Fine-Tuning and training of densenet for histopathology image representation using TCGA diagnostic slides.

Abtin Riasatian¹, Morteza Babaie², Danial Maleki¹, Shivam Kalra¹, Mojtaba Valipour³, Sobhan Hemati¹, Manit Zaveri¹, Amir Safarpoor¹, Sobhan Shafiei¹, Mehdi Afshari¹, Maral Rasoolijaberi¹, Milad Sikaroudi¹, Mohd Adnan¹, Sultaan Shah⁴, Charles Choi⁴, Savvas Damaskinos⁴, Clinton Jv Campbell⁵, Phedias Diamandis⁶, Liron Pantanowitz⁷, Hany Kashani¹, Ali Ghodsi⁸, H R Tizhoosh⁹

¹Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada.

²Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada. Electronic address: mbabaie@uwaterloo.ca.

³School of Computer Science, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada.

⁴Huron Digital Pathology, 1620 King Street North, St. Jacobs, ON, Canada.

⁵Department of Pathology and Molecular Medicine, McMaster University, Hamilton, Canada.

⁶Laboratory Medicine and Pathobiology, University of Toronto, ON, Canada.

⁷Department of Pathology, University of Pittsburgh Medical Center, PA, USA.

⁸School of Computer Science, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada; Vector Institute, 661 University Ave Suite 710, Toronto, ON, Canada.

⁹Kimia Lab, University of Waterloo, 200 University Ave. W., Waterloo, ON, Canada; Vector Institute, 661 University Ave Suite 710, Toronto, ON, Canada. Electronic address: hamid.tizhoosh@uwaterloo.ca.

PubMed DOI

Abstract

Feature vectors provided by pre-trained deep artificial neural networks have become a dominant source for image representation in recent literature. Their contribution to the performance of image analysis can be improved through fine-tuning. As an ultimate solution, one might even train a deep network from scratch with the domain-relevant images, a highly desirable option which is generally impede…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.