Lymph Nodes Short-axis Diameter Research Articles

Diagnostic performance of Node-RADS score for mesorectal lymph node metastasis in rectal cancer.

To explore the diagnostic performance of the Node-RADS scoring system on preoperative assessment of mesorectal lymph node metastasis (LNM) status in rectal cancer, in comparisonwith the ESGAR category and size of lymph node (LN). Preoperative clinical and MRI data of 154 rectal adenocarcinoma patients treated with radical resection surgery were retrospectively analyzed. The differences in the clinical, pathological and imaging characteristics between the pN- and pN + groups were surveyed. The correlations of Node-RADS score and ESGAR category to pN stage, LNM number and lymph node ratio (LNR) were investigated. The performances on assessing pathological LNM were compared among individual approaches. A nomogram combined the imaging and clinicalfeatures was also established and evaluated. Significant differences in CEA, tumor maximum diameter, tumor location, LN short-axis diameter, Node-RADS score and ESGAR category were found between the pN- and pN + groups. Node-RADS correlated significantly with pN stage, LNM number, and LNR (r = 0.665, 0.685, and 0.675, p < 0.001). Node-RADS had the highest AUC (0.862) for predicting pN + status, surpassing ESGAR (AUC = 0.797, p = 0.040) and LN size (AUC = 0.762, p = 0.015). The nomogram had the best diagnostic performance (AUC = 0.901), significantly outperforming Node-RADS alone (p = 0.037). The Node-RADS scoring system is comparable to the ESGAR category and surpasses short-axis diameter in preoperatively predicting LNM in rectal cancer. Integrating imaging and clinical features will lead to an enhancement in diagnostic performance. Moreover, a clear relationship was demonstrated between the Node-RADS score and the quantity-dependent pathological characteristics of LNM.

Prediction of regional lymph node metastasis in intrahepatic cholangiocarcinoma: it’s not all about size

ObjectivesLymph node metastases (LNM) are frequent in patients with intrahepatic cholangiocarcinoma (iCC) and worsen their prognosis even after surgery. Our aim was to investigate the predictive value of lymph node (LN) short axis, the most common discriminator for identifying LNM in tumor-imaging and to develop a predictive model for regional LNM in iCC taking computed tomography (CT) features of extranodal disease into account.Materials and methodsWe enrolled 102 patients with pathologically proven iCC who underwent CT prior to hepatic resection and hilar lymph node dissection (LND) from 2005 to 2021. Two blinded radiologists assessed various imaging characteristics and LN diameters, which were analyzed by bivariate and multivariate logistic regression to develop a prediction model for LNM.ResultsPrevalence of LNM was high (42.4 %) and estimated survival was shorter in LN-positive patients (p = 0.07). An LN short axis diameter of ≥ 9 mm demonstrated the highest predictive power for LNM. Three additional, statistically significant imaging features, presence of intrahepatic metastasis (p = 0.003), hilar tumor infiltration (p = 0.003), and tumor growth along the liver capsule (p = 0.004), were integrated into a prediction model, which substantially outperformed use of LN axis alone in ROC analysis (AUC 0.856 vs 0.701).ConclusionsLN diameter alone proved to be a relevant but unreliable imaging-marker for LNM prediction in iCC. Our proposed prognostic model, which additionally considers intrahepatic metastases and hilar and capsular infiltration, significantly improves discriminatory power. Hilar and capsular involvement might indicate direct tumor extension to lymphatic liver structures.

A machine learning tool to improve prediction of mediastinal lymph node metastases in non-small cell lung cancer using routinely obtainable [18F]FDG-PET/CT parameters

BackgroundIn patients with non-small cell lung cancer (NSCLC), accuracy of [18F]FDG-PET/CT for pretherapeutic lymph node (LN) staging is limited by false positive findings. Our aim was to evaluate machine learning with routinely obtainable variables to improve accuracy over standard visual image assessment.MethodsMonocentric retrospective analysis of pretherapeutic [18F]FDG-PET/CT in 491 consecutive patients with NSCLC using an analog PET/CT scanner (training + test cohort, n = 385) or digital scanner (validation, n = 106). Forty clinical variables, tumor characteristics, and image variables (e.g., primary tumor and LN SUVmax and size) were collected. Different combinations of machine learning methods for feature selection and classification of N0/1 vs. N2/3 disease were compared. Ten-fold nested cross-validation was used to derive the mean area under the ROC curve of the ten test folds (“test AUC”) and AUC in the validation cohort. Reference standard was the final N stage from interdisciplinary consensus (histological results for N2/3 LNs in 96%).ResultsN2/3 disease was present in 190 patients (39%; training + test, 37%; validation, 46%; p = 0.09). A gradient boosting classifier (GBM) with 10 features was selected as the final model based on test AUC of 0.91 (95% confidence interval, 0.87–0.94). Validation AUC was 0.94 (0.89–0.98). At a target sensitivity of approx. 90%, test/validation accuracy of the GBM was 0.78/0.87. This was significantly higher than the accuracy based on “mediastinal LN uptake > mediastinum” (0.7/0.75; each p < 0.05) or combined PET/CT criteria (PET positive and/or LN short axis diameter > 10 mm; 0.68/0.75; each p < 0.001). Harmonization of PET images between the two scanners affected SUVmax and visual assessment of the LNs but did not diminish the AUC of the GBM.ConclusionsA machine learning model based on routinely available variables from [18F]FDG-PET/CT improved accuracy in mediastinal LN staging compared to established visual assessment criteria. A web application implementing this model was made available.

