# Real-Time Cell Sorting with Scalable In Situ FPGA-Accelerated Deep Learning

arXiv: https://arxiv.org/abs/2503.12622 · HTML: https://mlsanity.com/paper/2503.12622/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 16 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Do Deep Nets Really Need to be Deep?](https://mlsanity.com/paper/1312.6184/) (2013)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [Fast convolutional neural networks on FPGAs with hls4ml](https://mlsanity.com/paper/2101.05108/) (2021)
- [What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective](https://mlsanity.com/paper/2012.02909/) (2020)
- [Understanding the Impact of Precision Quantization on the Accuracy and Energy of Neural Networks](https://mlsanity.com/paper/1612.03940/) (2016)
- [Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement](https://mlsanity.com/paper/2303.08983/) (2023)
- [Low latency optical-based mode tracking with machine learning deployed on FPGAs on a tokamak](https://mlsanity.com/paper/2312.00128/) (2023)
- [Deep Cytometry: Deep learning with Real-time Inference in Cell Sorting and Flow Cytometry](https://mlsanity.com/paper/1904.09233/) (2019)
- [Wise-SrNet: A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature Maps](https://mlsanity.com/paper/2104.12294/) (2021)
- [Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights](https://mlsanity.com/paper/2409.12586/) (2024)
- [Augmentations: An Insight into their Effectiveness on Convolution Neural Networks](https://mlsanity.com/paper/2205.04064/) (2022)
- [Towards Understanding How Data Augmentation Works with Imbalanced Data](https://mlsanity.com/paper/2304.05895/) (2023)
- [MIML: Multiplex Image Machine Learning for High Precision Cell Classification via Mechanical Traits within Microfluidic Systems](https://mlsanity.com/paper/2309.08421/) (2023)

## Built on by (most cited first, 1 of 1)

- [hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware](https://mlsanity.com/paper/2512.01463/) (2025)

## Abstract (arXiv)

Precise cell classification is essential in biomedical diagnostics and therapeutic monitoring, particularly for identifying diverse cell types involved in various diseases. Traditional cell classification methods such as flow cytometry depend on molecular labeling which is often costly, time-intensive, and can alter cell integrity. To overcome these limitations, we present a label-free machine learning framework for cell classification, designed for real-time sorting applications using bright-field microscopy images. This approach leverages a teacher-student model architecture enhanced by knowledge distillation, achieving high efficiency and scalability across different cell types. Demonstrated through a use case of classifying lymphocyte subsets, our framework accurately classifies T4, T8, and B cell types with a dataset of 80,000 preprocessed images, accessible via an open-source Python package for easy adaptation. Our teacher model attained 98% accuracy in differentiating T4 cells from B cells and 93% accuracy in zero-shot classification between T8 and B cells. Remarkably, our student model operates with only 0.02% of the teacher model's parameters, enabling field-programmable gate array (FPGA) deployment. Our FPGA-accelerated student model achieves an ultra-low inference latency of just 14.5~μs and a complete cell detection-to-sorting trigger time of 24.7~μs, delivering 12x and 40x improvements over the previous state-of-the-art real-time cell analysis algorithm in inference and total latency, respectively, while preserving accuracy comparable to the teacher model. This framework provides a scalable, cost-effective solution for lymphocyte classification, as well as a new SOTA real-time cell sorting implementation for rapid identification of subsets using in situ deep learning on off-the-shelf computing hardware.