Roles of DWI and T2-weighted MRI volumetry in the evaluation of lymph node metastasis and lymphovascular invasion of stage IB-IIA cervical cancer

Prediction of lymph node metastasis in operable cervical cancer using clinical parameters and deep learning with MRI data: a multicentre study

OBJECTIVES

To develop and validate a magnetic resonance imaging-based (MRI) deep multiple instance learning (D-MIL) model and combine it with clinical parameters for preoperative prediction of lymph node metastasis (LNM) in operable cervical cancer.

METHODS

A total of 392 patients with cervical cancer were retrospectively enrolled. Clinical parameters were analysed by logistical regression to construct a clinical model (M1). A ResNet50 structure is applied to extract features at the instance level without using manual annotations about the tumour region and then construct a D-MIL model (M2). A hybrid model (M3) was constructed by M1 and M2 scores. The diagnostic performance of each model was evaluated by the area under the receiver operating characteristic curve (AUC) and compared using the Delong method. Disease-free survival (DFS) was evaluated by the Kaplan‒Meier method.

RESULTS

SCC-Ag, maximum lymph node short diameter (LNmax), and tumour volume were found to be independent predictors of M1 model. For the diagnosis of LNM, the AUC of the training/internal/external cohort of M1 was 0.736/0.690/0.732, the AUC of the training/internal/external cohort of M2 was 0.757/0.714/0.765, and the AUC of the training/internal/external cohort of M3 was 0.838/0.764/0.835. M3 showed better performance than M1 and M2. Through the survival analysis, patients with higher hybrid model scores had a shorter time to reach DFS.

CONCLUSION

The proposed hybrid model could be used as a personalised non-invasive tool, which is helpful for predicting LNM in operable cervical cancer. The score of the hybrid model could also reflect the DFS of operable cervical cancer.

CRITICAL RELEVANCE STATEMENT

Lymph node metastasis is an important factor affecting the prognosis of cervical cancer. Preoperative prediction of lymph node status is helpful to make treatment decisions, improve prognosis, and prolong survival time.

KEY POINTS

• The MRI-based deep-learning model can predict the LNM in operable cervical cancer. • The hybrid model has the highest diagnostic efficiency for the LNM prediction. • The score of the hybrid model can reflect the DFS of operable cervical cancer.

Clinical value of conventional magnetic resonance imaging combined with diffusion-weighted imaging in predicting pelvic lymph node metastasis of cervical cancer

Background

In cervical cancer (CC), the involvement of pelvis lymph nodes is a crucial factor for patients' outcome. We aimed to investigate the value of conventional magnetic resonance imaging (MRI) combined with diffusion-weighted imaging (DWI) and the apparent diffusion coefficient (ADC) in predicting CC pelvic lymph node metastasis (PLNM).

Methods

This retrospective study included CC patients who received surgical treatments. Surgical pathology results served as the gold standard for investigating the diagnostic performance of conventional MRI combined with DWI. We analyzed the association between tumor ADC and PLNM, as well as other pathological factors. The areas under the receiver operating characteristic curves (AUCs) for ADC in assessing PLNM and pathological factors were evaluated, and optimal cut-off points were obtained.

Results

A total of 261 CC patients were analyzed. PLNM patients had significantly lower tumor ADC (0.829 ± 0.144×10-3mm2/s vs. 1.064 ± 0.345×10-3mm2/s, p<0.0001), than non-PLNM CC. The agreement between conventional MRI combined with DWI and pathological results on PLNM diagnosis was substantial (Kappa=0.7031, p<0.0001), with 76% sensitivity, 94.31% specificity, and 90.8% accuracy. The AUC of tumor ADC was 0.703, and the optimal cut-off was 0.95×10-3 mm2/s. In multivariate analysis model 1, tumor ADC<0.95×10-3mm2/s was significantly associated with PLNM (OR, 2.83; 95%CI, 1.08-7.43; p= 0.0346) after adjusting for age and pathological risk factors. In multivariate analysis model 2, tumor ADC<0.95×10-3mm2/s (OR, 4.00; 95%CI, 1.61-9.89; p=0.0027), age<35 years old (OR, 2.93; 95%CI, 1.04-8.30; p=0.0428), increased tumor diameter on MRI (OR, 2.17; 95%CI, 1.18-3.99; p=0.0128), vaginal vault involvement on MRI (OR, 2; 95%CI, 1.002-3.99; p=0.0494) were independent predictors for PLNM. Tumor ADC<0.95×10-3mm2/s was significantly associated with higher risk of tumor diameter ≥4cm (OR, 2.60; 95%CI, 1.43-4.73; p=0.0017), muscular layer infiltration >1/2 (OR, 5.46; 95%CI, 3.19-9.34; p<0.0001), vaginal vault involvement (OR, 2.25; 95%CI, 1.28-3.96; p=0.0051), and lymphovascular space involvement (OR, 3.81; 95%CI, 2.19-6.63; p<0.0001).

Conclusion

Conventional MRI combined with DWI had a good diagnostic performance in detecting PLNM. The tumor ADC value in PLNM patients was significantly lower than that in non-PLNM patients. Tumor ADC <0.95×10-3mm2/s, age <35 years old, increased tumor diameter on MRI, vaginal vault involvement on MRI were independent predictors for PLNM.

