WindowNet: Learnable Windows for Chest X-ray Classification
This work addresses image quality issues in chest X-ray classification for medical diagnosis, but it is incremental as it builds on existing windowing techniques.
The study tackled the problem of chest X-ray classification by investigating how windowing operations and bit-depth affect performance, finding that higher bit-depth and learned window settings improve results, with WindowNet significantly outperforming the baseline.
Chest X-ray (CXR) images are commonly compressed to a lower resolution and bit depth to reduce their size, potentially altering subtle diagnostic features. Radiologists use windowing operations to enhance image contrast, but the impact of such operations on CXR classification performance is unclear. In this study, we show that windowing can improve CXR classification performance, and propose WindowNet, a model that learns optimal window settings. We first investigate the impact of bit-depth on classification performance and find that a higher bit-depth (12-bit) leads to improved performance. We then evaluate different windowing settings and show that training with a distinct window generally improves pathology-wise classification performance. Finally, we propose and evaluate WindowNet, a model that learns optimal window settings, and show that it significantly improves performance compared to the baseline model without windowing.