LIVIVO - Das Suchportal für Lebenswissenschaften

switch to English language
Zurück zur letzten Suche Suchhistorie
Erweiterte Suche

Ihre letzten Suchen

  1. AU="Baugh, Matthew"
  2. AU="Qu, C"
  3. AU="Flett, Heather"
  4. AU="Shueh Lin Lim"
  5. AU="Schröder, Johann"
  6. AU=Butler Taylor
  7. AU="Yang, Fan"
  8. AU="Giacomo Frati"
  9. AU=Kokhaei P
  10. AU="Charikleia Triantopoulou"
  11. AU="Salil Bhargava"
  12. AU="Jong-Eun Lee"
  13. AU="Vargas C, Laura"

Suchergebnis

Treffer 1 - 7 von insgesamt 7

Suchoptionen

  1. Buch ; Online: Zero-Shot Anomaly Detection with Pre-trained Segmentation Models

    Baugh, Matthew / Batten, James / Müller, Johanna P. / Kainz, Bernhard

    2023  

    Abstract: This technical report outlines our submission to the zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. Building on the performance of the WINCLIP framework, we aim to enhance the system's localization capabilities by ... ...

    Abstract This technical report outlines our submission to the zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. Building on the performance of the WINCLIP framework, we aim to enhance the system's localization capabilities by integrating zero-shot segmentation models. In addition, we perform foreground instance segmentation which enables the model to focus on the relevant parts of the image, thus allowing the models to better identify small or subtle deviations. Our pipeline requires no external data or information, allowing for it to be directly applied to new datasets. Our team (Variance Vigilance Vanguard) ranked third in the zero-shot track of the VAND challenge, and achieve an average F1-max score of 81.5/24.2 at a sample/pixel level on the VisA dataset.

    Comment: Ranked 3rd in zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2023-06-15
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  2. Buch ; Online: Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models

    Dombrowski, Mischa / Reynaud, Hadrien / Baugh, Matthew / Kainz, Bernhard

    2022  

    Abstract: Curating datasets for object segmentation is a difficult task. With the advent of large-scale pre-trained generative models, conditional image generation has been given a significant boost in result quality and ease of use. In this paper, we present a ... ...

    Abstract Curating datasets for object segmentation is a difficult task. With the advent of large-scale pre-trained generative models, conditional image generation has been given a significant boost in result quality and ease of use. In this paper, we present a novel method that enables the generation of general foreground-background segmentation models from simple textual descriptions, without requiring segmentation labels. We leverage and explore pre-trained latent diffusion models, to automatically generate weak segmentation masks for concepts and objects. The masks are then used to fine-tune the diffusion model on an inpainting task, which enables fine-grained removal of the object, while at the same time providing a synthetic foreground and background dataset. We demonstrate that using this method beats previous methods in both discriminative and generative performance and closes the gap with fully supervised training while requiring no pixel-wise object labels. We show results on the task of segmenting four different objects (humans, dogs, cars, birds) and a use case scenario in medical image analysis. The code is available at https://github.com/MischaD/fobadiffusion.

    Comment: Accepted at ICCV2023
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition
    Thema/Rubrik (Code) 004
    Erscheinungsdatum 2022-12-29
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  3. Artikel: Interventions to minimize complications in hospitalized patients with Parkinson disease.

    Aslam, Sana / Simpson, Edith / Baugh, Matthew / Shill, Holly

    Neurology. Clinical practice

    2020  Band 10, Heft 1, Seite(n) 23–28

    Abstract: Background: In this study, we sought to evaluate the efficacy of inpatient interventions on hospitalization-related complications in patients with Parkinson disease (PD). Hospitalized patients with PD have an increased risk of complications. Although ... ...

    Abstract Background: In this study, we sought to evaluate the efficacy of inpatient interventions on hospitalization-related complications in patients with Parkinson disease (PD). Hospitalized patients with PD have an increased risk of complications. Although several interventions have been suggested in the literature, data-driven recommendations are limited.
    Methods: This study was designed as a prospective cohort study. A hospital-wide alert system was incorporated into the electronic medical record (EMR) system. The alert was triggered when a patient with PD or on dopaminergic therapy was admitted prompting the inpatient pharmacy to confirm medication details. A warning was also triggered if antidopaminergic medications were ordered. In-services were performed for nursing staff and physicians regarding these measures. Charts of patients with PD admitted 6 months before and after the intervention were reviewed to serve as the 2 comparison groups.
    Results: There were 73 patients (mean 73.2 years) preintervention group and 103 patients (mean 72.3 years) postintervention group. There were no significant differences in reasons for admission, admission to neurologic vs non-neurologic floor, or admitting service between the groups. The percentage of patients for whom contraindicated medications were ordered decreased from 42.5% to 17.5% (
    Conclusion: An intervention involving EMR alerts and in-service didactics for nurses and physicians decreased the frequency of contraindicated medications ordered in hospitalized patients with PD, but it did not change other hospital outcomes or complications.
    Sprache Englisch
    Erscheinungsdatum 2020-03-16
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ZDB-ID 2645818-4
    ISSN 2163-0933 ; 2163-0402
    ISSN (online) 2163-0933
    ISSN 2163-0402
    DOI 10.1212/CPJ.0000000000000709
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Über subito bestellen

    Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

  4. Buch ; Online: Confidence-Aware and Self-Supervised Image Anomaly Localisation

    Müller, Johanna P. / Baugh, Matthew / Tan, Jeremy / Dombrowski, Mischa / Kainz, Bernhard

    2023  

    Abstract: Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class of normative samples, e.g., through epistemic uncertainty estimates, auto- ...

