Economic Benefits and Diagnostic Quality of Diffusion-Weighted Magnetic Resonance Imaging for Primary Lung Cancer

Sarcomatoid pleural mesothelioma evaluated using diffusion-weighted whole-body imaging with background body signal suppression

An 83-year-old man with a history of asbestos exposure presented with dyspnea. Thoracic computed tomography showed right-sided pleural effusion and heterogeneous pleural thickening with calcified plaques. Thoracentesis revealed exudative fluid, and the cytology results were negative for malignancy. He didn't want to undergo invasive biopsy for pathological diagnosis. Diffusion-weighted whole-body imaging with background body signal suppression (DWIBS) detected signal enhancement in the pleural thickening, ruling out metastasis. The patient died after one month, and sarcomatoid pleural mesothelioma was confirmed by autopsy. DWIBS is free of radioactive materials and can be used to evaluate lesion spread and metastases in hospitals equipped with magnetic resonance imaging.

Accelerated Diffusion-Weighted MR Image Reconstruction Using Deep Neural Networks

Under-sampling in diffusion-weighted imaging (DWI) decreases the scan time that helps to reduce off-resonance effects, geometric distortions, and susceptibility artifacts; however, it leads to under-sampling artifacts. In this paper, diffusion-weighted MR image (DWI-MR) reconstruction using deep learning (DWI U-Net) is proposed to recover artifact-free DW images from variable density highly under-sampled k-space data. Additionally, different optimizers, i.e., RMSProp, Adam, Adagrad, and Adadelta, have been investigated to choose the best optimizers for DWI U-Net. The reconstruction results are compared with the conventional Compressed Sensing (CS) reconstruction. The quality of the recovered images is assessed using mean artifact power (AP), mean root mean square error (RMSE), mean structural similarity index measure (SSIM), and mean apparent diffusion coefficient (ADC). The proposed method provides up to 61.1%, 60.0%, 30.4%, and 28.7% improvements in the mean AP value of the reconstructed images in our experiments with different optimizers, i.e., RMSProp, Adam, Adagrad, and Adadelta, respectively, as compared to the conventional CS at an acceleration factor of 6 (i.e., AF = 6). The results of DWI U-Net with the RMSProp, Adam, Adagrad, and Adadelta optimizers show 13.6%, 10.0%, 8.7%, and 8.74% improvements, respectively, in terms of mean SSIM with respect to the conventional CS at AF = 6. Also, the proposed technique shows 51.4%, 29.5%, 24.04%, and 18.0% improvements in terms of mean RMSE using the RMSProp, Adam, Adagrad, and Adadelta optimizers, respectively, with reference to the conventional CS at AF = 6. The results confirm that DWI U-Net performs better than the conventional CS reconstruction. Also, when comparing the different optimizers in DWI U-Net, RMSProp provides better results than the other optimizers.

Radiomics model of diffusion-weighted whole-body imaging with background signal suppression (DWIBS) for predicting axillary lymph node status in breast cancer

BACKGROUND

In breast cancer diagnosis and treatment, non-invasive prediction of axillary lymph node (ALN) metastasis can help avoid complications related to sentinel lymph node biopsy.

OBJECTIVE

This study aims to develop and evaluate machine learning models using radiomics features extracted from diffusion-weighted whole-body imaging with background signal suppression (DWIBS) examination for predicting the ALN status.

METHODS

A total of 100 patients with histologically proven, invasive, clinically N0 breast cancer who underwent DWIBS examination consisting of short tau inversion recovery (STIR) and DWIBS sequences before surgery were enrolled. Radiomic features were calculated using segmented primary lesions in DWIBS and STIR sequences and were divided into training (n = 75) and test (n = 25) datasets based on the examination date. Using the training dataset, optimal feature selection was performed using the least absolute shrinkage and selection operator algorithm, and the logistic regression model and support vector machine (SVM) classifier model were constructed with DWIBS, STIR, or a combination of DWIBS and STIR sequences to predict ALN status. Receiver operating characteristic curves were used to assess the prediction performance of radiomics models.

RESULTS

For the test dataset, the logistic regression model using DWIBS, STIR, and a combination of both sequences yielded an area under the curve (AUC) of 0.765 (95% confidence interval: 0.548-0.982), 0.801 (0.597-1.000), and 0.779 (0.567-0.992), respectively, whereas the SVM classifier model using DWIBS, STIR, and a combination of both sequences yielded an AUC of 0.765 (0.548-0.982), 0.757 (0.538-0.977), and 0.779 (0.567-0.992), respectively.

