Dataset Information

Early detection of recurrent medulloblastoma: the critical role of diffusion-weighted imaging.

ABSTRACT:

Background

Imaging diagnosis of medulloblastoma recurrence relies heavily on identifying new contrast-enhancing lesions on surveillance imaging, with diffusion-weighted imaging (DWI) being used primarily for detection of complications. We propose that DWI is more sensitive in detecting distal and leptomeningeal recurrent medulloblastoma than T1-weighted postgadolinium imaging.

Methods

We identified 53 pediatric patients with medulloblastoma, 21 of whom developed definitive disease recurrence within the brain. MRI at diagnosis of recurrence and 6 months prior was evaluated for new lesions with reduced diffusion on DWI, contrast enhancement, size, and recurrence location.

Results

All recurrent medulloblastoma lesions demonstrated reduced diffusion. Apparent diffusion coefficient (ADC) measurements were statistically significantly lower (P = .00001) in recurrent lesions (mean=0.658, SD=0.072) as compared to contralateral normal region of interest (mean=0.923, SD=0.146). Sixteen patients (76.2%) with disease recurrence demonstrated contrast enhancement within the recurrent lesions. All 5 patients with nonenhancing recurrence demonstrated reduced diffusion, with a mean ADC of 0.695 ± 0.101 (normal=0.893 ± 0.100, P = .0027). While group 3 and group 4 molecular subtypes demonstrated distal recurrence more frequently, nonenhancing metastatic disease was found in all molecular subtypes.

Conclusion

Recurrent medulloblastoma lesions do not uniformly demonstrate contrast enhancement on MRI, but all demonstrate reduced diffusion. Our findings support that DWI is more sensitive than contrast enhancement for detection of medulloblastoma recurrence, particularly in cases of leptomeningeal nonenhancing disease and distal nonenhancing focal disease. As such, recurrent medulloblastoma can present as a reduced diffusion lesion in a patient with normal postgadolinium contrast MRI.

SUBMITTER: Aboian MS

PROVIDER: S-EPMC6213943 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundMetastatic complications are a major cause of cancer-related morbidity, with up to 40% of cancer patients experiencing at least one brain metastasis. Earlier detection may significantly improve patient outcomes and overall survival. We investigated machine learning (ML) models for early detection of brain metastases based on diffusion weighted imaging (DWI) radiomics.MethodsLongitudinal diffusion imaging from 116 patients previously treated with stereotactic radiosurgery (SRS) for brain metastases were retrospectively analyzed. Clinical contours from 600 metastases were extracted from radiosurgery planning computed tomography, and rigidly registered to corresponding contrast enhanced-T1 and apparent diffusion coefficient (ADC) maps. Contralateral contours located in healthy brain tissue were used as control. The dataset consisted of (I) radiomic features using ADC maps, (II) radiomic feature change calculated using timepoints before the metastasis manifested on contrast enhanced-T1, (III) primary cancer, and (IV) anatomical location. The dataset was divided into training and internal validation sets using an 80/20 split with stratification. Four classification algorithms [Linear Support Vector Machine (SVM), Random Forest (RF), AdaBoost, and XGBoost] underwent supervised classification training, with contours labeled either 'control' or 'metastasis'. Hyperparameters were optimized towards balanced accuracy. Various model metrics (receiver operating characteristic curve area scores, accuracy, recall, and precision) were calculated to gauge performance.ResultsThe radiomic and clinical data set, feature engineering, and ML models developed were able to identify metastases with an accuracy of up to 87.7% on the training set, and 85.8% on an unseen test set. XGBoost and RF showed superior accuracy (XGBoost: 0.877±0.021 and 0.833±0.47, RF: 0.823±0.024 and 0.858±0.045) for training and validation sets, respectively. XGBoost and RF also showed strong area under the receiver operating characteristic curve (AUC) performance on the validation set (0.910±0.037 and 0.922±0.034, respectively). AdaBoost performed slightly lower in all metrics. SVM model generalized poorly with the internal validation set. Important features involved changes in radiomics months before manifesting on contrast enhanced-T1.ConclusionsThe proposed models using diffusion-based radiomics showed encouraging results in differentiating healthy brain tissue from metastases using clinical imaging data. These findings suggest that longitudinal diffusion imaging and ML may help improve patient care through earlier diagnosis and increased patient monitoring/follow-up. Future work aims to improve model classification metrics, robustness, user-interface, and clinical applicability.

