Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- Fulltext
Accepted author manuscript, 615 KB, PDF document
The increasing energy consumption and carbon footprint of deep learning (DL) due to growing compute requirements has become a cause of concern. In this work, we focus on the carbon footprint of developing DL models for medical image analysis (MIA), where volumetric images of high spatial resolution are handled. In this study, we present and compare the features of four tools from literature to quantify the carbon footprint of DL. Using one of these tools we estimate the carbon footprint of medical image segmentation pipelines. We choose nnU-net as the proxy for a medical image segmentation pipeline and experiment on three common datasets. With our work we hope to inform on the increasing energy costs incurred by MIA. We discuss simple strategies to cut-down the environmental impact that can make model selection and training processes more efficient.
Original language | English |
---|---|
Title of host publication | Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 : 25th International Conference Singapore, September 18–22, 2022 Proceedings, Part V |
Publisher | Springer |
Publication date | 2022 |
Pages | 506–516 |
ISBN (Print) | 978-3-031-16442-2 |
ISBN (Electronic) | 978-3-031-16443-9 |
DOIs | |
Publication status | Published - 2022 |
Event | 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022 - Singapore, Singapore Duration: 18 Sep 2022 → 22 Sep 2022 |
Conference
Conference | 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022 |
---|---|
Land | Singapore |
By | Singapore |
Periode | 18/09/2022 → 22/09/2022 |
Series | Lecture Notes in Computer Science |
---|---|
Volume | 13435 |
ISSN | 0302-9743 |
Number of downloads are based on statistics from Google Scholar and www.ku.dk
No data available
ID: 322796000