M2 microglia-derived exosome-loaded electroconductive hydrogel for enhancing neurological recovery after spinal cord injury.

Electroconductive hydrogels offer a promising avenue for enhancing the repair efficacy of spinal cord injuries (SCI) by restoring disrupted electrical signals along the spinal cord's conduction pathway. Nonetheless, the application of hydrogels composed of diverse electroconductive materials has demonstrated limited capacity to mitigate the post-SCI inflammatory response. Recent research has indicated that the transplantation of M2 microglia effectively fosters SCI recovery by attenuating the excessive inflammatory response. Exosomes (Exos), small vesicles discharged by cells carrying similar biological functions to their originating cells, present a compelling alternative to cellular transplantation. This investigation endeavors to exploit M2 microglia-derived exosomes (M2-Exos) successfully isolated and reversibly bonded to electroconductive hydrogels through hydrogen bonding for synergistic promotion of SCI repair to synergistically enhance SCI repair. In vitro experiments substantiated the significant capacity of M2-Exos-laden electroconductive hydrogels to stimulate the growth of neural stem cells and axons in the dorsal root ganglion and modulate microglial M2 polarization. Furthermore, M2-Exos demonstrated a remarkable ability to mitigate the initial inflammatory reaction within the injury site. When combined with the electroconductive hydrogel, M2-Exos worked synergistically to expedite neuronal and axonal regeneration, substantially enhancing the functional recovery of rats afflicted with SCI. These findings underscore the potential of M2-Exos as a valuable reparative factor, amplifying the efficacy of electroconductive hydrogels in their capacity to foster SCI rehabilitation.

Development and Validation of a Prognostic Prediction Model for Postoperative Ovarian Sex Cord-Stromal Tumor Patients.

BACKGROUND We developed a nomogram for prognostic prediction of overall survival (OS) in postoperative ovarian sex cord-stromal tumor (SCST) patients and discuss the effect of chemotherapy at various FIGO stages. MATERIAL AND METHODS SCST patients after surgery from 2004 to 2015 were enrolled from the Surveillance, Epidemiology and End-Results (SEER) database, matched into pairs by propensity score matching (PSM), and divided into a training set and a validation set. Univariate and multivariate Cox analyses were conducted to identify significant variables for the development of the nomogram. The nomogram model was validated by concordance index (C-index), receiver operating characteristics (ROCs) curve, calibration plot, and decision curve analysis (DCA). Survival curves showed the integrative ability of prognostic prediction and the efficacy of chemotherapy. RESULTS A total of 913 SCST patients were initially enrolled, and after PSM, 506 patients were included. Age, marital status, CA125 levels, tumor size, FIGO stage, grade, and chemotherapy were indicators for building the OS nomogram. The C-index was 0.850 in the training set and 0.786 in the validation set. Calibration plots were satisfactory and the nomogram had relatively better clinical utility than FIGO stage. The survival analysis showed that the low-risk group had generally longer survival than the high-risk group based on the prognostic score, and chemotherapy had an overall reverse effect on OS. CONCLUSIONS The nomogram model displays the potential to provide individualized prognosis probability of SCSTs and to aid in clinical decision-making. The unfavorable results of chemotherapy in all stages shows the need for further exploration.

Generalizable Polyp Segmentation via Randomized Global Illumination Augmentation.

Accurately segmenting polyps from colonoscopy images is essential for diagnosing colorectal cancer. Despite the tremendous success of the deep convolutional neural networks in automatic polyp segmentation, it suffers from domain shift issues, where the trained model yields performance deterioration on unseen test datasets. This paper proposes an illumination enhancement-based domain generalization approach to improve the generalization capability of the model on unseen test datasets and alleviate this issue. In particular, an image decomposition module (IDM) was developed to separate colonoscopy images into reflectance, local, and global illumination components. An illumination transform module (ITM) was proposed to augment images with different global illuminations by synthesizing target-like global illumination maps. A novel illumination variance insensitiveness (IViSen) is also introduced to evaluate the robustness of the model against illumination disturbance. IViSen is easy to compute and correlates well with model generalizability. The segmentation performance of the proposed model on four colonoscopy datasets was examined: CVC-ClinicDB, CVC-ColonDB, ETIS-Larib, and Kvasir-SEG. The method outperformed the competitive methods when tested on unseen domains. In particular, the proposed approach yielded 60.82% and 53.19% in terms of mean Dice and IoU, respectively, with 2.06% and 2.31% improvements.

Biodegradable Dual-Cross-Linked Hydrogels with Stem Cell Differentiation Regulatory Properties Promote Growth Plate Injury Repair via Controllable Three-Dimensional Mechanics and a Cartilage-like Extracellular Matrix.

Recent breakthroughs in cell transplantation therapy have revealed the promising potential of bone marrow mesenchymal stem cells (BMSCs) for promoting the regeneration of growth plate cartilage injury. However, the high apoptosis rate and the uncertainty of the differentiation direction of cells often lead to poor therapeutic effects. Cells are often grown under three-dimensional (3D) conditions in vivo, and the stiffness and components of the extracellular matrix (ECM) are important regulators of stem cell differentiation. To this end, a 3D cartilage-like ECM hydrogel with tunable mechanical properties was designed and synthesized mainly from gelatin methacrylate (GM) and oxidized chondroitin sulfate (OCS) via dynamic Schiff base bonding under UV. The effects of scaffold stiffness and composition on the survival and differentiation of BMSCs in vitro were investigated. A rat model of growth plate injury was developed to validate the effect of the GMOCS hydrogels encapsulated with BMSCs on the repair of growth plate injury. The results showed that 3D GMOCS hydrogels with an appropriate modulus significantly promoted chondrogenic differentiation of BMSCs, and GMOCS/BMSC transplantation could effectively inhibit bone bridge formation and promote the repair of damaged growth plates. Accordingly, GMOCS/BMSC therapy can be engineered as a promising therapeutic candidate for growth plate injury.

