Improving lymph node characterization in staging malignant lymphoma using first-order ADC texture analysis from whole-body diffusion-weighted MRI

Histogram Analysis Based on Apparent Diffusion Coefficient Maps of Bone Marrow in Multiple Myeloma: An Independent Predictor for High-risk Patients Classified by the Revised International Staging System

RATIONALE AND OBJECTIVES

The revised International Staging System (R-ISS) is the current risk stratifier for patients with newly diagnosed multiple myeloma (NDMM). We used histogram analysis based on apparent diffusion coefficient (ADC) maps of bone marrow to predict high-risk NDMM patients staged as R-ISS stage III.

MATERIAL AND METHODS

Sixty-one NDMM patients were recruited prospectively and underwent whole-body diffusion-weighted MRI. Mean ADC and four ADC-based histogram parameters of representative background bone marrow were quantified with TexRAD software, including ADC entropy, ADC standard deviation (SD), ADC skewness and ADC kurtosis. Diagnostic performance to discriminate R-ISS III from I/II disease was evaluated by receiver-operating characteristics curve (ROC). Univariate and multivariate analysis using stepwise logistic regression model was performed to identify predictors for R-ISS III.

RESULTS

ADC entropy of background marrow showed the highest areas under the ROC (0.784, sensitivity = 93.3%, specificity = 63.0%) for the detection of R-ISS stage III disease. Multivariate analysis showed that increased ADC entropy (>3.612) of background marrow can independently predict R-ISS stage III disease in the overall patients (Model 1 corrected for diffuse infiltration [DI] pattern: odds ratio [OR], 10.647; p = 0.008; Model 2 corrected for mean ADC: OR, 10.485; p = 0.010) and in the subgroup with DI pattern (OR, 7.043; p = 0.037).

CONCLUSION

ADC entropy of background marrow may serve as a sensitive imaging biomarker facilitating the detection of high-risk NDMM patients staged as R-ISS stage III. Increased ADC entropy of background marrow can independently predict R-ISS stage III in the overall patients and in the subgroup with DI pattern.

Whole-body diffusion-weighted MRI of normal lymph nodes: prospective apparent diffusion coefficient histogram and nodal distribution analysis in a healthy cohort

BACKGROUND

Whole body DWI (WB-DWI) enables the identification of lymph nodes for disease evaluation. However, quantitative data of benign lymph nodes across the body are lacking to allow meaningful comparison of diseased states. We evaluated apparent diffusion coefficient (ADC) histogram parameters of all visible lymph nodes in healthy volunteers on WB-DWI and compared differences in nodal ADC values between anatomical regions.

METHODS

WB-DWI was performed on a 1.5 T MR system in 20 healthy volunteers (7 female, 13 male, mean age 35 years). The b900 images were evaluated by two radiologists and all visible nodes from the neck to groin areas were segmented and individual nodal median ADC recorded. All segmented nodes in a patient were summated to generate the total nodal volume. Descriptors of the global ADC histogram, derived from individual node median ADCs, including mean, median, skewness and kurtosis were obtained for the global volume and each nodal region per patient. ADC values between nodal regions were compared using one-way ANOVA with Bonferroni post hoc tests and a p-value ≤0.05 was deemed statistically significant.

RESULTS

One thousand sixty-seven lymph nodes were analyzed. The global mean and median ADC of all lymph nodes were 1.12 ± 0.27 (10^- 3 mm²/s) and 1.09 (10^- 3 mm²/s). The average median ADC skewness was 0.25 ± 0.02 and average median ADC kurtosis was 0.34 ± 0.04. The ADC values of intrathoracic, portal and retroperitoneal nodes were significantly higher (1.53 × 10^- 3, 1.75 × 10^- 3 and 1.58 × 10^- 3 mm²/s respectively) than in other regions. Intrathoracic, portal and mesenteric nodes were relatively uncommon, accounting for only 3% of the total nodes segmented.

CONCLUSIONS

The global mean and median ADC of all lymph nodes were 1.12 ± 0.27 (10^- 3 mm²/s) and 1.09 (10^- 3 mm²/s). Intrathoracic, portal and retroperitoneal nodes display significantly higher ADCs. Normal intrathoracic, portal and mesenteric nodes are infrequently visualized on WB-DWI of healthy individuals.

