Mark kligerman university of michigan linkedin

Abstract

Digital breast tomosynthesis (DBT) is a quasi-three-dimensional imaging modality that can reduce false negatives and false positives in mass lesion detection caused by overlapping breast tissue in conventional two-dimensional (2D) mammography. The patient dose of a DBT scan is similar to that of a single 2D mammogram, while acquisition of each projection view adds detector readout noise. The noise is propagated to the reconstructed DBT volume, possibly obscuring subtle signs of breast cancer such as microcalcifications (MCs). This study developed a deep convolutional neural network (DCNN) framework for denoising DBT images with a focus on improving the conspicuity of MCs as well as preserving the ill-defined margins of spiculated masses and normal tissue textures. We trained the DCNN using a weighted combination of mean squared error (MSE) loss and adversarial loss. We configured a dedicated x-ray imaging simulator in combination with digital breast phantoms to generate realistic in silico DBT data for training. We compared the DCNN training between using digital phantoms and using real physical phantoms. The proposed denoising method improved the contrast-to-noise ratio (CNR) and detectability index (d’) of the simulated MCs in the validation phantom DBTs. These performance measures improved with increasing training target dose and training sample size. Promising denoising results were observed on the transferability of the digital-phantom-trained denoiser to DBT reconstructed with different techniques and on a small independent test set of human subject DBT images.

Index Terms—: deep convolutional neural network, digital breast tomosynthesis, generative adversarial network, image denoising, microcalcification

I. Introduction

Digital breast tomosynthesis (DBT) is an important imaging modality for breast cancer screening and diagnosis. A

Herbert, Daniel. "Acknowledgments". Maverick Movies: New Line Cinema and the Transformation of American Film, Berkeley: University of California Press, 2023, pp. xi-xiv. https://doi.org/10.1525/9780520382367-001

Herbert, D. (2023). Acknowledgments. In Maverick Movies: New Line Cinema and the Transformation of American Film (pp. xi-xiv). Berkeley: University of California Press. https://doi.org/10.1525/9780520382367-001

Herbert, D. 2023. Acknowledgments. Maverick Movies: New Line Cinema and the Transformation of American Film. Berkeley: University of California Press, pp. xi-xiv. https://doi.org/10.1525/9780520382367-001

Herbert, Daniel. "Acknowledgments" In Maverick Movies: New Line Cinema and the Transformation of American Film, xi-xiv. Berkeley: University of California Press, 2023. https://doi.org/10.1525/9780520382367-001

Herbert D. Acknowledgments. In: Maverick Movies: New Line Cinema and the Transformation of American Film. Berkeley: University of California Press; 2023. p.xi-xiv. https://doi.org/10.1525/9780520382367-001

In die Zwischenablage kopiert

Acknowledgments

My most heartfelt thanks and appreciation go to my colleague Richard Abel, whose generosity and celerity in reading draft chapters bolstered and encouraged me in the most important of ways. From the beginning, his feedback has helped immeasurably in keeping the writing of this book on track. The Ciné Goes to Town, The Red Rooster Scare, and French Film Theory and Criticism continue to be the model of thoroughness, accuracy, and fully bilingual engagement to which I have always aspired. What a tremendous privilege it has been to have known Richard since 1994 and to have worked with him since 2011.

I cannot imagine an editor more suited to this book or the disposition of its author than Sara Cohen, who helped Méliès Boots become a material reality. She combined unwavering support with perceptive criticism and keen attention to argument and readability. Sara has made working with the University of Michigan Press an absolute dream. If I could somehow obtain a pair of Méliès bottines, I hope they would fit her. Additional editorial and publishing support was capably provided by Anna Pohlod, Lisa Stallings, and Sherondra Thedford.

Since we met in 2011, Anne-Marie Malthête-Quévrain has been a phenomenal resource for my research. Conversations in Cerisy, Paris, and Blois, and our many bilingual email exchanges have taught me much about Méliès that cannot be found in print. Her assistance has been tireless, including helping me compile a complete file of LesAmis de Georges Méliès, Cinémathèque Méliès, and Cinémathèque Méliès Lettre d’information, which have been essential sources. Her cousin Marie-Hélène Lehérissey has been similarly supportive and generous. Our conversations in Cerisy and Ann Arbor (with Lawrence Le