A s the most common cancer among women worldwide, breast cancer poses a great challenge to public health on a global scale (1). Identification of the presence of lymph node metastasis is pivotal for the pathologic staging, prognosis, and guidance of treatment in patients with breast cancer (2). Although several histopathologic findings, such as vascular and lymphatic invasion, epithelial hyperplasia, and necrosis, are associated with a higher risk for lymph node metastasis, they are available only postoperatively (3). The preoperative prediction of lymph node metastasis can provide valuable information for determining adjuvant therapy and developing surgical plans, thereby facilitating pretreatment decisions.Preoperative imaging assessment is of great value because of its convenient, comprehensive, and noninvasive properties. US plays a crucial role in detecting breast cancer and predicting lymph node metastasis (4). Most patients with early stage breast cancer who have clinically negative lymph nodes have no suspicious signs at either physical examination or imaging. Although radiologists often cannot find any signs of metastasis on US images of clinically negative lymph nodes, axillary lymph node metastasis is detected with sentinel lymph node biopsy in 15%-20% of patients (5). Several studies have found that numerous breast US characteristics are associated with lymph node metastasis. The distance

Artificial intelligence (AI), particularly deep learning algorithms, is gaining extensive attention for its excellent performance in image-recognition tasks. They can automatically make a quantitative assessment of complex medical image characteristics and achieve an increased accuracy for diagnosis with higher efficiency. AI is widely used and getting increasingly popular in the medical imaging of the liver, including radiology, ultrasound, and nuclear medicine. AI can assist physicians to make more accurate and reproductive imaging diagnosis and also reduce the physicians’ workload. This article illustrates basic technical knowledge about AI, including traditional machine learning and deep learning algorithms, especially convolutional neural networks, and their clinical application in the medical imaging of liver diseases, such as detecting and evaluating focal liver lesions, facilitating treatment, and predicting liver treatment response. We conclude that machine-assisted medical services will be a promising solution for future liver medical care. Lastly, we discuss the challenges and future directions of clinical application of deep learning techniques.

Background SF1126 is a peptidic pro-drug inhibitor of pan-PI3K/mTORC. A first-in-human study evaluated safety, dose limiting toxicities (DLT), maximum tolerated dose (MTD), pharmacokinetics (PK), pharmacodynamics (PD) and efficacy of SF1126, in patients with advanced solid and B-cell malignancies. Patients and methods SF1126 was administered IV days 1 and 4, weekly in 28 day-cycles. Dose escalation utilised modified Fibonacci 3+3. Samples to monitor PK and PD were obtained. Results Forty four patients were treated at 9 dose levels (90–1110 mg/m2/day). Most toxicity was grade 1 and 2 with a single DLT at180 mg/m2 (diarrhoea). Exposure measured by peak concentration (Cmax) and area under the time-concentration curve (AUC0-t) was dose proportional. Stable disease (SD) was the best response in 19 of 33 (58%) evaluable patients. MTD was not reached but the maximum administered dose (MAD) was 1110 mg/m2. The protocol was amended to enrol patients with CD20+ B-cell malignancies at 1110 mg/m2. A CLL patient who progressed on rituximab [R] achieved SD after 2 months on SF1126 alone but in combination with R achieved a 55% decrease in absolute lymphocyte count and a lymph node response. PD studies of CLL cells demonstrated SF1126 reduced p-AKT and increased apoptosis indicating inhibition of activated PI3K signalling. Conclusion SF1126 is well tolerated with SD as the best response in patients with advanced malignancies.

Postmenopausal osteoporosis severely jeopardizes human health. Seeking for therapeutic drugs without side effects is of great necessity. Our study was designed to investigate whether resveratrol, an agonist of SIRT1, could have favorable effect on osteoporosis and to explore the underlying mechanisms. Rat osteoporosis model (ovariectomy group, OVX) was established by bilateral ovariectomy. respectively; P < 0.05). Serum markers alkaline phosphatase (ALP) and osteocalcin were moderately restored by resveratrol. Moreover, resveratrol improved bone structure in OVX rats, demonstrated by hematoxylin-eosin staining and micro-computed tomographic results. In vitro results revealed that resveratrol promoted osteoblast differentiation of bone marrow mesenchymal stromal cells, evidenced by the increase of ALP generation and mRNA expression of collagen 1 (P < 0.05; RES MD , RES HD vs. control group). SIRT1 gene silencing by siRNA transfection blocked these beneficial effects of resveratrol (P < 0.05; RES 1 SIRT1 KD vs. RES HD ).Western blot results showed that resveratrol activated SIRT1 and subsequently suppressed the activity of NF-kB with decreased expression level of p-IkBa and NF-kB p65 (P < 0.05). Our findings verified the effects of specific dosed resveratrol on postmenopausal osteoporosis through osteoblast differentiation via SIRT1-NF-kB signaling pathway. This study suggested the therapeutic potential of resveratrol against osteoporosis and stressed the importance of effective doses.