Search

Your search keyword '"Becker, Anton S."' showing total 526 results
Start Over Author "Becker, Anton S."
526 results on '"Becker, Anton S."'

3. Author Correction: Predicting standardized uptake value of brown adipose tissue from CT scans using convolutional neural networks

Author

Erdil, Ertunc, Becker, Anton S., Schwyzer, Moritz, Martinez-Tellez, Borja, Ruiz, Jonatan R., Sartoretti, Thomas, Vargas, H. Alberto, Burger, A. Irene, Chirindel, Alin, Wild, Damian, Zamboni, Nicola, Deplancke, Bart, Gardeux, Vincent, Maushart, Claudia Irene, Betz, Matthias Johannes, Wolfrum, Christian, and Konukoglu, Ender

Published
2024
Full Text
View/download PDF

7. H&E-based Computational Biomarker Enables Universal EGFR Screening for Lung Adenocarcinoma

Author

Campanella, Gabriele, Ho, David, Häggström, Ida, Becker, Anton S, Chang, Jason, Vanderbilt, Chad, and Fuchs, Thomas J

Subjects
Computer Science - Computer Vision and Pattern Recognition, Quantitative Biology - Quantitative Methods
Abstract

Lung cancer is the leading cause of cancer death worldwide, with lung adenocarcinoma being the most prevalent form of lung cancer. EGFR positive lung adenocarcinomas have been shown to have high response rates to TKI therapy, underlying the essential nature of molecular testing for lung cancers. Despite current guidelines consider testing necessary, a large portion of patients are not routinely profiled, resulting in millions of people not receiving the optimal treatment for their lung cancer. Sequencing is the gold standard for molecular testing of EGFR mutations, but it can take several weeks for results to come back, which is not ideal in a time constrained scenario. The development of alternative screening tools capable of detecting EGFR mutations quickly and cheaply while preserving tissue for sequencing could help reduce the amount of sub-optimally treated patients. We propose a multi-modal approach which integrates pathology images and clinical variables to predict EGFR mutational status achieving an AUC of 84% on the largest clinical cohort to date. Such a computational model could be deployed at large at little additional cost. Its clinical application could reduce the number of patients who receive sub-optimal treatments by 53.1% in China, and up to 96.6% in the US.

Published
2022

9. Combining PCR and CT testing for COVID

Author

Shen, Chen, Mark, Ron, Kagetsu, Nolan J., Becker, Anton S., and Bar-Yam, Yaneer

Subjects
Quantitative Biology - Populations and Evolution, Nonlinear Sciences - Adaptation and Self-Organizing Systems, Physics - Physics and Society, Statistics - Applications
Abstract

We analyze the effect of using a screening CT-scan for evaluation of potential COVID-19 infections in order to isolate and perform contact tracing based upon a viral pneumonia diagnosis. RT-PCR is then used for continued isolation based upon a COVID diagnosis. Both the low false negative rates and rapid results of CT-scans lead to dramatically reduced transmission. The reduction in cases after 60 days with widespread use of CT-scan screening compared to PCR by itself is as high as $50\times$, and the reduction of effective reproduction rate $R(t)$ is $0.20$. Our results imply that much more rapid extinction of COVID is possible by combining social distancing with CT-scans and contact tracing., Comment: 6 pages, 14 figures

Published
2020

10. PHiSeg: Capturing Uncertainty in Medical Image Segmentation

Author

Baumgartner, Christian F., Tezcan, Kerem C., Chaitanya, Krishna, Hötker, Andreas M., Muehlematter, Urs J., Schawkat, Khoschy, Becker, Anton S., Donati, Olivio, and Konukoglu, Ender

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Segmentation of anatomical structures and pathologies is inherently ambiguous. For instance, structure borders may not be clearly visible or different experts may have different styles of annotating. The majority of current state-of-the-art methods do not account for such ambiguities but rather learn a single mapping from image to segmentation. In this work, we propose a novel method to model the conditional probability distribution of the segmentations given an input image. We derive a hierarchical probabilistic model, in which separate latent variables are responsible for modelling the segmentation at different resolutions. Inference in this model can be efficiently performed using the variational autoencoder framework. We show that our proposed method can be used to generate significantly more realistic and diverse segmentation samples compared to recent related work, both, when trained with annotations from a single or multiple annotators., Comment: Accepted to MICCAI 2019

Published
2019

13. Adversarial Augmentation for Enhancing Classification of Mammography Images

Author

Jendele, Lukas, Skopek, Ondrej, Becker, Anton S., and Konukoglu, Ender

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Supervised deep learning relies on the assumption that enough training data is available, which presents a problem for its application to several fields, like medical imaging. On the example of a binary image classification task (breast cancer recognition), we show that pretraining a generative model for meaningful image augmentation helps enhance the performance of the resulting classifier. By augmenting the data, performance on downstream classification tasks could be improved even with a relatively small training set. We show that this "adversarial augmentation" yields promising results compared to classical image augmentation on the example of breast cancer classification.

Published
2019

15. Injecting and removing malignant features in mammography with CycleGAN: Investigation of an automated adversarial attack using neural networks

Author

Becker, Anton S., Jendele, Lukas, Skopek, Ondrej, Berger, Nicole, Ghafoor, Soleen, Marcon, Magda, and Konukoglu, Ender

Subjects
Computer Science - Computer Vision and Pattern Recognition, 68T45
Abstract

$\textbf{Purpose}$ To train a cycle-consistent generative adversarial network (CycleGAN) on mammographic data to inject or remove features of malignancy, and to determine whether these AI-mediated attacks can be detected by radiologists. $\textbf{Material and Methods}$ From the two publicly available datasets, BCDR and INbreast, we selected images from cancer patients and healthy controls. An internal dataset served as test data, withheld during training. We ran two experiments training CycleGAN on low and higher resolution images ($256 \times 256$ px and $512 \times 408$ px). Three radiologists read the images and rated the likelihood of malignancy on a scale from 1-5 and the likelihood of the image being manipulated. The readout was evaluated by ROC analysis (Area under the ROC curve = AUC). $\textbf{Results}$ At the lower resolution, only one radiologist exhibited markedly lower detection of cancer (AUC=0.85 vs 0.63, p=0.06), while the other two were unaffected (0.67 vs. 0.69 and 0.75 vs. 0.77, p=0.55). Only one radiologist could discriminate between original and modified images slightly better than guessing/chance (0.66, p=0.008). At the higher resolution, all radiologists showed significantly lower detection rate of cancer in the modified images (0.77-0.84 vs. 0.59-0.69, p=0.008), however, they were now able to reliably detect modified images due to better visibility of artifacts (0.92, 0.92 and 0.97). $\textbf{Conclusion}$ A CycleGAN can implicitly learn malignant features and inject or remove them so that a substantial proportion of small mammographic images would consequently be misdiagnosed. At higher resolutions, however, the method is currently limited and has a clear trade-off between manipulation of images and introduction of artifacts., Comment: To be presented at RSNA 2018

Published
2018

24. Gouty arthritis: Can we avoid unnecessary dual-energy CT examinations using prior radiographs?

Author

Kupfer, Sivert, Winklhofer, Sebastian, Becker, Anton S, Distler, Oliver, Chung, Christine B, Alkadhi, Hatem, and Finkenstaedt, Tim

Subjects
Biomedical and Clinical Sciences, Clinical Sciences, Clinical Trials and Supportive Activities, Clinical Research, Biomedical Imaging, Detection, screening and diagnosis, 4.2 Evaluation of markers and technologies, Adult, Aged, Algorithms, Arthritis, Gouty, False Negative Reactions, Female, Gout, Humans, Male, Middle Aged, Observer Variation, Radiographic Image Interpretation, Computer-Assisted, Radiography, Dual-Energy Scanned Projection, Retrospective Studies, Sensitivity and Specificity, Uric Acid, General Science & Technology
Abstract

ObjectiveThe dual-energy CT (DECT) algorithm for urate detection is feasible only if hyperdense deposits are present. Based on our experience, around half of the performed DECT examinations show no such deposits and thus were useless for this indication. Our diagnostic accuracy study investigates whether conventional radiographs can serve as gatekeeper test prior to DECT for reliable exclusion of such radiopaque deposits.Materials and methodsIn this retrospective study, 77 clinically indicated DECT examinations of the hand (n = 29), foot (n = 36) and ankle (n = 12) of 55 patients (13 female, mean age 62±15 years) with suspected gouty arthritis were included. Two blinded readers independently evaluated DECT, gray-scale CT images (reference standard) and corresponding standardized radiographs for the presence/location of dense soft tissue deposits.ResultsInterreader agreement for detection of soft tissue deposits with DECT and radiographs was excellent (DECT: both readers, κ = 1; radiographs: both readers, κ = 0.94). DECT showed soft tissue deposits in 54/77 DECT (70%) scans. 30/54 scans (56%) showed deposits on the corresponding radiographs, while in 24 scans (44%) no deposits were seen on radiographs. Test performance of radiographs for soft tissue deposit detection: sensitivity 56%, specificity 100%, PPV 100%, NPV 48.9%, and accuracy 69%. Low density of the deposits was the main reasons for false-negative radiographs (19 cases, 79%), followed by superimposition of deposits by osseous structures (5 cases, 21%).ConclusionConventional radiographs of the hand, foot and ankle cannot serve as a gatekeeper test for reliable exclusion of radiopaque soft tissue deposits prior to DECT.

