Development and Validation of Machine Learning Models for Predicting Occult Nodal Metastasis in Early-Stage Oral Cavity Squamous Cell Carcinoma

Farrokhian, Nathan; Holcomb, Andrew J.; Dimon, Erin; Karadaghy, Omar A.; Ward, Christina; Whiteford, Erin; Tolan, Claire; Hanly, Elyse K.; Buchakjian, Marisa R.; Harding, Brette C.; Dooley, Laura; Shinn, Justin R.; Wood, C. Burton; Rohde, Sarah L.; Zhan, Kevin Y.; Parikh, Anuraag S.; Bulbul, Mustafa G.; Penn, Joseph; Goodwin, Sara; Bur, Andrés M.

doi:10.1001/jamanetworkopen.2022.7226

Cited by 28 publications

(20 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study results were similar to the previously reported rates of lymph node positivity of 5.6% and 16.9% in patients with pathological DOI at 3 mm and 4 mm 5 . Future studies may investigate the roles of other prognostic factors, in addition to T staging and DOI, that may be helpful as thresholds for ND 17 …”

Section: Discussionsupporting

confidence: 91%

“…5 Future studies may investigate the roles of other prognostic factors, in addition to T staging and DOI, that may be helpful as thresholds for ND. 17 The literature investigating DOI has helped with our understanding of the prognostic implications of DOI and its relationship with nodal positivity and survival. [1][2][3]5 In this study, we closely examined the clinical practice of DOI assessment, the accuracies of the assessment modalities, and the impact of the assessment on surgical and treatment planning.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Preoperative DOI Estimation in Oral Tongue Cancer With cN0 Disease

Miller

Deschler

et al. 2023

Otolaryngol.--head neck surg.

View full text Add to dashboard Cite

ObjectiveTo understand the accuracy of pre‐ and intraoperative estimation of tumor depth of invasion (DOI).Study DesignA retrospective case‐control study.SettingPatients who presented at 1 institution with oral tongue squamous cell carcinoma that underwent oncologic resection between 2017 and 2019 were identified.MethodsPatients that met the inclusion criteria were included. Patients with nodal, distant, or recurrent disease, prior history of head and neck cancer, or preoperative tumor assessment and/or final histopathology that did not include DOI were excluded. Preoperative DOI estimation and technique and pathology reports were obtained. Our primary outcome was the sensitivity and specificity of DOI estimation modalities including full‐thickness biopsy (FTB), manual palpation (MP), punch biopsy (PB), and intraoperative ultrasound (IOUS).ResultsTumor DOI was assessed quantitatively preoperatively in 40 patients by FTB (n = 19, 48%), MP (n = 17, 42%), or PB (n = 4, 10%). Additionally, 19 patients underwent IOUS to assess DOI. The sensitivities of FTB, MP, and IOUS for DOI ≥ 4 mm were 83% (confidence interval [CI]: 44%‐97%), 83% (CI: 55%‐95%), and 90% (CI: 60%‐98%), respectively, and the specificities were 85% (CI: 58%‐96%), 60% (CI: 23%‐88%), and 78% (CI: 45%‐94%).ConclusionOur study demonstrated that DOI assessment tools measured had similar sensitivity and specificity in stratifying patients with DOI ≥4 mm, with no statistically superior diagnostic test. Our results support the need for additional research into nodal disease prediction and continued refinement of ND decisions with respect to DOI.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Discussionmentioning

confidence: 99%

Comparison of Preoperative DOI Estimation in Oral Tongue Cancer With cN0 Disease

Miller

Deschler

et al. 2023

Otolaryngol.--head neck surg.

View full text Add to dashboard Cite

show abstract

“…This decision was based on our belief that measuring tumor thickness can be more easily automated in future investigations. Furthermore, many studies treat tumor thickness and infiltration depth as interchangeable, leading to inherent errors 21 . However, we acknowledge that using only one diagnostic slide per case may have limited our ability to accurately determine the depth of invasion because the slide may not necessarily show the deepest invasion.…”

Section: Discussionmentioning

confidence: 99%

“…10 Moreover, PNI and LVI, which proved to possess a high discriminatory potential, have been reported to be present in approximately 20%-40% and 10%-30% of the OSCC cases, respectively. 6,[21][22][23] This implies that in more than half of the OSCC cases, an additional descriptor of tumor aggressiveness would be of utmost importance, and that this descriptor should ideally be interpreted on a continuous scale, as converting inherently non-categorical into categorical data will potentially result in loss of information through a priori assumptions. 24 The approach to diagnosing and confirming cancer through microscopic examination of resected tissue has remained largely unchanged since the late 1800s.…”

Section: Introductionmentioning

confidence: 99%

“…However, conventional histological grading is known not to correlate well with clinical prognosis 19 . Machine learning algorithms have been developed, for example, to predict occult node metastases in OSCC 20,21 . However, these models have a limited input in terms of features characteristic of the intrinsic biological behavior of OSCC and do not take into account the pattern of invasion (POI), although a significant association between POI and nodal status, a strong predictor of OSCC, has been described 10 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The modified Polsby–Popper score, a novel quantitative histomorphological biomarker and its potential to predict lymph node positivity and cancer‐specific survival in oral tongue squamous cell carcinoma

