1
|
Cebeci S, Tokgoz N, Pula D, Yazol M, Ogut B, Sahin MM, Karamert R, Duzlu M. Efficacy of radiological depth of invasion measurements on magnetic resonance images acquired at different magnetic field strengths and imaging sequences in predicting cervical lymph node metastasis and other outcomes in tongue cancer. Oral Surg Oral Med Oral Pathol Oral Radiol 2023; 136:731-740. [PMID: 37586901 DOI: 10.1016/j.oooo.2023.07.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/04/2023] [Revised: 07/07/2023] [Accepted: 07/16/2023] [Indexed: 08/18/2023]
Abstract
OBJECTIVES We investigated the correlation between magnetic resonance imaging (MRI) parameters and tumor pathological depth of invasion (pDOI), between pDOI and radiological DOI (rDOI), between rDOI and duration between biopsy and MRI, and between rDOI and duration between MRI and surgery to determine the efficacy of rDOI in identifying small lesions and other conditions. STUDY DESIGN We examined 36 adult patients who had been diagnosed histopathologically with cancer of the tongue and had undergone a glossectomy. Using 1.5 Tesla (T) and 3.0T MRI, we measured rDOI at the deepest infiltration point on 4 MRI sequences. We calculated the correlations between rDOI and the variables examined by Spearman rho analysis and evaluated the diagnostic performance of rDOI by receiver operating characteristic curve analysis. RESULTS Axial T2-weighted images using 1.5T MRI provided the closest approximation of pDOI. Although the correlation between rDOI and pDOI was significant, rDOI showed poor or acceptable discrimination in identifying small lesions and other conditions. There were no significant correlations between rDOI and the time between biopsy and MRI or between MRI and surgery. CONCLUSIONS The correlation between rDOI and pDOI is significant, but rDOI is ineffective in predicting malignancy and other conditions. Axial T2-weighted images using 1.5T MRI provide the closest approximation of pDOI.
Collapse
Affiliation(s)
- Suleyman Cebeci
- Department of Otorhinolaryngology/Head and Neck Surgery, Gazi University Faculty of Medicine, Ankara, Turkey.
| | - Nil Tokgoz
- Department of Radiology, Gazi University Faculty of Medicine, Ankara, Turkey
| | - Drilon Pula
- Department of Otorhinolaryngology/Head and Neck Surgery, Gazi University Faculty of Medicine, Ankara, Turkey
| | - Merve Yazol
- Department of Radiology, Gazi University Faculty of Medicine, Ankara, Turkey
| | - Betul Ogut
- Department of Pathology, Gazi University Faculty of Medicine, Ankara, Turkey
| | - Muammer Melih Sahin
- Department of Otorhinolaryngology/Head and Neck Surgery, Gazi University Faculty of Medicine, Ankara, Turkey
| | - Recep Karamert
- Department of Otorhinolaryngology/Head and Neck Surgery, Gazi University Faculty of Medicine, Ankara, Turkey
| | - Mehmet Duzlu
- Department of Otorhinolaryngology/Head and Neck Surgery, Gazi University Faculty of Medicine, Ankara, Turkey
| |
Collapse
|
2
|
Vijayalakshmi KR, Jain V. Accuracy of magnetic resonance imaging in the assessment of depth of invasion in tongue carcinoma: A systematic review and meta-analysis. Natl J Maxillofac Surg 2023; 14:341-353. [PMID: 38273911 PMCID: PMC10806321 DOI: 10.4103/njms.njms_174_22] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2022] [Revised: 03/19/2023] [Accepted: 03/27/2023] [Indexed: 01/27/2024] Open
Abstract
Tongue carcinoma constitutes 10.4-46.9% of all oral squamous cell carcinomas (OSCCs) and is notoriously known for invading tissues deeper than the evident gross margins. The deeper the tumor invades, the higher are its chances of future morbidity and mortality due to extensive neck dissection and risk of recurrence. Magnetic resonance imaging (MRI) is a noninvasive diagnostic aid used for measuring a preoperative tumor's depth of invasion (DOI) as it can efficiently outline soft tissue tumors from adjacent normal tissue. To assess various MRI modalities used in measuring DOI in tongue carcinoma and their reliability compared with other DOI measuring modalities. The protocol was registered in the International Prospective Register of Systematic Reviews (PROSPERO) database (CRD42022330866), and the following Preferred Reporting Items for a Systematic Review and Meta-Analysis (PRISMA) Diagnostic Test Accuracy guidelines were performed. PubMed electronic database was searched using a combination of keywords for relevant articles in the English language since 2016. Critical appraisal was carried out using the Quality Assessment of Diagnostic Accuracy Studies-Comparative (QUADAS-C) risk-of-bias (RoB) assessment tool. A weighted mean difference (WMD) was calculated between MRI and histopathological DOI along with pooled correlation and subgroup analysis, where possible. A total of 795 records were retrieved of which 17 were included in the final review with 13 included for meta-analysis. A high RoB was found for most studies for all parameters except flow and timing. WMD showed a statistically significant MRI overestimation of 1.90 mm compared with histopathology. Subgroup analysis showed the 1.5 Tesla machine to be superior to the 3.0 Tesla machine, while imaging sequence subgroup analysis could not be performed. MRI is a viable preoperative DOI measurement modality that can help in efficient treatment planning to decrease surgical morbidity and mortality.
