Traversing the Terrain: Potential Pitfalls within the AJCC 8th Edition Staging System for Lip and Oral Cavity Cancers.

In 1977, the American Joint Committee on Cancer (AJCC) introduced the inaugural Cancer Staging Manual, which implemented the T (tumor extent), N (regional lymph node status), and M (presence or absence of distant metastasis) staging system. This systematic approach aimed to convey the extent of disease across various cancer types, providing clinicians with a practical framework to plan treatment strategies, predict prognosis, and assess outcomes. The AJCC 8th edition, effective from January 1, 2018, continues this tradition. However, certain shortcomings persist in the AJCC 8th edition, as identified through clinical experience. Specifically, challenges arise in accurately assessing depth of invasion in unique histological variants of oral squamous cell carcinoma (e.g., Oral verrucous carcinoma, Carcinoma cuniculatum, and Papillary squamous cell carcinoma) and minor salivary gland tumors. Additionally, discrepancies exist in the perception of bone invasion patterns and in reporting practices. There is also a need for staging guidelines for malignant odontogenic tumors and multifocal tumors of the oral cavity, supplemented by diagrammatic representations. Lastly, there is a call for comprehensive staging criteria for carcinomas of the ear, external auditory canal, and temporal bone. We advocate for the inclusion of these considerations in future editions of the AJCC Cancer Staging Manual.

Establishment and verification of novel TNM staging system for lung mucinous adenocarcinoma.

BACKGROUND: Lung adenocarcinoma is a high-mortality rate cancer. Within this category, Lung mucinous adenocarcinoma (LMAC) is a rare and distinct subtype of lung adenocarcinoma necessitating further investigation. The study was launched to compare the difference of survival features between LMAC and lung non-mucinous adenocarcinoma (LNMAC) and to investigate the significance and demand for developing a new staging system tailored to LMAC. METHODS: This retrospective study assessed the suitableness of the current staging system for LMAC. It compared the overall survival (OS) between LMAC and LNMAC from 2004 to 2020 (LNMAC: 160,387; LMAC: 6,341) and instituted a novel classification framework for LMAC based on US population. Verification group consisting of patients from two Chinese medical centers from 2010 to 2018 (n = 392) was set to ascertain the applicability of this novel system. The primary endpoint was OS. To minimize the bias, propensity score match (PSM) was employed. Survival analysis and Log-rank test were executed to explore the survival features of LMAC. RESULTS: The results indicated that the existed staging system was not suitable for LMAC. Patients diagnosed with LMAC exhibited a superior OS compared to those with LNMAC in stage IA2 (P < 0.0001), IA3 (P < 0.0001), IB (P = 0.0062), IIA (P = 0.0090), IIB (P = 0.0005). In contrast, a worse OS in stage IVA (P = 0.0103) was found in LMAC patients. The novel classification system proposed for LMAC proved to be highly applicable and demonstrated substantial efficacy, as confirmed by the verification group. CONCLUSION: The newly established classification system was more effective for LMAC, but it necessitates large-scale verification to confirm its applicability and reliability.

[Key updates and interpretation of the ninth version of AJCC staging system for neuroendocrine tumors of the stomach].

The cancer staging system of the American Joint Committee on Cancer (AJCC) is the most widely used clinical basis for tumor staging. In October 2023, AJCC released the staging system (ninth version) for the neuroendocrine tumors of stomach (NET), which has been implemented in January 2024. The ninth version of NET staging system mainly updated the histopathologic classification, diagnosis and staging methods, clinical and pathological staging, prognosis grade, tumor and non-tumor prognostic features. The update and implementation of the staging system provide a more detailed reference for the accurate diagnosis, staging and precise treatment of gastric neuroendocrine tumors. Moreover, it is convenient for clinicians to carry out clinical practice. The purpose of our article is to provide a high-level overview of the major changes in AJCC staging system (version 9) for gastric NET based on the latest evidence-based medical research.

