Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Investigation of Loss Functions for Improving Deep Segmentation of Abdominal Organs from MRI

Version 1 : Received: 29 October 2020 / Approved: 2 November 2020 / Online: 2 November 2020 (11:02:44 CET)

How to cite: Furtado, P. Investigation of Loss Functions for Improving Deep Segmentation of Abdominal Organs from MRI. Preprints 2020, 2020110023 (doi: 10.20944/preprints202011.0023.v1). Furtado, P. Investigation of Loss Functions for Improving Deep Segmentation of Abdominal Organs from MRI. Preprints 2020, 2020110023 (doi: 10.20944/preprints202011.0023.v1).

Abstract

Segmentation of Magnetic Resonance Images (MRI) of abdominal organs is useful for analysis prior to surgical procedures and for further processing. Deep Learning (DL) has become the standard, researchers have proposed improvements that include multiple views, ensembles and voting. Loss function alternatives, while being crucial to guide automated learning, have not been compared in detail. In this work we analyze limitations of popular metrics and their use as loss, study alternative loss variations based on those and other modifications and search for the best approach. An experimental setup was necessary to assess the alternatives. Results for the top scoring network and top scoring loss show improvements between 2 and 11 percentage points (pp) in Jaccard Index (JI), depending on organ and patient (sequence), for a total of 22 pp over 4 organs, all this being obtained just by choosing the best performing loss function instead of cross-entropy or dice. Our results apply directly to MRI of abdominal organs, with important practical implications for other architectures, as they can be applied easily to any of them. They also show the worth of variants of loss function and loss tuning, with future work needed to generalize and test in other contexts.

Subject Areas

Computers in Medicine; Segmentation; Machine Learning; Deep Learning; MRI

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.