Collapse
Affiliation(s)
| | - Vanshika Jain
- Department of Oral Medicine and Radiology, Government Dental College and Research Institute, Bangalore, Karnataka, India
| |
Collapse
|
3
|
Qin Z, Hu Z, Lai M, Wang F, Liu X, Yin L. A nomogram for predicting survival in Patients with oral tongue keratinized squamous cell carcinoma: A SEER-based study. JOURNAL OF STOMATOLOGY, ORAL AND MAXILLOFACIAL SURGERY 2023; 124:101422. [PMID: 36781109 DOI: 10.1016/j.jormas.2023.101422] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/23/2022] [Revised: 02/06/2023] [Accepted: 02/08/2023] [Indexed: 02/13/2023]
Abstract
OBJECTIVE Oral tongue keratinized squamous cell carcinoma (OTKSCC), a relatively rare form of tongue cancer (TC) in clinical practice, accompanied by features of cell keratosis, is an uncommon histological subtype. However, its specific clinicopathological features and prognosis have not been adequately described. In this study, we aimed to create a nomogram using R language software to predict overall survival (OS) of patients with OTKSCC to assess the prognosis of OTKSCC patients. METHODS We extracted clinical and related prognostic data of OTKSCC patients from 1975 to 2019 from the Surveillance, Epidemiology, and End Results database. Independent prognostic factors were selected using univariate and multivariate Cox analyses, and a nomogram was constructed using R software. The C-index, area under the curve (AUC) of receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA) were used to assess the clinical utility of the nomogram. Finally, OS was assessed using the Kaplan-Meier method. RESULTS A total of 2450 OTKSCC patients were included in the study. Univariate and multivariate Cox regression analyses were used to identify age, T stage, N stage, surgery, and radiation therapy as independent risk factors (p<0.05). In the training cohort, the calibration index of the nomogram was 0.725, while the AUC values for nomogram, age, T stage, N stage, surgery and radiation therapy were 0.878, 0.639, 0.781, 0.661, 0.724 and 0.354, respectively. At the same time, in the verification queue, the calibration index of the nomogram was 0.726, while the AUC values for nomogram, age, T stage, N stage, surgery and radiation therapy were 0.859,0.612,0.826,0.675,0.758 and 0.303, respectively. Ideal uniformity of the models from the training and validation cohorts was demonstrated in the calibration and DCA curves. Univariate survival analysis showed that age, T stage, N stage, surgery, and radiotherapy were statistically significant for prognosis (p<0.05). CONCLUSION Age, T stage, N stage, surgery, and radiation therapy are independently associated with the OS, and the established nomogram is an effective visualization tool for predicting the OS of OTKSCC patients.
Collapse
Affiliation(s)
- Zishun Qin
- The First Clinical Medical College, Lanzhou University, Lanzhou,730000, China; School/Hospital of Stomatology, Lanzhou university, Lanzhou,730000, China.
| | - Zonghao Hu
- School/Hospital of Stomatology, Lanzhou university, Lanzhou,730000, China.
| | - Minqin Lai
- School/Hospital of Stomatology, Lanzhou university, Lanzhou,730000, China.
| | - Feng Wang
- School/Hospital of Stomatology, Lanzhou university, Lanzhou,730000, China
| | - Xiaoyuan Liu
- School/Hospital of Stomatology, Lanzhou university, Lanzhou,730000, China
| | - Lihua Yin
- The First Clinical Medical College, Lanzhou University, Lanzhou,730000, China; School/Hospital of Stomatology, Lanzhou university, Lanzhou,730000, China.
