# Sculpting Efficiency: Pruning Medical Imaging Models for On-Device Inference

arXiv: https://arxiv.org/abs/2309.05090 · HTML: https://mlsanity.com/paper/2309.05090/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 39 references that are in the map.
- First posted on arXiv 10 Sep 2023.

## Builds on (most cited first, 16 of 16)

- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Predicting Parameters in Deep Learning](https://mlsanity.com/paper/1306.0543/) (2013)
- [Zero-Cost Proxies for Lightweight NAS](https://mlsanity.com/paper/2101.08134/) (2021)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [Efficient Medical Image Segmentation Based on Knowledge Distillation](https://mlsanity.com/paper/2108.09987/) (2021)
- [Exploring the Regularity of Sparse Structure in Convolutional Neural Networks](https://mlsanity.com/paper/1705.08922/) (2017)
- [Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-rays](https://mlsanity.com/paper/2004.08379/) (2020)
- [SparseDNN: Fast Sparse Deep Learning Inference on CPUs](https://mlsanity.com/paper/2101.07948/) (2021)
- [Domain Agnostic Pipeline for Retina Vessel Segmentation](https://mlsanity.com/paper/2302.09215/) (2023)

## 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.