Applying ML advancements to healthcare can improve patient outcomes. However,
the sheer operational complexity of ML models, combined with legacy hardware
and multi-modal gigapixel images, poses a severe deployment limitation for
real-time, on-device inference. We consider filter pruning as a solution,
exploring segmentation models in cardiology and ophthalmology. Our preliminary
results show a compression rate of up to 1148x with minimal loss in quality,
stressing the need to consider task complexity and architectural details when
using off-the-shelf models. At high compression rates, filter-pruned models
exhibit faster inference on a CPU than the GPU baseline. We also demonstrate
that such models' robustness and generalisability characteristics exceed that
of the baseline and weight-pruned counterparts. We uncover intriguing questions
and take a step towards realising cost-effective disease diagnosis, monitoring,
and preventive solutions.

应用机器学习进展于医疗可以改善患者结果，但是模型操作复杂性、遗留硬件和多模态千兆像素图像等问题限制了实时、设备内推理的部署。我们考虑滤波剪枝作为解决方案，在心脏病学和眼科学中探索分割模型。我们的初步结果显示最高可达 1148 倍的压缩率，质量损失最小，强调使用现成模型时应考虑任务复杂性和架构细节。在高压缩率下，滤波剪枝模型在 CPU 上比 GPU 基准具有更快的推理速度。我们还证明了这些模型的鲁棒性和泛化特性超过了基准和权重剪枝对照组。我们揭示了引人深思的问题，迈出了实现经济有效的疾病诊断、监测和预防解决方案的一步。