Deep learning-based PET/MR radiomics for the classification of annualized relapse rate in multiple sclerosis.

Background Annualized Relapse Rate (ARR) is one of the most important indicators of disease progression in patients with Multiple Sclerosis (MS). However, imaging markers that can effectively predict ARR are currently unavailable. In this study, we developed a deep learning-based method for the automated extraction of radiomics features from Positron Emission Computed Tomography (PET) and Magnetic Resonance (MR) images to predict ARR in patients with MS. Methods Twenty-five patients with a definite diagnosis of Relapsing-Remitting MS (RRMS) were enrolled in this study. We designed a multi-branch fully convolutional neural network to segment lesions from PET/MR images. After that, radiomics features were extracted from the obtained lesion volume of interest. Three feature selection methods were used to retain features highly correlated with ARR. We combined four classifiers with different feature selection methods to form twelve models for ARR classification. Finally, the model with the best performance was chosen. Results Our network achieved precise automatic lesion segmentation with a Dice Similarity Coefficient (DSC) of 0.81 and a precision of 0.86. Radiomics features from lesions filtered by Recursive Feature Elimination (RFE) achieved the best performance in the Support Vector Machines (SVM) classifier. The classification model performance was best when radiomics from both PET and MR were combined to predict ARR, with high accuracy at 0.88 and Area Under the ROC curves (AUC) at 0.96, which outperformed MR or PET-based model and clinical indicators-based model. Conclusion Our automatic segmentation masks can replace manual ones with excellent performance. Furthermore, the deep learning and PET/MR radiomics-based model in our research is an effective tool in assisting ARR classification of MS patients.

Multimodal Fusion Network for Detecting Hyperplastic Parathyroid Glands in SPECT/CT Images.

In secondary hyperparathyroidism (SHPT) disease, preoperatively localizing hyperplastic parathyroid glands is crucial in the surgical procedure. These glands can be detected via the dual-modality imaging technique single-photon emission computed tomography/computed tomography (SPECT/CT) since it has high sensitivity and provides an accurate location. However, due to possible low-uptake glands in SPECT images, manually labeling glands is challenging, not to mention automatic label methods. In this work, we present a deep learning method with a novel fusion network to detect hyperplastic parathyroid glands in SPECT/CT images. Our proposed fusion network follows the convolutional neural network (CNN) with a three-pathway architecture that extracts modality-specific feature maps. The fusion network, composed of the channel attention module, the feature selection module, and the modality-specific spatial attention module, is designed to integrate complementary anatomical and functional information, especially for low-uptake glands. Experiments with patient data show that our fusion method improves performance in discerning low-uptake glands compared with current fusion strategies, achieving an average sensitivity of 0.822. Our results prove the effectiveness of the three-pathway architecture with our proposed fusion network for solving the glands detection task. To our knowledge, this is the first study to detect abnormal parathyroid glands in SHPT disease using SPECT/CT images, which promotes the application of preoperative glands localization.

18F-florbetapir PET/MRI for quantitatively monitoring myelin loss and recovery in patients with multiple sclerosis: A longitudinal study.

BACKGROUND: Amyloid positron emission tomography (PET) can measure in-vivo demyelination in patients with multiple sclerosis (MS). However, the value of 18F-labeled amyloid PET tracer, 18F-florbetapir in the longitudinal study for monitoring myelin loss and recovery has not been confirmed. METHODS: From March 2019 to September 2020, twenty-three patients with MS and nine healthy controls (HCs) underwent a hybrid PET/MRI at baseline and expanded disability status scale (EDSS) assessment, and eight of 23 patients further underwent follow-up PET/MRI. The distribution volume ratio (DVR) and standard uptake value ratio (SUVR) of 18F-florbetapir in damaged white matter (DWM) and normal-appearance white matter (NAWM) were obtained from dynamic and static PET acquisition. Diffusion tensor imaging-derived parameters were also calculated. Data were expressed as mean ± standard deviation with 99% confidence interval (99%CI). FINDING: The mean DVR (1.08 ± 0.12, 99%CI [1.02 ~ 1.14]) but not the mean SUVR of DWM lesions was lower than that of NAWM in patients with MS (1.25 ± 0.10, 99%CI [1.20 ~ 1.31]) and HCs (1.29 ± 0.08, 99%CI [1.23 ~ 1.36]). A trend toward lower mean fractional anisotropy (374.95 ± 45.30 vs. 419.07 ± 4.83) and higher mean radial diffusivity (0.45 ± 0.05 vs. 0.40 ± 0.01) of NAWM in patients with MS than those in HCs was found. DVR decreased in DWM lesions with higher MD (rho = -0.261, 99%CI [-0.362 ~ -0.144]), higher AD (rho = -0.200, 99%CI [-0.318 ~ -0.070]) and higher RD (rho = -0.198, 99%CI [-0.313 ~ -0.075]). Patients' EDSS scores were reduced (B = 0.04, 99%CI [-0.005 ~ 0.084]) with decreased index of global demyelination in the longitudinal study. INTERPRETATION: Our exploratory study suggests that dynamic 18F-florbetapir PET/MRI may be a very promising tool for quantitatively monitoring myelin loss and recovery in patients with MS. FUNDING: Shanghai Pujiang Program, Shanghai Municipal Key Clinical Specialty, Shanghai Shuguang Plan Project, Shanghai Health and Family Planning Commission Research Project, Clinical Research Plan of SHDC, French-Chinese program "Xu Guangqi".