| |
Collapse
|
4
|
Joshi S, Bagade S, Naik C, Deore P, Garad A. Accuracy of Magnetic Resonance Imaging in Detecting Tumor Depth of Invasion in Squamous Cell Carcinoma of the Tongue: A Systematic Review. J Maxillofac Oral Surg 2023; 22:720-727. [PMID: 37534361 PMCID: PMC10390425 DOI: 10.1007/s12663-023-01886-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2022] [Accepted: 03/01/2023] [Indexed: 08/04/2023] Open
Abstract
Objective The objective of the study was to detect the accuracy of Magnetic Resonance Imaging (MRI) in assessing tumor depth of invasion (DOI) in squamous cell carcinoma (SCC) of the tongue. Material and Methods The electronic search of PubMed (including MEDLINE), COCHRANE CENTRAL and Google Scholar search engine for articles published from January 1, 2000, to September 31, 2021, was conducted and also searched the lists of references of relevant articles and reviews for studies involving patients with squamous cell carcinoma of the tongue. Results A total of 5362 articles were retrieved in the initial search. After the initial search process, 13 full-text articles were reviewed. Out of these 13 articles, seven met the inclusion criteria and were thus included in this systematic review. Conclusion The MRI-determined DOI based on T1-weighted sequences increases with increasing T stage. There is the highest correlation between the MRI-derived DOI and the histopathological DOI with increasing T stage. Therefore, MRI provides satisfactory diagnostic accuracy for measuring tumor DOI and, thus, may be considered a predictor of tumor stage.
Collapse
Affiliation(s)
- Sanjay Joshi
- Present Address: Department of Oral and Maxillofacial Surgery, TPCT’s Terna Dental College and Hospital, Plot No 12, opposite to Nerul West Railway station, sector 22, Nerul, Navi Mumbai, Maharashtra 400706 India
| | - Sachin Bagade
- Present Address: Department of Oral and Maxillofacial Surgery, TPCT’s Terna Dental College and Hospital, Plot No 12, opposite to Nerul West Railway station, sector 22, Nerul, Navi Mumbai, Maharashtra 400706 India
| | - Charudatta Naik
- Present Address: Department of Oral and Maxillofacial Surgery, TPCT’s Terna Dental College and Hospital, Plot No 12, opposite to Nerul West Railway station, sector 22, Nerul, Navi Mumbai, Maharashtra 400706 India
| | - Prachi Deore
- Present Address: Department of Oral and Maxillofacial Surgery, TPCT’s Terna Dental College and Hospital, Plot No 12, opposite to Nerul West Railway station, sector 22, Nerul, Navi Mumbai, Maharashtra 400706 India
| | - Aarti Garad
- Present Address: Department of Oral and Maxillofacial Surgery, TPCT’s Terna Dental College and Hospital, Plot No 12, opposite to Nerul West Railway station, sector 22, Nerul, Navi Mumbai, Maharashtra 400706 India
| |
Collapse
|
5
|
Vidiri A, Marzi S, Piludu F, Lucchese S, Dolcetti V, Polito E, Mazzola F, Marchesi P, Merenda E, Sperduti I, Pellini R, Covello R. Magnetic resonance imaging-based prediction models for tumor stage and cervical lymph node metastasis of tongue squamous cell carcinoma. Comput Struct Biotechnol J 2023; 21:4277-4287. [PMID: 37701020 PMCID: PMC10493896 DOI: 10.1016/j.csbj.2023.08.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2023] [Revised: 08/10/2023] [Accepted: 08/22/2023] [Indexed: 09/14/2023] Open
Abstract
Purpose To evaluate the ability of preoperative MRI-based measurements to predict the pathological T (pT) stage and cervical lymph node metastasis (CLNM) via machine learning (ML)-driven models trained in oral tongue squamous cell carcinoma (OTSCC). Materials and methods 108 patients with a new diagnosis of OTSCC were enrolled. The preoperative MRI study included post-contrast high-resolution T1-weighted images acquired in all patients. MRI-based depth of invasion (DOI) and tumor dimension-together with shape-based and intensity-based features-were extracted from the lesion volume segmentation. The entire dataset was randomly divided into a training set and a validation set, and the performances of different types of ML algorithms were evaluated and compared. Results MRI-based DOI and tumor dimension together with several shape-based and intensity-based signatures significantly discriminated the pT stage and LN status. The overall accuracy of the model for predicting the pT stage was 0.86 (95%CI, 0.78-0.92) and 0.81 (0.64-0.91) in the training and validation sets, respectively. There was no improvement in the model performance upon including shape-based and intensity-based features. The model for predicting CLNM based on DOI and tumor dimensions had a fair accuracy of 0.68 (0.57-0.78) and 0.69 (0.51-0.84) in the training and validation sets, respectively. The shape-based and intensity-based signatures have shown potential for improving the model sensitivity, with a comparable accuracy. Conclusion MRI-based models driven by ML algorithms could stratify patients with OTSCC according to the pT stages. They had a moderate ability to predict cervical lymph node metastasis.