Ga68-PSMA PET for lymph node staging in intermediate and high-risk prostate cancer patients undergoing robotic assisted radical prostatectomy.

BACKGROUND: In intermediate/high risk prostate cancer, preoperative staging exams are mandatory. The aim of these imaging studies is to evaluate eventual lymph nodes involvement and/or metastatic spread of the tumor. Nevertheless, computed tomography (CT), magnetic resonance imaging (MRI), bone scan modalities have controversial sensitivity. Introduction of PET-PSMA and its use also as preoperative exam, seems to improve diagnostic accuracy due to favorable negative predictive value. The aim of this study was to evaluate the accuracy of PET-PSMA as a preoperative staging exam and its accuracy in predicting lymph nodes involvement in intermediate/high risk prostate cancer (PCa) patients. METHODS: A retrospective analysis of 50 patients diagnosed with intermediate/high risk PCa between 2018 and 2022 has been performed. All patients underwent preoperative 68Ga-PSMA PET/CT prior to robot-assisted radical prostatectomy (RARP) + extended pelvic lymph node dissection (ePLND). The cohort was categorized into two groups: pathologically negative lymph nodes (pN0) vs. positive nodes (pN1). A descriptive and comparative analysis was conducted. Correlation analysis between continuous variables was performed using the Spearman's Rank Test. Using lymph nodes histopathological results as reference standard, the diagnostic performance of 68Ga-PSMA PET/CT was calculated. RESULTS: Overall, 50 patients were included. The mean age was 63.3 years with a median prostatic specific antigen (PSA) of 7.7 ng/dL. Forty-four percent of the patients exhibited an International Society of Urological Pathology (ISUP) score of 4 or higher, and 28% had a pT3 stage. Overall, 43 (86%) patients submitted to ePLND did not present lymph node metastases (pN0), while 8 (14%) patients were pN1. PET-PSMA showed low sensitivity in detecting lymph node metastases (25%) while a high specificity in excluding lymph-node disease (88.1%) has been observed. Finally, we noted a significant positive correlation between the total SUVmax of the prostate and the initial total PSA (r=0.38; P=0.019), as well as the percentage of tumor involvement (r=0.383; P=0.022). CONCLUSIONS: Evidence on the role of PET-PSMA in the primary staging of PCa is steadily building up. A positive correlation between SUV and prostate involvement indicates that PET-PSMA could reflect, with a good approximation, the pathological features of the prostate. However, the low sensitivity depicted remains the main limitation. Future prospective studies are needed to determine the impact on patient outcome.

A multi-Task Learning based applicable AI model simultaneously predicts stage, histology, grade and LNM for cervical cancer before surgery.

PURPOSE: To build an Mult-Task Learning (MTL) based Artificial Intelligence(AI) model that can simultaneously predict clinical stage, histology, grade and LNM for cervical cancer before surgery. METHODS: This retrospective and prospective cohort study was conducted from January 2001 to March 2014 for the training set and from January 2018 to November 2021 for the validation set at Beijing Chaoyang Hospital, Capital Medical University. Preoperative clinical information of cervical cancer patients was used. An Artificial Neural Network (ANN) algorithm was used to build the MTL-based AI model. Accuracy and weighted F1 scores were calculated as evaluation indicators. The performance of the MTL model was compared with Single-Task Learning (STL) models. Additionally, a Turing test was performed by 20 gynecologists and compared with this AI model. RESULTS: A total of 223 cervical cancer cases were retrospectively enrolled into the training set, and 58 cases were prospectively collected as independent validation set. The accuracy of this cervical cancer AI model constructed with ANN algorithm in predicting stage, histology, grade and LNM were 75%, 95%, 86% and 76%, respectively. And the corresponding weighted F1 score were 70%, 94%, 86%, and 76%, respectively. The average time consumption of AI simultaneously predicting stage, histology, grade and LNM for cervical cancer was 0.01s (95%CI: 0.01-0.01) per 20 patients. The mean time consumption doctor and doctor with AI were 581.1s (95%CI: 300.0-900.0) per 20 patients and 534.8s (95%CI: 255.0-720.0) per 20 patients, respectively. Except for LNM, both the accuracy and F-score of the AI model were significantly better than STL AI, doctors and AI-assisted doctors in predicting stage, grade and histology. (P < 0.05) The time consumption of AI was significantly less than that of doctors' prediction and AI-assisted doctors' results. (P < 0.05 CONCLUSION: A multi-task learning AI model can simultaneously predict stage, histology, grade, and LNM for cervical cancer preoperatively with minimal time consumption. To improve the conditions and use of the beneficiaries, the model should be integrated into routine clinical workflows, offering a decision-support tool for gynecologists. Future studies should focus on refining the model for broader clinical applications, increasing the diversity of the training datasets, and enhancing its adaptability to various clinical settings. Additionally, continuous feedback from clinical practice should be incorporated to ensure the model's accuracy and reliability, ultimately improving personalized patient care and treatment outcomes.

