Semantic segmentation of bone structures in chest X-rays including unhealthy radiographs: A robust and accurate approach. (September 2022)

• Record Type: Journal Article
• Authors: Singh, Anushikha; Lall, Brejesh; Panigrahi, B.K.; Agrawal, Anjali; Agrawal, Anurag; Thangakunam, Balamugesh; Christopher, Devasahayam J.
• Is Part Of: International journal of medical informatics. Volume 165(2022)
• Publication Date: 2022-09
• Subjects: Chest X-rays -- Bone structures -- Semantic segmentation; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2022.104831
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: To the best of our knowledge, this is the first work that evaluates the robustness of the bone segmentation method on severely unhealthy chest x-rays. We proposed encoder-decoder architecture based on the combination of U-Net and Deeplab v3+ network to achieve robustness and superior performance on normal and abnormal chest x-rays. We use pre-trained ResNet50 as a base network in the encoder and their fully connected layers have been replaced by ASPP block for improving the quality of the embedding. We consider symmetry in down sampling and up sampling steps to concatenate both low-level and high-level feature maps ensuring better embedding of both the edges and detail information. At each level, the up-sampled decoder features are concatenated with the encoder features at a similar level and further passes to fine-tuning block for better segmentation. Abstract: The chest X-ray is a widely used medical imaging technique for the diagnosis of several lung diseases. Some nodules or other pathologies present in the lungs are difficult to visualize on chest X-rays because they are obscured by overlying bone shadows. Segmentation of bone structures and suppressing them assist medical professionals in reliable diagnosis and organ morphometry. But segmentation of bone structures is challenging due to fuzzy boundaries of organs and inconsistent shape and size of organs due to health issues, age, and gender. The existing bone segmentation methods do not report their performance on abnormal chest X-rays, where it is even more critical to segment the bones. This work presents a robust encoder–decoder network for semantic segmentation of bone structures on normal as well as abnormal chest X-rays. The novelty here lies in combining techniques from two existing networks (Deeplabv3+ and U-net) to achieve robust and superior performance. The fully connected layers of the pre-trained ResNet50 network have been replaced by an Atrous spatial pyramid pooling block for improving the quality of the embedding in the encoder module. The decoder module includes four times upsampling blocks to connect both low-level and high-level features information enabling us to retain both the edges and detail information of the objects. At each level, the up-sampled decoder features are concatenated with the encoder features at a similar level and further fine-tuned to refine the segmentation output. We construct a diverse chest X-ray dataset with ground truth binary masks of anterior ribs, posterior ribs, and clavicle bone for experimentation. The dataset includes 100 samples of chest X-rays belonging to healthy and confirmed patients of lung diseases to maintain the diversity and test the robustness of our method. We test our method using multiple standard metrics and experimental results indicate an excellent performance on both normal and abnormal chest X-rays.