Sculpting Efficiency: Pruning Medical Imaging Models for On-Device Inference
Not on the map. Why?
Abstract (arXiv)
Leveraging ML advancements to augment healthcare systems can improve patient outcomes. Yet, uninformed engineering decisions in early-stage research inadvertently hinder the feasibility of such solutions for high-throughput, on-device inference, particularly in settings involving legacy hardware and multi-modal gigapixel images. Through a preliminary case study concerning segmentation in cardiology, we highlight the excess operational complexity in a suboptimally configured ML model from prior work and demonstrate that it can be sculpted away using pruning to meet deployment criteria. Our results show a compression rate of 1148x with minimal loss in quality (~4%) and, at higher rates, achieve faster inference on a CPU than the GPU baseline, stressing the need to consider task complexity and architectural details when using off-the-shelf models. With this, we consider avenues for future research in streamlining workflows for clinical researchers to develop models quicker and better suited for real-world use.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 39 references that are in the map. First posted on arXiv 10 Sep 2023.
Builds on
16 of 39 references.
References · 16
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
- 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
- 2016Pruning Filters for Efficient ConvNetscited by 1,129
- 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
- 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 596
- 2018Rethinking the Value of Network Pruningcited by 595
- 2020What is the State of Neural Network Pruning?cited by 578
- 2013Predicting Parameters in Deep Learningcited by 223
- 2021Zero-Cost Proxies for Lightweight NAScited by 194
- 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
- 2021Efficient Medical Image Segmentation Based on Knowledge Distillationcited by 43
4 more
- 2017Exploring the Regularity of Sparse Structure in Convolutional Neural Networkscited by 37
- 2020Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-rayscited by 21
- 2021SparseDNN: Fast Sparse Deep Learning Inference on CPUscited by 13
- 2023Domain Agnostic Pipeline for Retina Vessel Segmentationcited by 1
Built on by
Not cited yet.