TRIAL REGISTRATION

Royal Marsden Hospital committee for clinical research registration number 09/H0801/86, 19.10.2009.

Machine learning for evolutive lymphoma and residual masses recognition in whole body diffusion weighted magnetic resonance images

BACKGROUND

After the treatment of the patients with malignant lymphoma, there may persist lesions that must be labeled either as evolutive lymphoma requiring new treatments or as residual masses. We present in this work, a machine learning-based computer-aided diagnosis (CAD) applied to whole-body diffusion-weighted magnetic resonance images.

METHODS

The database consists of a total of 1005 MRI images with evolutive lymphoma and residual masses. More specifically, we propose a novel approach that leverages: (1)-The complementarity of the functional and anatomical criteria of MRI images through a fusion step based on the discrete wavelet transforms (DWT). (2)- The automatic segmentation of the lesions, their localization, and their enumeration using the Chan-Vese algorithm. (3)- The generation of the parametric image which contains the apparent diffusion coefficient value named ADC map. (4)- The features selection through the application of the sequential forward selection (SFS), Entropy, Symmetric uncertainty and Gain Ratio algorithm on 72 extracted features. (5)- The classification of the lesions by applying five well known supervised machine learning classification algorithms: the back-propagation artificial neural network (ANN), the support vector machine (SVM), the K-nearest neighbours (K-NN), Relevance Vectors Machine (RVM), and the random forest (RF) compared to deep learning based on convolutional neural network (CNN). Moreover, this study is achieved with an evaluation of the classification using 335 DW-MR images where 80% of them are used for the training and the remaining 20% for the test.

RESULTS

The obtained accuracy for the five classifiers recorded a slight superiority to the proposed method based on the back-propagation 3-9-1 ANN model which reaches 96,5%. In addition, we compared the proposed method to five other works from the literature. The proposed method gives much better results in terms of SE, SP, accuracy, F₁-measure, and geometric-mean which reaches respectively 96.4%, 90.9%, 95.5%, 0.97, and 91.61%.

CONCLUSIONS

Our initial results suggest that Combining functional, anatomical, and morphological features of ROI's have very good accuracy (97.01%) for evolutive lymphoma and residual masses recognition when we based on the new proposed approach using the back-propagation 3-9-1 ANN model. Proposed method based on machine learning gives less than Deep learning CNN, which is 98.5%.

Whole-body diffusion-weighted MRI in lymphoma-comparison of global apparent diffusion coefficient histogram parameters for differentiation of diseased nodes of lymphoma patients from normal lymph nodes of healthy individuals

Background

Morphologic features yield low diagnostic accuracy to distinguish between diseased and normal lymph nodes. The purpose of this study was to compare diseased lymphomatous and normal lymph nodes using global apparent diffusion coefficient (gADC) histogram parameters derived from whole-body diffusion-weighted MRI (WB-DWI).

Methods

1.5 Tesla WB-DWI of 23 lymphoma patients and 20 healthy volunteers performed between 09/2010 and 07/2015 were retrospectively reviewed. All diseased nodal groups in the lymphoma cohort and all nodes visible on b900 images in healthy volunteers were segmented from neck to groin to generate a total diffusion volume (tDV). A connected component-labelling algorithm separated spatially distinct nodes. Mean, median, skewness, kurtosis, minimum, maximum, interquartile range (IQR), standard deviation (SD), 10^th and 90^th centile of the gADC distribution were derived from the tDV of each patient/volunteer and from spatially distinct nodes. gADC and regional nodal ADC parameters were compared between malignant and normal nodes using t-tests and ROC curve analyses. A P value ≤0.05 was deemed statistically significant.

Results

Mean, median, IQR, 10th and 90th centiles of gADC and regional nodal ADC values were significantly lower in diseased compared with normal lymph nodes. Skewness, kurtosis and tDV were significantly higher in lymphoma. The SD, min and max gADC showed no significant difference between the two groups (P>0.128). The diagnostic accuracies of gADC parameters by AUC from highest to lowest were: 10th centile, mean, median, 90th centile, skewness, kurtosis and IQR. A 10th centile gADC threshold of 0.68×10^-3 mm²/s identified diseased lymphomatous nodes with 91% sensitivity and 95% specificity.

Conclusions

WB-DWI derived gADC histogram parameters can distinguish between malignant lymph nodes of lymphoma patients and normal lymph nodes of healthy individuals.

