Benign and malignant enlarged chest nodes staging by diffusion-weighted MRI: an alternative to mediastinoscopy?

Whole‑body MRI for metastatic workup in patients diagnosed with cancer

Early diagnosis and appropriate staging workup are crucial for cancer patients. Whole-body magnetic resonance imaging (WB-MRI) has been proposed as another practical whole-body approach for assessing local invasiveness and distant metastases in patients newly diagnosed with cancer. The current study aimed to evaluate the efficacy of WB-MRI in assessing metastasis in patients newly diagnosed with cancer using histopathologic data as the reference method. A prospective observational study was performed from April 2018 to July 2020. MRI sequences were utilized to acquire anatomical and functional images in three orthogonal planes. The discovery was classified as nodal, skeletal and visceral metastases. Patient-based analysis was used for visceral metastasis and region-based for skeletal, systemic and lymph node metastases. A total of 43 consecutive patients (mean age, 56±15.2 years) were assessed successively. In 41 patients, there was a concordance between the WB-MRI and histological confirmation. The most prevalent site of metastasis was the skeletal system (18 patients). There were 12 individuals with liver metastasis, 10 with lung metastasis and 4 with peritoneal metastasis, with just one brain metastatic lesion found. On WB-MRI, 38 lymph node groups were deemed positive. Out of the total, 66 skeletal locations contained metastases. The accuracy of WB-MRI for nodal, skeletal and visceral metastases was (98.45, 100 and 100%, respectively). In conclusion, WB-MRI in three orthogonal planes, including the diffusion-weighted MRI with background body signal suppression sequence, may be utilized efficiently and accurately for assessing metastasis staging and may thus be utilized in patients with newly diagnosed cancer.

Diffusion-weighted magnetic resonance imaging for differentiating between benign and malignant thoracic lymph nodes: a meta-analysis

OBJECTIVE

To establish the diagnostic performance of diffusion-weighted magnetic resonance imaging (DWI) in discriminating malignant from non-malignant thoracic lymph nodes.

MATERIALS AND METHODS

This was a meta-analysis involving systematic searches of the MEDLINE, EMBASE, and Web of Science databases up through April 2020. Studies reporting thoracic DWI and lymph node evaluation were included. The pooled sensitivity, specificity, diagnostic odds ratio, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) were calculated.

RESULTS

We evaluated six studies, involving a collective total of 356 mediastinal lymph nodes in 214 patients. Thoracic DWI had a pooled sensitivity and specificity of 92% (95% confidence interval [95% CI]: 71-98%) and 93% (95% CI: 79-98%), respectively. The positive and negative likelihood ratios were 13.2 (95% CI: 4.0-43.8) and 0.09 (95% CI: 0.02-0.36), respectively. The diagnostic odds ratio was 149 (95% CI: 18-1,243), and the AUC was 0.97 (95% CI: 0.95-0.98).

CONCLUSION

DWI is a reproducible technique and has demonstrated high accuracy for differentiating between malignant and benign states in thoracic lymph nodes.

MRI-based differentiation between lymphoma and sarcoidosis in mediastinal lymph nodes

OBJECTIVE

Evaluation of enlarged mediastinal lymph nodes is crucial for patient management. Malignant lymphoma and sarcoidosis are often difficult to differentiate. Our objective was to determine the diagnostic accuracy of MRI for differentiating between sarcoidosis and malignant lymphoma.

METHODS

This was a retrospective study involving 47 patients who underwent chest MRI and were diagnosed with one of the diseases between 2017 and 2019. T1, T2, and diffusion-weighted signal intensity were measured. Apparent diffusion coefficients (ADCs) and T2 ratios were calculated. The diagnostic performance of MRI was determined by ROC analysis.

RESULTS

Mean T2 ratio was significantly lower in the sarcoidosis group than in the lymphoma group (p = 0.009). The T2-ratio cutoff value that best differentiated between lymphoma-related and sarcoidosis-related enlarged lymph nodes was 7.1, with a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 58.3%, 95.6%, 76.5%, 93.3%, and 68.7%, respectively. The mean ADC was significantly lower in the lymphoma group than in the sarcoidosis group (p = 0.002). The ADC cutoff value that best differentiated between lymphoma-related and sarcoidosis-related enlarged lymph nodes was 1.205, with a sensitivity, specificity, positive predictive value, negative predictive value and accuracy of 87.5%, 82.6%, 85.1%, 84.0% and 86.3%, respectively. No significant differences were found between the two groups regarding T1 signal intensity, T2 signal intensity, and lymph node diameter.

CONCLUSIONS

MRI parameters such as ADC, diffusion, and T2 ratio can be useful in the differentiation between sarcoidosis and lymphoma in the evaluation of enlarged lymph nodes.

Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients

Evaluate whether texture analysis associated with machine learning approaches could differentiate between malignant and benign lymph nodes. A total 18 patients with lung cancer were selected, with 39 lymph nodes, being 15 malignant and 24 benign. Retrospective computed tomography scans were utilized both with and without contrast medium. The great differential of this work was the use of 15 textures from mediastinal lymph nodes, with five different physicians as operators. First and second order statistical textures such as gray level run length and co-occurrence matrix were extracted and applied to three different machine learning classifiers. The best machine learning classifier demonstrated a variability of less than 5% among operators. The support vector machine (SVM) classifier presented 95% of the area under the ROC curve (AUC) and 89% of sensitivity for sequences without contrast medium. SVM classifier presented 93% of AUC and 86% of sensitivity for sequences with contrast medium. Texture analysis and machine learning may be helpful in the differentiation between malign and benign lymph nodes. This study can aid the physician in diagnosis and staging of lymph nodes and potentially reduce the number of invasive analysis to histopathological confirmation.