Nomogram using intratumoral and peritumoral radiomics for the preoperative prediction of visceral pleural invasion in clinical stage IA lung adenocarcinoma.

BACKGROUND: Accurate prediction of visceral pleural invasion (VPI) in lung adenocarcinoma before operation can provide guidance and help for surgical operation and postoperative treatment. We investigate the value of intratumoral and peritumoral radiomics nomograms for preoperatively predicting the status of VPI in patients diagnosed with clinical stage IA lung adenocarcinoma. METHODS: A total of 404 patients from our hospital were randomly assigned to a training set (n = 283) and an internal validation set (n = 121) using a 7:3 ratio, while 81 patients from two other hospitals constituted the external validation set. We extracted 1218 CT-based radiomics features from the gross tumor volume (GTV) as well as the gross peritumoral tumor volume (GPTV5, 10, 15), respectively, and constructed radiomic models. Additionally, we developed a nomogram based on relevant CT features and the radscore derived from the optimal radiomics model. RESULTS: The GPTV10 radiomics model exhibited superior predictive performance compared to GTV, GPTV5, and GPTV15, with area under the curve (AUC) values of 0.855, 0.842, and 0.842 in the three respective sets. In the clinical model, the solid component size, pleural indentation, solid attachment, and vascular convergence sign were identified as independent risk factors among the CT features. The predictive performance of the nomogram, which incorporated relevant CT features and the GPTV10-radscore, outperformed both the radiomics model and clinical model alone, with AUC values of 0.894, 0.828, and 0.876 in the three respective sets. CONCLUSIONS: The nomogram, integrating radiomics features and CT morphological features, exhibits good performance in predicting VPI status in lung adenocarcinoma.

Clinicopathological Features and Outcomes of Endometrial Cancer: A single institution experience.

Objectives: This study aimed to report the demographic features, clinical presentation, pathological types and long-term outcomes of patients diagnosed with endometrial cancer (EC) in Oman. EC is the sixth most common cancer in women worldwide and the fifth most common cancer in women in Oman. Survival outcomes of EC have not been reported previously from Oman. Methods: This retrospective study was carried out on consecutive patients treated at the Sultan Qaboos University Hospital, Muscat, Oman, between 2008 and 2020. Survival was estimated using the Kaplan and Meier method. Results: A total of 50 patients with EC were included. The median age was 61 years (range: 31-86 years), and 72% of the patients had type I histology. Most patients were diagnosed with stage IA and IB EC (49% and 20%, respectively), and the majority had grade 1 or 2 tumours (40% and 34%, respectively). Overall, the 5-year survival and 10-year survival rates were estimated to be 70% and 56%, respectively. Weight (>75 kg) and body mass index (>30 kg/m2) were significantly associated with better survival. Tumour histology (type I versus type II or carcinosarcoma), grade (1 versus 2 versus 3) and stage (IA or IB versus II-IV) were associated with better overall survival (P = 0.007, P <0.0001 and P <0.0003, respectively). Patients diagnosed with EC with co-morbidities, other than obesity, had inferior survival compared to those without co-morbidities. Conclusion: Median age at presentation, histological sub-type, clinical stage and outcomes are comparable to the published literature. Almost two-thirds of the patients were obese. These data could be used as a benchmark for outcomes of EC in the region.