Csűry,

Balk

et al. 2023

Cancer Medicine

View full text Add to dashboard Cite

BackgroundThe significance of different histological spreading patterns of tumor tissue in oral tongue squamous cell carcinoma (TSCC) is well known. Our aim was to construct a numeric parameter on a continuous scale, that is, the modified Polsby–Popper (MPP) score, to describe the aggressiveness of tumor growth and infiltration, with the potential to analyze hematoxylin and eosin‐stained whole slide images (WSIs) in an automated manner. We investigated the application of the MPP score in predicting survival and cervical lymph node metastases as well as in determining patients at risk in the context of different surgical margin scenarios.MethodsWe developed a semiautomated image analysis pipeline to detect areas belonging to the tumor tissue compartment. Perimeter and area measurements of all detected tissue regions were derived, and a specific mathematical formula was applied to reflect the perimeter/area ratio in a comparable, observer‐independent manner across digitized WSIs. We demonstrated the plausibility of the MPP score by correlating it with well‐established clinicopathologic parameters. We then performed survival analysis to assess the relevance of the MPP score, with an emphasis on different surgical margin scenarios. Machine learning models were developed to assess the relevance of the MPP score in predicting survival and occult cervical nodal metastases.ResultsThe MPP score was associated with unfavorable tumor growth and infiltration patterns, the presence of lymph node metastases, the extracapsular spread of tumor cells, and higher tumor thickness. Higher MPP scores were associated with worse overall survival (OS) and tongue carcinoma‐specific survival (TCSS), both when assessing all pT‐categories and pT1‐pT2 categories only; moreover, higher MPP scores were associated with a significantly worse TCSS in cases where a cancer‐free surgical margin of <5 mm could be achieved on the main surgical specimen. This discriminatory capacity remained constant when examining pT1‐pT2 categories only. Importantly, the MPP score could successfully define cases at risk in terms of metastatic disease in pT1‐pT2 cancer where tumor thickness failed to exhibit a significant predictive value. Machine learning (ML) models incorporating the MPP score could predict the 5‐year TCSS efficiently. Furthermore, we demonstrated that machine learning models that predict occult cervical lymph node involvement can benefit from including the MPP score.ConclusionsWe introduced an objective, quantifiable, and observer‐independent parameter, the MPP score, representing the aggressiveness of tumor growth and infiltration in TSCC. We showed its prognostic relevance especially in pT1‐pT2 category TSCC, and its possible use in ML models predicting TCSS and occult lymph node metastases.

show abstract

Protecting Against Postsurgery Oral Cancer Recurrence with an Implantable Hydrogel Vaccine for In Situ Photoimmunotherapy

Chen,

Yin,

Zhang

et al. 2024

Advanced Science

View full text Add to dashboard Cite

Oral squamous cell carcinoma (OSCC) often recurs aggressively and metastasizes despite surgery and adjuvant therapy, driven by postoperative residual cancer cells near the primary tumor site. An implantable in situ vaccine hydrogel was designed to target residual OSCC cells post‐tumor removal. This hydrogel serves as a reservoir for the sustained localized release of δ‐aminolevulinic acid (δ‐ALA), enhancing protoporphyrin IX‐mediated photodynamic therapy (PDT), and a polydopamine‐hyaluronic acid composite for photothermal therapy (PTT). Additionally, immune adjuvants, including anti‐CD47 antibodies (aCD47) and CaCO3 nanoparticles, are directly released into the resected tumor bed. This approach induces apoptosis of residual OSCC cells through sequential near‐infrared irradiation, promoting calcium interference therapy (CIT). The hydrogel further stimulates immunogenic cell death (ICD), facilitating the polarization of tumor‐associated macrophages from the M2 to the M1 phenotype. This facilitates phagocytosis, dendritic cell activation, robust antigen presentation, and cytotoxic T lymphocyte‐mediated cytotoxicity. In murine OSCC models, the in situ vaccine effectively prevents local recurrence, inhibits orthotopic OSCC growth and pulmonary metastases, and provides long‐term protective immunity against tumor rechalle nge. These findings support postoperative in situ vaccination with a biocompatible hydrogel implant as a promising strategy to minimize residual tumor burden and reduce recurrence risk after OSCC resection.

show abstract

Development and Validation of Machine Learning Models for Predicting Occult Nodal Metastasis in Early-Stage Oral Cavity Squamous Cell Carcinoma

Cited by 28 publications

References 51 publications

Comparison of Preoperative DOI Estimation in Oral Tongue Cancer With cN0 Disease

Comparison of Preoperative DOI Estimation in Oral Tongue Cancer With cN0 Disease

The modified Polsby–Popper score, a novel quantitative histomorphological biomarker and its potential to predict lymph node positivity and cancer‐specific survival in oral tongue squamous cell carcinoma

Protecting Against Postsurgery Oral Cancer Recurrence with an Implantable Hydrogel Vaccine for In Situ Photoimmunotherapy

Contact Info

Product

Resources

About