Published
2018

32. Inguinal lymph node metastases from prostate cancer: clinical, pathology, and multimodality imaging considerations

Author

Woo, Sungmin; https://orcid.org/0000-0001-8459-8369, Becker, Anton S; https://orcid.org/0000-0001-8372-6496, Ghafoor, Soleen; https://orcid.org/0000-0002-8459-7363, Barbosa, Felipe de Galiza; https://orcid.org/0000-0002-3986-1778, Arita, Yuki; https://orcid.org/0000-0002-5285-0352, Vargas, Hebert A; https://orcid.org/0000-0003-1169-133X, Woo, Sungmin; https://orcid.org/0000-0001-8459-8369, Becker, Anton S; https://orcid.org/0000-0001-8372-6496, Ghafoor, Soleen; https://orcid.org/0000-0002-8459-7363, Barbosa, Felipe de Galiza; https://orcid.org/0000-0002-3986-1778, Arita, Yuki; https://orcid.org/0000-0002-5285-0352, and Vargas, Hebert A; https://orcid.org/0000-0003-1169-133X

Abstract

OBJECTIVE: To investigate clinical, pathology, and imaging findings associated with inguinal lymph node (LN) metastases in patients with prostate cancer (PCa). MATERIALS AND METHODS: This was a retrospective single-center study of patients with PCa who underwent imaging and inguinal LN biopsy between 2000 and 2023. We assessed the following aspects on multimodality imaging: inguinal LN morphology; extrainguinal lymphadenopathy; the extent of primary and recurrent tumors; and non-nodal metastases. Imaging, clinical, and pathology features were compared between patients with and without metastatic inguinal LNs. RESULTS: We evaluated 79 patients, of whom 38 (48.1%) had pathology-proven inguinal LN metastasis. Certain imaging aspects- short-axis diameter, prostate-specific membrane antigen uptake on positron-emission tomography, membranous urethra involvement by the tumor, extra-inguinal lymphadenopathy, and distant metastases-were associated with pathology-proven inguinal LN metastases (p < 0.01 for all). Associations with long-axis diameter, fatty hilum, laterality, and uptake of other tracers on positronemission tomography were not significant (p = 0.09-1.00). The patients with metastatic inguinal LNs had higher prostate-specific antigen levels and more commonly had castration-resistant PCa (p < 0.01), whereas age, histological grade, and treatment type were not significant factors (p = 0.07-0.37). None of the patients had inguinal LN metastasis in the absence of locally advanced disease with membranous urethra involvement or distant metastasis. CONCLUSION: Several imaging, clinical, and pathology features are associated with inguinal LN metastases in patients with PCa. Isolated metastasis to inguinal LNs is extremely rare and unlikely to occur in the absence of high-risk imaging, clinical, or pathology features. // OBJETIVO: Investigar achados clinicopatológicos e de imagem associados a metástases linfonodais inguinais em pacientes com câncer de próstata (CaP). MATE

Published
2024

37. Comparison of Magnetic Resonance Imaging-stratified Clinical Pathways and Systematic Transrectal Ultrasound-guided Biopsy Pathway for the Detection of Clinically Significant Prostate Cancer: A Systematic Review and Meta-analysis of Randomized Controlled Trials

Author

Woo, Sungmin, Suh, Chong Hyun, Eastham, James A., Zelefsky, Michael J., Morris, Michael J., Abida, Wassim, Scher, Howard I., Sidlow, Robert, Becker, Anton S., Wibmer, Andreas G., Hricak, Hedvig, and Vargas, Hebert Alberto

Published
2019
Full Text
View/download PDF

38. Inhibition of Mevalonate Pathway Prevents Adipocyte Browning in Mice and Men by Affecting Protein Prenylation

Author

Balaz, Miroslav, Becker, Anton S., Balazova, Lucia, Straub, Leon, Müller, Julian, Gashi, Gani, Maushart, Claudia Irene, Sun, Wenfei, Dong, Hua, Moser, Caroline, Horvath, Carla, Efthymiou, Vissarion, Rachamin, Yael, Modica, Salvatore, Zellweger, Caroline, Bacanovic, Sara, Stefanicka, Patrik, Varga, Lukas, Ukropcova, Barbara, Profant, Milan, Opitz, Lennart, Amri, Ez-Zoubir, Akula, Murali K., Bergo, Martin, Ukropec, Jozef, Falk, Christian, Zamboni, Nicola, Betz, Matthias Johannes, Burger, Irene A., and Wolfrum, Christian

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results