# Between Generating Noise and Generating Images: Noise in the Correct Frequency Improves the Quality of Synthetic Histopathology Images for Digital Pathology

arXiv: https://arxiv.org/abs/2302.06549 · HTML: https://mlsanity.com/paper/2302.06549/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation](https://mlsanity.com/paper/2002.02255/) (2020)
- [Synthetic Medical Images from Dual Generative Adversarial Networks](https://mlsanity.com/paper/1709.01872/) (2017)
- [PathologyGAN: Learning deep representations of cancer tissue](https://mlsanity.com/paper/1907.02644/) (2019)
- [Skin Lesion Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/1902.03253/) (2019)
- [A Deep Learning Algorithm for One-step Contour Aware Nuclei Segmentation of Histopathological Images](https://mlsanity.com/paper/1803.02786/) (2018)
- [Machine learning approach for biopsy-based identification of eosinophilic esophagitis reveals importance of global features](https://mlsanity.com/paper/2101.04989/) (2021)
- [Deep Semi Supervised Generative Learning for Automated PD-L1 Tumor Cell Scoring on NSCLC Tissue Needle Biopsies](https://mlsanity.com/paper/1806.11036/) (2018)
- [Harnessing Artificial Intelligence to Infer Novel Spatial Biomarkers for the Diagnosis of Eosinophilic Esophagitis](https://mlsanity.com/paper/2205.13583/) (2022)

## Built on by (most cited first, 5 of 5)

- [CSG: A Context-Semantic Guided Diffusion Approach in De Novo Musculoskeletal Ultrasound Image Generation](https://mlsanity.com/paper/2412.05833/) (2024)
- [Recover from Horcrux: A Spectrogram Augmentation Method for Cardiac Feature Monitoring from Radar Signal Components](https://mlsanity.com/paper/2503.19649/) (2025)
- [Comparative Analysis of Diffusion Generative Models in Computational Pathology](https://mlsanity.com/paper/2411.15719/) (2024)
- [PriorPath: Coarse-To-Fine Approach for Controlled De-Novo Pathology Semantic Masks Generation](https://mlsanity.com/paper/2411.16515/) (2024)
- [Generating synthetic multi-dimensional molecular-mediator time series data for artificial intelligence-based disease trajectory forecasting and drug development digital twins: Considerations](https://mlsanity.com/paper/2303.09056/) (2023)

## Abstract (arXiv)

Artificial intelligence and machine learning techniques have the promise to revolutionize the field of digital pathology. However, these models demand considerable amounts of data, while the availability of unbiased training data is limited. Synthetic images can augment existing datasets, to improve and validate AI algorithms. Yet, controlling the exact distribution of cellular features within them is still challenging. One of the solutions is harnessing conditional generative adversarial networks that take a semantic mask as an input rather than a random noise. Unlike other domains, outlining the exact cellular structure of tissues is hard, and most of the input masks depict regions of cell types. However, using polygon-based masks introduce inherent artifacts within the synthetic images - due to the mismatch between the polygon size and the single-cell size. In this work, we show that introducing random single-pixel noise with the appropriate spatial frequency into a polygon semantic mask can dramatically improve the quality of the synthetic images. We used our platform to generate synthetic images of immunohistochemistry-treated lung biopsies. We test the quality of the images using a three-fold validation procedure. First, we show that adding the appropriate noise frequency yields 87% of the similarity metrics improvement that is obtained by adding the actual single-cell features. Second, we show that the synthetic images pass the Turing test. Finally, we show that adding these synthetic images to the train set improves AI performance in terms of PD-L1 semantic segmentation performances. Our work suggests a simple and powerful approach for generating synthetic data on demand to unbias limited datasets to improve the algorithms' accuracy and validate their robustness.