The main metastatic route for lung cancer is lymph node metastasis, and studies have shown that non-small cell lung cancer (NSCLC) has a high risk of lymph node infiltration.
OBJECTIVE:
This study aimed to compare the performance of handcrafted radiomics (HR) features and deep transfer learning (DTL) features in Computed Tomography (CT) of intratumoral and peritumoral regions in predicting the metastatic status of NSCLC lymph nodes in different machine learning classifier models.
METHODS:
We retrospectively collected data of 199 patients with pathologically confirmed NSCLC. All patients were divided into training (n = 159) and validation (n = 40) cohorts, respectively. The best HR and DTL features in the intratumoral and peritumoral regions were extracted and selected, respectively. Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Light Gradient Boosting Machine (Light GBM), Multilayer Perceptron (MLP), and Logistic Regression (LR) models were constructed, and the performance of the models was evaluated.
RESULTS:
Among the five models in the training and validation cohorts, the LR classifier model performed best in terms of HR and DTL features. The AUCs of the training cohort were 0.841 (95% CI: 0.776–0.907) and 0.955 (95% CI: 0.926–0.983), and the AUCs of the validation cohort were 0.812 (95% CI: 0.677–0.948) and 0.893 (95% CI: 0.795–0.991), respectively. The DTL signature was superior to the handcrafted radiomics signature.
CONCLUSIONS:
Compared with the radiomics signature, the DTL signature constructed based on intratumoral and peritumoral areas in CT can better predict NSCLC lymph node metastasis.
Get full access to this article
View all access options for this article.
References
1.
SungH., FerlayJ., SiegelR.L., LaversanneM., SoerjomataramI., JemalA., et al., Global Cancer Statistics: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries, CA Cancer J Clin71 (2021), 209–249.
2.
MillerK.D., NogueiraL., DevasiaT., MariottoA.B., YabroffK.R., JemalA., et al., Cancer treatment and survivorship statistics, CA Cancer J Clin72 (2022), 409–436.
3.
HerbstR.S., MorgenszternD., BoshoffC.The biology and management of non-small cell lung cancer, Nature553 (2018), 446–454.
4.
HerbstR.S., MorgenszternD., BoshoffC.The biology and management of non-small cell lung cancer, Nature553 (2018), 446–454.
5.
SilvestriG.A., GonzalezA.V., JantzM.A., MargolisM.L., GouldM.K., TanoueL.T., et al., Methods for staging non-small cell lung cancer: Diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians evidence-based clinical practice guidelines, Chest143 (2013), e211S–e250S.
6.
RuschV.W., CrowleyJ., GirouxD.J., GoldstrawP., ImJ.-G., TsuboiM., et al., The IASLC Lung Cancer Staging Project: proposals for the revision of the N descriptors in the forthcoming seventh edition of the TNM classification for lung cancer, J Thorac Oncol2 (2007), 603–612.
7.
SilvestriG.A., GouldM.K., MargolisM.L., TanoueL.T., McCroryD., TolozaE., et al., Noninvasive staging of non-small cell lung cancer: ACCP evidenced-based clinical practice guidelines (2nd edition), Chest132 (2007), 178S–201S.
8.
LinW.-Y., HsuW.-H., LinK.-H., WangS.-J.Role of preoperative PET-CT in assessing mediastinal and hilar lymph node status in early stage lung cancer, J Chin Med Assoc75 (2012), 203–208.
9.
KanzakiR., HigashiyamaM., FujiwaraA., TokunagaT., MaedaJ., OkamiJ., et al., Occult mediastinal lymph node metastasis in NSCLC patients diagnosed as clinical N0-1 by preoperative integrated FDG-PET/CT and CT: Risk factors, pattern, and histopathological study, Lung Cancer71 (2011), 333–337.
10.
WuY., LiP., ZhangH., ShiY., WuH., ZhangJ., et al., Diagnostic value of fluorine 18 fluorodeoxyglucose positron emission tomography/computed tomography for the detection of metastases in non-small-cell lung cancer patients, Int J Cancer132 (2013), E37–47.
11.