Project description:PurposeTo compare integrated slice-specific dynamic shimming (iShim) diffusion weighted imaging (DWI) and single-shot echo-planar imaging (SS-EPI) DWI in image quality and pathological characterization of rectal cancer.Materials and methodsA total of 193 consecutive rectal tumor patients were enrolled for retrospective analysis. Among them, 101 patients underwent iShim-DWI (b = 0, 800, and 1600 s/mm2) and 92 patients underwent SS-EPI-DWI (b = 0, and 1000 s/mm2). Qualitative analyses of both DWI techniques was performed by two independent readers; including adequate fat suppression, the presence of artifacts and image quality. Quantitative analysis was performed by calculating standard deviation (SD) of the gluteus maximus, signal intensity (SI) of lesion and residual normal rectal wall, apparent diffusion coefficient (ADC) values (generated by b values of 0, 800 and 1600 s/mm2 for iShim-DWI, and by b values of 0 and 1000 s/mm2 for SS-EPI-DWI) and image quality parameters, such as signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of primary rectal tumor. For the primary rectal cancer, two pathological groups were divided according to pathological results: Group 1 (well-differentiated) and Group 2 (poorly differentiated). Statistical analyses were performed with p < 0.05 as significant difference.ResultsCompared with SS-EPI-DWI, significantly higher scores of image quality were obtained in iShim-DWI cases (P < 0.001). The SDbackground was significantly reduced on b = 1600 s/mm2 images and ADC maps of iShim-DWI. Both SNR and CNR of b = 800 s/mm2 and b = 1600 s/mm2 images in iShim-DWI were higher than those of b = 1000 s/mm2 images in SS-EPI-DWI. In primary rectal cancer of iShim-DWI cohort, SIlesion was significantly higher than SIrectum in both b = 800 and 1600 s/mm2 images. ADC values were significantly lower in Group 2 (0.732 ± 0.08) × 10- 3 mm2/s) than those in Group 1 ((0.912 ± 0.21) × 10- 3 mm2/s). ROC analyses showed significance of ADC values and SIlesion between the two groups.ConclusioniShim-DWI with b values of 0, 800 and 1600 s/mm2 is a promising technique of high image quality in rectal tumor imaging, and has potential ability to differentiate rectal cancer from normal wall and predicting pathological characterization.

Project description:The European Society of Breast Radiology (EUSOBI) established an International Breast DWI working group. The working group consists of clinical breast MRI experts, MRI physicists, and representatives from large vendors of MRI equipment, invited based upon proven expertise in breast MRI and/or in particular breast DWI, representing 25 sites from 16 countries. The aims of the working group are (a) to promote the use of breast DWI into clinical practice by issuing consensus statements and initiate collaborative research where appropriate; (b) to define necessary standards and provide practical guidance for clinical application of breast DWI; (c) to develop a standardized and translatable multisite multivendor quality assurance protocol, especially for multisite research studies; (d) to find consensus on optimal methods for image processing/analysis, visualization, and interpretation; and (e) to work collaboratively with system vendors to improve breast DWI sequences. First consensus recommendations, presented in this paper, include acquisition parameters for standard breast DWI sequences including specifications of b values, fat saturation, spatial resolution, and repetition and echo times. To describe lesions in an objective way, levels of diffusion restriction/hindrance in the breast have been defined based on the published literature on breast DWI. The use of a small ROI placed on the darkest part of the lesion on the ADC map, avoiding necrotic, noisy or non-enhancing lesion voxels is currently recommended. The working group emphasizes the need for standardization and quality assurance before ADC thresholds are applied. The working group encourages further research in advanced diffusion techniques and tailored DWI strategies for specific indications. Key Points • The working group considers breast DWI an essential part of a multiparametric breast MRI protocol and encourages its use. • Basic requirements for routine clinical application of breast DWI are provided, including recommendations on b values, fat saturation, spatial resolution, and other sequence parameters. • Diffusion levels in breast lesions are defined based on meta-analysis data and methods to obtain a reliable ADC value are detailed.