Search

Your search keyword '"Ward, Aaron D."' showing total 37 results
Start Over Author "Ward, Aaron D." Publisher spie
37 results on '"Ward, Aaron D."'

4. 3D human lung histology reconstruction and registration to in vivo imaging

Author

Johnson, Carol, primary, Landis, Mark, primary, Inculet, Richard, primary, Malthaner, Richard, primary, Fortin, Dalilah, primary, Rodrigues, George B., primary, Yaremko, Brian P., primary, Palma, David A., primary, Mattonen, Sarah A., primary, Ward, Aaron D., primary, Louie, Alexander V., primary, Pentinga, Sean, primary, and Kwan, Keith, primary

Published
2018
Full Text
View/download PDF

7. Models of temporal enhanced ultrasound data for prostate cancer diagnosis: the impact of time-series order

Author

Nahlawi, Layan, additional, Goncalves, Caroline, additional, Imani, Farhad, additional, Gaed, Mena, additional, Gomez, Jose A., additional, Moussa, Madeleine, additional, Gibson, Eli, additional, Fenster, Aaron, additional, Ward, Aaron D., additional, Abolmaesumi, Purang, additional, Mousavi, Parvin, additional, and Shatkay, Hagit, additional

Published
2017
Full Text
View/download PDF

9. Fusion of multi-parametric MRI and temporal ultrasound for characterization of prostate cancer: in vivo feasibility study

Author

Imani, Farhad, additional, Ghavidel, Sahar, additional, Abolmaesumi, Purang, additional, Khallaghi, Siavash, additional, Gibson, Eli, additional, Khojaste, Amir, additional, Gaed, Mena, additional, Moussa, Madeleine, additional, Gomez, Jose A., additional, Romagnoli, Cesare, additional, Cool, Derek W., additional, Bastian-Jordan, Matthew, additional, Kassam, Zahra, additional, Siemens, D. Robert, additional, Leveridge, Michael, additional, Chang, Silvia, additional, Fenster, Aaron, additional, Ward, Aaron D., additional, and Mousavi, Parvin, additional

Published
2016
Full Text
View/download PDF

12. Classification of prostate cancer grade using temporal ultrasound: in vivo feasibility study

Author

Ghavidel, Sahar, additional, Imani, Farhad, additional, Khallaghi, Siavash, additional, Gibson, Eli, additional, Khojaste, Amir, additional, Gaed, Mena, additional, Moussa, Madeleine, additional, Gomez, Jose A., additional, Siemens, D. Robert, additional, Leveridge, Michael, additional, Chang, Silvia, additional, Fenster, Aaron, additional, Ward, Aaron D., additional, Abolmaesumi, Purang, additional, and Mousavi, Parvin, additional

Published
2016
Full Text
View/download PDF

17. Multiparametric MR imaging of prostate cancer foci: assessing the detectability and localizability of Gleason 7 peripheral zone cancers based on image contrasts

Author

Gibson, Eli, additional, Gaed, Mena, additional, Hrinivich, Thomas, additional, Gómez, José A., additional, Moussa, Madeleine, additional, Romagnoli, Cesare, additional, Mandel, Jonathan, additional, Bastian-Jordan, Matthew, additional, Cool, Derek W., additional, Ghoul, Suha, additional, Pautler, Stephen E., additional, Chin, Joseph L., additional, Crukley, Cathie, additional, Bauman, Glenn S., additional, Fenster, Aaron, additional, and Ward, Aaron D., additional

Published
2014
Full Text
View/download PDF

19. Accuracy and variability of tumor burden measurement on multi-parametric MRI

Author

Salarian, Mehrnoush, additional, Gibson, Eli, additional, Shahedi, Maysam, additional, Gaed, Mena, additional, Gómez, José A., additional, Moussa, Madeleine, additional, Romagnoli, Cesare, additional, Cool, Derek W., additional, Bastian-Jordan, Matthew, additional, Chin, Joseph L., additional, Pautler, Stephen, additional, Bauman, Glenn S., additional, and Ward, Aaron D., additional

