John Paul Graff
University of California, Davis
15 Papers
13 Citations
John Paul Graff is an academic researcher from University of California, Davis. The author has contributed to research in topics: Medicine & Computer science. The author has an hindex of 3, co-authored 7 publications. Previous affiliations of John Paul Graff include University of California, Berkeley & University of California, Irvine.
Chat about Author
Papers
Leukoerythroblastic reaction in a patient with COVID-19 infection.
Anupam Mitra,Denis M. Dwyre,Michael Schivo,George Richard Thompson,Stuart H. Cohen,Nam K. Ku,John Paul Graff +6 more
TL;DR: This book aims to provide a chronology of the events that led to the publication of the Mahatma Gandhi assassination and some of the key players in its development.
Impact of pre-analytical variables on deep learning accuracy in histopathology.
Andrew D Jones,John Paul Graff,Morgan A. Darrow,Alexander D. Borowsky,Kristin A Olson,Regina F Gandour-Edwards,Ananya Datta Mitra,Dongguang Wei,Guofeng Gao,Blythe Durbin-Johnson,Hooman H. Rashidi +10 more
TL;DR: This work empirically compared training image file type, training set size, and two common convolutional neural networks (CNNs) using transfer learning (ResNet50 and SqueezeNet) to solve the challenge of binary classification in diagnostic histopathology.
Effects of Image Quantity and Image Source Variation on Machine Learning Histology Differential Diagnosis Models.
Elham Vali-Betts,Kevin Krause,Alanna Dubrovsky,Kristin A Olson,John Paul Graff,Anupam Mitra,Ananya Datta-Mitra,Kenneth A. Beck,Aristotelis Tsirigos,Cynthia A. Loomis,Antonio Galvao Neto,Esther Adler,Hooman H. Rashidi +12 more
TL;DR: In this article, a convolutional neural network (CNN) was used to classify microscopic images of human tissue samples with the ultimate goal of providing a differential diagnosis (a list of look-alikes) for each entity.
8
The Nokia Lumia 1020 smartphone as a 41-megapixel photomicroscope
John Paul Graff,Mark Li-cheng Wu +1 more
TL;DR: Smartphones may be used for photomicroscopy in the same way as point-and-shoot cameras, but are prone to similar problems relating to quality and blurring; an inconvenient, bulky apparatus is also available that stabilises images by mounting smartphones to microscopes, again compromising portability.
6
Limited number of cases may yield generalizable models, a proof of concept in deep learning for colon histology
Lorne Holland,Dongguang Wei,Kristin A Olson,Anupam Mitra,John Paul Graff,Andrew D. Jones,Blythe Durbin-Johnson,Ananya Datta Mitra,Hooman H. Rashidi +8 more
TL;DR: Increasing the number of images in a training set does not always improve model accuracy, and significant numbers of cases may not always be needed for generalization, especially for simple tasks.
6