# Practical Window Setting Optimization for Medical Image Deep Learning

arXiv: https://arxiv.org/abs/1812.00572 · HTML: https://mlsanity.com/paper/1812.00572/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2018.

## Built on by (most cited first, 8 of 8)

- [BHSD: A 3D Multi-Class Brain Hemorrhage Segmentation Dataset](https://mlsanity.com/paper/2308.11298/) (2023)
- [Zero-Shot Domain Adaptation in CT Segmentation by Filtered Back Projection Augmentation](https://mlsanity.com/paper/2107.08543/) (2021)
- [ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challenges](https://mlsanity.com/paper/2512.17838/) (2025)
- [Comparative Evaluation of 3D and 2D Deep Learning Techniques for Semantic Segmentation in CT Scans](https://mlsanity.com/paper/2101.07612/) (2021)
- [Adaptation to CT Reconstruction Kernels by Enforcing Cross-domain Feature Maps Consistency](https://mlsanity.com/paper/2203.14616/) (2022)
- [WindowNet: Learnable Windows for Chest X-ray Classification](https://mlsanity.com/paper/2306.06038/) (2023)
- [Optimizing Convolutional Neural Networks for Chronic Obstructive Pulmonary Disease Detection in Clinical Computed Tomography Imaging](https://mlsanity.com/paper/2303.07189/) (2023)
- [Deep learning in computed tomography pulmonary angiography imaging: a dual-pronged approach for pulmonary embolism detection](https://mlsanity.com/paper/2311.05197/) (2023)

## Abstract (arXiv)

The recent advancements in deep learning have allowed for numerous applications in computed tomography (CT), with potential to improve diagnostic accuracy, speed of interpretation, and clinical efficiency. However, the deep learning community has to date neglected window display settings - a key feature of clinical CT interpretation and opportunity for additional optimization. Here we propose a window setting optimization (WSO) module that is fully trainable with convolutional neural networks (CNNs) to find optimal window settings for clinical performance. Our approach was inspired by the method commonly used by practicing radiologists to interpret CT images by adjusting window settings to increase the visualization of certain pathologies. Our approach provides optimal window ranges to enhance the conspicuity of abnormalities, and was used to enable performance enhancement for intracranial hemorrhage and urinary stone detection. On each task, the WSO model outperformed models trained over the full range of Hounsfield unit values in CT images, as well as images windowed with pre-defined settings. The WSO module can be readily applied to any analysis of CT images, and can be further generalized to tasks on other medical imaging modalities.