Predicting Survival and Recurrence of Lung Ablation Patients Using Deep Learning-Based Automatic Segmentation and Radiomics Analysis

Overview

Journal Cardiovasc Intervent Radiol

Specialty Cardiology & Vascular Diseases

Date 2024 Nov 28

PMID 39604700

Authors

Hossam A Zaki

Karim Oueidat

Celina Hsieh

Helen Zhang

Scott Collins

Zhicheng Jiao

Aaron W P Maxwell

Affiliations

Soon will be listed here.

Abstract

Purpose: To predict survival and tumor recurrence following image-guided thermal ablation (IGTA) of lung tumors segmented using a deep learning approach.

Methods And Materials: A total of 113 patients who underwent IGTA for primary and metastatic lung tumors at a single institution between January 1, 2004 and July 14, 2022 were retrospectively identified. A pretrained U-Net model was applied to the dataset of pre- and post-procedure CT scans to segment lung zones. Following lung segmentation, a U-shaped encoder-decoder transformer architecture (UNETR) was trained to segment lung tumors from pre- and post-procedure CT scans, and radiomic features were automatically extracted. These features were input into a support vector machine (SVM)-based survival prediction model trained to assign rank scores to samples based on binary survival or recurrence label and follow-up time. C-index and time-dependent AUC were subsequently calculated to evaluate model performance.

Results: Initial tumor segmentation using UNETR achieved a Dice score of 0.75. Applying a radiomics-based survivability prediction model to the post-procedure scans resulted in a c-index of 0.71 and a time-dependent AUC of 0.75. In contrast, when this model was applied to pre-procedure scans, it achieved a 0.56 for both metrics. For predicting time to recurrence, the radiomics-based model achieved a c-index of 0.65 and a time-dependent AUC of 0.72 on post-procedure imaging. In contrast, when this model was applied to pre-procedure scans, it achieved a 0.54 for both metrics.

Conclusion: Radiomic feature analysis of lung tumors following automatic segmentation by a state-of-the-art transformer-based U-NET may predict survival and recurrence following image-guided thermal ablation of pulmonary malignancies.

Level Of Evidence: Level 3, Retrospective cohort study.

References

Shang Y, Li G, Zhang B, Wu Y, Chen Y, Li C . Image-guided percutaneous ablation for lung malignancies. Front Oncol. 2022; 12:1020296. PMC: 9685331. DOI: 10.3389/fonc.2022.1020296. View

Sugarbaker D . Lung cancer. 6: The case for limited surgical resection in non-small cell lung cancer. Thorax. 2003; 58(7):639-41. PMC: 1746726. DOI: 10.1136/thorax.58.7.639. View

Tselikas L, Garzelli L, Mercier O, Auperin A, Lamrani L, Deschamps F . Radiofrequency ablation versus surgical resection for the treatment of oligometastatic lung disease. Diagn Interv Imaging. 2020; 102(1):19-26. DOI: 10.1016/j.diii.2020.09.006. View

Genshaft S, Suh R, Abtin F, Baerlocher M, Chang A, Dariushnia S . Society of Interventional Radiology Multidisciplinary Position Statement on Percutaneous Ablation of Non-small Cell Lung Cancer and Metastatic Disease to the Lungs: Endorsed by the Canadian Association for Interventional Radiology, the.... J Vasc Interv Radiol. 2021; 32(8):1241.e1-1241.e12. DOI: 10.1016/j.jvir.2021.04.024. View

Wu X, Uhlig J, Blasberg J, Gettinger S, Suh R, Solomon S . Microwave Ablation versus Stereotactic Body Radiotherapy for Stage I Non-Small Cell Lung Cancer: A Cost-Effectiveness Analysis. J Vasc Interv Radiol. 2022; 33(8):964-971.e2. DOI: 10.1016/j.jvir.2022.04.019. View

Wang Y, Liu B, Cao P, Wang W, Wang W, Chang H . Comparison between computed tomography-guided percutaneous microwave ablation and thoracoscopic lobectomy for stage I non-small cell lung cancer. Thorac Cancer. 2018; 9(11):1376-1382. PMC: 6209786. DOI: 10.1111/1759-7714.12842. View

