Automated Deep Learning-Based Detection and Segmentation of Lung Tumors at CT.

Journal: Radiology
PMID:

Abstract

Background Detection and segmentation of lung tumors on CT scans are critical for monitoring cancer progression, evaluating treatment responses, and planning radiation therapy; however, manual delineation is labor-intensive and subject to physician variability. Purpose To develop and evaluate an ensemble deep learning model for automating identification and segmentation of lung tumors on CT scans. Materials and Methods A retrospective study was conducted between July 2019 and November 2024 using a large dataset of CT simulation scans and clinical lung tumor segmentations from radiotherapy plans. This dataset was used to train a 3D U-Net-based, image-multiresolution ensemble model to detect and segment lung tumors on CT scans. Model performance was evaluated on internal and external test sets composed of CT simulation scans and lung tumor segmentations from two affiliated medical centers, including single primary and metastatic lung tumors. Performance metrics included sensitivity, specificity, false positive rate, and Dice similarity coefficient (DSC). Model-predicted tumor volumes were compared with physician-delineated volumes. Group comparisons were made with Wilcoxon signed-rank test or one-way ANOVA. P < 0.05 indicated statistical significance. Results The model, trained on 1,504 CT scans with clinical lung tumor segmentations, achieved 92% sensitivity (92/100) and 82% specificity (41/50) in detecting lung tumors on the combined 150-CT scan test set. For a subset of 100 CT scans with a single lung tumor each, the model achieved a median model-physician DSC of 0.77 (IQR: 0.65-0.83) and an interphysician DSC of 0.80 (IQR: 0.72-0.86). Segmentation time was shorter for the model than for physicians (mean 76.6 vs. 166.1-187.7 seconds; p<0.001). Conclusion Routinely collected radiotherapy data were useful for model training. The key strengths of the model include a 3D U-Net ensemble approach for balancing volumetric context with resolution, robust tumor detection and segmentation performance, and the ability to generalize to an external site.

Authors

  • Mehr Kashyap
    Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, California, USA.
  • Xi Wang
    School of Information, Central University of Finance and Economics, Beijing, China.
  • Neil Panjwani
    Department of Radiation Oncology, Stanford University School of Medicine, 875 Blake Wilbur Drive, Stanford, CA, 94305, USA.
  • Mohammad Hasan
    Stanford University School of Medicine, Department of Radiation Oncology, Stanford, CA, US.
  • Qin Zhang
    Department of Burn, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China.
  • Charles Huang
    Department of Electrical Engineering, Stanford University, Stanford, California.
  • Karl Bush
    Stanford University School of Medicine, Department of Radiation Oncology, Stanford, CA, US.
  • Alexander Chin
    Stanford University School of Medicine, Department of Radiation Oncology, Stanford, CA, US.
  • Lucas K Vitzthum
    Aaron B. Simon, MD, PhD and Lucas K. Vitzthum, MD, Department of Radiation Medicine and Applied Sciences, University of California San Diego, La Jolla, CA; and Loren K. Mell, MD, Department of Radiation Medicine and Applied Sciences, University of California San Diego, and Center for Precision Radiation Medicine, La Jolla, CA.
  • Peng Dong
    Department of Radiation Oncology, Stanford University, CA, USA.
  • Sandra Zaky
    Stanford University School of Medicine, Department of Radiation Oncology, Stanford, CA, US.
  • Billy W Loo
    Department of Radiation Oncology, Stanford University School of Medicine, Stanford, California.
  • Maximilian Diehn
    Department of Radiation Oncology, Stanford University School of Medicine, Stanford, California.
  • Lei Xing
    Department of Radiation Oncology, Stanford University, CA, USA.
  • Ruijiang Li
    Global Station for Quantum Medical Science and Engineering, Global Institution for Collaborative Research and Education (GI-CoRE), Proton Beam Therapy Center, North 14 West 5 Kita-ku, Sapporo, Hokkaido, 060-8648, Japan.
  • Michael F Gensheimer
    Department of Radiation Oncology, Stanford University School of Medicine, Stanford, California.