Rajaraman Sivaramakrishnan, Yang Feng, Zamzmi Ghada, Xue Zhiyun, Antani Sameer
Computational Health Research Branch, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA.
Diagnostics (Basel). 2023 Feb 16;13(4):747. doi: 10.3390/diagnostics13040747.
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 with an Inception-V3 UNet model using various image resolutions with/without lung ROI cropping and aspect ratio adjustments and 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.
深度学习（DL）模型在医学图像中分割感兴趣的解剖区域和疾病区域方面处于先进水平。特别是，已经报道了大量基于DL的技术用于胸部X光片（CXR）。然而，据报道，由于缺乏计算资源，这些模型是在降低的图像分辨率上进行训练的。在讨论为分割CXR中与结核病（TB）相关的病变而训练这些模型的最佳图像分辨率方面，文献较少。在本研究中，我们使用具有/不具有肺部感兴趣区域裁剪和宽高比调整的各种图像分辨率，研究了Inception-V3 UNet模型的性能变化，并通过广泛的实证评估确定了最佳图像分辨率，以提高与TB相关的病变分割性能。我们使用深圳CXR数据集进行研究，该数据集包括326名正常患者和336名TB患者。我们提出了一种组合方法，包括存储模型快照、优化分割阈值和测试时增强（TTA），以及对快照预测进行平均，以在最佳分辨率下进一步提高性能。我们的实验结果表明，更高的图像分辨率并非总是必要的；然而，确定最佳图像分辨率对于实现卓越性能至关重要。