Learning curves and association of pathologist’s performance with the diagnostic accuracy of linear endobronchial ultrasound transbronchial needle aspiration (EBUS-TBNA): a cohort study in a tertiary care reference centre

ObjectivesWe aimed to assess the learning curves and the influence of the pathologist’s performance on the endobronchial ultrasound transbronchial needle aspiration’s (EBUS-TBNA’s) diagnostic accuracy in a real-world study.Design/settingCohort study conducted...

Hist-O-06 - Image-guided lymph node core-needle biopsy predicts survival in mycosis fungoides and Sézary syndrome

<h3>Background:</h3> The prognosis of Sézary syndrome (SS) and mycosis fungoides (MF) depends on lymph node (LN) involvement. The usefulness of LN image-guided core-needle biopsies (CNBs), instead of surgical sampling, has been poorly evaluated. <h3>Objectives:</h3> To determine the prognostic value of LN CNB in MF/SS. <h3>Methods:</h3> A retrospective search was conducted to identify all LN biopsy specimens of MF/SS between 2008 and 2019. Biopsies were staged according to the International Society for Cutaneous Lymphomas/European Organisation for Research and Treatment of Cancer (ISCL/EORTC) criteria. We performed immunolabelling and determined the tumour clone frequency (TCF) by high-throughput sequencing of the T-cell receptor beta locus. <h3>Results:</h3> We included 119 consecutive biopsies from 100 patients, 45 with MF and 55 with SS. N1, N2 and N3 stages were diagnosed in 34 (29%), 26 (22%) and 59 (49%) cases, respectively. The TCF, Ki67 index, and percentage of cells positive for thymocyte selection-associated high mobility group box protein (TOX), programmed cell death protein 1 (PD1), killer cell immunoglobulin-like receptor 3DL2 (KIR3DL2) and cluster of differentiation (CD)30 were all positively correlated with the N stage. Median overall survival (OS) for N1/N2 vs. N3 patients was 42 months (range 26–not reached) vs. 14 months (range 5–30), respectively (p<0.001). In univariate analyses, an age >75 years, LN short-axis diameter >15 mm, N3 stage, presence of large-cell transformation, TOX >60%, PD1 >25%, Ki67 >30%, KIR3DL2 >15%, CD30 >10% and TCF >25% were identified as adverse prognostic factors. In multivariate analyses, only an age >75 years and Ki67 index >30% were associated with reduced OS. We developed a new prognostic index associating the N stage and the Ki67 index, which better discriminates N3 patients with poor prognosis. <h3>Conclusions:</h3> CNB allows an objective assessment of the LN involvement in MF/SS, relevant for staging and prognosis.

Computer-Aided Segmentation and Machine Learning of Integrated Clinical and Diffusion-Weighted Imaging Parameters for Predicting Lymph Node Metastasis in Endometrial Cancer.

Simple SummaryComputer-aided segmentation and machine learning added values of clinical parameters and diffusion-weighted imaging radiomics for predicting nodal metastasis in endometrial cancer, with a diagnostic performance superior to criteria based on lymph node size or apparent diffusion coefficient.Precise risk stratification in lymphadenectomy is important for patients with endometrial cancer (EC), to balance the therapeutic benefit against the operation-related morbidity and mortality. We aimed to investigate added values of computer-aided segmentation and machine learning based on clinical parameters and diffusion-weighted imaging radiomics for predicting lymph node (LN) metastasis in EC. This prospective observational study included 236 women with EC (mean age ± standard deviation, 51.2 ± 11.6 years) who underwent magnetic resonance (MR) imaging before surgery during July 2010–July 2018, randomly split into training (n = 165) and test sets (n = 71). A decision-tree model was constructed based on mean apparent diffusion coefficient (ADC) value of the tumor (cutoff, 1.1 × 10−3 mm2/s), skewness of the relative ADC value (cutoff, 1.2), short-axis diameter of LN (cutoff, 1.7 mm) and skewness ADC value of the LN (cutoff, 7.2 × 10−2), as well as tumor grade (1 vs. 2 and 3), and clinical tumor size (cutoff, 20 mm). The sensitivity and specificity of the model were 94% and 80% for the training set and 86%, 78% for the independent testing set, respectively. The areas under the receiver operating characteristics curve (AUCs) of the decision-tree was 0.85—significantly higher than the mean ADC model (AUC = 0.54) and LN short-axis diameter criteria (AUC = 0.62) (both p < 0.0001). We concluded that a combination of clinical and MR radiomics generates a prediction model for LN metastasis in EC, with diagnostic performance surpassing the conventional ADC and size criteria.

