Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Oct;36(5):767-777.
doi: 10.1007/s10334-023-01084-0. Epub 2023 Apr 20.

Topology-based radiomic features for prediction of parotid gland cancer malignancy grade in magnetic resonance images

Kojiro Ikushima  1   2 , Hidetaka Arimura  3 , Ryuji Yasumatsu  4 , Hidemi Kamezawa  5 , Kenta Ninomiya  6
Affiliations

Topology-based radiomic features for prediction of parotid gland cancer malignancy grade in magnetic resonance images

Kojiro Ikushima et al. MAGMA. 2023 Oct.

Abstract

Purpose: The malignancy grades of parotid gland cancer (PGC) have been assessed for a decision of treatment policies. Therefore, we have investigated the feasibility of topology-based radiomic features for the prediction of parotid gland cancer (PGC) malignancy grade in magnetic resonance (MR) images.

Materials and methods: Two-dimensional T1- and T2-weighted MR images of 39 patients with PGC were selected for this study. Imaging properties of PGC can be quantified using the topology, which could be useful for assessing the number of the k-dimensional holes or heterogeneity in PGC regions using invariants of the Betti numbers. Radiomic signatures were constructed from 41,472 features obtained after a harmonization using an elastic net model. PGC patients were stratified using a logistic classification into low/intermediate- and high-grade malignancy groups. The training data were increased by four times to avoid the overfitting problem using a synthetic minority oversampling technique. The proposed approach was assessed using a 4-fold cross-validation test.

Results: The highest accuracy of the proposed approach was 0.975 for the validation cases, whereas that of the conventional approach was 0.694.

Conclusion: This study indicated that topology-based radiomic features could be feasible for the noninvasive prediction of the malignancy grade of PGCs.

Keywords: Malignancy grade; Parotid gland cancer; Radiomic features; Topology.

PubMed Disclaimer

Similar articles

See all similar articles

Cited by

References

    1. Chang JW, Hong HJ, Ban MJ, Shin YS, Kim WS, Koh YW et al (2015) Prognostic factors and treatment outcomes of parotid gland cancer: a 10-year single-center experience. Otolaryngol Head Neck Surg 153(6):981–989 - DOI - PubMed
    1. El-Naggar AK, Chan JK, Grandis JR et al (2017) World Health Organization classification of tumours. Chapter 7, tumours of salivary glands. IARC press, Lyon, pp 160–202
    1. Nishikawa S, Kawata R, Higashino M, Lee K, Terada T, Kurisu Y et al (2015) Assessing the histological type and grade of primary parotid carcinoma by fine-needle aspiration and frozen section. Auris Nasus Larynx 42(6):463–468 - DOI - PubMed
    1. Omura S, Kawata R, Higashino M, Nishikawa S, Terada T, Haginomori SI, Kurisu Y, Hirose Y (2020) Challenges with preoperative diagnosis of low/intermediate-grade carcinoma of the parotid gland: single-center study of 112 patients. Eur Arch Otorhinolaryngol 277(7):2031–2039. https://doi.org/10.1007/s00405-020-05871-6 - DOI - PubMed
    1. Leon B, John WE, Peter R, David S (2005) World Health Organization classification of tumours, pathology and genetics of head and neck tumours, IARC Press, Lyon, pp 209–281

LinkOut - more resources