Tumor Depth of Invasion vs Tumor Thickness in Determining Risk of Nodal Disease in Early Oral Tongue Squamous Cell Carcinoma

Abstract

For 20 cases, deep-learning delineation outperformed 4 of the 8 radiation oncologists, with mean DSC of 0.766 against 0.691, 0.699, 0.704 and 0.719 (all P < 0.05); while performed comparably to another 4 oncologists. With the assistance of deep-learning delineation, increased delineation accuracy was observed in 5 oncologists (mean DSC increased from 0.731 to 0.779; all P < 0.05) and stable DSC in 3 oncologists. Furthermore, decreased multi-observer DSC was observed (0.774 AE 0.0773 vs. 0.702 AE 0.114; P < 0.001). Average time spent decreased from 30.2 min on manual delineation to 18.3 min in editing deep-learning delineation (P < 0.001), saving 39.2% of the time. Conclusion: In GTV p delineation for NPC, deep-learning delineation achieved satisfactory agreement in comparison with expert-panel delineation, and outperformed 4 of 8 qualified radiation oncologists significantly. Assistance of deep-learning delineation consistently improved both the accuracy and efficiency.

Practical Challenges in Measurement of Depth of Invasion in Oral Squamous Cell Carcinoma: Pictographical Documentation to Improve Consistency of Reporting per the AJCC 8th Edition Recommendations

“…The difference was less than 1 mm in 21.2% [17]. Similarly, 53% of cases in a study by Liu et al had identical TT and DOI or a difference less than 1 mm [18]. Our review shows the difference between the mean DOI and TT to be 1.4 mm and median DOI and TT to be 1 mm.…”

Postoperative radiotherapy is associated with improved overall survival for alveolar ridge squamous cell carcinoma with adverse pathologic features

“…However, there were two notable shortcomings with the coding of tumor thickness/depth of invasion in this NCDB analysis. First, these two distinct pathologic features were coded as a single variable, which is problematic because of their differing numerical thresholds for predicting regional nodal metastasis 22 . Second, nearly half (48%) had missing data.…”

“…First, these two distinct pathologic features were coded as a single variable, which is problematic because of their differing numerical thresholds for predicting regional nodal metastasis. 22 Second, nearly half (48%) had missing data. A literature review and meta-analysis identified tumor thickness and depth of invasion as important prognostic factors for oral cavity cancers, although primary tumors involving the thin mucosal layer of the alveolar ridge were not included in these publications.…”