    Abstract Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class of normative samples, e.g., through epistemic uncertainty estimates, auto-encoding models, or from synthetic anomalies in a self-supervised way. The performance of self-supervised anomaly detection approaches is still inferior compared to methods that use examples from known unknown classes to shape the decision boundary. However, outlier exposure methods often do not identify unknown unknowns. Here we discuss an improved self-supervised single-class training strategy that supports the approximation of probabilistic inference with loosen feature locality constraints. We show that up-scaling of gradients with histogram-equalised images is beneficial for recently proposed self-supervision tasks. Our method is integrated into several out-of-distribution (OOD) detection models and we show evidence that our method outperforms the state-of-the-art on various benchmark datasets.

    Comment: Accepted for MICCAI UNSURE Workshop 2023 (Spotlight)
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition ; Electrical Engineering and Systems Science - Image and Video Processing
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2023-03-23
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  5. Buch ; Online: DISYRE

    Marimont, Sergio Naval / Baugh, Matthew / Siomos, Vasilis / Tzelepis, Christos / Kainz, Bernhard / Tarroni, Giacomo

    Diffusion-Inspired SYnthetic REstoration for Unsupervised Anomaly Detection

    2023  

    Abstract: Unsupervised Anomaly Detection (UAD) techniques aim to identify and localize anomalies without relying on annotations, only leveraging a model trained on a dataset known to be free of anomalies. Diffusion models learn to modify inputs $x$ to increase the ...

    Abstract Unsupervised Anomaly Detection (UAD) techniques aim to identify and localize anomalies without relying on annotations, only leveraging a model trained on a dataset known to be free of anomalies. Diffusion models learn to modify inputs $x$ to increase the probability of it belonging to a desired distribution, i.e., they model the score function $\nabla_x \log p(x)$. Such a score function is potentially relevant for UAD, since $\nabla_x \log p(x)$ is itself a pixel-wise anomaly score. However, diffusion models are trained to invert a corruption process based on Gaussian noise and the learned score function is unlikely to generalize to medical anomalies. This work addresses the problem of how to learn a score function relevant for UAD and proposes DISYRE: Diffusion-Inspired SYnthetic REstoration. We retain the diffusion-like pipeline but replace the Gaussian noise corruption with a gradual, synthetic anomaly corruption so the learned score function generalizes to medical, naturally occurring anomalies. We evaluate DISYRE on three common Brain MRI UAD benchmarks and substantially outperform other methods in two out of the three tasks.

    Comment: 5 pages, 3 figures
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition ; Electrical Engineering and Systems Science - Image and Video Processing
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2023-11-26
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  6. Buch ; Online: Trade-offs in Fine-tuned Diffusion Models Between Accuracy and Interpretability

    Dombrowski, Mischa / Reynaud, Hadrien / Müller, Johanna P. / Baugh, Matthew / Kainz, Bernhard

    2023  

    Abstract: Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-trained models using domain-specific text-to-image datasets. Notably, this ... ...

    Abstract Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-trained models using domain-specific text-to-image datasets. Notably, this method has been readily employed for medical applications, such as X-ray image synthesis, leveraging the plethora of associated radiology reports. Yet, a prevailing concern is the lack of assurance on whether these models genuinely comprehend their generated content. With the evolution of text-conditional image generation, these models have grown potent enough to facilitate object localization scrutiny. Our research underscores this advancement in the critical realm of medical imaging, emphasizing the crucial role of interpretability. We further unravel a consequential trade-off between image fidelity as gauged by conventional metrics and model interpretability in generative diffusion models. Specifically, the adoption of learnable text encoders when fine-tuning results in diminished interpretability. Our in-depth exploration uncovers the underlying factors responsible for this divergence. Consequently, we present a set of design principles for the development of truly interpretable generative models. Code is available at https://github.com/MischaD/chest-distillation.
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2023-03-31
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

  7. Buch ; Online: Many tasks make light work

    Baugh, Matthew / Tan, Jeremy / Müller, Johanna P. / Dombrowski, Mischa / Batten, James / Kainz, Bernhard

    Learning to localise medical anomalies from multiple synthetic tasks

    2023  

    Abstract: There is a growing interest in single-class modelling and out-of-distribution detection as fully supervised machine learning models cannot reliably identify classes not included in their training. The long tail of infinitely many out-of-distribution ... ...

    Abstract There is a growing interest in single-class modelling and out-of-distribution detection as fully supervised machine learning models cannot reliably identify classes not included in their training. The long tail of infinitely many out-of-distribution classes in real-world scenarios, e.g., for screening, triage, and quality control, means that it is often necessary to train single-class models that represent an expected feature distribution, e.g., from only strictly healthy volunteer data. Conventional supervised machine learning would require the collection of datasets that contain enough samples of all possible diseases in every imaging modality, which is not realistic. Self-supervised learning methods with synthetic anomalies are currently amongst the most promising approaches, alongside generative auto-encoders that analyse the residual reconstruction error. However, all methods suffer from a lack of structured validation, which makes calibration for deployment difficult and dataset-dependant. Our method alleviates this by making use of multiple visually-distinct synthetic anomaly learning tasks for both training and validation. This enables more robust training and generalisation. With our approach we can readily outperform state-of-the-art methods, which we demonstrate on exemplars in brain MRI and chest X-rays. Code is available at https://github.com/matt-baugh/many-tasks-make-light-work .

    Comment: Early accepted to MICCAI 2023
    Schlagwörter Computer Science - Computer Vision and Pattern Recognition
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2023-07-03
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    Fernleihe an ZB MED

    Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Zum Seitenanfang