journal article·2022-08-04Open access

An Investigation on Radiomics Feature Handling for HNSCC Staging Classification

Nadia Brancati, Massimo La Rosa, Giuseppe De Pietro, Giusy Esposito, Marika Valentino, Marco Aiello, Marco Salvatore

Applied Sciences· Volume 12· Issue 15

Abstract

The incidence of Head and Neck Squamous Cell Carcinoma (HNSCC) has been growing in the last few decades. Its diagnosis is usually performed through clinical evaluation and analyzing radiological images, then confirmed by histopathological examination, an invasive and time-consuming operation. The recent advances in the artificial intelligence field are leading to interesting results in the early diagnosis, personalized treatment and monitoring of HNSCC only by analyzing radiological images, without performing a tissue biopsy. The large amount of radiological images and the increasing interest in radiomics approaches can help to develop machine learning (ML) methods to support diagnosis. In this work, we propose an ML method based on the use of radiomics features, extracted from CT and PET images, to classify the disease in terms of pN-Stage, pT-Stage and Overall Stage. After the extraction of radiomics features, a selection step is performed to remove dataset redundancy. Finally, ML methods are employed to complete the classification task. Our pipeline is applied on the “Head-Neck-PET-CT” TCIA open-source dataset, considering a cohort of 201 patients from four different institutions. An AUC of 97%, 83% and 93% in terms of pN-Stage, pT-Stage and Overall Stage classification, respectively, is achieved. The obtained results are promising, showing the potential efficiency of the use of radiomics approaches in staging classification.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Radiomics and Machine Learning in Medical Imaging · Sarcoma Diagnosis and Treatment · AI in cancer detection

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Institute for High Performance Computing and Networking, National Research Council of Italy (ICAR-CNR), 80131 Naples, Italy

Bio Check Up S.r.l., 80122 Naples, Italy

Department of Advanced Biomedical Sciences, University of Naples “Federico II”, 80131 Naples, Italy

Institute of Applied Sciences and Intelligent Systems, National Research Council of Italy (ISASI-CNR), 80078 Naples, Italy

Department of Electrical Engineering and Information Technologies, University of Naples “Federico II”, 80125 Naples, Italy

IRCCS SYNLAB SDN, Istituto di Ricerca Diagnostica e Nucleare, 80143 Naples, Italy

Funding

Technological Platform: eMORFORAD-Campania

References (54)

