Diagnosis of Spinal Lesions Using Heuristic and Pharmacokinetic Parameters Measured by Dynamic Contrast-Enhanced MRI

Contrast-enhanced magnetic resonance image segmentation based on improved U-Net and Inception-ResNet in the diagnosis of spinal metastases

Objective

The objective of this study was to investigate the use of contrast-enhanced magnetic resonance imaging (CE-MRI) combined with radiomics and deep learning technology for the identification of spinal metastases and primary malignant spinal bone tumor.

Methods

The region growing algorithm was utilized to segment the lesions, and two parameters were defined based on the region of interest (ROI). Deep learning algorithms were employed: improved U-Net, which utilized CE-MRI parameter maps as input, and used 10 layers of CE images as input. Inception-ResNet model was used to extract relevant features for disease identification and construct a diagnosis classifier.

Results

The diagnostic accuracy of radiomics was 0.74, while the average diagnostic accuracy of improved U-Net was 0.98, respectively. the PA of our model is as high as 98.001%. The findings indicate that CE-MRI based radiomics and deep learning have the potential to assist in the differential diagnosis of spinal metastases and primary malignant spinal bone tumor.

Conclusion

CE-MRI combined with radiomics and deep learning technology can potentially assist in the differential diagnosis of spinal metastases and primary malignant spinal bone tumor, providing a promising approach for clinical diagnosis.

Subregional radiomics analysis for the detection of the EGFR mutation on thoracic spinal metastases from lung cancer

The present study intended to use radiomic analysis of spinal metastasis subregions to detect epidermal growth factor receptor (EGFR) mutation. In total, 94 patients with thoracic spinal metastasis originated from primary lung adenocarcinoma (2017-2020) were studied. All patients underwent T1-weighted (T1W) and T2 fat-suppressed (T2FS) MRI scans. The spinal metastases (tumor region) were subdivided into phenotypically consistent subregions based on patient- and population-level clustering: Three subregions, S1, S2 and S3, and the total tumor region. Radiomics features were extracted from each subregion and from the whole tumor region as well. Least shrinkage and selection operator (LASSO) regression were used for feature selection and radiomics signature definition. Detection performance of S3 was better than all other regions using T1W (AUCs, S1 versus S2 versus S3 versus whole tumor, 0.720 versus 0.764 versus 0.786 versus 0.758) and T2FS (AUCs, S1 versus S2 versus S3 versus whole tumor, 0.791 versus 0.708 versus 0.838 versus 0.797) MRI. The multi-regional radiomics signature derived from the joint of inner subregion S3 from T1W and T2FS MRI achieved the best detection capabilities with AUCs of 0.879 (ACC = 0.774, SEN = 0.838, SPE = 0.840) and 0.777 (ACC = 0.688, SEN = 0.947, SPE = 0.615) in the training and test sets, respectively. Our study revealed that MRI-based radiomic analysis of spinal metastasis subregions has the potential to detect the EGFR mutation in patients with primary lung adenocarcinoma.

Differentiating Between Multiple Myeloma and Metastasis Subtypes of Lumbar Vertebra Lesions Using Machine Learning-Based Radiomics

Objective

To determine whether machine learning based on conventional magnetic resonance imaging (MRI) sequences have the potential for the differential diagnosis of multiple myeloma (MM), and different tumor metastasis lesions of the lumbar vertebra.

Methods

We retrospectively enrolled 107 patients newly diagnosed with MM and different metastasis of the lumbar vertebra. In total 60 MM lesions and 118 metastasis lesions were selected for training classifiers (70%) and subsequent validation (30%). Following segmentation, 282 texture features were extracted from both T1WI and T2WI images. Following regression analysis using the least absolute shrinkage and selection operator (LASSO) algorithm, the following machine learning models were selected: Support‐Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Artificial Neural Networks (ANN), and Naïve Bayes (NB) using 10-fold cross validation, and the performances were evaluated using a confusion matrix. Matthews correlation coefficient (MCC), sensitivity, specificity, and accuracy of the models were also calculated.

Results

To differentiate MM and metastasis, 13 features in the T1WI images and 9 features in the T2WI images were obtained. Among the 10 classifiers, the ANN classifier from the T2WI images achieved the best performance (MCC = 0.605) with accuracy, sensitivity, and specificity of 0.815, 0.879, and 0.790, respectively, in the validation cohort. To differentiate MM and metastasis subtypes, eight features in the T1WI images and seven features in the T2WI images were obtained. Among the 10 classifiers, the ANN classifier from the T2WI images achieved the best performance (MCC = 0.560, 0.412, 0.449), respectively, with accuracy = 0.648; sensitivity 0.714, 0.821, 0.897 and specificity 0.775, 0.600, 0.640 for the MM, lung, and other metastases, respectively, in the validation cohort.