Collapse
Affiliation(s)
- Antonello Vidiri
- Radiology and Diagnostic Imaging Department, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome,Italy
| | - Simona Marzi
- Medical Physics Laboratory, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 0 0144 Rome, Italy
| | - Francesca Piludu
- Radiology and Diagnostic Imaging Department, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome,Italy
| | - Sonia Lucchese
- Radiology and Diagnostic Imaging Department, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome,Italy
- Scuola di Specializzazione in Radiodiagnostica, Sapienza University of Rome, Policlinico Umberto I, Viale Regina Elena 324, 00161 Rome, Italy
| | - Vincenzo Dolcetti
- Radiology and Diagnostic Imaging Department, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome,Italy
- Scuola di Specializzazione in Radiodiagnostica, Sapienza University of Rome, Policlinico Umberto I, Viale Regina Elena 324, 00161 Rome, Italy
| | - Eleonora Polito
- Radiology and Diagnostic Imaging Department, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome,Italy
| | - Francesco Mazzola
- Department of Otolaryngology and Head and Neck Surgery, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy
| | - Paolo Marchesi
- Department of Otolaryngology and Head and Neck Surgery, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy
| | - Elisabetta Merenda
- Department of Radiological, Oncological and Pathological Sciences, Sapienza University of Rome, Policlinico Umberto I, 00161 Rome, Italy
| | - Isabella Sperduti
- Biostatistics Unit, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy
| | - Raul Pellini
- Department of Otolaryngology and Head and Neck Surgery, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy
| | - Renato Covello
- Department of Pathology, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy
| |
Collapse
|
6
|
Lo Casto A, Cannella R, Taravella R, Cordova A, Matta D, Campisi G, Attanasio M, Rinaldi G, Rodolico V. Diagnostic and prognostic value of magnetic resonance imaging in the detection of tumor depth of invasion and bone invasion in patients with oral cavity cancer. LA RADIOLOGIA MEDICA 2022; 127:1364-1372. [PMID: 36255660 DOI: 10.1007/s11547-022-01565-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/03/2022] [Accepted: 09/30/2022] [Indexed: 11/05/2022]
Abstract
PURPOSE To evaluate the accuracy of preoperative contrast-enhanced magnetic resonance imaging (MRI) in the assessment of radiological depth of invasion (rDOI) and bone invasion in patients with oral cavity cancer, and the prognostic value of preoperative rDOI. MATERIALS AND METHODS This retrospective study included patients with surgically resected oral cavity cancer and preoperative MRI acquired within four weeks before surgery. Two readers evaluated the MRI to assess the superficial and deep bone invasion, preoperative T stage, and measured the rDOI. The rDOI was compared to the histopathological DOI (pDOI), used as reference standard. Prognostic value of preoperative features for the disease-specific survival was evaluated using the Kaplan-Meier curve and multivariable Cox proportional hazards analysis. RESULTS The final population included 80 patients (50 males, mean age 67.7 ± 13.6 years). There was a strong statistically significant correlation between the rDOI (median 10 mm) and the pDOI (median 9 mm) (ρ: 0.978, p < 0.001). The agreement between MRI and histopathological T stage was excellent (k = 0.93, 95% CI 0.86, 0.99). The sensitivity and specificity of preoperative MRI were 93.3% and 98.8% for deep bone invasion, while they were 75.0% and 95.8% for superficial bone invasion, respectively. The rDOI > 10 mm was associated with poorer disease-specific survival (log-rank p = 0.016). The rDOI remained the only independent preoperative predictor associated with poorer disease-specific survival at multivariable analysis (hazard ratio 5.5; 95% CI 1.14, 26.58; p = 0.033). CONCLUSION Preoperative MRI is accurate for the assessment of DOI and bone invasion. The rDOI is an independent preoperative predictor of disease-specific survival in patients with oral cavity cancer.