KadotaK., YehY.-C., Villena-VargasJ., CherkasskyL., DrillE.N., SimaC.S., et al., Tumor Budding Correlates With the Protumor Immune Microenvironment and Is an Independent Prognostic Factor for Recurrence of Stage I Lung Adenocarcinoma, Chest148 (2015), 711–721.
12.
KadotaK., NitadoriJ.-I., SimaC.S., UjiieH., RizkN.P., JonesD.R., et al., Tumor Spread through Air Spaces is an Important Pattern of Invasion and Impacts the Frequency and Location of Recurrences after Limited Resection for Small Stage I Lung Adenocarcinomas, J Thorac Oncol10 (2015), 806–814.
13.
VaghjianiR.G., TakahashiY., EguchiT., LuS., KamedaK., TanoZ., et al., Tumor Spread Through Air Spaces Is a Predictor of Occult Lymph Node Metastasis in Clinical Stage IA Lung Adenocarcinoma, J Thorac Oncol15 (2020), 792–802.
14.
LambinP., Rios-VelazquezE., LeijenaarR., CarvalhoS., van StiphoutR.G.P.M.,GrantonP., et al., Radiomics: extracting more information from medical images using advanced feature analysis, Eur J Cancer48 (2012), 441–446.
15.
GilliesR.J., KinahanP.E., HricakH.Radiomics: Images Are More than Pictures, They Are Data, Radiology278 (2016), 563–577.
16.
LiaoG., HuangL., WuS., ZhangP., XieD., YaoL., et al., Preoperative CT-based peritumoral and tumoral radiomic features prediction for tumor spread through air spaces in clinical stage I lung adenocarcinoma, Lung Cancer163 (2022), 87–95.
17.
TunaliI., HallL.O., NapelS., CherezovD., GuvenisA., GilliesR.J., et al., Stability and reproducibility of computed tomography radiomic features extracted from peritumoral regions of lung cancer lesions, Med Phys46 (2019), 5075–5085.
18.
HanW., QinL., BayC., ChenX., YuK.-H., MiskinN., et al., Deep Transfer Learning and Radiomics Feature Prediction of Survival of Patients with High-Grade Gliomas, AJNR Am J Neuroradiol41 (2020), 40–48.
19.
WuX., LiY., ChenX., HuangY., HeL., ZhaoK., et al., Deep Learning Features Improve the Performance of a Radiomics Signature for Predicting KRAS Status in Patients with Colorectal Cancer, Acad Radiol27 (2020), e254–e262.
20.
LaoJ., ChenY., LiZ.-C., LiQ., ZhangJ., LiuJ., et al. A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme, Sci Rep7 (2017), 10353.
21.
LitjensG., KooiT., BejnordiB.E., SetioA.A.A., CiompiF., GhafoorianM., et al. A survey on deep learning in medical image analysis, Med Image Anal42 (2017), 60–88.
22.
CiceroM., BilbilyA., ColakE., DowdellT., GrayB., PerampaladasK., et al., Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs, Invest Radiol52 (2017), 281–287.
23.
XueL.-Y., JiangZ.-Y., FuT.-T., WangQ.-M., ZhuY.-L., DaiM., et al., Transfer learning radiomics based on multimodal ultrasound imaging for staging liver fibrosis, Eur Radiol30 (2020), 2973–2983.
24.
HuY., XieC., YangH., HoJ.W.K., WenJ., HanL., et al., Computed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma, Radiother Oncol154 (2021), 6–13.
25.
ChristodoulidisS., AnthimopoulosM., EbnerL., ChristeA., MougiakakouS.Multisource Transfer Learning With Convolutional Neural Networks for Lung Pattern Analysis, IEEE J Biomed Health Inform21 (2017), 76–84.
26.
HeP., JiaP., QiaoS., DuanS.Self-Taught Learning Based on Sparse Autoencoder for E-Nose in Wound Infection Detection, Sensors (Basel)17 (2017), E2279.
27.
ZhuX., DongD., ChenZ., FangM., ZhangL., SongJ., et al., Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer, Eur Radiol28 (2018), 2772–2778.
28.