Show source-provided references
1. Incidence and survival of HNSCC patients living with HIV compared with HIV-negative HNSCC patients10.1007/s00405-020-06573-9 ↗
2. Lymph node ratio as a prognostic factor in head and neck cancer patients10.1186/s13014-015-0490-9 ↗
3. Metastatic lymph node burden and survival in oral cavity cancer10.1200/JCO.2016.71.1176 ↗
4. Imaging of patients with head and neck cancer: From staging to surveillance10.1016/j.coms.2018.06.004 ↗
5. Applications of radiomics in precision diagnosis, prognostication and treatment planning of head and neck squamous cell carcinomas10.1186/s41199-020-00053-7 ↗
6. Machine and deep learning methods for radiomics10.1002/mp.13678 ↗
7. D’Amico, N.C., Sicilia, R., Cordelli, E., Tronchin, L., Greco, C., Fiore, M., Carnevale, A., Iannello, G., Ramella, S., and Soda, P. (2020). Radiomics-Based Prediction of Overall Survival in Lung Cancer Using Different Volumes-Of-Interest. Appl. Sci., 10.10.3390/app10186425 ↗
8. Alongi, P., Stefano, A., Comelli, A., Spataro, A., Formica, G., Laudicella, R., Lanzafame, H., Panasiti, F., Longo, C., and Midiri, F. (2022). Artificial Intelligence Applications on Restaging [18F] FDG PET/CT in Metastatic Colorectal Cancer: A Preliminary Report of Morpho-Functional Radiomics Classification for Prediction of Disease Outcome. Appl. Sci., 12.10.3390/app12062941 ↗
9. Prognostic value of tumor metabolic imaging phenotype by FDG PET radiomics in HNSCC10.1007/s12149-021-01586-8 ↗
10. Radiomics AI prediction for head and neck squamous cell carcinoma (HNSCC) prognosis and recurrence with target volume approach10.1259/bjro.20200073 ↗
11. Keek, S.A., Wesseling, F.W., Woodruff, H.C., van Timmeren, J.E., Nauta, I.H., Hoffmann, T.K., Cavalieri, S., Calareso, G., Primakov, S., and Leijenaar, R.T. (2021). A prospectively validated prognostic model for patients with locally advanced squamous cell carcinoma of the head and neck based on radiomics of computed tomography images. Cancers, 13.10.3390/cancers13133271 ↗
12. Zhang, M.H., Cao, D., and Ginat, D.T. (2021). Radiomic Model Predicts Lymph Node Response to Induction Chemotherapy in Locally Advanced Head and Neck Cancer. Diagnostics, 11.10.3390/diagnostics11040588 ↗
13. Radiomics: Extracting more information from medical images using advanced feature analysis10.1016/j.ejca.2011.11.036 ↗
14. The development and validation of a CT-based radiomics signature for the preoperative discrimination of stage I-II and stage III-IV colorectal cancer10.18632/oncotarget.8919 ↗
15. Radiomic features of pretreatment MRI could identify T stage in patients with rectal cancer: Preliminary findings10.1002/jmri.25969 ↗
16. Ma, X., Shen, F., Jia, Y., Xia, Y., Li, Q., and Lu, J. (2019). MRI-based radiomics of rectal cancer: Preoperative assessment of the pathological features. BMC Med. Imaging, 19.10.1186/s12880-019-0392-7 ↗
17. Radiomic nomogram improves preoperative T category accuracy in locally advanced laryngeal carcinoma10.3389/fonc.2019.01064 ↗
18. Magnetic resonance imaging based radiomics signature for the preoperative discrimination of stage I-II and III-IV head and neck squamous cell carcinoma10.1016/j.ejrad.2018.07.002 ↗
19. Prediction of lymph node metastasis in patients with papillary thyroid carcinoma: A radiomics method based on preoperative ultrasound images10.1177/1533033819831713 ↗
20. Prediction of tumor grade and nodal status in oropharyngeal and oral cavity squamous-cell carcinoma using a radiomic approach10.21873/anticanres.13949 ↗
21. Tumor radiomics signature for artificial neural network-assisted detection of neck metastasis in patient with tongue cancer10.1016/j.neurad.2021.07.006 ↗
22. Combining many-objective radiomics and 3D convolutional neural network through evidential reasoning to predict lymph node metastasis in head and neck cancer10.1088/1361-6560/ab083a ↗
23. Investigation of radiomic signatures for local recurrence using primary tumor texture analysis in oropharyngeal head and neck cancer patients10.1038/s41598-017-14687-0 ↗
24. Evaluating the effect of right-censored end point transformation for radiomic feature selection of data from patients with oropharyngeal cancer10.1200/CCI.18.00052 ↗
25. T2w-MRI signal normalization affects radiomics features reproducibility10.1002/mp.14038 ↗
26. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach10.1038/ncomms5006 ↗
27. Radiomic machine-learning classifiers for prognostic biomarkers of head and neck cancer10.3389/fonc.2015.00272 ↗
28. Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma10.1080/0284186X.2017.1346382 ↗
29. A comparative study of machine learning methods for time-to-event survival data for radiomics risk modelling10.1038/s41598-017-13448-3 ↗
30. Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test–retest and image registration analyses10.1002/mp.14368 ↗
31. Radiomics-based machine learning model to predict risk of death within 5-years in clear cell renal cell carcinoma patients10.1016/j.compbiomed.2020.104135 ↗
32. Chaddad, A., Kucharczyk, M.J., and Niazi, T. (2018). Multimodal radiomic features for the predicting gleason score of prostate cancer. Cancers, 10.10.3390/cancers10080249 ↗
33. Machine learning for radiomics-based multimodality and multiparametric modeling10.23736/S1824-4785.19.03213-8 ↗
34. A Novel multimodal radiomics model for preoperative prediction of lymphovascular invasion in rectal cancer10.3389/fonc.2020.00457 ↗
35. (2021, March 29). Head-Neck-PET-CT. Available online: https://wiki.cancerimagingarchive.net/display/Public/Head-Neck-PET-CT#242838670b323d6250cc42fa8fa09821fabe0bd7.
36. Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer10.1038/s41598-017-10371-5 ↗
37. Computational radiomics system to decode the radiographic phenotype10.1158/0008-5472.CAN-17-0339 ↗
38. Zwanenburg, A., Leger, S., Vallières, M., and Löck, S. (2016). Image biomarker standardisation initiative. arXiv.
39. Theory of edge detection
40. Volume data and wavelet transforms10.1109/38.219451 ↗
41. Machine learning, medical diagnosis, and biomedical engineering research-commentary10.1186/1475-925X-13-94 ↗
42. Impact of feature selection methods and subgroup factors on prognostic analysis with CT-based radiomics in non-small cell lung cancer patients10.1186/s13014-021-01810-9 ↗
43. CT-based radiomic signature as a prognostic factor in stage IV ALK-positive non-small-cell lung cancer treated with TKI crizotinib: A proof-of-concept study10.3389/fonc.2020.00057 ↗
44. Kuhn, M., and Johnson, K. (2013). Applied Predictive Modeling, Springer.10.1007/978-1-4614-6849-3 ↗
45. Gene Selection for Cancer Classification using Support Vector Machines10.1023/A:1012487302797 ↗
46. Magee, J.F. (1964). Decision Trees for Decision Making, Harvard Business Review.
47. Nearest neighbor pattern classification10.1109/TIT.1967.1053964 ↗
48. Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1985). Learning Internal Representations by Error Propagation, California University, Institute for Cognitive Science. Technical Report.10.21236/ADA164453 ↗
49. Langley, P., Iba, W., and Thompson, K. (1992). An Analysis of Bayesian Classifiers, Aaai Citeseer.
50. Ho, T.K. (1995, January 14–16). Random decision forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada.
51. Vapnik, V. (2013). The Nature of Statistical Learning Theory, Springer Science & Business Media.
52. SMOTE: Synthetic minority over-sampling technique10.1613/jair.953 ↗
53. Scikit-learn: Machine Learning in Python
54. Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning