Multiple organ segmentation framework for brain metastasis radiotherapy.

Radiotherapy is a preferred treatment for brain metastases, which kills cancer cells via high doses of radiation meanwhile hardly avoiding damage to surrounding healthy cells. Therefore, the delineation of organs-at-risk (OARs) is vital in treatment planning to minimize radiation-induced toxicity. However, the following aspects make OAR delineation a challenging task: extremely imbalanced organ sizes, ambiguous boundaries, and complex anatomical structures. To alleviate these challenges, we imitate how specialized clinicians delineate OARs and present a novel cascaded multi-OAR segmentation framework, called OAR-SegNet. OAR-SegNet comprises two distinct levels of segmentation networks: an Anatomical-Prior-Guided network (APG-Net) and a Point-Cloud-Guided network (PCG-Net). Specifically, APG-Net handles segmentation for all organs, where multi-view segmentation modules and a deep prior loss are designed under the guidance of prior knowledge. After APG-Net, PCG-Net refines small organs through the mini-segmentation and the point-cloud alignment heads. The mini-segmentation head is further equipped with the deep prior feature. Extensive experiments were conducted to demonstrate the superior performance of the proposed method compared to other state-of-the-art medical segmentation methods.

Promoting fast MR imaging pipeline by full-stack AI.

Magnetic resonance imaging (MRI) is a widely used imaging modality in clinics for medical disease diagnosis, staging, and follow-up. Deep learning has been extensively used to accelerate k-space data acquisition, enhance MR image reconstruction, and automate tissue segmentation. However, these three tasks are usually treated as independent tasks and optimized for evaluation by radiologists, thus ignoring the strong dependencies among them; this may be suboptimal for downstream intelligent processing. Here, we present a novel paradigm, full-stack learning (FSL), which can simultaneously solve these three tasks by considering the overall imaging process and leverage the strong dependence among them to further improve each task, significantly boosting the efficiency and efficacy of practical MRI workflows. Experimental results obtained on multiple open MR datasets validate the superiority of FSL over existing state-of-the-art methods on each task. FSL has great potential to optimize the practical workflow of MRI for medical diagnosis and radiotherapy.

Evidence-based uncertainty-aware semi-supervised medical image segmentation.

Semi-Supervised Learning (SSL) has demonstrated great potential to reduce the dependence on a large set of annotated data, which is challenging to collect in clinical practice. One of the most important SSL methods is to generate pseudo labels from the unlabeled data using a network model trained with labeled data, which will inevitably introduce false pseudo labels into the training process and potentially jeopardize performance. To address this issue, uncertainty-aware methods have emerged as a promising solution and have gained considerable attention recently. However, current uncertainty-aware methods usually face the dilemma of balancing the additional computational cost, uncertainty estimation accuracy, and theoretical basis in a unified training paradigm. To address this issue, we propose to integrate the Dempster-Shafer Theory of Evidence (DST) into SSL-based medical image segmentation, dubbed EVidential Inference Learning (EVIL). EVIL performs as a novel consistency regularization-based training paradigm, which enforces consistency on predictions perturbed by two networks with different parameters to enhance generalization Additionally, EVIL provides a theoretically assured solution for precise uncertainty quantification within a single forward pass. By discarding highly unreliable pseudo labels after uncertainty estimation, trustworthy pseudo labels can be generated and incorporated into subsequent model training. The experimental results demonstrate that the proposed approach performs competitively when benchmarked against several state-of-the-art methods on public datasets, i.e., ACDC, MM-WHS, and MonuSeg. The code can be found at https://github.com/CYYukio/EVidential-Inference-Learning.

DeSeg: auto detector-based segmentation for brain metastases.

