Bone suppression on pediatric chest radiographs via a deep learning-based cascade model. (March 2022)

• Record Type: Journal Article
• Authors: Cho, Kyungjin; Seo, Jiyeon; Kyung, Sunggu; Kim, Mingyu; Hong, Gil-Sun; Kim, Namkug
• Is Part Of: Computer methods and programs in biomedicine. Volume 215(2022)
• Publication Date: 2022-03
• Subjects: Bone suppression -- Chest radiograph -- Deep learning -- Image translation -- Pediatric; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106627
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: In this study, we developed a novel deep-learning-based BSI-generation method for pediatric CXRs by leveraging a model that combined adult and pediatric DRRs (CXRs and BSIs), and adult bone suppression models to overcome the paucity of pediatric CT images. Our main outcomes are 1) the novel development of an age-robust bone suppression model for pediatric CXRs that dissects the bone suppression task into a cascade scheme; and 2) bone removal without deteriorating the soft-tissue regions. As it has with adults, the use of pediatric BSIs is expected to improve subtle lung lesion detection in CXRs, and it may be particularly helpful to inexperienced clinicians and residents in identifying pediatric patients with early-stage lung disease. Abstract: Background and objective: Bone suppression images (BSIs) of chest radiographs (CXRs) have been proven to improve diagnosis of pulmonary diseases. To acquire BSIs, dual-energy subtraction (DES) or a deep-learning-based model trained with DES-based BSIs have been used. However, neither technique could be applied to pediatric patients owing to the harmful effects of DES. In this study, we developed a novel method for bone suppression in pediatric CXRs. Methods: First, a model using digitally reconstructed radiographs (DRRs) of adults, which were used to generate pseudo-CXRs from computed tomography images, was developed by training a 2-channel contrastive-unpaired-image-translation network. Second, this model was applied to 129 pediatric DRRs to generate the paired training data of pseudo-pediatric CXRs. Finally, by training a U-Net with these paired data, a bone suppression model for pediatric CXRs was developed. Results: The evaluation metrics were peak signal to noise ratio, root mean absolute error and structural similarity index measure at soft-tissue and bone region of the lung. In addition, an expert radiologist scored the effectiveness of BSIs on a scale of 1–5. The obtained result of 3.31 ± 0.48 indicates that the BSIs show homogeneous bone removal despite subtle residual bone shadow. Conclusion: Our method shows that the pixel intensity at soft-tissue regions was preserved, and bones were well subtracted; this can be useful for detecting early pulmonary disease in pediatric CXRs.