scispace - formally typeset
Search or ask a question

Showing papers by "Kevin Smith published in 2017"

Journal Article•DOI•
Digital image analysis in breast pathology-from image processing techniques to artificial intelligence.

[...]

Stephanie Robertson1, Hossein Azizpour2, Kevin Smith2, Johan Hartman1•
Karolinska Institutet1, Royal Institute of Technology2
07 Nov 2017-Translational Research
TL;DR: The use of AI and deep learning in diagnostic breast pathology, and other recent developments in digital image analysis are covered.

197 citations

Journal Article•DOI•
Advanced Cell Classifier: User-Friendly Machine-Learning-Based Software for Discovering Phenotypes in High-Content Imaging Data

[...]

Filippo Piccinini, Tamas Balassa1, Abel Szkalisity1, Csaba Molnar1, Lassi Paavolainen2, Kaisa Kujala2, Krisztina Buzas3, Krisztina Buzas1, Marie Sarazova4, Vilja Pietiäinen2, Ulrike Kutay4, Kevin Smith5, Kevin Smith6, Peter Horvath2, Peter Horvath1 •
Hungarian Academy of Sciences1, University of Helsinki2, University of Szeged3, ETH Zurich4, Royal Institute of Technology5, Science for Life Laboratory6
28 Jun 2017-Cell systems
TL;DR: Advanced Cell Classifier is presented, a graphical software package for phenotypic analysis that applies machine-learning and image-analysis methods to high-content data generated by large-scale, cell-based experiments and features methods to mine microscopic image data, discover new phenotypes, and improve recognition performance.
Abstract: High-content, imaging-based screens now routinely generate data on a scale that precludes manual verification and interrogation. Software applying machine learning has become an essential tool to a ...

64 citations

Proceedings Article•
The Preimage of Rectifier Network Activities

[...]

Stefan Carlsson1, Hossein Azizpour1, Ali Sharif Razavian1, Josephine Sullivan1, Kevin Smith2 •
Royal Institute of Technology1, Science for Life Laboratory2
17 Feb 2017
TL;DR: A procedure for explicitly computing the complete preimage of activities of a layer in a rectifier network with fully connected layers, from knowledge of the weights in the network, is given.
Abstract: The preimage of the activity at a certain level of a deep network is the set of inputs that result in the same node activity. For fully connected multi layer rectifier networks we demonstrate how t ...

6 citations