CONCLUSIONS

Use of machine learning models incorporating with the quantitative radiomic features derived from the DWIBS and STIR sequences can potentially predict ALN status.

Auxiliary Diagnosis of Lung Cancer with Magnetic Resonance Imaging Data under Deep Learning

This study was aimed at two image segmentation methods of three-dimensional (3D) U-shaped network (U-Net) and multilevel boundary sensing residual U-shaped network (RUNet) and their application values on the auxiliary diagnosis of lung cancer. In this study, on the basis of the 3D U-Net segmentation method, the multilevel boundary sensing RUNet was worked out after optimization. 92 patients with lung cancer were selected, and their clinical data were counted; meanwhile, the lung nodule detection was performed to obtain the segmentation effect under 3D U-Net. The accuracy of 3D U-Net and multilevel boundary sensing RUNet was compared on lung magnetic resonance imaging (MRI) after lung nodule segmentation. Patients with benign lung tumors were taken as controls; the blood immune biochemical indicators progastrin-releasing peptide (pro-CRP), carcinoembryonic antigen (CEA), and neuron-specific enolase (NSE) in patients with malignant lung tumors were analyzed. It was found that the accuracy, sensitivity, and specificity were all greater than 90% under the algorithm-based MRI of benign and malignant tumor patients. Based on the imaging signs for the MRI image of lung nodules, the segmentation effect of the RUNet was clearer than that of the 3D U-Net. In addition, serum levels of pro-CRP, NSE, and CAE in patients with benign lung tumors were 28.9 pg/mL, 12.5 ng/mL, and 10.8 ng/mL, respectively, which were lower than 175.6 pg/mL, 33.6 ng/mL, and 31.9 ng/mL in patients with malignant lung tumors significantly (P < 0.05). Thus, the RUNet image segmentation method was better than the 3D U-Net. The pro-CRP, CEA, and NSE could be used as diagnostic indicators for malignant lung tumors.

Low-Field Magnetic Resonance Imaging: Its History and Renaissance

ABSTRACT

Low-field magnetic resonance imaging (MRI) systems have seen a renaissance recently due to improvements in technology (both hardware and software). Originally, the performance of low-field MRI systems was rated lower than their actual clinical usefulness, and they were viewed as low-cost but poorly performing systems. However, various applications similar to high-field MRI systems (1.5 T and 3 T) have gradually become possible, culminating with high-performance low-field MRI systems and their adaptations now being proposed that have unique advantages over high-field MRI systems in various aspects. This review article describes the physical characteristics of low-field MRI systems and presents both their advantages and disadvantages for clinical use (past to present), along with their cutting-edge clinical applications.

Development and Validation of a Combined Model for Preoperative Prediction of Lymph Node Metastasis in Peripheral Lung Adenocarcinoma

Background

Based on the “seed and soil” theory proposed by previous studies, we aimed to develop and validate a combined model of machine learning for predicting lymph node metastasis (LNM) in patients with peripheral lung adenocarcinoma (PLADC).

Methods

Radiomics models were developed in a primary cohort of 390 patients (training cohort) with pathologically confirmed PLADC from January 2016 to August 2018. The patients were divided into the LNM (−) and LNM (+) groups. Thereafter, the patients were subdivided according to TNM stages N0, N1, N2, and N3. Radiomic features from unenhanced computed tomography (CT) were extracted. Radiomic signatures of the primary tumor (R1) and adjacent pleura (R2) were built as predictors of LNM. CT morphological features and clinical characteristics were compared between both groups. A combined model incorporating R1, R2, and CT morphological features, and clinical risk factors was developed by multivariate analysis. The combined model’s performance was assessed by receiver operating characteristic (ROC) curve. An internal validation cohort containing 166 consecutive patients from September 2018 to November 2019 was also assessed.

Results

Thirty-one radiomic features of R1 and R2 were significant predictors of LNM (all P < 0.05). Sex, smoking history, tumor size, density, air bronchogram, spiculation, lobulation, necrosis, pleural effusion, and pleural involvement also differed significantly between the groups (all P < 0.05). R1, R2, tumor size, and spiculation in the combined model were independent risk factors for predicting LNM in patients with PLADC, with area under the ROC curves (AUCs) of 0.897 and 0.883 in the training and validation cohorts, respectively. The combined model identified N0, N1, N2, and N3, with AUCs ranging from 0.691–0.927 in the training cohort and 0.700–0.951 in the validation cohort, respectively, thereby indicating good performance.

Conclusion

CT phenotypes of the primary tumor and adjacent pleura were significantly associated with LNM. A combined model incorporating radiomic signatures, CT morphological features, and clinical risk factors can assess LNM of patients with PLADC accurately and non-invasively.