Whole-Body Magnetic Resonance Imaging: Current Role in Patients with Lymphoma

Imaging of lymphoma is based on the use of ¹⁸F-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG-PET/CT) and/or contrast-enhanced CT, but concerns have been raised regarding radiation exposure related to imaging scans in patients with cancer, and its association with increased risk of secondary tumors in patients with lymphoma has been established. To date, lymphoproliferative disorders are among the most common indications to perform whole-body magnetic resonance imaging (MRI). Whole-body MRI is superior to contrast-enhanced CT for staging the disease, also being less dependent on histology if compared to ¹⁸F-FDG-PET/CT. As well, it does not require exposure to ionizing radiation and could be used for the surveillance of lymphoma. The current role of whole-body MRI in the diagnostic workup in lymphoma is examined in the present review along with the diagnostic performance in staging, response assessment and surveillance of different lymphoma subtypes.

Quantitative Whole-Body Diffusion-weighted MRI after One Treatment Cycle for Aggressive Non-Hodgkin Lymphoma Is an Independent Prognostic Factor of Outcome

Purpose

To evaluate the prognostic utility of apparent diffusion coefficient (ADC) changes at whole-body diffusion-weighted (WB-DW) MRI after one treatment cycle for aggressive non-Hodgkin lymphoma (NHL) compared with response assessment at interim and end-of-treatment fluorine 18 (¹⁸F) fluorodeoxyglucose (FDG) PET/CT.

Materials and Methods

This was a secondary analysis of a prospective study (ClinicalTrials.gov identifier: NCT01231269) in which participants with aggressive NHL were recruited between March 2011 and April 2015 and underwent WB-DW MRI before and after one cycle of immunochemotherapy. Volunteers were recruited for test-retest WB-DW MRI (ClinicalTrials.gov identifier: NCT01231282) to assess ADC measurement repeatability. Response assessment was based on ADC change after one treatment cycle at WB-DW MRI and Deauville criteria at ¹⁸F-FDG PET/CT. To evaluate prognostic factors of disease-free survival (DFS), Kaplan-Meier survival analysis and univariable and multivariable Cox regression were performed; intraclass correlation coefficient (ICC) and mean difference with limits of agreement were calculated to determine inter- and intraobserver repeatability of ADC measurements.

Results

Forty-five patients (mean age, 58 years ± 17 [standard deviation]; 31 men) and nine volunteers (mean age, 22 years ± 3; seven men) were enrolled. Median DFS was 48 months (range, 2-48 months). Outcome prediction accuracy was 86.7% (39 of 45), 71.4% (30 of 42), and 73.8% (31 of 42) for WB-DW MRI and interim and end-of-treatment ¹⁸F-FDG PET/CT, respectively. WB-DW MRI (hazard ratio [HR], 17.8; P < .001) and interim (HR, 5; P = .008) and end-of-treatment (HR, 4.3; P = .017) ¹⁸F-FDG PET/CT were prognostic of DFS. After multivariable analysis, WB-DW MRI remained an independent predictor of outcome (HR, 26.8; P = .002). Intra- and interobserver agreement for ADC measurements were excellent (ICC = 0.85-0.99).

Conclusion

Quantitative WB-DW MRI after only one cycle of immunochemotherapy predicts DFS in aggressive NHL and is noninferior to routinely performed interim and end-of-treatment ¹⁸F-FDG PET/CT.Keywords: MR-Diffusion Weighted Imaging, Lymphoma, Oncology, Tumor Response, Whole-Body ImagingSupplemental material is available for this article.© RSNA, 2021.

Preoperative T2-weighted MR imaging texture analysis of gastric cancer: prediction of TNM stages

PURPOSE

To explore the capability of algorithms to build multivariate models integrating morphological and texture features derived from preoperative T₂-weighted magnetic resonance (MR) images of gastric cancer (GC) to evaluate tumor- (T), node- (N), and metastasis- (M) stages.

METHODS

A total of 80 patients at our hospital who underwent abdominal MR imaging and were diagnosed with GC from December 2011 to November 2016 were retrospectively included. Texture features were calculated using T₂-weighted images with a manual region of interest. Morphological characteristics were also evaluated. Classifiers and regression analyses were used to build multivariate models. Receiver operating characteristic (ROC) curve analysis was performed to assess diagnostic efficacy.

