Feasibility of Universal Anomaly Detection without Knowing the Abnormality in Medical Images
Ontology highlight
ABSTRACT:
SUBMITTER: Cui C
PROVIDER: S-EPMC10959499 | biostudies-literature | 2023 Oct
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:We consider the privacy-preserving computation of node influence in distributed social networks, as measured by egocentric betweenness centrality (EBC). Motivated by modern communication networks spanning multiple providers, we show for the first time how multiple mutually-distrusting parties can successfully compute node EBC while revealing only differentially-private information about their internal network connections. A theoretical utility analysis upper bounds a primary source of private EBC error—private release of ego networks—with high probability. Empirical results demonstrate practical applicability with a low 1.07 relative error achievable at strong privacy budget Electronic supplementary material The online version of this chapter (10.1007/978-3-030-47436-2_12) contains supplementary material, which is available to authorized users.
| S-EPMC7206295 | biostudies-literature
Project description:This research offers a method for separating the components of tissue impedance, namely resistance and capacitive reactance. Two objects that have similar impedance or low contrast can be improved through separating the real and imaginary images. This method requires an Electrical Impedance Tomography (EIT) device. EIT can obtain potential data and the phase angle between the current and the potential measured. In the future, the device is very suitable for imaging organs in the thorax and abdomen that have the same impedance but different resistance and capacitive reactance. This device consists of programmable generators, Voltage Controlled Current Source (VCCS), mulptiplexer-demultiplexer potential meters, and phase meters. Data collecting was done by employing neighboring, while reconstruction was used the linear back-projection method from two different data frequencies, namely 10 kHz and 100 kHz. Phantom used in this experiment consists of distillated water and a carrot as an anomaly. Potential and phase data from the device is reconstructed to produce impedance, real, and imaginary images. Image analysis is performed by comparing the three images to the phantom. The experimental results show that the device is reliable.
| S-EPMC7181121 | biostudies-literature
Project description:Background aimsCell therapy is a promising treatment method that uses living cells to address a variety of diseases and conditions, including cardiovascular diseases, neurologic disorders and certain cancers. As interest in cell therapy grows, there is a need to shift to a more efficient, scalable and automated manufacturing process that can produce high-quality products at a lower cost.MethodsOne way to achieve this is using non-invasive imaging and real-time image analysis techniques to monitor and control the manufacturing process. This work presents a machine learning-based image analysis pipeline that includes semantic segmentation and anomaly detection capabilities.Results/conclusionsThis method can be easily implemented even when given a limited dataset of annotated images, is able to segment cells and debris and can identify anomalies such as contamination or hardware failure.
| S-EPMC10719834 | biostudies-literature
Project description:Establishing the invariance property of an instrument (e.g., a questionnaire or test) is a key step for establishing its measurement validity. Measurement invariance is typically assessed by differential item functioning (DIF) analysis, i.e., detecting DIF items whose response distribution depends not only on the latent trait measured by the instrument but also on the group membership. DIF analysis is confounded by the group difference in the latent trait distributions. Many DIF analyses require knowing several anchor items that are DIF-free in order to draw inferences on whether each of the rest is a DIF item, where the anchor items are used to identify the latent trait distributions. When no prior information on anchor items is available, or some anchor items are misspecified, item purification methods and regularized estimation methods can be used. The former iteratively purifies the anchor set by a stepwise model selection procedure, and the latter selects the DIF-free items by a LASSO-type regularization approach. Unfortunately, unlike the methods based on a correctly specified anchor set, these methods are not guaranteed to provide valid statistical inference (e.g., confidence intervals and p-values). In this paper, we propose a new method for DIF analysis under a multiple indicators and multiple causes (MIMIC) model for DIF. This method adopts a minimal [Formula: see text] norm condition for identifying the latent trait distributions. Without requiring prior knowledge about an anchor set, it can accurately estimate the DIF effects of individual items and further draw valid statistical inferences for quantifying the uncertainty. Specifically, the inference results allow us to control the type-I error for DIF detection, which may not be possible with item purification and regularized estimation methods. We conduct simulation studies to evaluate the performance of the proposed method and compare it with the anchor-set-based likelihood ratio test approach and the LASSO approach. The proposed method is applied to analysing the three personality scales of the Eysenck personality questionnaire-revised (EPQ-R).
| S-EPMC10656337 | biostudies-literature
Project description:Cancer is a highly heterogeneous condition best visualised in positron emission tomography. Due to this heterogeneity, a general-purpose cancer detection model can be built using unsupervised learning anomaly detection models. While prior work in this field has showcased the efficacy of abnormality detection methods (e.g. Transformer-based), these have shown significant vulnerabilities to differences in data geometry. Changes in image resolution or observed field of view can result in inaccurate predictions, even with significant data pre-processing and augmentation. We propose a new spatial conditioning mechanism that enables models to adapt and learn from varying data geometries, and apply it to a state-of-the-art Vector-Quantized Variational Autoencoder + Transformer abnormality detection model. We showcase that this spatial conditioning mechanism statistically-significantly improves model performance on whole-body data compared to the same model without conditioning, while allowing the model to perform inference at varying data geometries.