YoonH.J., SohnI., ChoJ.H., LeeH.Y., KimJ.-H., ChoiY.-L., et al., Decoding Tumor Phenotypes for ALK, ROS1, and RET Fusions in Lung Adenocarcinoma Using a Radiomics Approach, Medicine (Baltimore)94 (2015), e1753.
29.
M KP,A GP,PP,PdV,RT, et al. Changes in CT Radiomic Features Associated with Lymphocyte Distribution Predict Overall Survival and Response to Immunotherapy in Non-Small Cell Lung Cancer, Cancer Immunology Research (2020), 8.
30.
VaidyaP., BeraK., PatilP.D., GuptaA., JainP., AlilouM., et al., Novel, non-invasive imaging approach to identify patients with advanced non-small cell lung cancer at risk of hyperprogressive disease with immune checkpoint blockade, J Immunother Cancer8 (2020), e001343.
31.
DouT.H., CorollerT.P., van GriethuysenJ.J.M.MakR.H.,AertsH.J.W.L.,Peritumoral radiomics features predict distant metastasis in locally advanced NSCLC, PLoS One13 (2018), e0206108.
32.
WangX., ZhaoX., LiQ., XiaW., PengZ., ZhangR., et al., Can peritumoral radiomics increase the efficiency of the prediction for lymph node metastasis in clinical stage T1 lung adenocarcinoma on CT?Eur Radiol29 (2019), 6049–6058.
33.
DouT.H., CorollerT.P., van GriethuysenJ.J.M.MakR.H., AertsH.J.W.L., Peritumoral radiomics features predict distant metastasis in locally advanced NSCLC, PLoS One13 (2018), e0206108.
34.
WangS., WuW., FengJ., LiuF., YuH.Low-dose spectral CT reconstruction based on image-gradient L0-norm and adaptive spectral PICCS, Phys Med Biol65 (2020), 245005.
35.
ZhangT., YuH., XiY., WangS., LiuF.Spectral CT Image-Domain Material Decomposition via Sparsity Residual Prior and Dictionary Learning, IEEE Trans. Instrum. Meas72 (2023), 1–13.
36.
WangS., YuH., XiY., GongC., WuW., LiuF.Spectral-Image Decomposition With Energy-Fusion Sensing for Spectral CT Reconstruction, IEEE Trans. Instrum. Meas.70 (2021), 1–11.
37.
ZhangY., Lobo-MuellerE.M., KaranicolasP., GallingerS., HaiderM.A., KhalvatiF.Improving prognostic performance in resectable pancreatic ductal adenocarcinoma using radiomics and deep learning features fusion in CT images, Sci Rep11 (2021), 1378.
38.
YuJ., DengY., LiuT., ZhouJ., JiaX., XiaoT., et al., Lymph node metastasis prediction of papillary thyroid carcinoma based on transfer learning radiomics, Nat Commun11 (2020), 4807.
39.
SofferS., Ben-CohenA., ShimonO., AmitaiM.M., GreenspanH., KlangE.Convolutional Neural Networks for Radiologic Images: A Radiologist’s Guide, Radiology290 (2019), 590–606.
40.
SunQ., LinX., ZhaoY., LiL., YanK., LiangD., et al., Deep Learning vs. Radiomics for Predicting Axillary Lymph Node Metastasis of Breast Cancer Using Ultrasound Images: Don’t Forget the Peritumoral Region, Front Oncol10 (2020), 53.
41.
LiY., WeiD., LiuX., FanX., WangK., LiS., et al., Molecular subtyping of diffuse gliomas using magnetic resonance imaging: comparison and correlation between radiomics and deep learning, Eur Radiol32 (2022), 747–758.
42.
ChoiY.S., BaeS., ChangJ.H., KangS.-G., KimS.H., KimJ., et al., Fully automated hybrid approach to predict themutation status of gliomas via deep learning and radiomics, Neuro-Oncology23 (2021), 304–313.
43.
ZhuY., ManC., GongL., DongD., YuX., WangS., et al., A deep learning radiomics model for preoperative grading in meningioma, Eur J Radiol116 (2019), 128–134.