RESULTS

There were 8, 10, and 3 texture parameters that showed significant differences in GCs at different overall (I-II vs. III-IV), T (1-2 vs. 3-4), and N (- vs. +) stages (all p < 0.05), respectively. Mild thickening was more common in stages I-II, T1-2, and N- GCs (all p < 0.05). An irregular outer contour was more commonly observed in stages III-IV (p = 0.001) and T3-4 (p = 0.001) GCs. T3-4 and N+ GCs tended to be thickening type lesions (p = 0.005 and 0.032, respectively). The multivariate models using the naive bayes algorithm showed the highest diagnostic efficacy in predicting T and N stages (area under the ROC curves [AUC] = 0.900 and 0.863, respectively), and the model based on regression analysis had the best predictive performance in overall staging (AUC = 0.839).

CONCLUSION

Multivariate models combining morphological characteristics with texture parameters based on machine learning algorithms were able to improve diagnostic efficacy in predicting the overall, T, and N stages of GCs.

Texture analysis and multiple-instance learning for the classification of malignant lymphomas

BACKGROUND AND OBJECTIVES

Malignant lymphomas are cancers of the immune system and are characterized by enlarged lymph nodes that typically spread across many different sites. Many different histological subtypes exist, whose diagnosis is typically based on sampling (biopsy) of a single tumor site, whereas total body examinations with computed tomography and positron emission tomography, though not diagnostic, are able to provide a comprehensive picture of the patient. In this work, we exploit a data-driven approach based on multiple-instance learning algorithms and texture analysis features extracted from positron emission tomography, to predict differential diagnosis of the main malignant lymphomas subtypes.

METHODS

We exploit a multiple-instance learning setting where support vector machines and random forests are used as classifiers both at the level of single VOIs (instances) and at the level of patients (bags). We present results on two datasets comprising patients that suffer from four different types of malignant lymphomas, namely diffuse large B cell lymphoma, follicular lymphoma, Hodgkin's lymphoma, and mantle cell lymphoma.

RESULTS

Despite the complexity of the task, experimental results show that, with sufficient data samples, some cancer subtypes, such as the Hodgkin's lymphoma, can be identified from texture information: in particular, we achieve a 97.0% of sensitivity (recall) and a 94.1% of predictive positive value (precision) on a dataset that consists in 60 patients.

CONCLUSIONS

The presented study indicates that texture analysis features extracted from positron emission tomography, combined with multiple-instance machine learning algorithms, can be discriminating for different malignant lymphomas subtypes.

Comparison of whole-body MRI with diffusion-weighted imaging and PET/CT in lymphoma staging

OBJECTIVES

To compare the diagnostic efficiency of whole-body MRI-DWI and PET/CT in lymphoma staging.

METHODS

A prospective study enrolled 92 patients with lymphoma. Prior to treatment, all patients underwent whole-body MRI-DWI and PET-CT. The methods' efficiency was compared in the diagnosis of lymph node (LN) and organ involvement, and in determining lymphoma stage.

RESULTS

Sensitivity, specificity, and accuracy in the diagnosis of enlarged LN involvement were 98.2%, 99.9%, and 99.3%, respectively, for MRI-DWI, and 99.4%, 100.0%, and 99.8%, respectively, for PET/CT. ROC analysis showed similar methods' efficiency in the diagnosis of enlarged LN involvement (p > 0.06). MRI-DWI and PET/CT sensitivity in the diagnosis of non-enlarged LN involvement was 77.8% and 88.1%, respectively (p < 0.001). MRI-DWI and PET/CT sensitivity, specificity, and accuracy in the diagnosis of lung involvement were 73.3%, 98.7%, 94.6% and 86.7%, 98.7%, 96.7%; spleen involvement 54.8%, 98.3%, 83.3% and 100.0%, 100.0%, 100.0%; bone marrow involvement 87.1%, 96.4%, 93.0% and 64.5%, 87.3%, 79.1%; and all-organ involvement 72.9%, 98.1%, 91.4% and 80.0%, 96.6%, 92.2%, respectively. ROC analysis showed similar methods' efficiency in the diagnosis of lung involvement (р > 0.3), higher for PET/CT in spleen involvement (р < 0.0001), higher for MRI-DWI in bone marrow involvement (р < 0.0008), and similar in all-organ involvement (р > 0.35). MRI-DWI and PET/CT determined the correct lymphoma stage in 79 (86%) patients.

