Pulmonary nodule segmentation framework based on fine-tuned and pre-trained deep neural network using CT images

Ananya Bhattacharjee, R. Murugan, Tripti Goel, Seyedali Mirjalili

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)


Deep learning is one of the most rapidly growing and emerging technologies in pulmonary nodule segmentation. However, the different shape, size and location of the nodules make it extremely difficult to segment correctly. The purpose of this study is to obtain a fast and accurate segmentation algorithm with less number of stages. A fine-tuned dual skip connectionbased segmentation framework is proposed that integrates pretrained ResNet 152 with the U-Net architecture, namely, ResiUNet. Nine different pre-trained and fine-tuned encoder backbones such as ResNet18, ResNet 34, ResNet 50, ResNet 101, ResNet 152, SEResNet18, SE-ResNet34, ResNext 101, ResNext 50 are compared and the proposed ResiU-Net approach gives the best results. Also, the fine-tuned ResiU-Net performs better than nontuned ResiU-Net. 1224 computed tomography patient images with different nodule shapes and sizes are selected. The proposed method achieves 97.44% F score,95.02% intersection over union score, 94.87% dice score, 0.34% binary cross-entropy loss and 0.7585 combined dice coefficient and binary focal loss. The proposed ResiU-Net outperforms the state-of-the-art methods and reports the best evaluation metrics. The time taken by the model to train is 43 minutes. Hence, the proposed model is a fast and accurate segmentation approach.

Original languageEnglish
Pages (from-to)1
Number of pages1
JournalIEEE Transactions on Radiation and Plasma Medical Sciences
Publication statusPublished - 2023


  • Biomedical imaging
  • Cancer
  • Computed tomography
  • Computer architecture
  • Image segmentation
  • Lung
  • lung
  • Lung cancer
  • nodule
  • pretrained
  • ResNet
  • segmentation
  • U-Net


Dive into the research topics of 'Pulmonary nodule segmentation framework based on fine-tuned and pre-trained deep neural network using CT images'. Together they form a unique fingerprint.

Cite this