Delineation of brain metastases (BMs) is a paramount step in stereotactic radiosurgery treatment. Clinical practice has specific expectation on BM auto-delineation that the method is supposed to avoid missing of small lesions and yield accurate contours for large lesions. In this study, we propose a novel coarse-to-fine framework, named detector-based segmentation (DeSeg), to incorporate object-level detection into pixel-wise segmentation so as to meet the clinical demand. DeSeg consists of three components: a center-point-guided single-shot detector to localize the potential lesion regions, a multi-head U-Net segmentation model to refine contours, and a data cascade unit to connect both tasks smoothly. Performance on tiny lesions is measured by the object-based sensitivity and positive predictive value (PPV), while that on large lesions is quantified by dice similarity coefficient (DSC), average symmetric surface distance (ASSD) and 95% Hausdorff distance (HD95). Besides, computational complexity is also considered to study the potential of method in real-time processing. This study retrospectively collected 240 BM patients with Gadolinium injected contrast-enhanced T1-weighted magnetic resonance imaging (T1c-MRI), which were randomly split into training, validating and testing datasets (192, 24 and 24 scans, respectively). The lesions in the testing dataset were further divided into two groups based on the volume size (smallS: ≤1.5 cc,N= 88; largeL: > 1.5 cc,N= 15). On average, DeSeg yielded a sensitivity of 0.91 and a PPV of 0.77 on S group, and a DSC of 0.86, an ASSD 0f 0.76 mm and a HD95 of 2.31 mm onLgroup. The results indicated that DeSeg achieved leading sensitivity and PPV for tiny lesions as well as segmentation metrics for large ones. After our clinical validation, DeSeg showed competitive segmentation performance while kept faster processing speed comparing with existing 3D models.

SDF-1 secreted by mesenchymal stem cells promotes the migration of endothelial progenitor cells via CXCR4/PI3K/AKT pathway.

Cell-based therapeutics bring great hope in areas of unmet medical needs. Mesenchymal stem cells (MSCs) have been suggested to facilitate neovascularization mainly by paracrine action. Endothelial progenitor cells (EPCs) can migrate to ischemic sites and participate in angiogenesis. The combination cell therapy that includes MSCs and EPCs has a favorable effect on ischemic limbs. However, the mechanism of combination cell therapy remains unclear. Herein, we investigate whether stromal cell-derived factor (SDF)-1 secreted by MSCs contributes to EPC migration to ischemic sites via CXCR4/Phosphoinositide 3-Kinases (PI3K)/protein kinase B (termed as AKT) signaling pathway. First, by a "dual-administration" approach, intramuscular MSC injections were supplemented with intravenous Qdot® 525 labeled-EPC injections in the mouse model of hind limb ischemia. Then, the mechanism of MSC effect on EPC migration was detected by the transwell system, tube-like structure formation assays, western blot assays in vitro. Results showed that the combination delivery of MSCs and EPCs enhanced the incorporation of EPCs into the vasculature and increased the capillary density in mouse ischemic hind limb. The numbers of CXCR4-positive EPCs increased after incubation with MSC-conditioned medium (CM). MSCs contributed to EPC migration and tube-like structure formation, both of which were suppressed by AMD3100 and wortmannin. Phospho-AKT induced by MSC-CM was attenuated when EPCs were pretreated with AMD3100 and wortmannin. In conclusion, we confirmed that MSCs contributes to EPC migration, which is mediated via CXCR4/PI3K/AKT signaling pathway.

Effect of a Novel Flame Retardant on the Mechanical, Thermal and Combustion Properties of Poly(Lactic Acid).

Poly(lactic) acid (PLA) is one of the most promising biobased materials, but its inherent flammability limits its applications. A novel flame retardant hexa-(DOPO-hydroxymethylphenoxy-dihydroxybiphenyl)-cyclotriphosphazene (HABP-DOPO) for PLA was prepared by bonding 9,10-dihydro-9-oxy-10-phosphaphenanthrene-10-oxide (DOPO) to cyclotriphosphazene. The morphologies, mechanical properties, thermal stability and burning behaviors of PLA/HABP-DOPO blends were investigated using a scanning electron microscope (SEM), a universal mechanical testing machine, thermogravimetric analysis (TGA), differential scanning calorimetry (DSC), limiting oxygen index (LOI), vertical burning (UL-94) and a cone calorimeter test (CCT). The LOI value reached 28.5% and UL-94 could pass V-0 for the PLA blend containing 25 wt% HABP-DOPO. A significant improvement in fire retardant performance was observed for PLA/HABP-DOPO blends. PLA/HABP-DOPO blends exhibited balanced mechanical properties. The flame retardant mechanism of PLA/HABP-DOPO blends was evaluated.