Comparison of a modified staging system with 8th edition AJCC criteria in a North American cohort of pT2/pT3 HPV-negative penile squamous cell carcinoma.

The staging for pT2/pT3 penile squamous cell carcinoma (pSCC) has undergone major changes. Some authors proposed criteria wherein the distinction between pT2/pT3 was made using the same histopathological variables that are currently utilized to differentiate pT1a/pT1b. In this single-institution, North American study, we focused on (HPV-negative) pT2/3 pSCCs (i.e., tumors invading corpus spongiosum/corpus cavernosum), and compared the prognostic ability of the following systems: (i) AJCC (8th edition) criteria; (ii) modified staging criteria proposed by Sali et al. (Am J Surg Pathol. 2020; 44:1112-7). In the proposed system, pT2 tumors were defined as those devoid of lymphovascular invasion (LVI) or perineural invasion (PNI), and were not poorly differentiated; whereas pT3 showed one or more of the following: LVI, PNI, and/or grade 3. 48 pT2/pT3 cases were included (AJCC, pT2: 27 and pT3: 21; Proposed, pT2: 22 and pT3: 26). The disease-free survival (DFS) and progression-free survival (PFS) did not differ between pT2 and pT3, following the current AJCC definitions (p = 0.19 and p = 0.10, respectively). When the pT2/3 stages were reconstructed using the modified criteria, however, a statistically significant difference was present in both DFS and PFS between pT2 and pT3 (p = 0.004 and p = 0.003, respectively). The proposed staging system has the potential to improve the prognostication of pT2/pT3 tumors in pSCC. Each of these histopathologic variables has been shown to have a significant association with outcomes in pSCC, which is an advantage. Further studies are needed to demonstrate the utility of this modified staging system in patient populations from other geographic regions.

Imaging in Lung Cancer Staging.

Lung cancer remains one of the leading causes of mortality worldwide, as well as in the United States. Clinical staging, primarily with imaging, is integral to stratify patients into groups that determine treatment options and predict survival. The eighth edition of the tumor, node, metastasis (TNM-8) staging system proposed in 2016 by the International Association for the Study of Lung Cancer remains the current standard for lung cancer staging. The system is used for all subtypes of lung cancer, including non-small cell lung cancer, small cell lung cancer, and bronchopulmonary carcinoid tumors.

Advances in Diagnostic, Staging, and Restaging Evaluation of Esophageal and Gastric Cancer.

The initial endoscopic and staging evaluation of esophagogastric cancers must be accurate and comprehensive in order to select the optimal therapeutic plan for the patient. Esophageal and gastric cancers (and treatment paradigms) are delineated by their proximity to the cardia (within 2 cm). The most frequent and important symptom that informs the initial staging evaluation is dysphagia, which is associated with at least cT3 or locally advanced disease. Endoscopic ultrasound is often needed if earlier stage disease is suspected, preferably in combination with endoscopic mucosal or submucosal resection or fine-needle aspiration of suspicious lymph nodes to enhance staging accuracy.

New staging of endometrial carcinoma - FIGO 2023.