Collapse
Affiliation(s)
- Antonio Lo Casto
- Sezione di Scienze Radiologiche, Dipartimento di Biomedicina, Neuroscienze e Diagnostica Avanzata (Bi.N.D.), Università degli Studi di Palermo, Via del Vespro 129, 90127, Palermo, Italy
| | - Roberto Cannella
- Sezione di Scienze Radiologiche, Dipartimento di Biomedicina, Neuroscienze e Diagnostica Avanzata (Bi.N.D.), Università degli Studi di Palermo, Via del Vespro 129, 90127, Palermo, Italy.
- Dipartimento di Promozione della Salute, Materno-Infantile, di Medicina Interna e Specialistica di Eccellenza "G. D'Alessandro", PROMISE, Università degli Studi di Palermo, Palermo, Italy.
| | | | - Adriana Cordova
- Divisione di Chirurgia Plastica e Ricostruttiva, Dipartimento di Discipline Chirurgiche, Oncologiche e Stomatologiche (Di.Chir.On.S.), Università degli Studi di Palermo, Palermo, Italy
| | - Daniele Matta
- Divisione di Chirurgia Plastica e Ricostruttiva, Dipartimento di Discipline Chirurgiche, Oncologiche e Stomatologiche (Di.Chir.On.S.), Università degli Studi di Palermo, Palermo, Italy
| | - Giuseppina Campisi
- Dipartimento di Discipline Chirurgiche, Oncologiche e Stomatologiche (Di.Chir.On.S.), Università degli Studi di Palermo, Palermo, Italy
| | - Massimo Attanasio
- Departmentimento di Scienze Economiche, Aziendali e Statistiche, Università degli Studi di Palermo, Palermo, Italy
| | - Gaetana Rinaldi
- Sezione di Oncologia, Dipartimento di Discipline Chirurgiche, Oncologiche e Stomatologiche (Di.Chir.On.S.), Università degli Studi di Palermo, Palermo, Italy
| | - Vito Rodolico
- Dipartimento di Promozione della Salute, Materno-Infantile, di Medicina Interna e Specialistica di Eccellenza "G. D'Alessandro", PROMISE, Università degli Studi di Palermo, Palermo, Italy
| |
Collapse
|
7
|
Ng EFY, Kaida A, Nojima H, Miura M. Roles of IGFBP-3 in cell migration and growth in an endophytic tongue squamous cell carcinoma cell line. Sci Rep 2022; 12:11503. [PMID: 35798794 PMCID: PMC9262895 DOI: 10.1038/s41598-022-15737-y] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2021] [Accepted: 06/28/2022] [Indexed: 11/20/2022] Open
Abstract
Insulin-like growth factor binding protein-3 (IGFBP-3) is a member of the IGFBP family that has high affinity for IGFs and functions as either an oncogene or tumor suppressor in various types of cancer. We previously found that IGFBP3 mRNA levels are higher in endophytic-type human tongue squamous cell carcinoma (TSCC) that is more invasive and more prone to metastasis than exophytic and superficial types. This finding prompted us to investigate the roles of IGFBP-3 in TSCC using SAS cells, which were originally derived from endophytic-type TSCC. Specifically, we used SAS cells that express a fluorescent ubiquitination-based cell-cycle indicator (Fucci). RNA-sequencing analysis indicated that IGFBP-3 is associated with cell migration and cell growth. In fact, IGFBP-3 knockdown downregulates cell migration and causes cells to arrest in G1. This migratory potential appears to be cell cycle–independent. IGFBP-3 knockdown also reduced levels of secreted IGFBP-3; however, decreased migratory potential was not rescued by exogenous recombinant human IGFBP-3. Furthermore, ERK activity was downregulated by IGFBP-3 depletion, which suggests that MEK/ERK signaling may be involved in IGFBP-3-mediated cell migration. We therefore conclude that intracellular IGFBP-3 enhances cell migration independently of the cell cycle in TSCC with a higher metastatic potential.
