mlsanityData to 7 Oct 2026

Carbon Footprint of Selecting and Training Deep Learning Models for Medical Image Analysis

arXiv 2203.02202 ↗First posted 4 Mar 2022eess.IV cs.CV cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 13 of its 36 references that are in the map. First posted on arXiv 4 Mar 2022.

Builds on

13 of 36 references.

References · 13

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  4. 2017Mixed Precision Trainingcited by 1,135
  5. 2014Deep Learning in Neural Networks: An Overviewcited by 765
  6. 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
  7. 2019A large annotated medical image dataset for the development and evaluation of segmentation algorithmscited by 371
  8. 2020Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learningcited by 246
  9. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 200
  10. 2020Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Modelscited by 168
  11. 2022Compute Trends Across Three Eras of Machine Learningcited by 161
  12. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
1 more
  1. 2021HyperMorph: Amortized Hyperparameter Learning for Image Registrationcited by 84

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 5; 2024: 3; 2025: 4; 2026: 3.

18 papers.

Sort:

  1. 2023FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcarecited by 59
  2. 2022Towards Climate Awareness in NLP Researchcited by 19
  3. 2023Watt For What: Rethinking Deep Learning's Energy-Performance Relationshipcited by 16
  4. 2022medigan: a Python library of pretrained generative models for medical image synthesiscited by 14
  5. 2022EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Searchcited by 11
  6. 2025Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Modelscited by 11
  7. 2023Operating critical machine learning models in resource constrained regimescited by 6
  8. 2024Progressive Growing of Patch Size: Resource-Efficient Curriculum Learning for Dense Prediction Taskscited by 5
  9. 2024PePR: Performance Per Resource Unit as a Metric to Promote Small-Scale Deep Learning in Medical Image Analysiscited by 4
  10. 2023CACTUS: a Comprehensive Abstraction and Classification Tool for Uncovering Structurescited by 3
  11. 2024Embeddings are all you need! Achieving High Performance Medical Image Classification through Training-Free Embedding Analysiscited by 2
  12. 2025Position: Neglecting the Sustainability of AI is Fuelling a Global AI Arms Racecited by 2
6 more
  1. 2026Efficient Deep Learning for Medical Imaging: Bridging the Gap Between High-Performance AI and Clinical Deploymentcited by 1
  2. 2023FSDA-DG: Improving Cross-Domain Generalizability of Medical Image Segmentation with Few Source Domain Annotationscited by 0
  3. 2025DuPLUS: Dual-Prompt Vision-Language Framework for Universal Medical Image Segmentation and Prognosiscited by 0
  4. 2025Progressive Growing of Patch Size: Curriculum Learning for Accelerated and Improved Medical Image Segmentationcited by 0
  5. 2026FairQuant: Fairness-Aware Mixed-Precision Quantization for Medical Image Classificationcited by 0
  6. 2026MedicalRec: Medical recommender system for image classification without retrainingcited by 0