Predicting nodal metastasis progression of oral tongue cancer using a hidden Markov model in MRI

• Verfasst von: Gang, Qiangqiang [VerfasserIn]
• Verfasst von: Feng, Jie [VerfasserIn]
• Verfasst von: Kauczor, Hans-Ulrich [VerfasserIn]
• Verfasst von: Zhang, Ke [VerfasserIn]
• Titel: Predicting nodal metastasis progression of oral tongue cancer using a hidden Markov model in MRI
• Verf.angabe: Qiangqiang Gang, Jie Feng, Hans-Ulrich Kauczor and Ke Zhang
• E-Jahr: 2024
• Jahr: 06 June 2024
• Umfang: 11 S.
• Illustrationen: Illustrationen
• Fussnoten: Gesehen am 21.11.2024
• Titel Quelle: Enthalten in: Frontiers in oncology
• Ort Quelle: Lausanne : Frontiers Media, 2011
• Jahr Quelle: 2024
• Band/Heft Quelle: 14(2024) vom: Juni, Artikel-ID 1360253, Seite 1-11
• ISSN Quelle: 2234-943X
• DOI: doi:10.3389/fonc.2024.1360253
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: artificial intelligence
• Sach-SW: Hidden markov model
• Sach-SW: level of metastatic lymph nodes
• Sach-SW: Lymph node metastases
• Sach-SW: Oral cavity squamous cell carcinoma
• K10plus-PPN: 1909299286
• K10plus-PPN:
  Universitätsbibliothek
• Lokale URL UB: Zum Volltext

Abstract

Objectives: The presence of occult nodal metastases in patients with oral tongue squamous cell carcinomas (OTSCCs) has implications for treatment. More than 30% of patients will have occult nodal metastases, yet a considerable number of patients undergo unnecessary invasive neck dissection to confirm nodal status. In this work, we propose a probabilistic model for lymphatic metastatic spread that can quantify the risk of microscopic involvement at the lymph node level (LNL) given the location of macroscopic metastases and the tumor stage using the MRI method. Materials and methods: A total of 108 patients of OTSCCs were included in the study. A hidden Markov model (HMM) was used to compute the probabilities of transitions between states over time based on MRI. Learning of the transition probabilities was performed via Markov chain Monte Carlo sampling and was based on a dataset of OTSCC patients for whom involvement of individual LNLs was reported. Results: Our model found that the most common involvement was that of level I and level II, corresponding to a high probability of ????b1 = 0.39 ± 0.05, ????b2 = 0.53 ± 0.09; lymph node level I had metastasis, and the probability of metastasis in lymph node II was high (93.79%); lymph node level II had metastasis, and the probability of metastasis in lymph node III was small (7.88%). Lymph nodes progress faster in the early stage and slower in the late stage. Conclusion: An HMM can produce an algorithm that is able to predict nodal metastasis evolution in patients with OTSCCs by analyzing the macroscopic metastases observed in the upstream levels, and tumor category.