AIM: To review the changes in the new version of the FIGO 2023 staging system for endometrial cancer. METHODS AND RESULTS: The new FIGO 2023 endometrial cancer staging system provides key updates for the diagnosis and treatment of endometrial cancer. An important step in diagnosis is molecular classification, which allows more accurate risk stratification for recurrence and the identification of targeted therapies. The new staging system, based on the recommendations of the international societies ESGO, ESTRO and ESP, incorporates not only the description of the pathological and anatomical extent of the disease, but also the histopathological characteristics of the tumour, including the histological type and the presence of lymphovascular space invasion. In addition, the staging system uses molecular testing to classify endometrial cancers into four prognostic groups: POLEmut, MMRd, NSMP and p53abn. Each group has its own specific characteristics and prognosis. The most significant changes have occurred in stages I and II, in which the sub-staging better reflects the biological behaviour of the tumour. This update increases the accuracy of prognosis and improves individualized treatment options for patients with endometrial cancer. CONCLUSION: The updated FIGO staging of endometrial cancer for 2023 incorporates different histologic types, tumour features, and molecular classifications to better reflect the current improved understanding of the complex nature of several endometrial cancer types and their underlying bio logic behaviour. The aim of the new endometrial cancer staging system is to better define stages with similar prognosis, allowing for more precise indication of individualised adjuvant radiation or systemic treatment, including the use of immunotherapy.

MRI-based radiomics feature combined with tumor markers to predict TN staging of rectal cancer.

The aim of this study is to evaluate the predictive ability of MRI-based radiomics combined with tumor markers for TN staging in patients with rectal cancer and to develop a prediction model for TN staging. A total of 190 patients with rectal adenocarcinoma who underwent total mesorectal excision at the First Affiliated Hospital of the Air Force Medical University between January 2016 and December 2020 were included in the study. An additional 54 patients from a prospective validation cohort were included between August 2022 and August 2023. Preoperative tumor markers and MRI imaging data were collected from all enrolled patients. The 190 patients were divided into a training cohort (n = 133) and a validation cohort (n = 57). Radiomics features were extracted by outlining the region of interest (ROI) on T2WI sequence images. Feature selection and radiomics score (Rad-score) construction were performed using least absolute shrinkage and selection operator regression analysis (LASSO). The postoperative pathology TNM stage was used to differentiate locally advanced rectal cancer (T3/4 or N1/2) from locally early rectal cancer (T1/2, N0). Logistic regression was used to construct separate prediction models for T stage and N stage. The models' predictive performance was evaluated using DCA curves and calibration curves. The T staging model showed that Rad-score, based on 8 radiomics features, was an independent predictor of T staging. When combined with CEA, tumor diameter, mesoretal fascia (MRF), and extramural venous invasion (EMVI), it effectively differentiated between T1/2 and T3/4 stage rectal cancers in the training cohort (AUC 0.87 [95% CI: 0.81-0.93]). The N-staging model found that Rad-score, based on 10 radiomics features, was an independent predictor of N-staging. When combined with CA19.9, degree of differentiation, and EMVI, it effectively differentiated between N0 and N1/2 stage rectal cancers. The training cohort had an AUC of 0.84 (95% CI: 0.77-0.91). The calibration curves demonstrated good precision between the predicted and actual results. The DCA curves indicated that both sets of predictive models could provide net clinical benefits for diagnosis. MRI-based radiomics features are independent predictors of T staging and N staging. When combined with tumor markers, they have good predictive efficacy for TN staging of rectal cancer.

Incidence rate of occult lymph node metastasis in clinical T1-2N0M0 small cell lung cancer patients and radiomic prediction based on contrast-enhanced CT imaging: a multicenter study : Original research.

