Analog In-Memory Computing with Uncertainty Quantification for Efficient Edge-based Medical Imaging Segmentation

Published: 19 Mar 2024, Last Modified: 17 May 2024Tiny Papers @ ICLR 2024 NotableEveryoneRevisionsBibTeXCC BY 4.0
Keywords: analog AI, medical imaging analysis, energy efficiency
TL;DR: his study examines the effectiveness of Analog In-memory Computing (AIMC) in medical AI, highlighting its advantages over traditional digital computing in power efficiency, speed, certainty, and scalability for medical tasks
Abstract: This work investigates the role of the emerging Analog In-memory computing (AIMC) paradigm in enabling Medical AI analysis and improving the certainty of these models at the edge. It contrasts AIMC's efficiency with traditional digital computing's limitations in power, speed, and scalability. Our comprehensive evaluation focuses on brain tumor analysis, spleen segmentation, and nuclei detection. The study highlights the superior robustness of isotropic architectures, which exhibit a minimal accuracy drop (0.04) in analog-aware training, compared to significant drops (up to 0.15) in pyramidal structures. Additionally, the paper emphasizes IMC's effective data pipelining, reducing latency and increasing throughput as well as the exploitation of inherent noise within AIMC, strategically harnessed to augment model certainty.
Supplementary Material: zip
Submission Number: 135