# Feature Imitating Networks Enhance The Performance, Reliability And Speed Of Deep Learning On Biomedical Image Processing Tasks

arXiv: https://arxiv.org/abs/2306.14572 · HTML: https://mlsanity.com/paper/2306.14572/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 26 Jun 2023.

## Builds on (most cited first, 7 of 7)

- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [U-Net and its variants for medical image segmentation: theory and applications](https://mlsanity.com/paper/2011.01118/) (2020)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective](https://mlsanity.com/paper/2112.06409/) (2021)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [Repeatability of Multiparametric Prostate MRI Radiomics Features](https://mlsanity.com/paper/1807.06089/) (2018)
- [Feature Imitating Networks](https://mlsanity.com/paper/2110.04831/) (2021)

## Built on by (most cited first, 2 of 2)

- [The Broad Impact of Feature Imitation: Neural Enhancements Across Financial, Speech, and Physiological Domains](https://mlsanity.com/paper/2309.12279/) (2023)
- [An LSTM Feature Imitation Network for Hand Movement Recognition from sEMG Signals](https://mlsanity.com/paper/2405.19356/) (2024)

## Abstract (arXiv)

Feature-Imitating-Networks (FINs) are neural networks that are first trained to approximate closed-form statistical features (e.g. Entropy), and then embedded into other networks to enhance their performance. In this work, we perform the first evaluation of FINs for biomedical image processing tasks. We begin by training a set of FINs to imitate six common radiomics features, and then compare the performance of larger networks (with and without embedding the FINs) for three experimental tasks: COVID-19 detection from CT scans, brain tumor classification from MRI scans, and brain-tumor segmentation from MRI scans. We found that models embedded with FINs provided enhanced performance for all three tasks when compared to baseline networks without FINs, even when those baseline networks had more parameters. Additionally, we found that models embedded with FINs converged faster and more consistently compared to baseline networks with similar or greater representational capacity. The results of our experiments provide evidence that FINs may offer state-of-the-art performance for a variety of other biomedical image processing tasks.