BACKGROUND: This study aimed to explore the incidence of occult lymph node metastasis (OLM) in clinical T1 - 2N0M0 (cT1 - 2N0M0) small cell lung cancer (SCLC) patients and develop machine learning prediction models using preoperative intratumoral and peritumoral contrast-enhanced CT-based radiomic data. METHODS: By conducting a retrospective analysis involving 242 eligible patients from 4 centeres, we determined the incidence of OLM in cT1 - 2N0M0 SCLC patients. For each lesion, two ROIs were defined using the gross tumour volume (GTV) and peritumoral volume 15 mm around the tumour (PTV). By extracting a comprehensive set of 1595 enhanced CT-based radiomic features individually from the GTV and PTV, five models were constucted and we rigorously evaluated the model performance using various metrics, including the area under the curve (AUC), accuracy, sensitivity, specificity, calibration curve, and decision curve analysis (DCA). For enhanced clinical applicability, we formulated a nomogram that integrates clinical parameters and the rad_score (GTV and PTV). RESULTS: The initial investigation revealed a 33.9% OLM positivity rate in cT1 - 2N0M0 SCLC patients. Our combined model, which incorporates three radiomic features from the GTV and PTV, along with two clinical parameters (smoking status and shape), exhibited robust predictive capabilities. With a peak AUC value of 0.772 in the external validation cohort, the model outperformed the alternative models. The nomogram significantly enhanced diagnostic precision for radiologists and added substantial value to the clinical decision-making process for cT1 - 2N0M0 SCLC patients. CONCLUSIONS: The incidence of OLM in SCLC patients surpassed that in non-small cell lung cancer patients. The combined model demonstrated a notable generalization effect, effectively distinguishing between positive and negative OLMs in a noninvasive manner, thereby guiding individualized clinical decisions for patients with cT1 - 2N0M0 SCLC.

Depth of invasion analysis to predict acral melanoma outcomes.

BACKGROUND: Acral melanoma is a subtype with worse outcomes. The Breslow micrometric measurement is the most critical parameter in planning treatment and predicting outcomes. However, for acral lentiginous melanoma, the value of the Breslow thickness is a matter of debate. Depth of Invasion (DOI) is a well-established measure for staging oral squamous cell carcinoma. OBJECTIVE: This study compared DOI and Breslow thickness for predicting acral melanoma outcomes. METHODS: We performed a retrospective cross-sectional study of 71 acral melanoma lesions subjected to sentinel lymph node biopsy at one Brazilian referral center. RESULTS: Cox model univariate analysis showed that both DOI and Breslow thickness predicted melanoma specific survival (HR 1.12; p = 0.0255 and HR 1.144; p = 0.0006, respectively), although Kaplan Meier curve was only significant for Breslow (χ2 = 5.792; p = 0.0161) and not for DOI (χ2 = 0.2556; p = 0.6132). Sentinel lymph node status and presence or absence of ulceration also predicted specific survival in patients with acral melanoma (χ2 = 6.3514; p = 0.0117 and χ2 = 4.2793; p = 0.0386, respectively). Multivariate analysis, however, demonstrated that Breslow depth was the only independent parameter for predicting acral melanoma specific survival (HR 1.144; p = 0.0006). CONCLUSION: Even though Breslow thickness remains the main predictor for survival in acral melanoma, it is not a perfect parameter. The introduction of DOI in this context opens new perspectives for predicting acral melanoma outcomes.

The International Association for the Study of Lung Cancer Lung Cancer Staging Project: Proposals for Revision of the Classification of Residual Tumor After Resection for the Forthcoming (Ninth) Edition of the TNM Classification of Lung Cancer.

INTRODUCTION: The goal of surgical resection is to completely remove a cancer; it is useful to have a system to describe how well this was accomplished. This is captured by the residual tumor (R) classification, which is separate from the TNM classification that describes the anatomic extent of a cancer independent of treatment. The traditional R-classification designates as R0 a complete resection, as R1 a macroscopically complete resection but with microscopic tumor at the surgical margin, and as R2 a resection that leaves gross tumor behind. For lung cancer, an additional category encompasses situations in which the presence of residual tumor is uncertain. METHODS: This paper represents a comprehensive review of evidence regarding these R categories and the descriptors thereof, focusing on studies published after the year 2000 and with adjustment for potential confounders. RESULTS: Consistent discrimination between complete, uncertain, and incomplete resection is revealed with respect to overall survival. Evidence regarding specific descriptors is generally somewhat limited and only partially consistent; nevertheless, the data suggest retaining all descriptors but with clarifications to address ambiguities. CONCLUSION: On the basis of this review, the R-classification for the ninth edition of stage classification of lung cancer is proposed to retain the same overall framework and descriptors, with more precise definitions of descriptors. These refinements should facilitate application and further research.

Critical updates in neuroendocrine tumors: Version 9 American Joint Committee on Cancer staging system for gastroenteropancreatic neuroendocrine tumors.

The American Joint Committee on Cancer (AJCC) staging system for all cancer sites, including gastroenteropancreatic neuroendocrine tumors (GEP-NETs), is meant to be dynamic, requiring periodic updates to optimize AJCC staging definitions. This entails the collaboration of experts charged with evaluating new evidence that supports changes to each staging system. GEP-NETs are the second most prevalent neoplasm of gastrointestinal origin after colorectal cancer. Since publication of the AJCC eighth edition, the World Health Organization has updated the classification and separates grade 3 GEP-NETs from poorly differentiated neuroendocrine carcinoma. In addition, because of major advancements in diagnostic and therapeutic technologies for GEP-NETs, AJCC version 9 advocates against the use of serum chromogranin A for the diagnosis and monitoring of GEP-NETs. Furthermore, AJCC version 9 recognizes the increasing role of endoscopy and endoscopic resection in the diagnosis and management of NETs, particularly in the stomach, duodenum, and colorectum. Finally, T1NXM0 has been added to stage I in these disease sites as well as in the appendix.

Japanese Classification of Esophageal Cancer, 12th Edition: Part I.

This is the first half of English edition of Japanese Classification of Esophageal Cancer, 12th Edition that was published by the Japan Esophageal Society in 2022.

A CT-based integrated model for preoperative prediction of occult lymph node metastasis in early tongue cancer.

Background: Occult lymph node metastasis (OLNM) is an essential prognostic factor for early-stage tongue cancer (cT1-2N0M0) and a determinant of treatment decisions. Therefore, accurate prediction of OLNM can significantly impact the clinical management and outcomes of patients with tongue cancer. The aim of this study was to develop and validate a multiomics-based model to predict OLNM in patients with early-stage tongue cancer. Methods: The data of 125 patients diagnosed with early-stage tongue cancer (cT1-2N0M0) who underwent primary surgical treatment and elective neck dissection were retrospectively analyzed. A total of 100 patients were randomly assigned to the training set and 25 to the test set. The preoperative contrast-enhanced computed tomography (CT) and clinical data on these patients were collected. Radiomics features were extracted from the primary tumor as the region of interest (ROI) on CT images, and correlation analysis and the least absolute shrinkage and selection operator (LASSO) method were used to identify the most relevant features. A support vector machine (SVM) classifier was constructed and compared with other machine learning algorithms. With the same method, a clinical model was built and the peri-tumoral and intra-tumoral images were selected as the input for the deep learning model. The stacking ensemble technique was used to combine the multiple models. The predictive performance of the integrated model was evaluated for accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC-ROC), and compared with expert assessment. Internal validation was performed using a stratified five-fold cross-validation approach. Results: Of the 125 patients, 41 (32.8%) showed OLNM on postoperative pathological examination. The integrated model achieved higher predictive performance compared with the individual models, with an accuracy of 84%, a sensitivity of 100%, a specificity of 76.5%, and an AUC-ROC of 0.949 (95% CI [0.870-1.000]). In addition, the performance of the integrated model surpassed that of younger doctors and was comparable to the evaluation of experienced doctors. Conclusions: The multiomics-based model can accurately predict OLNM in patients with early-stage tongue cancer, and may serve as a valuable decision-making tool to determine the appropriate treatment and avoid unnecessary neck surgery in patients without OLNM.

Japanese Classification of Esophageal Cancer, 12th Edition: Part II.

This is the second half of English edition of Japanese Classification of Esophageal Cancer, 12th Edition that was published by the Japan Esophageal Society in 2022.