Published
2014
Full Text
View/download PDF

33. Deep learning segmentation of invasive melanoma

Author

Shah, Aman, Mehta, Amal, Wang, Michael, Neumann, Neil, Zakhor, Avideh, McCalmont, Timothy, Tomaszewski, John E, and Ward, Aaron D

Subjects
Clinical Research, Cancer
Abstract

Melanoma is the deadliest skin cancer with the fastest rising incidence rate in the United States. The most important predictor of melanoma patient survival is the volume of invasive tumor at the initial biopsy. The appearance of in-situ melanoma in epidermis and invasive melanoma in dermis, which invades the underlying soft tissue and drives mortality, is often visually similar. We propose a novel two-stage method to segment invasive melanoma. The first stage computes two segmentation maps, one for tumor vs non-tumor and one for dermis vs epidermis. These two segmentation prediction maps of tumor and epidermis from the first stage combine to yield invasive melanoma predictions. Our method utilizes multiple resolutions and downscaling to increase information passed to the model and to improve model accuracy. Using an HRNet+OCR model for both epidermis and melanoma segmentation in our proposed two-stage system results in a marked improvement of F1 score (mIoU) to 0.44 (0.64) as compared to the current state-of-the-art of 0.14 (0.53).

Published
2023

34. Anonymising pathology data using generative adversarial networks

Author

David Morrison, David Harris-Birtill, Tomaszewski, John E., Ward, Aaron D., Richard M., and University of St Andrews. School of Computer Science

Subjects
MCC, QA75, Generative adversarial networks, Anonymisation, RC0254 Neoplasms. Tumors. Oncology (including Cancer), QA75 Electronic computers. Computer science, Histopathology, DAS, QA76, RC0254, QA76 Computer software, SDG 3 - Good Health and Well-being, RB Pathology, Digital pathology, Medical anonymisation, GANs, RB
Abstract

Anonymising medical data for use in machine learning is important to preserve patient privacy and, in many circumstances, is a requirement before data can be made available. One approach to anonymising image data is to train a generative model to produce data that is statistically similar to the input data and then use the output of the model for downstream tasks, such as image classification, instead of the original sensitive data. In digital pathology, it's not yet well understood how using generative models to anonymise histology slide data impacts the performance of downstream tasks. To begin addressing this, we present an evaluation of a histology image classifier trained using patches extracted from the Camelyon 16 dataset and compare it to a classifier trained on the same number of synthetic images generated with a Deep Convolutional Generative Adversarial Network (DCGAN), from the same data. When predicting the class of an image patch as either cancer or normal it's shown that the accuracy reduces from 0.78 for original alone to 0.59 for synthetic alone, and the recall is significantly reduced from 0.70 to 0.44 when training exclusively on the same amount of synthetic data. If retaining a similar accuracy is required for the downstream task, then either the original data must be used or an improved anonymisation strategy must be devised. We conclude that using this DCGAN to anonymise the dataset, degrades the accuracy of the classifier which implies that it has failed to capture the required variation in the original data to generalise and act as a sufficient anonymisation strategy. Publisher PDF Publisher PDF

Published
2022

35. Display systems for digital pathology: what are proper luminance, contrast and resolution settings?

Author

Varun Vasudev, Albert Xthona, Tom R. L. Kimpe, Tomaszewski, John E., Ward, Aaron D., and Levenson, Richard M.

Subjects
FORMULA, Technology and Engineering, workflow, observer, Digital pathology, COLOR, viewing conditions, display, visualization
Abstract

The past few years digital pathology has been widely adopted. The display system is a crucial component in the overall digital pathology system, since pathologists decide based upon images visualized on the display. Quality of the display can influence clinical performance, but also workflow efficiency and ergonomics. Performance of radiology display systems has been extensively studied, and this resulted into standardization and clear requirements and guidelines. Digital pathology images and viewing conditions are very different compared to radiology. Fewer effort has gone in understanding what makes a digital pathology display fit for use, and there is no consensus yet in the digital pathology community about ideal specifications for digital pathology displays. This paper studies specific characteristics of digital pathology display systems, such as luminance, contrast and resolution. Effects of these characteristics on visibility of relevant pathological features is described, and recommendations are made for clinically meaningful levels of luminance, contrast and resolution.