Healey T, March B, Baird G, Dupuy D . Microwave Ablation for Lung Neoplasms: A Retrospective Analysis of Long-Term Results. J Vasc Interv Radiol. 2016; 28(2):206-211. DOI: 10.1016/j.jvir.2016.10.030. View

Hasegawa T, Takaki H, Kodama H, Matsuo K, Yamanaka T, Nakatsuka A . Impact of the Ablative Margin on Local Tumor Progression after Radiofrequency Ablation for Lung Metastases from Colorectal Carcinoma: Supplementary Analysis of a Phase II Trial (MLCSG-0802). J Vasc Interv Radiol. 2022; 34(1):31-37.e1. DOI: 10.1016/j.jvir.2022.08.032. View

Ziv E, Erinjeri J, Yarmohammadi H, Boas F, Petre E, Gao S . Lung Adenocarcinoma: Predictive Value of KRAS Mutation Status in Assessing Local Recurrence in Patients Undergoing Image-guided Ablation. Radiology. 2016; 282(1):251-258. PMC: 5207123. DOI: 10.1148/radiol.2016160003. View

10.

Chen X, Sun S, Bai N, Han K, Liu Q, Yao S . A deep learning-based auto-segmentation system for organs-at-risk on whole-body computed tomography images for radiation therapy. Radiother Oncol. 2021; 160:175-184. DOI: 10.1016/j.radonc.2021.04.019. View

11.

Suzuki K, Abe H, MacMahon H, Doi K . Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN). IEEE Trans Med Imaging. 2006; 25(4):406-16. DOI: 10.1109/TMI.2006.871549. View

12.

Taghavi M, Staal F, Munoz F, Imani F, Meek D, Simoes R . CT-Based Radiomics Analysis Before Thermal Ablation to Predict Local Tumor Progression for Colorectal Liver Metastases. Cardiovasc Intervent Radiol. 2021; 44(6):913-920. DOI: 10.1007/s00270-020-02735-8. View

13.

Xv Y, Lv F, Guo H, Zhou X, Tan H, Xiao M . Machine learning-based CT radiomics approach for predicting WHO/ISUP nuclear grade of clear cell renal cell carcinoma: an exploratory and comparative study. Insights Imaging. 2021; 12(1):170. PMC: 8605949. DOI: 10.1186/s13244-021-01107-1. View

14.

Hofmanninger J, Prayer F, Pan J, Rohrich S, Prosch H, Langs G . Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. Eur Radiol Exp. 2020; 4(1):50. PMC: 7438418. DOI: 10.1186/s41747-020-00173-2. View

15.

Hesamian M, Jia W, He X, Kennedy P . Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges. J Digit Imaging. 2019; 32(4):582-596. PMC: 6646484. DOI: 10.1007/s10278-019-00227-x. View

16.

van Griethuysen J, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V . Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017; 77(21):e104-e107. PMC: 5672828. DOI: 10.1158/0008-5472.CAN-17-0339. View

17.

Tortora M, Gemini L, Scaravilli A, Ugga L, Ponsiglione A, Stanzione A . Radiomics Applications in Head and Neck Tumor Imaging: A Narrative Review. Cancers (Basel). 2023; 15(4). PMC: 9954362. DOI: 10.3390/cancers15041174. View

18.

Wu Y, Xu L, Yang P, Lin N, Huang X, Pan W . Survival Prediction in High-grade Osteosarcoma Using Radiomics of Diagnostic Computed Tomography. EBioMedicine. 2018; 34:27-34. PMC: 6116348. DOI: 10.1016/j.ebiom.2018.07.006. View

19.

Hou K, Chen J, Wang Y, Chiu M, Lin S, Mo Y . Radiomics-Based Deep Learning Prediction of Overall Survival in Non-Small-Cell Lung Cancer Using Contrast-Enhanced Computed Tomography. Cancers (Basel). 2022; 14(15). PMC: 9367244. DOI: 10.3390/cancers14153798. View

20.

Zhu F, Yang C, Xia Y, Wang J, Zou J, Zhao L . CT-based radiomics models may predict the early efficacy of microwave ablation in malignant lung tumors. Cancer Imaging. 2023; 23(1):60. PMC: 10258945. DOI: 10.1186/s40644-023-00571-w. View