surgical planning. We describe the case of a 40-year-old woman who presented with heart failure symptoms and was found to have ruptured sinus of Valsalva aneurysm on transthoracic echocardiogram. Cardiac computed tomography angiography further characterized the defect and the associated anomalies. Right heart catheterization assessed the hemodynamic significance of the left to right shunt. Intraoperative findings highlighted the associated congenital anomalies including supracristal ventricular septal defect. The use of intraoperative transesophageal echocardiography proved essential in detecting worsening of the right ventricular outflow track infundibular dynamic obstruction post repair thus delineating the importance of maintaining adequate cardiac preload. This case highlights a stepwise approach in the anatomical characterization of sinus of Valsalva aneurysm using multimodality imaging and the use of hemodynamic assessment and intraoperative imaging to guide surgical planning.

BackgroundAcquired pulmonary vein stenosis (PVS) is a rare, but serious, complication that can develop after treatment with ablations for atrial fibrillation. Prompt diagnosis is difficult because it can often present similarly to other pulmonary disease processes.Case summaryWe describe a 62-year-old female with history of persistent symptomatic atrial fibrillation that resolved status post two radio-frequency ablations who presents with ongoing dyspnoea, productive cough, pleuritic chest pain, and haemoptysis over multiple admissions. She was misdiagnosed with recurrent pneumonias and pulmonary embolism that failed to improve her symptoms. She was referred to our centre for further evaluation finding severe stenosis in the left superior pulmonary vein with complete obliteration of the left inferior pulmonary vein on computed tomography scan. Multi-modal imaging including an echocardiogram and pulmonary angiogram was used to confirm the diagnosis. Percutaneous intervention with transvenous pulmonary vein venoplasty with pulmonary vein stenting of the left upper pulmonary vein was offered which resolved the patient’s aforementioned symptoms.ConclusionPrompt diagnosis of acquired pulmonary vein stenosis is critical to plan for effective management. Our case highlights the need to consider PVS with a high index of clinical suspicion when a patient’s medical history is significant for a prior history of ablation. We also review the use of multi-modal imaging to diagnose and plan for effective management with percutaneous intervention.

Multimodal imaging systems assist medical practitioners in cost-effective diagnostic methods in clinical pathologies. Multimodal imaging of the same organ or the region of interest reveals complementing anatomical and functional details. Multimodal image fusion algorithms integrate complementary image details into a composite image that reduces clinician's time for effective diagnosis. Deep learning networks have their role in feature extraction for the fusion of multimodal images. This chapter analyzes the performance of a pre-trained VGG19 deep learning network that extracts features from the base and detail layers of the source images for constructing a weight map to fuse the source image details. Maximum and averaging fusion rules are adopted for base layer fusion. The performance of the fusion algorithm for multimodal medical image fusion is analyzed by peak signal to noise ratio, structural similarity index, fusion factor, and figure of merit. Performance analysis of the fusion algorithms is also carried out for the source images with the presence of impulse and Gaussian noise.

Guided wave-based structural health monitoring is extensively utilized in various industrial applications to ensure the integrity of components within industrial systems. Among these monitoring techniques, principal component analysis (PCA) reconstruction methods are widely used for anomaly detection due to their computational efficiency and interoperability. However, existing PCA reconstruction methods are semisupervised anomaly detection approaches that require training on historical normal data and fail to detect anomalous signals within the training set. To address this limitation, this work proposes a correntropy PCA (C-PCA), enabling fully unsupervised anomaly detection on raw training data without requiring label information, when the dataset contains a high proportion of abnormal signals. This method allows anomaly detection on real-time measurements without the need for precleaned historical normal data or can also be used to generate clean data for existing semisupervised anomaly detection methods. In correntropy PCA, principal components are extracted from the correntropy matrix rather than the correlation matrix. The correntropy, representing the statistical dependence between samples of guided waves, is estimated utilizing a Gaussian kernel with a specified kernel width. Through the optimization of the kernel width, the correntropy PCA reconstruction method demonstrates superior anomaly detection performance compared with the standard PCA reconstruction method, especially in scenarios where training data are contaminated by a significant proportion of abnormal signals. Guidelines for the optimization of the kernel width are provided. The effectiveness of the correntropy PCA reconstruction-based anomaly detection method is validated using data collected from ten regions over an 80-day period, encompassing guided waves induced by damage occurring over durations ranging from 2 to 20 days.

To defend a network system from security risks, intrusion detection systems (IDSs) have been playing an important role in recent years. There are two types of detection algorithms of IDSs: misuse detection and anomaly detection. Because misuse detection is based on a signature which is created from the features of attack traffic by security experts, it can achieve accurate and stable detection. However, its weakness is the difficulty of detecting new attacks (i.e., 0-day attack), and the cost of maintaining the latest signature version. Thinking of the increase of the skillful intrusion, e.g., intrusion showing similar access behavior to normal, misuse detection cannot handle these critical attacks, which results in a large number of false alarms. To cope with these problems, we present a clustering algorithm based on an unsupervised anomaly detection. We evaluated our system using Kyoto2006+ data set and KDD Cup 1999 data set. Evaluation results show that our approach achieved a higher detection rate in the region of very low false positive rate and real-time preprocessing capability.

Effectively monitoring the operational status of reactor coolant pumps (RCPs) is crucial for enhancing the safety and stability of nuclear power operations. To address the challenges of limited interpretability and suboptimal detection performance in existing methods for detecting abnormal operating states of RCPs, this paper proposes an interpretable, unsupervised anomaly detection approach. This innovative method designs a framework that combines Kernel Self-Organizing Map (Kernel SOM) clustering with Bayesian Posterior Inference. Specifically, the proposed method uses Kernel SOM to extract typical patterns from normal operation data. Subsequently, a distance probability distribution model reflecting the data distribution structure within each cluster is constructed, providing a robust tool for data distribution analysis for anomaly detection. Finally, based on prior knowledge, such as distance probability distribution, the Bayesian Posterior Inference is employed to infer the probability of the equipment being in a normal state. By constructing distribution models that reflect data distribution structures and combining them with posterior inference, this approach realizes the traceability and interpretability of the anomaly detection process, improving the transparency of anomaly detection and enabling operators to understand the decision logic and the analysis of the causes of anomalous occurrences. Verification via real-world operational data demonstrates the method’s superior effectiveness. This work offers a highly interpretable solution for RCP anomaly detection, with significant implications for safety-critical applications in the nuclear energy sector.

A case of biventricular thrombi in a patient with dilated cardiomyopathy: Utility of multimodality imaging for diagnosis and management of treatment strategy