# Does image resolution impact chest X-ray based fine-grained Tuberculosis-consistent lesion segmentation?

arXiv: https://arxiv.org/abs/2301.04032 · HTML: https://mlsanity.com/paper/2301.04032/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 10 Jan 2023.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1708.08987/) (2017)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network](https://mlsanity.com/paper/1803.04271/) (2018)
- [A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation](https://mlsanity.com/paper/2107.12435/) (2021)
- [Chest X-Ray Analysis of Tuberculosis by Deep Learning with Segmentation and Augmentation](https://mlsanity.com/paper/1803.01199/) (2018)
- [Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: from convolutional neural networks to visual transformers](https://mlsanity.com/paper/2105.07402/) (2021)
- [Chest X-Ray Bone Suppression for Improving Classification of Tuberculosis-Consistent Findings](https://mlsanity.com/paper/2104.04518/) (2021)
- [Deep Learning with Lung Segmentation and Bone Shadow Exclusion Techniques for Chest X-Ray Analysis of Lung Cancer](https://mlsanity.com/paper/1712.07632/) (2017)
- [Uncertainty Quantification using Variational Inference for Biomedical Image Segmentation](https://mlsanity.com/paper/2008.07588/) (2020)
- [Correlation Maximized Structural Similarity Loss for Semantic Segmentation](https://mlsanity.com/paper/1910.08711/) (2019)
- [ECOVNet: An Ensemble of Deep Convolutional Neural Networks Based on EfficientNet to Detect COVID-19 From Chest X-rays](https://mlsanity.com/paper/2009.11850/) (2020)
- [Unified Representation Learning for Efficient Medical Image Analysis](https://mlsanity.com/paper/2006.11223/) (2020)
- [SemSegLoss: A python package of loss functions for semantic segmentation](https://mlsanity.com/paper/2106.05844/) (2021)

## Abstract (arXiv)

Deep learning (DL) models are state-of-the-art in segmenting anatomical and disease regions of interest (ROIs) in medical images. Particularly, a large number of DL-based techniques have been reported using chest X-rays (CXRs). However, these models are reportedly trained on reduced image resolutions for reasons related to the lack of computational resources. Literature is sparse in discussing the optimal image resolution to train these models for segmenting the Tuberculosis (TB)-consistent lesions in CXRs. In this study, we investigated the performance variations using an Inception-V3 UNet model using various image resolutions with/without lung ROI cropping and aspect ratio adjustments, and (ii) identified the optimal image resolution through extensive empirical evaluations to improve TB-consistent lesion segmentation performance. We used the Shenzhen CXR dataset for the study which includes 326 normal patients and 336 TB patients. We proposed a combinatorial approach consisting of storing model snapshots, optimizing segmentation threshold and test-time augmentation (TTA), and averaging the snapshot predictions, to further improve performance with the optimal resolution. Our experimental results demonstrate that higher image resolutions are not always necessary, however, identifying the optimal image resolution is critical to achieving superior performance.