Predicting lymphovascular invasion in rectal cancer: evaluating the performance of golden-angle radial sparse parallel MRI for rectal perfusion assessment

This study aims to determine whether the dual-parameter approach combined with either time-resolved angiography with stochastic trajectories (TWIST) or golden-angle radial sparse parallel (GRASP) and diffusion-weighted imaging (DWI) has superior diagnostic performance in predicting pathological lymphovascular invasion (pLVI) rectal cancer when compared with traditional single-parameter evaluations using DWI alone. Patients with pathologically confirmed rectal cancer were enrolled. Perfusion (influx forward volume transfer constant [Ktrans] and rate constant [Kep]) and apparent diffusion coefficient (ADC) were measured by two researchers. For both sequences, areas under receiver operating characteristic (ROCs) to predict pLVI-positive rectal cancer were compared. A total of 179 patients were enrolled in our study. A combined analysis of ADC and perfusion parameters (Ktrans) acquired with GRASP yielded a higher diagnostic performance compared with diffusion parameters alone (area under the curve, 0.91 ± 0.03 vs. 0.71 ± 0.06, P < 0.001); However, ADC with GRASP-acquired Kep and ADC with TWIST-acquired perfusion parameters (Ktrans or Kep) did not offer any additional benefit. The Ktrans of the GRASP technique improved the diagnostic performance of multiparametric MRI to predict rectal cancers with pLVI-positive. In contrast, TWIST did not achieve this effect.

Whole-Lesion Apparent Diffusion Coefficient Histogram Analysis for Assessing Normal-Sized Lymph Node Metastasis in Cervical Cancer: Comparison Between Readout-Segmented and Single-Shot Echo-Planar Diffusion-Weighted Imaging

OBJECTIVE

To compare the value of whole-lesion apparent diffusion coefficient (ADC) histogram analysis derived from readout-segmented echo-planar imaging (RS-EPI) and single-shot echo-planar imaging (SS-EPI) diffusion-weighted imaging (DWI) in evaluating normal-sized lymph node metastasis (LNM) in cervical cancer.

METHODS

Seventy-six pathologically confirmed cervical cancer patients (stages IB and IIA) were enrolled, including 61 patients with non-LNM (group A) and 15 patients with normal-sized LNM (group B). The recorded tumor volume on T2-weighted imaging was the reference against which both DWIs were evaluated. Each ADC histogram parameter (including ADCmax, ADC90, ADCmedian, ADCmean, ADC10, ADCmin, ADCskewness, ADCkurtosis, and ADCentropy) was compared between SS-EPI and RS-EPI and between the 2 groups.

RESULTS

There was no significant difference in tumor volume between the 2 DWIs and T2-weighted imaging (both P > 0.05). Higher ADCmax and ADCentropy but lower ADC10, ADCmin and ADCskewness were found in SS-EPI than those in RS-EPI (all P < 0.05). For SS-EPI, lower ADC90 and higher ADCkurtosis were found in group B than those in group A (both P < 0.05). For RS-EPI, lower ADC90 and higher ADCkurtosis and ADCentropy were found in group B than those in group A (all P < 0.05). Readout-segmented echo-planar imaging ADCkurtosis showed the highest area under the curve of 0.792 in the differentiation of the 2 groups (sensitivity, 80%; specificity, 73.77%).

CONCLUSIONS

Compared with SS-EPI, the ADC histogram parameters derived from RS-EPI were more accurate, and ADCkurtosis held great potential in differentiating normal-sized LNM in cervical cancer.

Diagnosis of Metastatic Lymph Nodes in Patients With Hepatocellular Carcinoma Using Dual-Energy Computed Tomography

OBJECTIVE

Our study aimed to investigate the role of quantitative parameters derived from dual-energy computed tomography (DECT) in discriminating metastatic from nonmetastatic lymph nodes in hepatocellular carcinoma (HCC).

METHODS

Forty-two patients (34 males; mean age, 53.7 years) with HCC underwent unenhanced computed tomography scans and triple-phase DECT scans of the upper abdomen. A total of 72 suspected lymph nodes were resected, including 43 nonmetastatic and 29 metastatic lymph nodes. The maximum short-axis diameter of the lymph nodes, iodine concentration, normalized iodine concentration (NIC), and slope of the spectral curve were analyzed for the HCC primary lesions and the suspected lymph nodes. Lymph node metastasis was confirmed by pathologic examination.

RESULTS

A maximum short-axis diameter of >10 mm had a sensitivity and a specificity of 75.9% (22/29) and 53.5% (23/43) in diagnosing metastatic lymph nodes. The iodine concentration, NIC, and slope of the spectral curve of the nonmetastatic lymph nodes were significantly higher than those of the primary HCC lesions and the metastatic lymph nodes (all P < 0.05). Among all the analyzed spectral parameters, the NIC in the arterial phase had the highest sensitivity and specificity of 88.4% and 86.2% in diagnosing metastatic lymph nodes.

CONCLUSIONS

The arterial phase NIC of DECT has superior diagnostic performance than the traditional lymph node size in diagnosing metastatic lymph nodes in HCC.