Lung cancer is one of the leading causes of cancer-related deaths. Chest CT is widely used to screen and diagnose lung cancer, but identifying small nodules is very burdensome and radiologists often miss them (Figure 1). In this paper , authors developed a computer-aided detection (CAD) system that automatically detects lung nodules in CT images using 3D convolutional neural network (Figure 2). The robustness of the CAD system to changes in radiation dose was evaluated by a phantom study, and the results showed that sensitivity did not change within the range of practical dose levels. In addition, reader performance test involving 10 doctors showed that the use of the CAD as a second reader could increase detection performance for nodules that require follow-up examinations. It is hoped that the CAD system will help more reliable management of lung cancer in the future.
 Katase, S., Ichinose, A., Hayashi, M. et al. Development and performance evaluation of a deep learning lung nodule detection system. BMC Med Imaging 22, 203 (2022).
CAUTION：This is Fujifilm Global Website. Fujifilm makes no representation that products on this website are commercially available in all countries. Approved uses of products vary by country and region. Specifications and appearance of products are subject to change without notice.