CONCLUSIONS

Whole-body MRI-DWI and PET/CT determined the correct lymphoma stage in similar numbers of patients. MRI-DWI can serve as a non-irradiative alternative to PET/CT in lymphoma staging.

KEY POINTS

• Whole-body MRI-DWI efficiency compared with that of PET/CT is similar in the diagnosis of enlarged LN involvement, inferior in the diagnosis of non-enlarged LN and spleen involvement, but superior in the diagnosis of bone marrow involvement. • A new efficient MRI-DWI sign for diagnosis of diffuse bone marrow involvement has been proposed, i.e., a diffuse increase in spine signal intensity on high b value DWI images above the kidney parenchyma. • MRI-DWI and PET/CT determined the correct lymphoma stage in similar numbers of patients.

MRI and PET/MRI in hematologic malignancies

The role of MRI differs considerably between the three main groups of hematological malignancies: lymphoma, leukemia, and myeloma. In myeloma, whole‐body MRI (WB‐MRI) is recognized as a highly sensitive test for the assessment of myeloma, and is also endorsed by clinical guidelines, especially for detection and staging. In lymphoma, WB‐MRI is presently not recommended, and merely serves as an alternative technique to the current standard imaging test, [¹⁸F]FDG‐PET/CT, especially in pediatric patients. Even for lymphomas with variable FDG avidity, such as extranodal mucosa‐associated lymphoid tissue lymphoma (MALT), contrast‐enhanced computed tomography (CT), but not WB‐MRI, is presently recommended, despite the high sensitivity of diffusion‐weighted MRI and its ability to capture treatment response that has been reported in the literature. In leukemia, neither MRI nor any other cross‐sectional imaging test (including positron emission tomography [PET]) is currently recommended outside of clinical trials. This review article discusses current clinical applications as well as the main research topics for MRI, as well as PET/MRI, in the field of hematological malignancies, with a focus on functional MRI techniques such as diffusion‐weighted imaging and dynamic contrast‐enhanced MRI, on the one hand, and novel, non‐FDG PET imaging probes such as the CXCR4 radiotracer [⁶⁸Ga]Ga‐Pentixafor and the amino acid radiotracer [¹¹C]methionine, on the other hand.

Level of Evidence: 5

Technical Efficacy Stage: 3

J. Magn. Reson. Imaging 2020;51:1325–1335.

Can texture analysis in ultrashort echo-time MRI distinguish primary graft dysfunction from acute rejection in lung transplants? A multidimensional assessment in a mouse model

BACKGROUND

Differentiation of early postoperative complications affects treatment options after lung transplantation.

PURPOSE

To assess if texture analysis in ultrashort echo-time (UTE) MRI allows distinction of primary graft dysfunction (PGD) from acute transplant rejection (ATR) in a mouse lung transplant model.

STUDY TYPE

Longitudinal.

ANIMAL MODEL

Single left lung transplantation was performed in two cohorts of six mice (strain C57BL/6) receiving six syngeneic (strain C57BL/6) and six allogeneic lung transplants (strain BALB/c (H-2K^d )).

FIELD STRENGTH/SEQUENCE

4.7T small-animal MRI/eight different UTE sequences (echo times: 50-5000 μs) at three different postoperative timepoints (1, 3, and 7 days after transplantation).

ASSESSMENT

Nineteen different first- and higher-order texture features were computed on multiple axial slices for each combination of UTE and timepoint (24 setups) in each mouse. Texture features were compared for transplanted (graft) and contralateral native lungs between and within syngeneic and allogeneic cohorts. Histopathology served as a reference.

STATISTICAL TESTS

Nonparametric tests and correlation matrix analysis were used.

RESULTS

Pathology revealed PGD in the syngeneic and ATR in the allogeneic cohort. Skewness and low-gray-level run-length features were significantly different between PGD and ATR for all investigated setups (P < 0.03). These features were significantly different between graft and native lung in ATR for most setups (minimum of 20/24 setups; all P < 0.05). The number of significantly different features between PGD and ATR increased with elapsing postoperative time. Differences in significant features were highest for an echo-time of 1500 μs.

DATA CONCLUSION

Our findings suggest that texture analysis in UTE-MRI might be a tool for the differentiation of PGD and ATR in the early postoperative phase after lung transplantation.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2020;51:108-116.