Key result
Knowledge-distilled CNN achieves ~99% accuracy for real-time classification of angiographic plaque findings on FPGA.
Why the study?
Deploying deep learning-based diagnostic models for coronary angiography images on resource-constrained embedded platforms remains challenging due to computational complexity and memory requirements.
A novel hardware-aware knowledge-distilled CNN deployed on FPGA provides highly accurate, low-latency real-time classification of coronary plaque-associated angiographic findings.
Answers are grounded in this paper and cite their sources.
May enable on-device real-time plaque detection in angiography; leaves open prospective clinical validation before practice integration.
Coronary artery disease (CAD) is one of the leading causes of global mortality, necessitating accurate assessment of coronary artery stenosis and plaque-associated angiographic findings from coronary angiography images. Although deep learning-based diagnostic models have demonstrated high predictive capability, their deployment on resource-constrained embedded platforms remains challenging because of computational complexity and memory requirements. To address these limitations, this study proposes a knowledge-distillation-based hardware-aware framework that transfers discriminative knowledge from a high-capacity teacher network to a lightweight convolutional neural network (CNN). The proposed framework integrates software-level localization of plaque-associated angiographic findings with FPGA-oriented optimization. Using a 90% training and 10% testing split, the proposed model achieved an accuracy of 98.64% , precision of 99.06% , recall of 97.82% , PPV of 0.99 , NPV of 0.98 , MCC of 0.96 , and an AUC of 0.9940 . And under 10-fold cross-validation, the model achieved a mean accuracy of 97.53% ± 0.27% , precision of 97.82% , recall of 96.94% , PPV of 0.98 , NPV of 0.97 , MCC of 0.95 , and a mean AUC of 0.9897 , which confirms that our proposed model exhibits high robust performance. For hardware realization, the optimized student CNN was deployed on a Xilinx Zynq UltraScale + MPSoC FPGA using the Vitis High-Level Synthesis (HLS) toolchain. The implemented accelerator achieved a kernel-level inference latency of 10.6 µs and a Peak On-Chip Kernel Throughput of approximately 94,339 inferences/s , while maintaining balanced hardware resource utilization and low power consumption. Overall, the proposed framework demonstrates accurate classification of plaque-associated angiographic findings with efficient FPGA deployment.
No takes yet. Share an insight, caveat, or question.
Pravalika et al. (2026) studied Coronary artery disease (n=1,500). Knowledge-distilled CNN on FPGA vs. Teacher model and baseline architectures was evaluated on Classification accuracy. The proposed knowledge-distilled hardware-aware CNN achieved an accuracy of 98.64% and an AUC of 0.9940 for real-time classification of plaque-associated angiographic findings on FPGA.
Synapse has enriched 10 related papers. Consider them for comparative context: