Prediction Of Lymph Node Metastasis Research Articles

Individualized prediction of non-sentinel lymph node metastasis in Chinese breast cancer patients with ≥ 3 positive sentinel lymph nodes based on machine-learning algorithms

BackgroundAxillary lymph node dissection (ALND) is a standard procedure for early-stage breast cancer (BC) patients with three or more positive sentinel lymph nodes (SLNs). However, ALND can lead to significant postoperative complications without always providing additional clinical benefits. This study aims to develop machine-learning (ML) models to predict non-sentinel lymph node (non-SLN) metastasis in Chinese BC patients with three or more positive SLNs, potentially allowing the omission of ALND.MethodsData from 2217 BC patients who underwent SLN biopsy at Shantou University Medical College were analyzed, with 634 having positive SLNs. Patients were categorized into those with ≤ 2 positive SLNs and those with ≥ 3 positive SLNs. We applied nine ML algorithms to predict non-SLN metastasis. Model performance was evaluated using ROC curves, precision-recall curves, and calibration curves. Decision Curve Analysis (DCA) assessed the clinical utility of the models.ResultsThe RF model showed superior predictive performance, achieving an AUC of 0.987 in the training set and 0.828 in the validation set. Key predictive features included size of positive SLNs, tumor size, number of SLNs, and ER status. In external validation, the RF model achieved an AUC of 0.870, demonstrating robust predictive capabilities.ConclusionThe developed RF model accurately predicts non-SLN metastasis in BC patients with ≥ 3 positive SLNs, suggesting that ALND might be avoided in selected patients by applying additional axillary radiotherapy. This approach could reduce the incidence of postoperative complications and improve patient quality of life. Further validation in prospective clinical trials is warranted.

A Novel Ultrasound-Based Radiomics Model for the Preoperative Prediction of Lymph Node Metastasis in Cervical Cancer

ObjectiveThe purpose of this retrospective study was to establish a combined model based on ultrasound (US)-radiomics and clinical factors to predict preoperative lymph node metastasis (LNM) in cervical cancer (CC) patients non-invasively. MethodsA total of 131 CC patients who had cervical lesions found by transvaginal sonography (TVS) from the First Affiliated Hospital of Anhui Medical University (Hefei, China) were retrospectively analyzed. The clinical independent predictors were selected using univariate and multivariate logistic regression analysis. US-radiomics features were extracted from US images; after selecting the most significant features by univariate analysis, Spearman's correlation analysis, and the least absolute shrinkage and selection operator (LASSO) algorithm; four machine-learning classification algorithms were used to build the US-radiomics model. Fivefold cross-validation was then used to test the performance of the model and compare the ability of the clinical, US-radiomics and combined models to predict LNM in CC patients. ResultsRed blood cell, platelet and squamous cell carcinoma-associated antigen were independent clinical predictors of LNM (+) in CC patients. eXtreme Gradient Boosting performed the best among the four machine-learning classification algorithms. Fivefold cross-validation confirmed that eXtreme Gradient Boosting indeed performs the best, with average area under the curve values in the training and validation sets of 0.897 and 0.898. In the three prediction models, both the US-radiomics model and the combined model showed good predictive efficacy, with average area under the curve values in the training and validation sets of 0.897, 0.898 and 0.912, 0.905, respectively. ConclusionUS-radiomics features combined with clinical factors can preoperatively predict LNM in CC patients non-invasively.

504. SENTINEL LYMPH NODE NAVIGATED SURGERY IN ESOPHAGOGASTRIC JUNCTION ADENOCARCINOMA USING INDOCYANINE GREEN AND FLUORESCENCE IMAGING

Abstract Background Sentinel lymph node navigated surgery (SNNS) has been adopted for various cancers to reduce the negative impact of lymphadenectomy. Limited lymph node dissection using SNNS might be employed in the management of clinically lymph node negative early esophagogastric junction adenocarcinoma (EGJAC). However, it must be sure that sentinel lymph nodes (SLNs) reflect the patient's overall pN status. The aim of this study was to determine the feasibility and safety of SNNS using near-infrared fluorescence imaging and to obtain preliminary data about sensitivity of prediction of lymph node metastasis using SNNS. Methods Patients with cT1-2cN0 EGJAC without neoadjuvant therapy were prospectively included. One patient was enrolled after non-radical endoscopic resection of a high-risk pT1 tumor. Solution of indocyanine green (ICG) and 10% human serum albumin (ICG concentration 1,25mg/mL) was injected endoscopically into the submucosal layer at four quadrants (á 0.5mL) around the tumor or endoscopic resection scar just before the surgery. Subsequently, SLNs were identified and removed laparoscopically using fluorescence imaging. Then, esophagectomy or gastrectomy with radical lymphadenectomy were performed in all patients. Results A total of nine patients underwent SNNS followed by radical surgery. Histopathology revealed pT0pN0 in 1 patient, pT1bN0 in 3 patients, pT1bN3 in 1 patient, pT2pN1 in 2 patients, pT3pN0 in 1 patient and pT3pN2 in 1 patient. Overall, 62 SLNs were detected (median 7 SLNs per patient, range 1-16). Metastases in SLNs were found in four patients. All patients with pathologically positive lymph nodes had at least one SLN positive for metastasis. Sensitivity of prediction of pN positive status was 100%, false negative rate was 0%. There were no ICG-related adverse events or complications associated with SNNS procedure. Conclusion These results suggest that SNNS using ICG and fluorescence imaging in early EGJAC is feasible and safe. Our pilot data show promising diagnostic accuracy of predicting pathological lymph node status using SNNS. However, further studies with a larger number of patients are needed before introducing SNNS into clinical practice.

Preoperative prediction model of lymph node metastasis in the inguinal and femoral region based on radiomics and artificial intelligence

ObjectiveTo predict preoperative inguinal lymph node metastasis in vulvar cancer patients using a machine learning model based on imaging features and clinical data from pelvic magnetic resonance imaging (MRI).Methods52 vulvar...

1441P Clinical application of a machine learning-based pathomics signature for predicting lymph node metastasis in early gastric cancer

1441P Clinical application of a machine learning-based pathomics signature for predicting lymph node metastasis in early gastric cancer

A transformer-based deep learning model for early prediction of lymph node metastasis in locally advanced gastric cancer after neoadjuvant chemotherapy using pretreatment CT images

Early prediction of lymph node status after neoadjuvant chemotherapy (NAC) facilitates promptly optimization of treatment strategies. This study aimed to develop and validate a deep learning network (DLN) using baseline computed tomography images to predict lymph node metastasis (LNM) after NAC in patients with locally advanced gastric cancer (LAGC). A total of 1205 LAGC patients were retrospectively recruited from three hospitals between January 2013 and March 2023, constituting a training cohort, an internal validation cohort, and two external validation cohorts. A transformer-based DLN was developed using 3D tumor images to predict LNM after NAC. A clinical model was constructed through multivariate logistic regression analysis as a baseline for subsequent comparisons. The performance of the models was evaluated through discrimination, calibration, and clinical applicability. Furthermore, Kaplan-Meier survival analysis was conducted to assess overall survival (OS) of LAGC patients at two follow-up centers. The DLN outperformed the clinical model and demonstrated a robust performance for predicting LNM in the training and validation cohorts, with areas under the curve (AUCs) of 0.804 (95% confidence interval [CI], 0.752-0.849), 0.748 (95% CI, 0.660-0.830), 0.788 (95% CI, 0.735-0.835), and 0.766 (95% CI, 0.717-0.814), respectively. Decision curve analysis exhibited a high net clinical benefit of the DLN. Moreover, the DLN was significantly associated with the OS of LAGC patients [Center 1: hazard ratio (HR), 1.789, P<0.001; Center 2:HR, 1.776, P=0.013]. The transformer-based DLN provides early and effective prediction of LNM and survival outcomes in LAGC patients receiving NAC, with promise to guide individualized therapy. Future prospective multicenter studies are warranted to further validate our model. National Natural Science Foundation of China (NO. 82373432, 82171923, 82202142), Project Funded by China Postdoctoral Science Foundation (NO. 2022M720857), Regional Innovation and Development Joint Fund of National Natural Science Foundation of China (NO. U22A20345), National Science Fund for Distinguished Young Scholars of China (NO. 81925023), Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application (NO. 2022B1212010011), High-level Hospital Construction Project (NO. DFJHBF202105), Natural Science Foundation of Guangdong Province for Distinguished Young Scholars (NO. 2024B1515020091).

Intravoxel incoherent motion diffusion-weighted imaging in evaluating preoperative staging of esophageal squamous cell carcinoma

BackgroundThe aim of this research is to prospectively investigate the diagnostic performance of intravoxel incoherent motion (IVIM) using the integrated slice-specific dynamic shimming (iShim) technique in staging primary esophageal squamous cell carcinoma (ESCC) and predicting presence of lymph node metastases from ESCC.MethodsSixty-three patients with ESCC were prospectively enrolled from April 2016 to April 2019. MR and IVIM using iShim technique (b = 0, 25, 50, 75, 100, 200, 400, 600, 800 s/mm2) were performed on 3.0T MRI system before operation. Primary tumour apparent diffusion coefficient (ADC) and IVIM parameters, including true diffusion coefficient (D), pseudodiffusion coefficient (D*), pseudodiffusion fraction (f) were measured by two independent radiologists. The differences in D, D*, f and ADC values of different T and N stages were assessed. Intraclass correlation coefficients (ICCs) were calculated to evaluate the interobserver agreement between two readers. The diagnostic performances of D, D*, f and ADC values in primary tumour staging and prediction of lymph node metastasis of ESCC were determined using receiver operating characteristic (ROC) curve analysis.ResultsThe inter-observer consensus was excellent for IVIM parameters and ADC (D: ICC = 0.922; D*: ICC = 0.892; f: ICC = 0.948; ADC: ICC = 0.958). The ADC, D, D* and f values of group T1 + T2 were significantly higher than those of group T3 + T4a [ADC: (2.55 ± 0.43) ×10− 3 mm2/s vs. (2.27 ± 0.40) ×10− 3 mm2/s, t = 2.670, P = 0.010; D: (1.82 ± 0.39) ×10− 3 mm2/s vs. (1.53 ± 0.33) ×10− 3 mm2/s, t = 3.189, P = 0.002; D*: 46.45 (30.30,55.53) ×10− 3 mm2/s vs. 32.30 (18.60,40.95) ×10− 3 mm2/s, z=-2.408, P = 0.016; f: 0.45 ± 0.12 vs. 0.37 ± 0.12, t = 2.538, P = 0.014]. The ADC, D and f values of the lymph nodes-positive (N+) group were significantly lower than those of lymph nodes-negative (N0) group [ADC: (2.10 ± 0.33) ×10− 3 mm2/s vs. (2.55 ± 0.40) ×10− 3 mm2/s, t=-4.564, P < 0.001; D: (1.44 ± 0.30) ×10− 3 mm2/s vs. (1.78 ± 0.37) ×10− 3 mm2/s, t=-3.726, P < 0.001; f: 0.32 ± 0.10 vs. 0.45 ± 0.11, t=-4.524, P < 0.001]. The combination of D, D* and f yielded the highest area under the curve (AUC) (0.814) in distinguishing group T1 + T2 from group T3 + T4a. D combined with f provided the highest diagnostic performance (AUC = 0.849) in identifying group N + and group N0 of ESCC.ConclusionsIVIM may be used as an effective functional imaging technique to evaluate preoperative stage of primary tumour and predict presence of lymph node metastases from ESCC.

Enhancing lymph node metastasis prediction in adenocarcinoma of the esophagogastric junction: A study combining radiomic with clinical features.

The incidence of adenocarcinoma of the esophagogastric junction (AEJ) is increasing, and with poor prognosis. Lymph node status (LNs) is particularly important for planning treatment and evaluating the prognosis of patients with AEJ. However, the use of radiomic based on enhanced computed tomography (CT) to predict the preoperative lymph node metastasis (PLNM) status of the AEJ has yet to be reported. We sought to investigate the value of radiomic features based on enhanced CT in the accurate prediction of PLNM in patients with AEJ. Clinical features and enhanced CT data of 235 patients with AEJ from October 2017 to May 2023 were retrospectively analyzed. The data were randomly assigned to the training cohort (n=164) or the external testing cohort (n=71) at a ratio of 7:3. A CT-report model, clinical model, radiomic model, and radiomic-clinical combined model were developed to predict PLNM in patients with AEJ. Univariate and multivariate logistic regression were used to screen for independent clinical risk factors. Least absolute shrinkage and selection operator (LASSO) regression was used to select the radiomic features. Finally, a nomogram for the preoperative prediction of PLNM in AEJ was constructed by combining Radiomics-score and clinical risk factors. The models were evaluated by area under the receiver operating characteristic curve (AUC-ROC), calibration curve, and decision curve analyses. A total of 181 patients (181/235, 77.02%) had LNM. In the testing cohort, the AUC of the radiomic-clinical model was 0.863 [95% confidence interval (CI)=0.738-0.957], and the radiomic model (0.816; 95% CI=0.681-0.929), clinical model (0.792; 95% CI=0.677-0.888), and CT-report model (0.755; 95% CI=0.647-0.840). The radiomic-clinical model is a feasible method for predicting PLNM in patients with AEJ, helping to guide clinical decision-making and personalized treatment planning.

An interpretable multimodal model based on cytology ultrasound noninvasively predicts lymph node metastasis in cN0 papillary thyroid cancer:a retrospective, ulticentre study.

An interpretable multimodal model based on cytology ultrasound noninvasively predicts lymph node metastasis in cN0 papillary thyroid cancer:a retrospective, ulticentre study.

Editorial Comment to "Can the Briganti 2019 nomogram be modified to predict lymph node metastasis risk in patients with prostate cancer detected with in-bore biopsy?"

Editorial Comment to "Can the Briganti 2019 nomogram be modified to predict lymph node metastasis risk in patients with prostate cancer detected with in-bore biopsy?"

Can the Briganti 2019 nomogram be modified to predict lymph node metastasis risk in patients with prostate cancer detected with in-bore biopsy?

We aimed to modify the Briganti 2019 nomogram and to test whether it is valid for patients who were diagnosed with prostate cancer through in-bore prostate biopsies. Data for 204 patients with positive multiparametric prostate MRI and prostate cancer identified either by mpMRI-cognitive/software fusion or in-bore biopsy and who underwent robot-assisted radical prostatectomy and extended pelvic lymph node dissection between 2012 and 2023 were retrospectively analyzed. The Briganti 2019 nomogram was applied to the mpMRI-cognitive/software fusion biopsy group (142 patients) in the original form, and then, two modifications were tested for the targeted component. Original and modified scores were compared. These modifications were adapted for the in-bore biopsy group (62 patients). The final histopathologic stage was regarded as the gold standard. Nodal metastases were identified in 18/142 (12.6%) of mpMRI-cognitive/software fusion biopsy patients and 8/62 (12.9%) of the in-bore biopsy patients. In the mpMRI-cognitive/software fusion biopsy group, tumor size/core size (%) of targeted biopsy cores and positive core percentage on systematic biopsy were significant parameters for lymph node metastasis based on univariate logistic regression analyses (p < 0.05). With the modifications of these parameters for the in-bore biopsy group, V1 modification of the Briganti 2019 nomogram provided 100% sensitivity and 31.5% specificity (AUC:0.627), while V2 modification provided 75% sensitivity and 46.3% specificity (AUC:0.645). Briganti 2019 nomogram may be modified by utilizing tumor size/core size (%) for targeted biopsy cores instead of positive core percentage on systematic biopsy or by not taking both parameters into consideration to detect node metastasis risk of patients diagnosed with in-bore biopsies.

Development of a multi-modal learning-based lymph node metastasis prediction model for lung cancer

PurposeThis study proposed a three-dimensional (3D) multi-modal learning-based model for the automated prediction and classification of lymph node metastasis in patients with non-small cell lung cancer (NSCLC) using computed tomography (CT) images and clinical information. MethodsWe utilized clinical information and CT image data from 4239 patients with NSCLC across multiple institutions. Four deep learning algorithm-based multi-modal models were constructed and evaluated for lymph node classification. To further enhance classification performance, a soft-voting ensemble technique was applied to integrate the outcomes of multiple multi-modal models. ResultsA comparison of the classification performance revealed that the multi-modal model, which integrated CT images and clinical information, outperformed the single-modal models. Among the four multi-modal models, the Xception model demonstrated the highest classification performance, with an area under the curve (AUC) of 0.756 for the internal test dataset and 0.736 for the external validation dataset. The ensemble model (SEResNet50_DenseNet121_Xception) exhibited even better performance, with an AUC of 0.762 for the internal test dataset and 0.751 for the external validation dataset, surpassing the multi-modal model's performance. ConclusionsIntegrating CT images and clinical information improved the performance of the lymph node metastasis prediction models in patients with NSCLC. The proposed 3D multi-modal lymph node prediction model can serve as an auxiliary tool for evaluating lymph node metastasis in patients with non-pretreated NSCLC, aiding in patient screening and treatment planning.

Outcomes of noncurative endoscopic submucosal dissection for T1 colorectal cancer: Prospective, multicenter, cohort study in Japan.

This study investigated the incidence of lymph node metastasis and long-term outcomes in patients with T1 colorectal cancer where endoscopic submucosal dissection (ESD) resulted in noncurative treatment. It is focused on those with deep submucosal invasion, a factor considered a weak predictor of lymph node metastasis in the absence of other risk factors. This nationwide, multicenter, prospective study conducted a post-hoc analysis of 141 patients with T1 colorectal cancer ≥20 mm where ESD of the lesion resulted in noncurative outcomes, characterized by poor differentiation, deep submucosal invasion (≥1000 μm), lymphovascular invasion, high-grade tumor budding, or positive vertical margins. Clinicopathologic features and patient prognoses focusing on lesion sites and additional surgery requirements were evaluated. Lymph node metastasis incidence in the low-risk T1 group, identified by deep submucosal invasion as the sole high-risk histological feature, was assessed. Lymph node metastasis occurred in 14% of patients undergoing additional surgery post-noncurative endoscopic submucosal dissection for T1 colorectal cancer. In the low-risk T1 group, in the absence of other risk factors, the frequency was 9.7%. The lymph node metastasis rates in patients with T1 colon and rectal cancers did not differ significantly (14% vs. 16%). Distant recurrence was observed in one patient (2.3%) in the ESD only group and in one (1.0%) in the additional surgery group, both of whom had had rectal cancer removed. The risk of lymph node metastasis or distant occurrence was not negligible, even in the low-risk T1 group. The findings suggest the need for considering additional surgery, particularly for rectal lesions (Clinical Trial Registration: UMIN000010136).

A CT-based radiomics model for predicting lymph node metastasis in hepatic alveolar echinococcosis patients to support lymph node dissection

BackgroundHepatic alveolar echinococcosis (AE) is a severe zoonotic parasitic disease, and accurate preoperative prediction of lymph node (LN) metastasis in AE patients is crucial for disease management, but it remains an unresolved challenge. The aim of this study was to establish a radiomics model for the preoperative prediction of LN metastasis in hepatic AE patients.MethodsA total of 100 hepatic AE patients who underwent hepatectomy and hepatoduodenal ligament LN dissection at Qinghai Provincial People's Hospital between January 2016 and August 2023 were included in the study. The patients were randomly divided into a training set and a validation set at an 8:2 ratio. Radiomic features were extracted from three-dimensional images of the hepatoduodenal ligament LNs delineated on arterial phase computed tomography (CT) scans of hepatic AE patients. Least absolute shrinkage and selection operator (LASSO) regression was applied for data dimensionality reduction and feature selection. Multivariate logistic regression analysis was performed to develop a prediction model, and the predictive performance of the model was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA).ResultsA total of 7 radiomics features associated with LN status were selected using LASSO regression. The classification performances of the training set and validation set were consistent, with area under the operating characteristic curve (AUC) values of 0.928 and 0.890, respectively. The model also demonstrated good stability in subsequent validation.ConclusionIn this study, we established and evaluated a radiomics-based prediction model for LN metastasis in patients with hepatic AE using CT imaging. Our findings may provide a valuable reference for clinicians to determine the occurrence of LN metastasis in hepatic AE patients preoperatively, and help guide the implementation of individualized surgical plans to improve patient prognosis.

Based on 3D-PDU and clinical characteristics nomogram for prediction of lymph node metastasis and lymph-vascular space invasion of early cervical cancer preoperatively

PurposeTo develop and validate a nomogram based on 3D-PDU parameters and clinical characteristics to predict LNM and LVSI in early-stage cervical cancer preoperatively.Materials and methodsA total of first diagnosis 138 patients with cervical cancer who had undergone 3D-PDU examination before radical hysterectomy plus lymph dissection between 2014 and 2019 were enrolled for this study. Multivariate logistic regression analyses were performed to analyze the 3D-PDU parameters and selected clinicopathologic features and develop a nomogram to predict the probability of LNM and LVSI in the early stage. ROC curve was used to evaluate model differentiation, calibration curve and Hosmer-Lemeshow test were used to evaluate calibration, and DCA was used to evaluate clinical practicability.ResultsMenopause status, FIGO stage and VI were independent predictors of LNM. BMI and maximum tumor diameter were independent predictors of LVSI. The predicted AUC of the LNM and LSVI models were 0.845 (95%CI,0.765–0.926) and 0.714 (95%CI,0.615–0.813). Calibration curve and H-L test (LNM groups P = 0.478; LVSI P = 0.783) all showed that the predicted value of the model had a good fit with the actual observed value, and DCA indicated that the model had a good clinical net benefit.ConclusionThe proposed nomogram based on 3D-PDU parameters and clinical characteristics has been proposed to predict LNM and LVSI with high accuracy, demonstrating for the first time the potential of non-invasive prediction. The probability derived from this nomogram may have the potential to provide valuable guidance for physicians to develop clinical individualized treatment plans of FIGO patients with early cervical cancer.

Artificial Intelligence to Predict the Risk of Lymph Node Metastasis in T2 Colorectal Cancer.

To develop and externally validate an updated artificial intelligence (AI) prediction system for stratifying the risk of lymph node metastasis (LNM) in T2 colorectal cancer (CRC). Recent technical advances allow complete local excision of T2 CRC, traditionally treated with surgical resection. Yet, the widespread adoption of this approach is hampered by the inability to stratify the risk of LNM. Data from pT2 CRC patients undergoing surgical resection between April 2000 and May 2022 at one Japanese and one Italian center were analyzed. Primary goal was AI system development for accurate LNM prediction. Predictors encompassed seven variables: age, sex, tumor size and location, lympho-vascular invasion, histological differentiation, and carcinoembryonic antigen level. The tool's discriminating power was assessed via Area Under the Curve (AUC), sensitivity, and specificity. Out of 735 initial patients, 692 were eligible. Training and validation cohorts comprised of 492 and 200 patients, respectively. The AI model displayed an AUC of 0.75 in the combined validation dataset. Sensitivity for LNM prediction was 97.8% and specificity was 15.6%. The Positive and the Negative Predictive Value were 25.7% and 96% respectively. The False Negative (FN) rate was 2.2%, the False Positive was 84.4%. Our AI model, based on easily accessible clinical and pathological variables, moderately predicts LNM in T2 CRC. However, the risk of FN needs to be considered. The training of the model including more patients across Western and Eastern centers -differentiating between colon and rectal cancers- may improve its performance and accuracy.

Prognostic Significance of "High" Tumor Budding and "High" Poorly Differentiated Clusters in Endometrial Carcinomas: Independent Predictors of Lymphovascular Space Invasion and Lymph Node Metastasis.

Tumor budding (TB) and poorly differentiated clusters (PDCs) are well-established prognostic factors in various cancers. This study aimed to assess the independent prognostic role of these markers in endometrial carcinomas. Retrospective analysis of endometrial carcinoma resection specimens by examining traditional histologic prognostic parameters. TB and PDC were observed at 20× magnification in ten fields at the invasive front and categorized as present or absent. In addition, a count of ≥5 was stratified as "high." Clinical and follow-up details were extracted from Gynecologic Oncology records. Sixty-five endometrial carcinomas were studied and were predominantly endometrioid (n=47, 72.3%). TB was identified in 52.3% of cases, with high TB observed in 38.5%. PDC was evident in 44.6%, with high PDC seen in 29.2%. Associations were significant between the presence of TB/high TB and higher tumor grade (P < 0.001), deep myometrial invasion (P = 0.006/P = 0.002), diffuse pattern of invasion (P = 0.007/P = 0.03), microcystic elongated and fragmented pattern (P < 0.001), lymphovascular space invasion, lymph node metastasis (P=<0.001) and International Federation of Gynecology and Obstetrics stage (P = 0.000/P = 0.002). PDC/high PDC showed similar associations, and, in addition, with nonendometrioid histologic type (P = 0.02) and tumor location in a lower uterine segment (high PDC, P = 0.009). After adjusting for other significant parameters, both high TB (P = 0.03) and high PDC (P = 0.031) emerged as independent prognostic parameters for lymphovascular space invasion or Lymph node metastasis. No recorded deaths or significant events occurred, precluding commentary on overall survival status. High TB and PDC are independent predictors of Lymph node metastasis in endometrial carcinomas. Their association with the microcystic elongated and fragmented pattern makes them histologic predictors of epithelial-mesenchymal transition. Their simple application underscores their potential as valuable additional prognostic indicators for endometrial carcinomas.

Artificial intelligence assisted ultrasound for the non-invasive prediction of axillary lymph node metastasis in breast cancer

PurposeA practical noninvasive method is needed to identify lymph node (LN) status in breast cancer patients diagnosed with a suspicious axillary lymph node (ALN) at ultrasound but a negative clinical physical examination. To predict ALN metastasis effectively and noninvasively, we developed an artificial intelligence-assisted ultrasound system and validated it in a retrospective study.MethodsA total of 266 patients treated with sentinel LN biopsy and ALN dissection at Peking Union Medical College & Hospital(PUMCH) between the year 2017 and 2019 were assigned to training, validation and test sets (8:1:1). A deep learning model architecture named DeepLabV3 + was used together with ResNet-101 as the backbone network to create an ultrasound image segmentation diagnosis model. Subsequently, the segmented images are classified by a Convolutional Neural Network to predict ALN metastasis.ResultsThe area under the receiver operating characteristic curve of the model for identifying metastasis was 0.799 (95% CI: 0.514–1.000), with good end-to-end classification accuracy of 0.889 (95% CI: 0.741–1.000). Moreover, the specificity and positive predictive value of this model was 100%, providing high accuracy for clinical diagnosis.ConclusionThis model can be a direct and reliable tool for the evaluation of individual LN status. Our study focuses on predicting ALN metastasis by radiomic analysis, which can be used to guide further treatment planning in breast cancer.

Radiogenomic analysis for predicting lymph node metastasis and molecular annotation of radiomic features in pancreatic cancer

BackgroundTo provide a preoperative prediction model for lymph node metastasis in pancreatic cancer patients and provide molecular information of key radiomic features.MethodsTwo cohorts comprising 151 and 54 pancreatic cancer patients were included in the analysis. Radiomic features from the tumor region of interests were extracted by using PyRadiomics software. We used a framework that incorporated 10 machine learning algorithms and generated 77 combinations to construct radiomics-based models for lymph node metastasis prediction. Weighted gene coexpression network analysis (WGCNA) was subsequently performed to determine the relationships between gene expression levels and radiomic features. Molecular pathways enrichment analysis was performed to uncover the underlying molecular features.ResultsPatients in the in-house cohort (mean age, 61.3 years ± 9.6 [SD]; 91 men [60%]) were separated into training (n = 105, 70%) and validation (n = 46, 30%) cohorts. A total of 1,239 features were extracted and subjected to machine learning algorithms. The 77 radiomic models showed moderate performance for predicting lymph node metastasis, and the combination of the StepGBM and Enet algorithms had the best performance in the training (AUC = 0.84, 95% CI = 0.77–0.91) and validation (AUC = 0.85, 95% CI = 0.73–0.98) cohorts. We determined that 15 features were core variables for lymph node metastasis. Proliferation-related processes may respond to the main molecular alterations underlying these features.ConclusionsMachine learning-based radiomics could predict the status of lymph node metastasis in pancreatic cancer, which is associated with proliferation-related alterations.

Biparametric MRI of the prostate radiomics model for prediction of pelvic lymph node metastasis in prostate cancers : a two-centre study

ObjectivesExploring the value of adding correlation analysis (radiomic features (RFs) of pelvic metastatic lymph nodes and primary lesions) to screen RFs of primary lesions in the feature selection process of establishing prediction model.MethodsA total of 394 prostate cancer (PCa) patients (263 in the training group, 74 in the internal validation group and 57 in the external validation group) from two tertiary hospitals were included in the study. The cases with pelvic lymph node metastasis (PLNM) positive in the training group were diagnosed by biopsy or MRI with a short-axis diameter ≥ 1.5 cm, PLNM-negative cases in the training group and all cases in validation group were underwent both radical prostatectomy (RP) and extended pelvic lymph node dissection (ePLND). The RFs of PLNM-negative lesion and PLNM-positive tissues including primary lesions and their metastatic lymph nodes (MLNs) in the training group were extracted from T2WI and apparent diffusion coefficient (ADC) map to build the following two models by fivefold cross-validation: the lesion model, established according to the primary lesion RFs selected by t tests and absolute shrinkage and selection operator (LASSO); the lesion-correlation model, established according to the primary lesion RFs selected by Pearson correlation analysis (RFs of primary lesions and their MLNs, correlation coefficient > 0.9), t test and LASSO. Finally, we compared the performance of these two models in predicting PLNM.ResultsThe AUC and the DeLong test of AUC in the lesion model and lesion-correlation model were as follows: training groups (0.8053, 0.8466, p = 0.0002), internal validation group (0.7321, 0.8268, p = 0.0429), and external validation group (0.6445, 0.7874, p = 0.0431), respectively.ConclusionThe lesion-correlation model established by features of primary tumors correlated with MLNs has more advantages than the lesion model in predicting PLNM.