Artificial Intelligence Empowered Surgeons: A novel machine learning model to determine surgical resectability in squamous cell carcinoma of the buccal mucosa.

Author:

Basu Shouptik1

Affiliation:

1. All India Institute of Medical Sciences, Patna

Abstract

Abstract

Purpose Indian patients with squamous cell carcinoma of the buccal mucosa tend to present with advanced-stage disease, which is linked to poor prognosis. The treatment is primarily surgical but the current staging system, lacks specificity in accurately categorizing surgical candidates. This study aims to develop an innovative deep learning model to analyse imaging data from Contrast Enhanced Computed Tomography (CECT) to predict whether the patient may benefit from surgery upfront or need neoadjuvant chemotherapy for tumour downsizing prior to surgery, since T4b tumours may be technically unresectable (borderline resectable) and may render positive margins on upfront surgery.Methods This prospective observational pilot study, from April 2022 - March 2024 curated a dataset of 256 preoperative CECT scans of patients with T4a and T4b Squamous cell Carcinomas (SCC) of the buccal mucosa, which were integrated into a novel artificial intelligence-based machine learning model designed to predict resectability for upfront surgery. A Convolutional Neural Network (CNN) based predictive model has been developed to distinguish between "Borderline Resectable" and "Resectable Upfront" disease.Results The model displayed high performance with an overall F1 score of 0.8, efficiently stratifying tumors based on resectability. The AUC for the training set was 0.9652, with 50.39% sensitivity, 96.65% specificity, 65.75% negative predictive value, and 94.20% positive predictive value. The validation set had an AUC of 0.9735, along with 98.40% Specificity, 67.96% Negative Predictive Value, 55.73% Sensitivity, and 97.33% Positive Predictive Value.Conclusion This study represents the first step toward the use of artificial intelligence-based machine learning model to aid in the treatment stratification of patients with squamous cell carcinoma buccal mucosa, thus avoiding the possibility of margin positive resection with upfront surgery.

Publisher

Springer Science and Business Media LLC

Reference25 articles.

1. 1. Patil, V. M., Prabhash, K., Noronha, V., Joshi, A., Muddu, V., Dhumal, S., Arya, S., Juvekar, S., Chaturvedi, P., Chaukar, D., Pai, P., Kane, S., Patil, A., Agarwal, J. P., Ghosh-Lashkar, S., & Dcruz, A. (2014). Neoadjuvant chemotherapy followed by surgery in very locally advanced technically unresectable oral cavity cancers. Oral oncology, 50(10), 1000–1004. https://doi.org/10.1016/j.oraloncology.2014.07.015

2. 2. Lydiatt WM, et al., Head and Neck cancers-major changes in the American Joint Committee on cancer eighth edition cancer staging manual. CA Cancer J Clin, 2017. 67(2): p. 122–137.

3. 3. Zanoni, D. K., Patel, S. G., & Shah, J. P. (2019). Changes in the 8th Edition of the American Joint Committee on Cancer (AJCC) Staging of Head and Neck Cancer: Rationale and Implications. Current oncology reports, 21(6), 52. https://doi.org/10.1007/s11912-019-0799-x

4. 4. Mahajan, A., Agarwal, U., Patil, V. M., Patil, V., Vaish, R., Noronha, V., D' Cruz, A. K., Chaturvedi, P. P., Laskar, S. G., Sable, N., Janu, A., Patil, A., Menon, M., Rane, S., Mittal, N., Joshi, A., Menon, N., & Prabhash, K. (2022). Proposed sub-compartmentalization of high infratemporal fossa involvement in gingivobuccal cancers and its impact on clinical outcome and staging: A narrative review. Cancer Research, Statistics, and Treatment, 5(2), 269–275. DOI: 10.4103/crst.crst_293_21

5. 5. Trivedi, N.P., Kekatpure, V. and Kuriakose, M.A. (2012), Radical (compartment) resection for advanced buccal cancer involving masticator space (T4b): Our experience in thirty patients. Clinical Otolaryngology, 37: 477–483. https://doi.org/10.1111/j.1749-4486.2012.02529.x

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3