Development of a radiomics and machine learning model for predicting occult cervical lymph node metastasis in patients with tongue cancer

Kubo, Katsumaro; Kawahara, Daisuke; Murakami, Yuji; Takeuchi, Yuki; Katsuta, T.; Imano, Nobuki; Nishibuchi, Ikuno; Saito, A.; Konishi, Masaru; Kakimoto, Naoya; Yoshioka, Yukio; Toratani, Shigeaki; Ono, Shigehiro; Ueda, Tsutomu; Takeno, Sachio; Nagata, Yasushi

doi:10.1016/j.oooo.2021.12.122

Cited by 22 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The higher order statistical features used a wavelet imaging filter with low-pass and high-pass filters to prevent interference from gas. 14 Image features extracted by Pyradiomics, an open source software useful for radiomics analysis, were used (see https://pyradiomics. readthedocs.io/en/latest/features.html).…”

Section: Region Of Interest Segmentation and Radiomics Feature Extrac...mentioning

confidence: 99%

“…Previous studies have performed radiomics analysis using medical images to extract image features for lesion diagnosis and prognosis prediction, a widely used method in recent years 12–16 . Various studies on prognostic prediction in patients with head and neck cancer used magnetic resonance imaging (MRI) 12 or positron emission tomography (PET)/computed tomography (CT) images, 13 predicted occult lymph node metastasis using CT images, 14 evaluated the response to radiotherapy, 15 and predicted adverse events after radiotherapy 16 …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Radiomics analysis of intraoral ultrasound images for prediction of late cervical lymph node metastasis in patients with tongue cancer

Konishi

Kakimoto

2023

Head & Neck

Self Cite

View full text Add to dashboard Cite

BackgroundWe investigated the predictability of late cervical lymph node metastasis using radiomics analysis of ultrasonographic images of tongue cancer.MethodsWe selected 120 patients with tongue cancer who underwent intraoral ultrasonography, 30 of which had late cervical lymph node metastasis. Radiomics analysis was used to extract and quantify the image features. Bootstrap forest (BF), support vector machine (SVM), and neural tanh boost (NTB) were used as the machine learning models, and receiver operating characteristic curve analysis was conducted to determine diagnostic performance.ResultsThe sensitivity, specificity, accuracy, and AUC in the validation group were, respectively, 0.600, 0.967, 0.875, and 0.923 for the BF model; 0.700, 0.967, 0.900, and 0.950 for the SVM model; and 0.900, 0.967, 0.950, and 0.967 for NTB model.ConclusionsRadiomics analysis and machine learning models using ultrasonographic images of pretreated tongue cancer could predict late cervical lymph node metastasis with high accuracy.

show abstract

Section: Region Of Interest Segmentation and Radiomics Feature Extrac...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Radiomics analysis of intraoral ultrasound images for prediction of late cervical lymph node metastasis in patients with tongue cancer

Konishi

Kakimoto

2023

Head & Neck

Self Cite

View full text Add to dashboard Cite

show abstract

“…85 This limitation of technology creates an uncertainty for CLNs akin to Schrodinger's cat, where metastasis is hard to determine before lymph nodes are removed and examined histopathologically. Emerging non-invasive methods for assessing CLNs primarily include artificial intelligence-assisted predictive models, 86,87 nanoparticle-based lymphatic system imaging, 88 and biomarker-based liquid biopsies. 89 These studies are still in the experimental stage, and their widespread clinical application remains a distant goal.…”

Section: Preoperative Assessment For Clnsmentioning

confidence: 99%

Lymph node metastasis in oral squamous cell carcinoma: Where we are and where we are going

