National Library of Medicine, National Institutes of Health, Bethesda, Maryland, United States of America.
Clinical Center, Department of Radiology and Imaging Sciences, National Institutes of Health, Bethesda, Maryland, United States of America.
PLoS One. 2022 Mar 31;17(3):e0265691. doi: 10.1371/journal.pone.0265691. eCollection 2022.
Automatic detection of some pulmonary abnormalities using chest X-rays may be impacted adversely due to obscuring by bony structures like the ribs and the clavicles. Automated bone suppression methods would increase soft tissue visibility and enhance automated disease detection. We evaluate this hypothesis using a custom ensemble of convolutional neural network models, which we call DeBoNet, that suppresses bones in frontal CXRs. First, we train and evaluate variants of U-Nets, Feature Pyramid Networks, and other proposed custom models using a private collection of CXR images and their bone-suppressed counterparts. The DeBoNet, constructed using the top-3 performing models, outperformed the individual models in terms of peak signal-to-noise ratio (PSNR) (36.7977±1.6207), multi-scale structural similarity index measure (MS-SSIM) (0.9848±0.0073), and other metrics. Next, the best-performing bone-suppression model is applied to CXR images that are pooled from several sources, showing no abnormality and other findings consistent with COVID-19. The impact of bone suppression is demonstrated by evaluating the gain in performance in detecting pulmonary abnormality consistent with COVID-19 disease. We observe that the model trained on bone-suppressed CXRs (MCC: 0.9645, 95% confidence interval (0.9510, 0.9780)) significantly outperformed (p < 0.05) the model trained on non-bone-suppressed images (MCC: 0.7961, 95% confidence interval (0.7667, 0.8255)) in detecting findings consistent with COVID-19 indicating benefits derived from automatic bone suppression on disease classification. The code is available at https://github.com/sivaramakrishnan-rajaraman/Bone-Suppresion-Ensemble.
使用胸部 X 光片自动检测某些肺部异常可能会因肋骨和锁骨等骨骼结构的遮挡而受到不利影响。自动化骨骼抑制方法可以提高软组织的可见度，并增强自动疾病检测。我们使用一个名为 DeBoNet 的自定义卷积神经网络模型集合来评估这一假设，该模型可以抑制前位 CXR 中的骨骼。首先，我们使用私人的 CXR 图像及其骨骼抑制图像数据集来训练和评估 U-Net、特征金字塔网络和其他提出的自定义模型的变体。使用排名前 3 的模型构建的 DeBoNet 在峰值信噪比（PSNR）（36.7977±1.6207）、多尺度结构相似性指数度量（MS-SSIM）（0.9848±0.0073）和其他指标方面均优于单个模型。接下来，将表现最佳的骨骼抑制模型应用于从多个来源汇集的 CXR 图像，结果显示没有异常和其他与 COVID-19 一致的发现。通过评估在检测与 COVID-19 疾病一致的肺部异常方面性能的提升，证明了骨骼抑制的效果。我们观察到，在骨骼抑制的 CXR 上训练的模型（MCC：0.9645，95%置信区间（0.9510，0.9780））显著优于（p<0.05）在非骨骼抑制图像上训练的模型（MCC：0.7961，95%置信区间（0.7667，0.8255））在检测与 COVID-19 一致的发现方面，这表明自动骨骼抑制在疾病分类方面带来了益处。代码可在 https://github.com/sivaramakrishnan-rajaraman/Bone-Suppresion-Ensemble 上获取。
