# How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?

arXiv: https://arxiv.org/abs/1511.06348 · HTML: https://mlsanity.com/paper/1511.06348/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 30 of 45)

- [Revisiting Neural Scaling Laws in Language and Vision](https://mlsanity.com/paper/2209.06640/) (2022)
- [Diffusion Probabilistic Models beat GANs on Medical Images](https://mlsanity.com/paper/2212.07501/) (2022)
- [Learning Curves for Decision Making in Supervised Machine Learning: A Survey](https://mlsanity.com/paper/2201.12150/) (2022)
- [Scaling Laws for Deep Learning](https://mlsanity.com/paper/2108.07686/) (2021)
- [Scaling Pre-training to One Hundred Billion Data for Vision Language Models](https://mlsanity.com/paper/2502.07617/) (2025)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [Pretrained ViTs Yield Versatile Representations For Medical Images](https://mlsanity.com/paper/2303.07034/) (2023)
- [Anatomy-aware Self-supervised Learning for Anomaly Detection in Chest Radiographs](https://mlsanity.com/paper/2205.04282/) (2022)
- [Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems](https://mlsanity.com/paper/2502.07503/) (2025)
- [Lung-DDPM: Semantic Layout-guided Diffusion Models for Thoracic CT Image Synthesis](https://mlsanity.com/paper/2502.15204/) (2025)
- [Data Scaling Laws for Radiology Foundation Models](https://mlsanity.com/paper/2509.12818/) (2025)
- [Voxel-level Siamese Representation Learning for Abdominal Multi-Organ Segmentation](https://mlsanity.com/paper/2105.07672/) (2021)
- [Deep Learning for Ultrasound Speed-of-Sound Reconstruction: Impacts of Training Data Diversity on Stability and Robustness](https://mlsanity.com/paper/2202.01208/) (2022)
- [Is More Data All You Need? A Causal Exploration](https://mlsanity.com/paper/2206.02409/) (2022)
- [Recommending Training Set Sizes for Classification](https://mlsanity.com/paper/2102.09382/) (2021)
- [Human Age Estimation from Gene Expression Data using Artificial Neural Networks](https://mlsanity.com/paper/2111.02692/) (2021)
- [Lirot.ai: A Novel Platform for Crowd-Sourcing Retinal Image Segmentations](https://mlsanity.com/paper/2208.10100/) (2022)
- [Ten Quick Tips for Deep Learning in Biology](https://mlsanity.com/paper/2105.14372/) (2021)
- [Deep Convolutional Neural Networks for Onychomycosis Detection](https://mlsanity.com/paper/2106.16139/) (2021)
- [On the benefits of self-taught learning for brain decoding](https://mlsanity.com/paper/2209.10099/) (2022)
- [Does Deep Learning REALLY Outperform Non-deep Machine Learning for Clinical Prediction on Physiological Time Series?](https://mlsanity.com/paper/2211.06034/) (2022)
- [Navigating causal deep learning](https://mlsanity.com/paper/2212.00911/) (2022)
- [How much data do you need? Part 2: Predicting DL class specific training dataset sizes](https://mlsanity.com/paper/2403.06311/) (2024)
- [Advancing Histopathology with Deep Learning Under Data Scarcity: A Decade in Review](https://mlsanity.com/paper/2410.19820/) (2024)
- [Comparative Analysis of Diffusion Generative Models in Computational Pathology](https://mlsanity.com/paper/2411.15719/) (2024)
- [LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought](https://mlsanity.com/paper/2505.15657/) (2025)
- [Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks](https://mlsanity.com/paper/2505.23032/) (2025)
- [Neural Scaling Laws for Deep Regression](https://mlsanity.com/paper/2509.10000/) (2025)
- [Meta-learning Amidst Heterogeneity and Ambiguity](https://mlsanity.com/paper/2107.02228/) (2021)
- [A deep neural network for multi-species fish detection using multiple acoustic cameras](https://mlsanity.com/paper/2109.10664/) (2021)

## Abstract (arXiv)

The use of Convolutional Neural Networks (CNN) in natural image classification systems has produced very impressive results. Combined with the inherent nature of medical images that make them ideal for deep-learning, further application of such systems to medical image classification holds much promise. However, the usefulness and potential impact of such a system can be completely negated if it does not reach a target accuracy. In this paper, we present a study on determining the optimum size of the training data set necessary to achieve high classification accuracy with low variance in medical image classification systems. The CNN was applied to classify axial Computed Tomography (CT) images into six anatomical classes. We trained the CNN using six different sizes of training data set (5, 10, 20, 50, 100, and 200) and then tested the resulting system with a total of 6000 CT images. All images were acquired from the Massachusetts General Hospital (MGH) Picture Archiving and Communication System (PACS). Using this data, we employ the learning curve approach to predict classification accuracy at a given training sample size. Our research will present a general methodology for determining the training data set size necessary to achieve a certain target classification accuracy that can be easily applied to other problems within such systems.