| S-EPMC7616404 | biostudies-literature
Project description:BackgroundPolarization of tissue is achieved by asymmetric distribution of proteins and organelles within individual cells. However, existing quantitative assays to measure this asymmetry in an automated and unbiased manner suffer from significant limitations.ResultsHere, we report a new way to assess protein and organelle localization in tissue based on correlative fluorescence analysis. As a proof of principle, we successfully characterized planar cell polarity dependent asymmetry in developing Drosophila melanogaster tissues on the single cell level using fluorescence cross-correlation.ConclusionsSystematic modulation of signal strength and distribution show that fluorescence cross-correlation reliably detects asymmetry over a broad parameter space. The novel method described here produces robust, rapid, and unbiased measurement of biometrical properties of cell components in live tissue that is readily applicable in other model systems.
| S-EPMC3469164 | biostudies-literature
Project description:BackgroundGallbladder agenesis (GA) is a very uncommon disorder of the biliary system. Diagnosis of GA can be difficult and may result in unnecessary procedures. In this case report, we will discuss our experience with an intraoperative accidental diagnosis of GA in a middle-aged woman that was effectively treated. Case Presentation. A 46-year-old woman presented with abdominal pain, nausea, vomiting, and intolerance to meals. Laparoscopic surgery was conducted based on sonographic imaging and a preliminary diagnosis of chronic cholecystitis. No gallbladder was seen during laparoscopy, and the patient was diagnosed as a case of GA. The laparoscopy was terminated, and the patient was referred for magnetic resonance cholangiopancreatography (MRCP) to confirm the diagnosis. Finally, endoscopic retrograde cholangiopancreatography (ERCP) and sphincterotomy were performed to alleviate symptoms. After one year of follow-up, the patient's overall condition is satisfactory and symptom-free.ConclusionOur case exemplifies this common blunder. Therefore, we are reporting a case of GA discovered intraoperatively to increase surgeons' awareness and preparedness for this possible differential diagnosis and minimize unnecessary operational intervention.
| S-EPMC9246627 | biostudies-literature
Project description:The collapse of ecosystems, the extinction of species, and the breakdown of economic and financial networks usually hinges on topological properties of the underlying networks, such as the existence of self-sustaining (or autocatalytic) feedback cycles. Such collapses can be understood as a massive change of network topology, usually accompanied by the extinction of a macroscopic fraction of nodes and links. It is often related to the breakdown of the last relevant directed catalytic cycle within a dynamical system. Without detailed structural information it seems impossible to state, whether a network is robust or if it is likely to collapse in the near future. Here we show that it is nevertheless possible to predict collapse for a large class of systems that are governed by a linear (or linearized) dynamics. To compute the corresponding early warning signal, we require only non-structural information about the nodes' states such as species abundances in ecosystems, or company revenues in economic networks. It is shown that the existence of a single directed cycle in the network can be detected by a "quantization effect" of node states, that exists as a direct consequence of a corollary of the Perron-Frobenius theorem. The proposed early warning signal for the collapse of networked systems captures their structural instability without relying on structural information. We illustrate the validity of the approach in a transparent model of co-evolutionary ecosystems and show this quantization in systems of species evolution, epidemiology, and population dynamics.
| S-EPMC6985233 | biostudies-literature
Project description:Hyperspectral images include information from a wide range of spectral bands deemed valuable for computer vision applications in various domains such as agriculture, surveillance, and reconnaissance. Anomaly detection in hyperspectral images has proven to be a crucial component of change and abnormality identification, enabling improved decision-making across various applications. These abnormalities/anomalies can be detected using background estimation techniques that do not require the prior knowledge of outliers. However, each hyperspectral anomaly detection (HS-AD) algorithm models the background differently. These different assumptions may fail to consider all the background constraints in various scenarios. We have developed a new approach called Greedy Ensemble Anomaly Detection (GE-AD) to address this shortcoming. It includes a greedy search algorithm to systematically determine the suitable base models from HS-AD algorithms and hyperspectral unmixing for the first stage of a stacking ensemble and employs a supervised classifier in the second stage of a stacking ensemble. It helps researchers with limited knowledge of the suitability of the HS-AD algorithms for the application scenarios to select the best methods automatically. Our evaluation shows that the proposed method achieves a higher average F1-macro score with statistical significance compared to the other individual methods used in the ensemble. This is validated on multiple datasets, including the Airport-Beach-Urban (ABU) dataset, the San Diego dataset, the Salinas dataset, the Hydice Urban dataset, and the Arizona dataset. The evaluation using the airport scenes from the ABU dataset shows that GE-AD achieves a 14.97% higher average F1-macro score than our previous method (HUE-AD), at least 17.19% higher than the individual methods used in the ensemble, and at least 28.53% higher than the other state-of-the-art ensemble anomaly detection algorithms. As using the combination of greedy algorithm and stacking ensemble to automatically select suitable base models and associated weights have not been widely explored in hyperspectral anomaly detection, we believe that our work will expand the knowledge in this research area and contribute to the wider application of this approach.
| S-EPMC11204925 | biostudies-literature
Project description:Relative scores such as Local Outlying Factor and mass ratio have been shown to be better scores than global scores in detecting anomalies. While this is true, our analysis reveals for the first time that these relative scores have a key shortcoming: anomalies have greatly different relative scores if they are located in different regions where the curvatures of the density surface are very different. As a result, the low-score anomalies could be ranked lower than some normal points. This revelation motivates (i) a new score called Neighbourhood Contrast (NC) which produces approximately the same high scores for all anomalies, regardless of varying curvatures of the density surface in different regions; and (ii) an anomaly detection method based on NC. Our experiments show that the proposed method which employs the new score significantly outperforms methods using the aforementioned relative scores on benchmark datasets.
| S-EPMC7206296 | biostudies-literature