Published
2022

36. Generative modeling for label-free glomerular modeling and classification

Author

Kuang-Yu Jen, Wen Dong, Brendon Lutnick, Pinaki Sarder, Brandon Ginley, Tomaszewski, John E, and Ward, Aaron D

Subjects
business.industry, Computer science, generative adversarial network, Bioengineering, Pattern recognition, glomeruli, Real image, ENCODE, Class (biology), Article, Unsupervised data-mining, Generative modeling, variational autoencoder, Relevance (information retrieval), Artificial intelligence, business, Generative adversarial network, Generative grammar, Label free
Abstract

Generative modeling using GANs has gained traction in machine learning literature, as training does not require labeled datasets. This is perfect for applications in biological datasets, where large labeled datasets are often difficult and expensive to acquire. However, generative models offer no easy way to encode real images into feature-sets, something that is desirable for network explainability and may yield potentially informative image features. For this reason, we test a VAE-GAN architecture for label-free modeling of glomerular structural features. We show that this network can generate realistic looking synthetic images, and be used to interpolate between images. To prove the biological relevance of the network encodings, we classify small-labeled sets of encoded glomeruli by biopsy Tervaert class and for the presence of sclerosis, obtaining a Cohen’s kappa values of 0.87 and 0.78 respectfully.

Published
2020

37. Cancer detection in mass spectrometry imaging data by dilated convolutional neural networks

Author

van Kersbergen, Jannis, Zanjani, F.G., Zinger, S., van der Sommen, Fons, Balluff, Benjamin, Vos, Naomi, Ellis, Shane, Heeren, Ron, Lucas, Marit, Marquering, Henk, Jansen, I., Savci-Heijink, C. D., de Bruin, D.M., de With, Peter H. N., Tomaszewski, JE, Ward, AD, Tomaszewski, John E., Ward, Aaron D., RS: M4I - Imaging Mass Spectrometry (IMS), Imaging Mass Spectrometry (IMS), Pathology, Electrical Engineering, Video Coding & Architectures, Signal Processing Systems, Center for Care & Cure Technology Eindhoven, Biomedical Diagnostics Lab, Radiology and Nuclear Medicine, ACS - Atherosclerosis & ischemic syndromes, Graduate School, APH - Quality of Care, CCA - Imaging and biomarkers, Biomedical Engineering and Physics, and Urology

Subjects
Resolution (mass spectrometry), Computational complexity theory, business.industry, Computer science, Pattern recognition, Cancer detection, mass spectrometry imaging, SDG 3 – Goede gezondheid en welzijn, dilated convolution, Convolutional neural network, Mass spectrometry imaging, cancer detection, Computational pathology, SDG 3 - Good Health and Well-being, convolutional neural networks, Cancer biomarkers, Artificial intelligence, Molecular imaging, business, computational pathology
Abstract

Imaging mass spectrometry (IMS) is a novel molecular imaging technique to investigate how molecules are distributed between tumors and within tumor region in order to shed light into tumor biology or find potential biomarkers. Convolutional neural networks (CNNs) have proven to be very potent classifiers often outperforming other machine learning algorithms, especially in computational pathology. To overcome the challenge of complexity and high-dimensionality of the IMS data, the proposed CNNs are either very deep or use large kernels, which results in large amount of parameters and therefore a high computational complexity. An alternative is down-sampling the data, which inherently leads to a loss of information. In this paper, we propose using dilated CNNs as a possible solution to this challenge, since it allows for an increase of the receptive field size, neither by increasing the network parameters nor by decreasing the input signal resolution. Since the mass signature of cancer biomarkers are distributed over the whole mass spectrum, both locally- and globally-distributed patterns need to be captured to correctly classify the spectrum. By experiment, we show that employing dilated convolutions in the architecture of a CNN leads to a higher performance in tumor classification. Our proposed model outperforms the state-of-the-art for tumor classification in both clinical lung and bladder datasets by 1-3%.

Published
2019

Catalog

Books, media, physical & digital resources
See catalog results