BBox-Guided Segmentor: Leveraging expert knowledge for accurate stroke lesion segmentation using weakly supervised bounding box prior.

Stroke is one of the leading causes of death and disability in the world. Despite intensive research on automatic stroke lesion segmentation from non-invasive imaging modalities including diffusion-weighted imaging (DWI), challenges remain such as a lack of sufficient labeled data for training deep learning models and failure in detecting small lesions. In this paper, we propose BBox-Guided Segmentor, a method that significantly improves the accuracy of stroke lesion segmentation by leveraging expert knowledge. Specifically, our model uses a very coarse bounding box label provided by the expert and then performs accurate segmentation automatically. The small overhead of having the expert provide a rough bounding box leads to large performance improvement in segmentation, which is paramount to accurate stroke diagnosis. To train our model, we employ a weakly-supervised approach that uses a large number of weakly-labeled images with only bounding boxes and a small number of fully labeled images. The scarce fully labeled images are used to train a generator segmentation network, while adversarial training is used to leverage the large number of weakly-labeled images to provide additional learning signals. We evaluate our method extensively using a unique clinical dataset of 99 fully labeled cases (i.e., with full segmentation map labels) and 831 weakly labeled cases (i.e., with only bounding box labels), and the results demonstrate the superior performance of our approach over state-of-the-art stroke lesion segmentation models. We also achieve competitive performance as a SOTA fully supervised method using less than one-tenth of the complete labels. Our proposed approach has the potential to improve stroke diagnosis and treatment planning, which may lead to better patient outcomes.

Saikokeishikankyoto extract alleviates muscle atrophy in KKAy mice.

Sarcopenic obesity is associated with increased visceral fat and decreased muscle mass, resulting in decreased insulin sensitivity, increased production of inflammatory cytokines, and oxidative stress. In this study, we first evaluated the effects of herbal medicines on the transcriptional activity of the Sirtuin 1 (sirt1) promoter in vitro as an indicator of their therapeutic effect. Our data suggested that hot water Saikokeishikankyoto (SKK) extracts increased sirt1 transcriptional activity in vitro, identifying it as a candidate therapeutic for evaluation in the KKAy type 2 diabetic obesity mouse model. These in vivo evaluations revealed that SKK treatment increased the wet weight and muscle fiber content in cross sections of the gastrocnemius muscle (GA) and restored motor function in these animals. In addition, SKK treatment reduced tumor necrosis factor-α (TNFα) expression in the sera and suppressed Atrogin1 and MuRF1 transcription in the GA samples. This treatment also increased sirt1 expression in these tissues. These results suggest that SKK inhibits skeletal muscle atrophy and improves motor function in KKAy mice by suppressing inflammation. In actual clinical practice, SKK is expected to inhibit muscle atrophy and improve motor dysfunction in sarcopenic obesity.

Juzentaihoto Suppresses Muscle Atrophy in Streptozotocin-Induced Diabetic Mice.

In diabetic patients, skeletal muscle atrophy occurs due to increased oxidative stress and inflammation. Skeletal muscle atrophy reduces the QOL of patients and worsens life prognosis. Therefore, development of preventive therapy for muscle atrophy in hyperglycemic state is eagerly awaited. Juzentaihoto is a medicinal herb that has a function to supplement physical strength, and it is expected to prevent muscle atrophy. To determine the preventive effect of juzentaihoto on muscle atrophy in hyperglycemic state, streptozotocin (STZ) was administered to induce diabetes in mice and the preventive effect of juzentaihoto was evaluated. Mice that received juzentaihoto extract (JTT) showed that the decrease in muscle fiber cross-sectional area in the gastrocnemius muscle was reversed. Additionally, the expression level of tumor necrosis factor α (TNF-α), an inflammatory cytokine, in serum decreased, and that of ubiquitin ligase (atrogin-1, muscle RING-finger protein-1) mRNA in skeletal muscle decreased. An anti-inflammatory cytokine interleukin-10 showed increased levels in the serum and increased levels in spleen cell culture supernatant collected from mice that received JTT. JTT had no effect on the blood glucose level. These results suggest that prophylactic administration of JTT to STZ-induced diabetic mice affects immune cells such as in spleen, causing an anti-inflammatory effect and inhibiting excessive activation of the ubiquitin-proteasome system, to reverse muscle atrophy.

Juzentaihoto hot water extract alleviates muscle atrophy and improves motor function in streptozotocin-induced diabetic oxidative stress mice.

A decrease in skeletal muscle mass and motor function occurs in diabetic patients. In type 1 diabetic patients, in particular, fast-type fiber-dominated muscle atrophy occurs due to increased oxidative stress and inflammation. Juzentaihoto is a herbal medicine that has been found to be effective in reducing oxidative stress. In this study, juzentaihoto hot water extract (JTT) was administered prophylactically to mice with diabetic oxidative stress, which was induced by an injection of streptozotocin, and the effects on skeletal muscle mass, motor function, and antioxidant activity were evaluated. In mice that were administered JTT, skeletal muscle atrophy and loss of motor function were suppressed. Additionally, the administration of JTT increased the mRNA expression level of Sirt1 and the activity of superoxide dismutase in the gastrocnemius. In addition to skeletal muscle atrophy, atrophy of the liver, spleen and thymus gland, and kidney hypertrophy were also suppressed. Furthermore, in order to evaluate the antioxidant activity of 10 constituent crude drugs that comprise juzentaihoto, Sirt1 transcriptional activity in C2C12 cells was evaluated. The Sirt1 transcriptional activity was increased by Cinnamomi Cortex, Astragali Radix, and Glycyrrhizae Radix extracts. These three constituent crude drugs play an important function in the antioxidant action of juzentaihoto, suggesting that juzentaihoto can prevent muscle atrophy by decreasing oxidative stress.