Dual center validation of deep learning for automated multi-label segmentation of thoracic anatomy in bedside chest radiographs

• Published in: Computer methods and programs in biomedicine 2023-06, Vol.234, p.107505-107505, Article 107505
• Main Authors: Busch, Felix, Xu, Lina, Sushko, Dmitry, Weidlich, Matthias, Truhn, Daniel, Müller-Franzes, Gustav, Heimer, Maurice M., Niehues, Stefan M., Makowski, Marcus R., Hinsche, Markus, Vahldiek, Janis L., Aerts, Hugo JWL, Adams, Lisa C., Bressem, Keno K.
• Format: Article
• Language: English
• Subjects: Active learning; Anatomy; Artificial Intelligence; Chest radiograph; Convolutional neural network; Deep Learning; Humans; Image Processing, Computer-Assisted - methods; Neural Networks, Computer; Thorax
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2023.107505

•A lightweight convolutional neural network was trained using 2000 bedside CXRs.•Segmentation included lungs, heart, clavicles, trachea, and mediastinum.•The model achieves highly comparable performance to state-of-the-art approaches.•A human-in-the-loop annotation workflow reduced annotation times by 32%.•The implemented workflow allows for more efficient use of the human workforce. Bedside chest radiographs (CXRs) are challenging to interpret but important for monitoring cardiothoracic disease and invasive therapy devices in critical care and emergency medicine. Taking surrounding anatomy into account is likely to improve the diagnostic accuracy of artificial intelligence and bring its performance closer to that of a radiologist. Therefore, we aimed to develop a deep convolutional neural network for efficient automatic anatomy segmentation of bedside CXRs. To improve the efficiency of the segmentation process, we introduced a "human-in-the-loop" segmentation workflow with an active learning approach, looking at five major anatomical structures in the chest (heart, lungs, mediastinum, trachea, and clavicles). This allowed us to decrease the time needed for segmentation by 32% and select the most complex cases to utilize human expert annotators efficiently. After annotation of 2,000 CXRs from different Level 1 medical centers at Charité – University Hospital Berlin, there was no relevant improvement in model performance, and the annotation process was stopped. A 5-layer U-ResNet was trained for 150 epochs using a combined soft Dice similarity coefficient (DSC) and cross-entropy as a loss function. DSC, Jaccard index (JI), Hausdorff distance (HD) in mm, and average symmetric surface distance (ASSD) in mm were used to assess model performance. External validation was performed using an independent external test dataset from Aachen University Hospital (n = 20). The final training, validation, and testing dataset consisted of 1900/50/50 segmentation masks for each anatomical structure. Our model achieved a mean DSC/JI/HD/ASSD of 0.93/0.88/32.1/5.8 for the lung, 0.92/0.86/21.65/4.85 for the mediastinum, 0.91/0.84/11.83/1.35 for the clavicles, 0.9/0.85/9.6/2.19 for the trachea, and 0.88/0.8/31.74/8.73 for the heart. Validation using the external dataset showed an overall robust performance of our algorithm. Using an efficient computer-aided segmentation method with active learning, our anatomy-based model achieves comparable performance to state-of-the-art appro