Conclusions

Machine learning–based classifiers showed a satisfactory performance in differentiating MM lesions from those of tumor metastasis. While their value for distinguishing myeloma from different metastasis subtypes was moderate.

[CT spectral curve in differentiating spinal tumor metastasis and infections]

OBJECTIVE

To evaluate the value of CT spectral curve in differentiating spinal tumor metastasis (STM) from spinal infections (SI).

METHODS

In the study, 29 STM and 18 SI patients proved pathologically and clinically were examined by dual energy spectral CT (DESCT). The monochromatic images and CT spectral curves were generated automatically by GSI Viewer software. The attenuation values at different energy levels (40-140 keV, every 10 keV), the attenuation values of the lesions on the conventional polychromatic CT images and the gradients of the curve were calculated and compared between STM and SI.

RESULTS

The median age of STM and SI (58 years vs. 64 years) were not significantly different (U=171, P=0.4). The attenuation values of STM at 40-100 keV were 281.79 (143.67, 446.19) HU, 199.68 (100.04, 321.49) HU, 151.54 (81.47, 243.49) HU, (122.64±27.72) HU, (99.90±23.88) HU, (85.82±21.61) HU, and (75.94±20.27) HU, respectively, which were significantly higher than SI: 185.29 (164.19, 277.03) HU, 138.44 (124.98, 238.56) HU, 105.46 (92.94, 169.53) HU, (93.77±15.55) HU, (79.15±12.84) HU, (68.99±11.75) HU, and (62.22±11.71) HU (all P < 0.05). The attenuation values at 110-140 keV and the attenuation value on the conventional CT images were not significantly different between STM and SI. The gradient of CT spectral curve of STM was 2.43±0.58, which was higher than the value of 1.50±0.40 for SI (P < 0.001). Using 1.72 and 248.80 HU as the threshold value for CT spectral curve slope and the attenuation value at 40 keV, could obtain the area under receiver operating characteristic (ROC) curve of 0.905 and 0.892, sensitivity of 88.0% and 80.0%, and specificity of 76.9% and 92.3%.

CONCLUSION

CT spectral curve provides valuable semi-quantitative information for the differential diagnosis of STM and SI, which can be used as a supplement to traditional CT imaging.

Rapid-kilovoltage-switching dual-energy computed tomography (CT) for differentiating spinal osteolytic metastases from spinal infections

Background

Rapid-kilovoltage-switching dual-energy computed tomography (RDECT) is a non-invasive, alternative technique for quantitative diagnosis. This study aimed to investigate the value of RDECT for differentiating spinal osteolytic metastases (SOM) from spinal infections (SIs).

Methods

RDECT was performed on 29 patients with SOM and 18 patients with SIs. Both iodine-based and water-based material decomposition images were generated from the spectral CT scan. The iodine/water densities of lesions on iodine/water material-decomposition images and the CT attenuation values on traditional CT images were measured three times at different image levels, and the averages were calculated. The lesion-to-muscle ratio (LMR) and lesion-to-artery ratio (LAR) for iodine density measurements were calculated. All parameters were compared between the two groups using the two-tailed Student's t-test. A P value <0.05 was considered statistically significant. The sensitivity and specificity for differentiating SOM from SIs were determined using receiver operating characteristic curves (ROC).

Results

Iodine density, LMR, and LAR during the arterial phase (AP) and venous phase (VP) were all significantly higher for SOM than for SIs (all P<0.05). The water densities and traditional CT attenuation values during the AP and VP were not significantly different between the two groups. For ROC analysis, LAR during the VP (LAR_VP) showed the best diagnostic performance, with an area under the ROC curve (AUC) value of 0.862. When the LARVP was 0.54, the sensitivity was 82.80% and the specificity was 77.80% for differentiating SOM from SIs.

Conclusions

RDECT can provide additional information that may be useful for differentiating atypical SOM from SIs.