The Value of PETRA in Pulmonary Nodules of <3 cm Among Patients With Lung Cancer

Objective

This study aimed to evaluate the visibility of different subgroups of lung nodules of <3 cm using the pointwise encoding time reduction with radial acquisition (PETRA) sequence on 3T magnetic resonance imaging (MRI) in comparison with that obtained using low-dose computed tomography (LDCT).

Methods

The appropriate detection rate was calculated for each of the different subgroups of lung nodules of <3 cm. The mean diameter of each detected nodule was determined. The detection rates and diameters of the lung nodules detected by MRI with the PETRA sequence were compared with those detected by computed tomography (CT). The sensitivity of detection for the different subgroups of pulmonary nodules was determined based on the location, size, type of nodules and morphologic characteristics. Agreement of nodule characteristics between CT and MRI were assessed by intraclass correlation coefficient (ICC) and Kappa test.

Results

The CT scans detected 256 lung nodules, comprising 99 solid nodules (SNs) and 157 subsolid nodules with a mean nodule diameter of 8.3 mm. For the SNs, the MRI detected 30/47 nodules of <6 mm in diameter and 52/52 nodules of ≥6 mm in diameter. For the subsolid nodules, the MRI detected 30/51 nodules of <6 mm in diameter and 102/106 nodules of ≥6 mm in diameter. The PETRA sequence returned a high detection rate (84%). The detection rates of SN, ground glass nodules, and PSN were 82%, 72%, and 94%, respectively. For nodules with a diameter of >6 mm, the sensitivity of the PETRA sequence reached 97%, with a higher rate for nodules located in the upper lung fields than those in the middle and lower lung fields. Strong agreement was found between the CT and PETRA results (correlation coefficients = 0.97).

Conclusion

The PETRA technique had high sensitivity for different type of nodule detection and enabled accurate assessment of their diameter and morphologic characteristics. It may be an effective alternative to CT as a tool for screening and follow up pulmonary nodules.

Diffusion-weighted whole-body imaging with background suppression (DWIBS) is effective and economical for detection of metastasis or recurrence of lung cancer

BACKGROUND

Diffusion-weighted whole-body imaging with background suppression (DWIBS) is used for the diagnosis and staging of cancers. The medical cost of an MR examination including DWIBS is $123, which is 80% less expensive than the cost ($798) of F18-fluorodeoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) examination.

METHODS

This study examined the efficacy of DWIBS for relapses after lung cancer resection. A total of 55 patients who had pulmonary resection of lung cancer, postoperative computed tomography (CT) every six months, and DWIBS and FDG-PET/CT (every year) were enrolled in this study. If a metastatic lesion was detected on CT scan, DWIBS and FDG-PET/CT were also used.

RESULTS

A total of 55 patients who underwent pulmonary resections for lung cancer, and had CT, DWIBS and FDG-PET/CT examination during follow-up after pulmonary resection were enrolled in this study. Lung cancer in 32 patients relapsed. Postoperative radiographic examinations revealed pulmonary metastases in 17 patients, bone metastases in seven, liver metastases in five, lymph node metastases in five, pleural metastases in four, metastases to the chest wall in two, brain metastases in two, adrenal gland metastasis in one, and renal metastasis in one. The mean apparent diffusion coefficient (ADC) value of the relapse was 0.9 to 1.70 × 10^-3 mm² /s. The accuracy 0.98 (54/55) of DWIBS for detecting multiple metastatic lesions was likely to be higher than 0.94 (52/55) of CT or 0.94 (52/55) of FDG-PET/CT, but there were no significant differences.

CONCLUSIONS

DWIBS can detect multiple metastatic lesions throughout the entire body and differentiate malignancy from benignity in only one examination. DWIBS has benefits of diagnostic accuracy and is less expensive in medical costs for the detection of a relapse. DWIBS could potentially replace FDG-PET/CT after lung cancer resection.