Cao

Zhong

et al. 2023

Clinical and Translational Dis

View full text Add to dashboard Cite

BackgroundOral cancer is a common malignant tumour in the head and neck region, with over 90% of cases being oral squamous cell carcinoma (OSCC). Lymph node metastasis (LNM) is a significant adverse prognostic factor in OSCC; however, the mechanism of LNM in OSCC remains unclear, while the strategies for managing cervical lymph nodes (CLNs) in OSCC continue to evolve. At present, neck dissection is necessary for the vast majority of OSCC patients, but complications of surgery can significantly impair patients’ postoperative quality of life. A recent clinical trial discovery indicates that immunotherapy can activate anti‐tumour T cells in nearby lymph nodes, leading to vibrant discussions among clinicians about the importance of preserving lymph nodes during surgical treatment.AimThis review aims to provide an overview of where we are: the current knowledge of OSCC LNM patterns and management strategies, and where we are going: prospects for clinical and basic research on the issue of OSCC LNM in the era of cancer immunotherapy.ResultWe summarize the general patterns and management strategies of OSCC LNM. The process of LNM in OSCC encompasses four stages: Preparation, Unleash, Migration, and Planting (‘PUMP’ principle). We propose adopting the ‘PRECISE’ model, an overall workflow that includes seven elements—prevention, radiology, preoperative evaluation, chemotherapy, immunotherapy, surgery, and postoperative evaluation—for neck management in OSCC, promoting personalized precision medicine augmented by neoadjuvant therapy. We further discussed recent advances in clinical and basic research on OSCC LNM and provided an outlook on future research directions.ConclusionOver the past two centuries, our understanding and management strategies of LNM in OSCC have evolved, seeking more precise and personalized approaches to reduce patient burden and enhance survival and quality of life. Further research should explore lymph nodes’ role in cancer immunotherapy and OSCC interactions, leading to better, less invasive treatments and improved outcomes.

show abstract

“…Yuan et al ( 36 ) extracted texture features from MR images and constructed six ML models, among which the Naïve Bayes model achieved the best performance. Kubo et al ( 37 ) used radiomics features of lymph nodes to construct ML models for predicting occult cervical lymph node metastasis. Zhong et al ( 38 ) built artificial neural network (ANN) models incorporating computed tomography radiomics of the primary tumor with traditional lymph node evaluation to detect cervical lymph node metastasis.…”

Section: Applications Of ML In Tsccmentioning

confidence: 99%

A narrative review on machine learning in diagnosis and prognosis prediction for tongue squamous cell carcinoma

Lin¹,

Tang²,

Liu³

et al. 2022

Transl Cancer Res

View full text Add to dashboard Cite

Background: Tongue squamous cell carcinoma (TSCC) is the most common subtype of oral cavity squamous cell carcinoma (OCSCC), and it also has the worst prognosis. It is crucial to find an effective way to solve the challenges in diagnosis and prognosis prediction for TSCC. Machine learning (ML) has been widely used in medical research and has shown good performance. It can be used for feature extraction, feature selection, model construction, etc. Radiomics and deep learning (DL), the new components of ML, have also been utilized to explore the relationship between image features and diseases. The current study aimed to highlight the importance of ML as a potential method for addressing the challenges in diagnosis and prognosis prediction of TSCC by reviewing studies on ML in TSCC. Methods: The studies on ML in TSCC in PubMed, Scopus, Web of Science, and China National Knowledge Infrastructure published between the dates of inception of these databases and April 30, 2022, were reviewed. Key Content and Findings: ML (including radiomics and DL) which was used in diagnosis and prognosis prediction for TSCC, has shown promising performance.Conclusions: Despite its limitations, ML is still a potential approach that can help to deal with the challenges in diagnosis and prognosis prediction for TSCC. Nevertheless, more efforts are needed to enhance the usefulness of ML in this field.

show abstract

Development of a radiomics and machine learning model for predicting occult cervical lymph node metastasis in patients with tongue cancer

Cited by 22 publications

References 33 publications

Radiomics analysis of intraoral ultrasound images for prediction of late cervical lymph node metastasis in patients with tongue cancer

Radiomics analysis of intraoral ultrasound images for prediction of late cervical lymph node metastasis in patients with tongue cancer

Lymph node metastasis in oral squamous cell carcinoma: Where we are and where we are going

A narrative review on machine learning in diagnosis and prognosis prediction for tongue squamous cell carcinoma

Contact Info

Product

Resources

About