The Value of Quantitative Musculoskeletal Imaging

Musculoskeletal imaging is mainly based on the subjective and qualitative analysis of imaging examinations. However, integration of quantitative assessment of imaging data could increase the value of imaging in both research and clinical practice. Some imaging modalities, such as perfusion magnetic resonance imaging (MRI), diffusion MRI, or T2 mapping, are intrinsically quantitative. But conventional morphological imaging can also be analyzed through the quantification of various parameters. The quantitative data retrieved from imaging examinations can serve as biomarkers and be used to support diagnosis, determine patient prognosis, or monitor therapy.

We focus on the value, or clinical utility, of quantitative imaging in the musculoskeletal field. There is currently a trend to move from volume- to value-based payments. This review contains definitions and examines the role that quantitative imaging may play in the implementation of value-based health care. The influence of artificial intelligence on the value of quantitative musculoskeletal imaging is also discussed.

Diagnosis of spinal lesions using perfusion parameters measured by DCE-MRI and metabolism parameters measured by PET/CT

PURPOSE

To investigate the correlation of parameters measured by dynamic-contrast-enhanced MRI (DCE-MRI) and ¹⁸F-FDG PET/CT in spinal tumors, and their role in differential diagnosis.

METHODS

A total of 49 patients with pathologically confirmed spinal tumors, including 38 malignant, six benign and five borderline tumors, were analyzed. The MRI and PET/CT were done within 3 days, before biopsy. On MRI, the ROI was manually placed on area showing the strongest enhancement to measure pharmacokinetic parameters K^trans and k_ep. On PET, the maximum standardized uptake value SUV_max was measured. The parameters in different histological groups were compared. ROC was performed to differentiate between the two largest subtypes, metastases and plasmacytomas. Spearman rank correlation was performed to compare DCE-MRI and PET/CT parameters.

RESULTS

The K^trans, k_ep and SUV_max were not statistically different among malignant, benign and borderline groups (P = 0.95, 0.50, 0.11). There was no significant correlation between K^trans and SUV_max (r = - 0.20, P = 0.18), or between k_ep and SUV_max (r = - 0.16, P = 0.28). The k_ep was significantly higher in plasmacytoma than in metastasis (0.78 ± 0.17 vs. 0.61 ± 0.18, P = 0.02); in contrast, the SUV_max was significantly lower in plasmacytoma than in metastasis (5.58 ± 2.16 vs. 9.37 ± 4.26, P = 0.03). In differential diagnosis, the AUC of k_ep and SUV_max was 0.79 and 0.78, respectively.

CONCLUSIONS

The vascular parameters measured by DCE-MRI and glucose metabolism measured by PET/CT from the most aggressive tumor area did not show a significant correlation. The results suggest they provide complementary information reflecting different aspects of the tumor, which may aid in diagnosis of spinal lesions. These slides can be retrieved under Electronic Supplementary Material.

Differentiation of spinal metastases originated from lung and other cancers using radiomics and deep learning based on DCE-MRI

PURPOSE

To differentiate metastatic lesions in the spine originated from primary lung cancer and other cancers using radiomics and deep learning, compared to traditional hot-spot ROI analysis.

METHODS

In a retrospective review of clinical spinal MRI database with a dynamic contrast enhanced (DCE) sequence, a total of 61 patients without prior cancer diagnosis and later confirmed to have metastases (30 lung; 31 non-lung cancers) were identified. For hot-spot analysis, a manual ROI was placed to calculate three heuristic parameters from the wash-in, maximum, and wash-out phases in the DCE kinetics. For each case, the 3D tumor mask was generated by using the normalized-cut algorithm. Radiomics analysis was performed to extract histogram and texture features from three DCE parametric maps. Deep learning was performed using these maps as inputs into a conventional convolutional neural network (CNN), as well as using all 12 sets of DCE images into a convolutional long short term memory (CLSTM) network.

RESULTS

For hot-spot ROI analysis, mean wash-out slope was 0.25 ± 10% for lung metastases and -9.8 ± 12.9% for other tumors. CHAID classification using a wash-out slope of -6.6% followed by wash-in enhancement ratio of 98% achieved a diagnostic accuracy of 0.79. Radiomics analysis using features representing tumor heterogeneity only reached the highest accuracy of 0.71. Classification using CNN achieved a mean accuracy of 0.71 ± 0.043, whereas a CLSTM improved accuracy to 0.81 ± 0.034.

CONCLUSIONS

DCE-MRI machine-learning analysis methods have potential to predict lung cancer metastases in the spine, which may be used to guide subsequent workup for confirmed diagnosis.