Magnetic particle targeting for diagnosis and therapy of lung cancers

Over the past decade, the growing interest in targeted lung cancer therapy has guided researchers toward the cutting edge of controlled drug delivery, particularly magnetic particle targeting. Targeting of tissues by magnetic particles has tackled several limitations of traditional drug delivery methods for both cancer detection (e.g., using magnetic resonance imaging) and therapy. Delivery of magnetic particles offers the key advantage of high efficiency in the local deposition of drugs in the target tissue with the least harmful effect on other healthy tissues. This review first overviews clinical aspects of lung morphology and pathogenesis as well as clinical features of lung cancer. It is followed by reviewing the advances in using magnetic particles for diagnosis and therapy of lung cancers: (i) a combination of magnetic particle targeting with MRI imaging for diagnosis and screening of lung cancers, (ii) magnetic drug targeting (MDT) through either intravenous injection and pulmonary delivery for lung cancer therapy, and (iii) computational simulations that models new and effective approaches for magnetic particle drug delivery to the lung, all supporting improved lung cancer treatment. The review further discusses future opportunities to improve the clinical performance of MDT for diagnosis and treatment of lung cancer and highlights clinical therapy application of the MDT as a new horizon to cure with minimal side effects a wide variety of lung diseases and possibly other acute respiratory syndromes (COVID-19, MERS, and SARS).

18F-FDG PET/CT and whole-body MRI diagnostic performance in M staging for non-small cell lung cancer: a systematic review and meta-analysis

OBJECTIVES

To evaluate the diagnostic test accuracy of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT), whole-body magnetic resonance imaging (WB-MRI), and whole-body diffusion-weighted imaging (WB-DWI) for the detection of metastases in patients with non-small cell lung cancer (NSCLC).

METHODS

MEDLINE, Embase, and Cochrane Library databases were searched up to June 2019. Studies were selected if they reported data that could be used to construct contingency tables to compare 18F-FDG PET/CT, WB-MRI, and WB-DWI. Two authors independently extracted data on study characteristics and assessed methodological quality using the Quality Assessment of Diagnostic Accuracy Studies. Forest plots were generated for sensitivity and specificity of 18F-FDG PET/CT, WB-MRI, and whole-body diffusion-weighted imaging (WB-DWI). Summary receiver operating characteristic plots were created.

RESULTS

The 4 studies meeting inclusion criteria had a total of 564 patients and 559 lesions, 233 of which were metastases. In studies of 18F-FDG PET/CT, the pooled estimates of sensitivity and specificity were 0.83 (95% confidence interval [CI], 0.54-0.95) and 0.93 (95% CI, 0.87-0.96), respectively. For WB-MRI, pooled sensitivity was 0.92 (95% CI, 0.18-1.00) and pooled specificity was 0.93 (95% CI, 0.85-0.95). Pooled sensitivity and specificity for WB-DWI were 0.78 (95% CI, 0.46-0.93) and 0.91 (95% CI, 0.79-0.96), respectively. There was no statistical difference between the diagnostic odds ratio of WB-MRI and WB-DWI compared with that of PET/CT (p = 0.186 for WB-DWI; p = 0.638 for WB-MRI).

CONCLUSION

WB-MRI and DWI are radiation-free alternatives with comparable diagnostic performance to 18F-FDG PET/CT for M staging of NSCLC.

KEY POINTS

• Whole-body MRI with or without diffusion-weighted imaging has a high accuracy for the diagnostic evaluation of metastases in patients with non-small cell lung cancer. • Whole-body MRI may be used as a non-invasive and radiation-free alternative to positron emission tomography with CT with similar diagnostic performance.

Diffusion-Weighted Magnetic Resonance Imaging for Early Detection of Chemotherapy Resistance in Non-Small Cell Lung Cancer

Background

The aim of this study was to examine the role of magnetic resonance imaging-diffusion weighted imaging (MRI-DWI) in the early detection of chemotherapy resistance in non-small cell lung cancer (NSCLC) patients.

Material/Methods

MRI-DWI and computed tomography (CT) were carried out in 75 patients with newly diagnostic NSCLC before and after first, second, fourth, and sixth cycles of chemotherapy. Resistance to chemotherapy was assessed based on the change in the largest tumor diameter after chemotherapy. Diffusion of water molecule in each lesion was quantitatively measured by apparent diffusion coefficient (ADC). The diagnostic results of DWI after first and second cycle of chemotherapy were analyzed by the area under receiver operating characteristics curve (ROC).

Results

Among the patients, 43 patients were chemo-resistance while 32 patients were chemo-sensitive. The ADC changing rate between second and first cycle of chemotherapy was significantly higher in chemo-sensitive patients compared with chemo-resistance patients (t=3.236, P=0.002). The ROC showed cutoff values of the ADC changing rate after first and second cycles of chemotherapy for resistance/sensitive discrimination were 23.6% and 5.56%, respectively. DWI after first and second cycles of therapy showed sensitivities of 55.8% and 55.8%, specificities of 65.6% and 87.5%, and area under ROC of 0.568 and 0.733, respectively.

Conclusions

ADC changing rate between first and second cycles of chemotherapy could sensitively distinguish chemo-sensitive and chemo-resistant tumors at earlier stages, which may direct treatment adjustment and improve the prognosis of patients.

The many (sur)faces of B cells

This issue of the Biomedical Journal is dedicated to the latest findings concerning the complex development and functions of B lymphocytes, including their origins during embryogenesis, their meticulous control by the CD22 receptor and different types of T cells, as well as the immunosuppressive abilities of certain B cell subsets. Furthermore, we learn about the complicated genetic background of a rare cardiac disease, the surgical outcomes of pure conus medullaris syndrome and occurrences of tuberculous spondylitis after percutaneous vertebroplasty. Finally, we discover that brain waves could very well be used for biometric authentication and that diffusion imaging displays good reproducibility through a spectrum of spatial resolutions.

[Diffusion-weighted imaging-diagnostic supplement or alternative to contrast agents in early detection of malignancies?]

Medical research in the field of oncologic imaging diagnostics using magnetic resonance imaging increasingly includes diffusion-weighted imaging (DWI) sequences. The DWI sequences allow insights into different microstructural diffusion properties of water molecules in tissues depending on the sequence modification used and enable visual and quantitative analysis of the acquired imaging data. In DWI, the application of intravenous gadolinium-containing contrast agents is unnecessary and only the mobility of naturally occurring water molecules in tissues is quantified. These characteristics predispose DWI as a potential candidate for emerging as an independent diagnostic tool in selected cases and specific points in question. Current clinical diagnostic studies and the ongoing technical developments, including the increasing influence of artificial intelligence in radiology, support the growing importance of DWI. Especially with respect to selective approaches for early detection of malignancies, DWI could make an essential contribution as an eligible diagnostic tool; however, prior to discussing a broader clinical implementation, challenges regarding reliable data quality, standardization and quality assurance must be overcome.

Can MRI contribute to pulmonary nodule analysis?

BACKGROUND

There is no accurate method distinguishing different types of pulmonary nodules.

PURPOSE

To investigate whether multiparametric 3T MRI biomarkers can distinguish malignant from benign pulmonary nodules, differentiate different types of neoplasms, and compare MRI-derived measurements with values from commonly used noninvasive imaging modalities.

STUDY TYPE

Prospective.

SUBJECTS

Sixty-eight adults with pulmonary nodules undergoing resection.

SEQUENCES

Respiratory triggered diffusion-weighted imaging (DWI), periodically rotated overlapping parallel lines with enhanced reconstruction (PROPELLER) fat saturated T₂ -weighted imaging, T₁ -weighted 3D volumetric interpolated breath-hold examination (VIBE) using CAIPIRINHA (controlled aliasing in parallel imaging results in a higher acceleration).

ASSESSMENT/STATISTICS

Apparent diffusion coefficient (ADC), T₁ , T₂ , T₁ and T₂ normalized to muscle (T₁ /M and T₂ /M), and dynamic contrast enhancement (DCE) values were compared with histology to determine whether they could distinguish malignant from benign nodules and discern primary from secondary malignancies using logistic regression. Predictability of primary neoplasm types was assessed using two-sample t-tests. MRI values were compared with positron emission tomography / computed tomography (PET/CT) to examine if they correlated with standardized uptake value (SUV) or CT Hounsfield unit (HU). Intra- and interreader agreements were assessed using intraclass correlations.

RESULTS

Forty-nine of 74 nodules were malignant. There was a significant association between ADC and malignancy (odds ratio 4.47, P < 0.05). ADC ≥1.3 μm² /ms predicted malignancy. ADC, T₁ , and T₂ together predicted malignancy (P = 0.003). No MRI parameter distinguished primary from metastatic neoplasms. T₂ predicted PET positivity (P = 0.016). T₂ and T₁ /M correlated with SUV (P < 0.05). Of 18 PET-negative malignant nodules, 12 (67%) had an ADC ≥1.3 μm² /ms. With the exception of T₂ , all noncontrast MRI parameters distinguished adenocarcinomas from carcinoid tumors (P < 0.05). T₁ , T₂ , T₁ /M, and T₂ /M correlated with HU and therefore can predict nodule density. Combined with ADC, washout enhancement, arrival time (AT), peak enhancement intensity (PEI), K^trans , K_ep , V_e collectively were predictive of malignancy (P = 0.012). Combined washin, washout, time to peak (TTP), AT, and PEI values predicted malignancy (P = 0.043). There was good observer agreement for most noncontrast MRI biomarkers.

DATA CONCLUSION

MRI can contribute to pulmonary nodule analysis. Multiparametric MRI might be better than individual MRI biomarkers in pulmonary nodule risk stratification.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018.