C2 -GAN: Content-consistent generative adversarial networks for unsupervised domain adaptation in medical image segmentation.

PURPOSE: In clinical practice, medical image analysis has played a key role in disease diagnosis. One of the important steps is to perform an accurate organ or tissue segmentation for assisting medical professionals in making correct diagnoses. Despite the tremendous progress in the deep learning-based medical image segmentation approaches, they often fail to generalize to test datasets due to distribution discrepancies across domains. Recent advances aligning the domain gaps by using bi-directional GANs (e.g., CycleGAN) have shown promising results, but the strict constraints of the cycle consistency hamper these methods from yielding better performance. The purpose of this study is to propose a novel bi-directional GAN-based segmentation model with fewer constraints on the cycle consistency to improve the generalized segmentation results. METHODS: We propose a novel unsupervised domain adaptation approach by designing content-consistent generative adversarial networks ( C 2 -GAN $\text{C}^2\text{-GAN}$ ) for medical image segmentation. First, we introduce content consistency instead of cycle consistency to relax the constraint of the invertibility map to encourage the synthetic domain generated with a large domain transportation distance. The synthetic domain is thus pulled close to the target domain for the reduction of domain discrepancy. Second, we suggest a novel style transfer loss based on the difference in low-frequency magnitude to further mitigate the appearance shifts across domains. RESULTS: We validate our proposed approach on three public X-ray datasets, including the Montgomery, JSRT, and Shenzhen datasets. For an accurate evaluation, we randomly divided the images of each dataset into 70% for training, 10% for evaluation, and 20% for testing. The mean Dice was 95.73 ± 0.22%, 95.16 ± 1.42% for JSRT and Shenzhen datasets, respectively. For the recall and precision metrics, our model also achieved better or comparable performance than the state-of-the-art CycleGAN-based UDA approaches. CONCLUSIONS: The experimental results validate the effectiveness of our method in mitigating the domain gaps and improving generalized segmentation results for X-ray image segmentation.

Robust Medical Image Colorization with Spatial Mask-Guided Generative Adversarial Network.

Color medical images provide better visualization and diagnostic information for doctors during clinical procedures than grayscale medical images. Although generative adversarial network-based image colorization approaches have shown promising results, in these methods, adversarial training is applied to the whole image without considering the appearance conflicts between the foreground objects and the background contents, resulting in generating various artifacts. To remedy this issue, we propose a fully automatic spatial mask-guided colorization with generative adversarial network (SMCGAN) framework for medical image colorization. It generates colorized images with fewer artifacts by introducing spatial masks, which encourage the network to focus on the colorization of the foreground regions instead of the whole image. Specifically, we propose a novel spatial mask-guided method by introducing an auxiliary foreground segmentation branch combined with the main colorization branch to obtain the spatial masks. The spatial masks are then used to generate masked colorized images where most background contents are filtered out. Moreover, two discriminators are utilized for the generated colorized images and masked generated colorized images, respectively, to assist the model in focusing on the colorization of foreground regions. We validate our proposed framework on two publicly available datasets, including the Visible Human Project (VHP) dataset and the prostate dataset from NCI-ISBI 2013 challenge. The experimental results demonstrate that SMCGAN outperforms the state-of-the-art GAN-based image colorization approaches with an average improvement of 8.48% in the PSNR metric. The proposed SMCGAN can also generate colorized medical images with fewer artifacts.

Robust color medical image segmentation on unseen domain by randomized illumination enhancement.

Owing to the data distribution shifts generated by collecting images using various imaging protocols and device vendors, the generalization capability of deep models is crucial for medical image analysis when applied to test datasets in clinical environments. Domain generalization (DG) methods have shown promising generalization performance in the field of medical image segmentation. In contrast to conventional DG, which has strict requirements regarding the availability of multiple source domains, we consider a more challenging problem, that is, single-domain generalization (SDG), where only a single source is available during network training. In this scenario, the augmentation of the entire image to improve the model generalization ability may cause alteration of hue values, resulting in the wrong segmentation of tissues in color medical images. To resolve this problem, we first present a novel illumination-randomized SDG framework to improve the model generalization power for color medical image segmentation by synthesizing randomized illumination maps. Specifically, we devise unsupervised retinex-based image decomposition neural networks (ID-Nets) to decompose color medical images into reflectance and illumination maps. Illumination maps are augmented by performing illumination randomization to generate medical color images under diverse illumination conditions. Second, to measure the quality of retinex-based image decomposition, we devise a novel metric, the transport gradient consistency index, by modeling physical illumination. Extensive experiments are performed to evaluate our proposed framework on two retinal fundus image segmentation tasks: optic cup and disc segmentation. The experimental results demonstrate that our framework outperforms other SDG and image enhancement methods, surpassing the state-of-the-art SDG methods by up to 9.6% with respect to the Dice coefficient.