Automatic identification of suspicious bone metastatic lesions in bone scintigraphy using convolutional neural network.

BACKGROUND: We aimed to construct an artificial intelligence (AI) guided identification of suspicious bone metastatic lesions from the whole-body bone scintigraphy (WBS) images by convolutional neural networks (CNNs). METHODS: We retrospectively collected the 99mTc-MDP WBS images with confirmed bone lesions from 3352 patients with malignancy. 14,972 bone lesions were delineated manually by physicians and annotated as benign and malignant. The lesion-based differentiating performance of the proposed network was evaluated by fivefold cross validation, and compared with the other three popular CNN architectures for medical imaging. The average sensitivity, specificity, accuracy and the area under receiver operating characteristic curve (AUC) were calculated. To delve the outcomes of this study, we conducted subgroup analyses, including lesion burden number and tumor type for the classifying ability of the CNN. RESULTS: In the fivefold cross validation, our proposed network reached the best average accuracy (81.23%) in identifying suspicious bone lesions compared with InceptionV3 (80.61%), VGG16 (81.13%) and DenseNet169 (76.71%). Additionally, the CNN model's lesion-based average sensitivity and specificity were 81.30% and 81.14%, respectively. Based on the lesion burden numbers of each image, the area under the receiver operating characteristic curve (AUC) was 0.847 in the few group (lesion number n ≤ 3), 0.838 in the medium group (n = 4-6), and 0.862 in the extensive group (n > 6). For the three major primary tumor types, the CNN-based lesion identifying AUC value was 0.870 for lung cancer, 0.900 for prostate cancer, and 0.899 for breast cancer. CONCLUSION: The CNN model suggests potential in identifying suspicious benign and malignant bone lesions from whole-body bone scintigraphic images.

Spironolactone Protects against Diabetic Cardiomyopathy in Streptozotocin-Induced Diabetic Rats.

Spironolactone (SPR) has been shown to protect diabetic cardiomyopathy (DCM), but the specific mechanisms are not fully understood. Here, we determined the cardioprotective role of SPR in diabetic mice and further explored the potential mechanisms in both in vivo and in vitro models. Streptozotocin- (STZ-) induced diabetic rats were used as the in vivo model. After the onset of diabetes, rats were treated with either SPR (STZ + SPR) or saline (STZ + NS) for 12 weeks; nondiabetic rats were used as controls (NDCs). In vitro, H9C2 cells were exposed to aldosterone, with or without SPR. Cardiac structure was investigated with transmission electron microscopy and pathological examination; immunohistochemistry was performed to detect nitrotyrosine, collagen-1, TGF-ß1, TNF-α, and F4/80 expression; and gene expression of markers for oxidative stress, inflammation, fibrosis, and energy metabolism was detected. Our results suggested that SPR attenuated mitochondrial morphological abnormalities and sarcoplasmic reticulum enlargement in diabetic rats. Compared to the STZ + NS group, cardiac oxidative stress, fibrosis, inflammation, and mitochondrial dysfunction were improved by SPR treatment. Our study showed that SPR had cardioprotective effects in diabetic rats by ameliorating mitochondrial dysfunction and reducing fibrosis, oxidative stress, and inflammation. This study, for the first time, indicates that SPR might be a potential treatment for DCM.

Exogenous kallikrein protects against diabetic nephropathy.

The kallikrein-kinin system has been shown to be involved in the development of diabetic nephropathy, but specific mechanisms are not fully understood. Here, we determined the renal-protective role of exogenous pancreatic kallikrein in diabetic mice and studied potential mechanisms in db/db type 2 diabetic and streptozotocin-induced type 1 diabetic mice. After the onset of diabetes, mice were treated with either pancreatic kallikrein (db/db+kallikrein, streptozotocin+kallikrein) or saline (db/db+saline, streptozotocin+saline) for 16 weeks, while another group of streptozotocin-induced diabetic mice received the same treatment after onset of albuminuria (streptozotocin'+kallikrein, streptozotocin'+saline). Db/m littermates or wild type mice were used as non-diabetic controls. Pancreatic kallikrein had no effects on body weight, blood glucose and blood pressure, but significantly reduced albuminuria among all three groups. Pathological analysis showed that exogenous kallikrein decreased the thickness of the glomerular basement membrane, protected against the effacement of foot process, the loss of endothelial fenestrae, and prevented the loss of podocytes in diabetic mice. Renal fibrosis, inflammation and oxidative stress were reduced in kallikrein-treated mice compared to diabetic controls. The expression of kininogen1, tissue kallikrein, kinin B1 and B2 receptors were all increased in the kallikrein-treated compared to saline-treated mice. Thus, exogenous pancreatic kallikrein both prevented and ameliorated diabetic nephropathy, which may be mediated by activating the kallikrein-kinin system.