Collapse
Affiliation(s)
- Esther Feng Ying Ng
- Department of Oral Radiation Oncology, Graduate School of Medical and Dental Sciences, Tokyo Medical & Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo, 113-8549, Japan
| | - Atsushi Kaida
- Department of Oral Radiation Oncology, Graduate School of Medical and Dental Sciences, Tokyo Medical & Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo, 113-8549, Japan.
| | - Hitomi Nojima
- Department of Oral Radiation Oncology, Graduate School of Medical and Dental Sciences, Tokyo Medical & Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo, 113-8549, Japan
| | - Masahiko Miura
- Department of Oral Radiation Oncology, Graduate School of Medical and Dental Sciences, Tokyo Medical & Dental University, 1-5-45 Yushima, Bunkyo-ku, Tokyo, 113-8549, Japan.
| |
Collapse
|
8
|
Kubo K, Kawahara D, Murakami Y, Takeuchi Y, Katsuta T, Imano N, Nishibuchi I, Saito A, Konishi M, Kakimoto N, Yoshioka Y, Toratani S, Ono S, Ueda T, Takeno S, Nagata Y. Development of a radiomics and machine learning model for predicting occult cervical lymph node metastasis in patients with tongue cancer. Oral Surg Oral Med Oral Pathol Oral Radiol 2022; 134:93-101. [PMID: 35431177 DOI: 10.1016/j.oooo.2021.12.122] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2021] [Revised: 11/10/2021] [Accepted: 12/10/2021] [Indexed: 10/19/2022]
Abstract
OBJECTIVE We aimed to develop a predictive model for occult cervical lymph node metastasis in patients with tongue cancer using radiomics and machine learning from pretreatment contrast-enhanced computed tomography. STUDY DESIGN This study included 161 patients with tongue cancer who received local treatment. Computed tomography images were transferred to a radiomics platform. The volume of interest was the total neck node level, including levels Ia, Ib, II, III, and IVa at the ipsilateral side, and each neck node level. The dimensionality of the radiomics features was reduced using least absolute shrinkage and selection operator logistic regression analysis. We compared 5 classifiers with or without the synthetic minority oversampling technique (SMOTE). RESULTS For the analysis at the total neck node level, random forest with SMOTE was the best model, with an accuracy of 0.85 and an area under the curve score of 0.92. For the analysis at each neck node level, a support vector machine with SMOTE was the best model, with an accuracy of 0.96 and an area under the curve score of 0.98. CONCLUSIONS Predictive models using radiomics and machine learning have potential as clinical decision support tools in the management of patients with tongue cancer for prediction of occult cervical lymph node metastasis.
Collapse
Affiliation(s)
- Katsumaro Kubo
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Daisuke Kawahara
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Yuji Murakami
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan.
| | - Yuki Takeuchi
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Tsuyoshi Katsuta
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Nobuki Imano
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Ikuno Nishibuchi
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Akito Saito
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Masaru Konishi
- Department of Oral and Maxillofacial Radiology, Hiroshima University Hospital, Hiroshima, Japan
| | - Naoya Kakimoto
- Department of Oral and Maxillofacial Radiology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Yukio Yoshioka
- Department of Molecular Oral Medicine and Maxillofacial Surgery, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Shigeaki Toratani
- Department of Molecular Oral Medicine and Maxillofacial Surgery, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Shigehiro Ono
- Department of Oral and Maxillofacial Surgery, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Tsutomu Ueda
- Department of Otolaryngology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan; Department of Head and Neck Surgery, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Sachio Takeno
- Department of Otolaryngology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan; Department of Head and Neck Surgery, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Yasushi Nagata
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| |
Collapse
|
9
|
Sarode G, Sarode SC, Sengupta N, Patil S. Letter to the editor: Enhancing the predictive potential of preoperative DOI assessment using imaging techniques. Oral Surg Oral Med Oral Pathol Oral Radiol 2020; 131:265. [PMID: 33309264 DOI: 10.1016/j.oooo.2020.10.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2020] [Accepted: 10/03/2020] [Indexed: 10/23/2022]
Affiliation(s)
- Gargi Sarode
- Department of Oral Pathology and Microbiology, Dr D. Y. Patil Dental College and Hospital, Dr D. Y. Patil Vidyapeeth, Pimpri, Pune, India
| | - Sachin C Sarode
- Department of Oral Pathology and Microbiology, Dr D. Y. Patil Dental College and Hospital, Dr D. Y. Patil Vidyapeeth, Pimpri, Pune, India
| | - Namrata Sengupta
- Department of Oral Pathology and Microbiology, Dr D. Y. Patil Dental College and Hospital, Dr D. Y. Patil Vidyapeeth, Pimpri, Pune, India
| | - Shankargouda Patil
- Department of Maxillofacial Surgery and Diagnostic Sciences, Division of Oral Pathology, College of Dentistry, Jazan University, Jazan, Saudi Arabia
| |
Collapse
|