Image-guided lymph node core-needle biopsy predicts survival in mycosis fungoides and Sézary syndrome.

The prognosis of Sézary syndrome (SS) and mycosis fungoides (MF) depends on lymph node (LN) involvement. The usefulness of LN image-guided core-needle biopsies (CNBs), instead of surgical sampling, has been poorly evaluated. To determine the prognostic value of LN CNB in MF/SS. A retrospective search was conducted to identify all LN biopsy specimens of MF/SS between 2008 and 2019. Biopsies were staged according to the International Society for Cutaneous Lymphomas/European Organisation for Research and Treatment of Cancer (ISCL/EORTC) criteria. We performed immunolabelling and determined the tumour clone frequency (TCF) by high-throughput sequencing of the T-cell receptor beta locus. We included 119 consecutive biopsies from 100 patients, 45 with MF and 55 with SS. N1, N2 and N3 stages were diagnosed in 34 (29%), 26 (22%) and 59 (49%) cases, respectively. The TCF, Ki67 index, and percentage of cells positive for thymocyte selection-associated high mobility group box protein (TOX), programmed cell death protein 1 (PD1), killer cell immunoglobulin-like receptor 3DL2 (KIR3DL2) and cluster of differentiation (CD)30 were all positively correlated with the N stage. Median overall survival (OS) for N1/N2 vs. N3 patients was 42months (range 26-not reached) vs. 14months (range 5-30), respectively (P<0·001). In univariate analyses, an age>75years, LN short-axis diameter>15mm, N3 stage, presence of large-cell transformation, TOX>60%, PD1>25%, Ki67>30%, KIR3DL2>15%, CD30>10% and TCF>25% were identified as adverse prognostic factors. In multivariate analyses, only an age>75years and Ki67 index>30% were associated with reduced OS. We developed a new prognostic index associating the N stage and the Ki67 index, which better discriminates N3 patients with poor prognosis. CNB allows an objective assessment of the LN involvement in MF/SS, relevant for staging and prognosis.

Successful Identification of Head and Neck Cancer (HNC) Nodal Metastasis (NM) and Extranodal Extension (ENE) Using Deep Learning Neural Networks

Despite modern imaging modalities, radiologic detection of clinically meaningful tumor characteristics, such as NM and, particularly tumor ENE remains difficult, with reported areas under the receiver operating characteristic curve (AUC) <.70 and accuracies <70%. Emerging machine learning techniques, including deep learning, have had success with computer vision analysis. We hypothesized that computer vision with deep convolutional neural networks (DCNNs) could achieve favorable performance in identifying NM and ENE on pretreatment HNC imaging. We identified and segmented 653 lymph nodes (LN) on preoperative, diagnostic, contrast-enhanced, HNC CT scans from 270 patients with HN squamous cell carcinoma who subsequently underwent LN dissection at a single institution from 2013 - 2017. Radiographic segmentations were correlated with pathology reports and labeled as “negative”, “NM”, or “ENE.” A centralized re-review of the pathology reports documenting ENE was conducted to confirm ENE presence. A 3-dimensional DCNN was constructed using multilayer convolutional neural networks with input features consisting of normalized Hounsfield units corresponding to CT voxels within and surrounding the segmented LN. Shuffled and stratified training (64%), validation (16%), and blinded test (20%) sets were isolated a priori. The DCNN was trained using oversampling, data augmentation, dropout, regularization, and cross-validation. Performance on the blinded test set was evaluated using AUC, accuracy, sensitivity, and specificity. ENE detection performance was tested on LN samples with short axis diameter (SAD) ≥1 cm. A separate multivariable logistic regression model with bootstrapping was constructed as a benchmark comparison, using clinical characteristics and LN SAD. There were 380 negative LNs, 153 NM without ENE, and 120 NM with ENE identified and segmented. On logistic regression, clinical N-stage and greater SAD, were predictive of ENE (each P<.001) with a negative interaction between HPV-status and SAD (P<.05). Primary site (oropharynx) and SAD were predictive of NM (each P <.001). The DCNN had higher test-set performance than the benchmark logistic model for ENE (AUC: .91 vs .81, accuracy: 85.7% vs 77.7%) and NM prediction, and both models outperformed historical controls for ENE prediction (Table 1). Deep neural networks identify HNC NM and ENE with superior predictive performance than traditional logistic models and human-operator historical controls and show promise as clinician decision-making tools. External validation and prospective testing is being planned to determine the generalizability of these algorithms.Abstract 118; Table 1ENENMDCNNLogisticDCNNLogisticAUC.91.81.91.86Accuracy (%)85.777.785.576.1Sensitivity.88.72.84.79Specificity.85.80.87.74 Open table in a new tab

