Lymph node detection in CT scans using modified U-Net with residual learning and 3D deep network

• Published in: International journal for computer assisted radiology and surgery 2023-04, Vol.18 (4), p.723-732
• Main Authors: Manjunatha, Yashwanth, Sharma, Vanshali, Iwahori, Yuji, Bhuyan, M. K., Wang, Aili, Ouchi, Akira, Shimizu, Yasuhiro
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Automation; Computed tomography; Computer Imaging; Computer Science; Datasets; Deep learning; Health Informatics; Humans; Image contrast; Imaging; Lymph Nodes - diagnostic imaging; Lymphatic system; Machine learning; Mediastinum; Medical imaging; Medicine; Medicine & Public Health; Neoplasms; Neural Networks, Computer; Original Article; Pattern Recognition and Graphics; Radiology; Sensitivity; Surgery; Tomography, X-Ray Computed - methods; Vision
• ISSN: 1861-6429; 1861-6410; 1861-6429
• DOI: 10.1007/s11548-022-02822-w

Purpose Lymph node (LN) detection is a crucial step that complements the diagnosis and treatments involved during cancer investigations. However, the low-contrast structures in the CT scan images and the nodes’ varied shapes, sizes, and poses, along with their sparsely distributed locations, make the detection step challenging and lead to many false positives. The manual examination of the CT scan slices could be time-consuming, and false positives could divert the clinician’s focus. To overcome these issues, our work aims at providing an automated framework for LNs detection in order to obtain more accurate detection results with low false positives. Methods The proposed work consists of two stages: candidate generation and false positive reduction. The first stage generates volumes of interest (VOI) of probable LN candidates using a modified U-Net with ResNet architecture to obtain high sensitivity but with the cost of increased false positives. The second-stage processes the obtained candidate LNs for false positive reduction using 3D convolutional neural network (CNN) classifier. We further present an analysis of various deep learning models while decomposing 3D VOI into different representations. Results The method is evaluated on two publicly available datasets containing CT scans of mediastinal and abdominal LNs. Our proposed approach yields sensitivities of 87% at 2.75 false positives per volume (FP/vol.) and 79% at 1.74 FP/vol. with the mediastinal and abdominal datasets, respectively. Our method presented a competitive performance in terms of sensitivity compared to the state-of-the-art methods and encountered very few false positives. Conclusion We developed an automated framework for LNs detection using a modified U-Net with residual learning and 3D CNNs. The results indicate that our method could achieve high sensitivity with relatively low false positives, which helps avoid ineffective treatments.