Detecting metastases in normal-sized pelvic lymph nodes in patients with bladder cancer: comparison of computed tomography and magnetic resonance imaging

Objective To estimate the diagnostic performance of computer tomography (CT) and magnetic resonance imaging (MRI) for detecting metastasis in pelvic lymph nodes with normal size in patients with bladder cancer. Methods Imaging of CT and MRI and clinical data of 118 patients who underwent radical cystectomy and pelvic lymphadenectomy were reviewed. The diagnostic efficacy of CT and MRI were analyzed when taking lymph nodes short axis diameter ≥0.3 cm and ≥1.0 cm respectively as diagnostic criterion of metastasis with correlation of pathological results. Results 22.7% (27/118) of patients were confirmed lymph nodes malignancies among 118 patients based on pathology. Totally 1 705 lymph nodes were detected in surgery and 119 of them were observed malignancy according to pathological presentation. The malignant nodes were mainly distributed in the perivesical (35.4%, 41/119), internal iliac (12.6%, 15/119), external iliac (30.3%, 36/119), obturator region (21.0%, 25/119) and presarcal region (1.7%, 2/119). Imaging of CT and MRI showed that when taking nodes with ≥0.3 cm in maximum short-axis diameter (MSAD) as positive, the sensitivity (Se), specificity (Sp), and positive predictive values (PPV) were 16.0%, 99.2%, 54.2% and 56.5%, 99.2%, 86.7% respectively. While taking MSAD≥1.0 cm as malignant, the Se, Sp and PPV of CT and MRI were 6.2%, 99.9%, 83.3% and 13%, 100%, 100% respectively. When taking MSAD ≥0.3 cm as positive, the Se and PPV between CT and MR were statistically different(P<0.001 and P=0.036, respectively). When taking MSAD ≥1.0 cm as positive, there was no statistically difference (P=0.275 and 1.000, respectively). Conclusions The incidence of normal-sized lymph node metastasis was higher in patients with bladder cancer. At this phase the MRI evaluation was superior to that of CT. When the MSAD ≥1.0 cm, there was no significant difference between CT and MRI. Key words: Bladder cancer; Lymph node metastasis; Computed tomography(CT); Magnetic resonance imaging(MRI); Diagnosis

Radiographic size of retroperitoneal lymph nodes predicts pathological nodal involvement for patients with renal cell carcinoma: development of a risk prediction model.

To evaluate the ability of clinical and radiographic features to predict lymph node (pN1) disease among patients with renal cell carcinoma undergoing radical nephrectomy (RN), and to develop a preoperative risk prediction model. In all, 220 patients with preoperative computed tomography scans available for review underwent RN with lymph node dissection (LND) from 2000 to 2010. Radiographic features were assessed by one genitourinary radiologist blinded to pN status. Associations of features with pN1 disease were evaluated using logistic regression to develop predictive models. Model performance was assessed using area under the receiver operating characteristic curve (AUC) and decision curve analysis. The median (interquartile range) lymph node yield was 10 (5-18). In all, 55 patients (25%) had pN1 disease at RN. On univariable analysis, the maximum lymph node (LN) short axis diameter [odds ratio (OR) 1.17; P < 0.001] predicted pN1 disease with an AUC of 0.84. Although several clinical and radiographic features were associated with pN1 disease, only two were retained in the multivariable model: maximum LN short axis diameter (OR 1.19; P <0.001) and radiographic perinephric/sinus fat invasion (OR 44.64; P = 0.01), with an AUC of 0.85. On decision curve analysis, the single variable and multivariable models showed similar net benefit. Two radiographic features, maximum LN short axis diameter and perinephric/sinus fat invasion, outperformed traditional clinical variables in predicting pN1 disease. Maximum LN short axis diameter alone showed excellent predictive performance, and, if validated externally, would provide for a simple model to guide patient selection for LND.