Intersection-union dual-stream cross-attention Lova-SwinUnet for skin cancer hair segmentation and image repair.

Skin cancer images have hair occlusion problems, which greatly affects the accuracy of diagnosis and classification. Current dermoscopic hair removal methods use segmentation networks to locate hairs, and then uses repair networks to perform image repair. However, it is difficult to segment hair and capture the overall structure between hairs because of the hair being thin, unclear, and similar in color to the entire image. When conducting image restoration tasks, the only available images are those obstructed by hair, and there is no corresponding ground truth (supervised data) of the same scene without hair obstruction. In addition, the texture information and structural information used in existing repair methods are often insufficient, which leads to poor results in skin cancer image repair. To address these challenges, we propose the intersection-union dual-stream cross-attention Lova-SwinUnet (IUDC-LS). Firstly, we propose the Lova-SwinUnet module, which embeds Lovasz loss function into Swin-Unet, enabling the network to better capture features of various scales, thus obtaining better hair mask segmentation results. Secondly, we design the intersection-union (IU) module, which takes the mask results obtained in the previous step for pairwise intersection or union, and then overlays the results on the skin cancer image without hair to generate the labeled training data. This turns the unsupervised image repair task into the supervised one. Finally, we propose the dual-stream cross-attention (DC) module, which makes texture information and structure information interact with each other, and then uses cross-attention to make the network pay attention to the more important texture information and structure information in the fusion process of texture information and structure information, so as to improve the effect of image repair. The experimental results show that the PSNR index and SSIM index of the proposed method are increased by 5.4875 and 0.0401 compared with the other common methods. Experimental results unequivocally demonstrate the effectiveness of our approach, which serves as a potent tool for skin cancer detection, significantly surpassing the performance of comparable methods.

Cardiotoxicity from neoadjuvant targeted treatment for breast cancer prior to surgery.

Cancer treatment has been gradually shifting from non-specific cytotoxic agents to molecularly targeted drugs. Breast cancer (BC), a malignant tumor with one of the highest incidence worldwide, has seen a rapid development in terms of targeted therapies, leading to a radical change in the treatment paradigm. However, the use of targeted drugs is accompanied by an increasing rate of deaths due to non-tumor-related causes in BC patients, with cardiovascular complications as the most common cause. Cardiovascular toxicity during antitumor therapy has become a high-risk factor for survival in BC patients. Targeted drug-induced cardiotoxicity exerts a wide range of effects on cardiac structure and function, including conduction disturbances, QT interval prolongation, impaired myocardial contractility, myocardial fibrosis, and hypertrophy, resulting in various clinical manifestations, e.g., arrhythmias, cardiomyopathy, heart failure, and even sudden death. In adult patients, the incidence of antitumor targeted drug-induced cardiotoxicity can reach 50%, and current preclinical evaluation tools are often insufficiently effective in predicting clinical cardiotoxicity. Herein, we reviewed the current status of the occurrence, causative mechanisms, monitoring methods, and progress in the prevention and treatment of cardiotoxicity associated with preoperative neoadjuvant targeted therapy for BC. It supplements the absence of relevant review on the latest research progress of preoperative neoadjuvant targeted therapy for cardiotoxicity, with a view to providing more reference for clinical treatment of BC patients.

Effect of High Suspension and Low Incision Surgery Based on Traditional Ligation of Chinese Medicine in Treatment of Mixed Haemorrhoids: A Multi-centre, Randomized, Single-Blind, Non-inferiority Clinical Trial.

OBJECTIVE: To observe the clinical effect of high suspension and low incision (HSLI) surgery on mixed haemorrhoids, compared with Milligan-Morgan haemorrhoidectomy. METHODS: A multi-centre, randomized, single-blind, non-inferiority clinical trial was performed. Participants with mixed haemorrhoids from Xiyuan Hospital of China Academy of Chinese Medical Sciences, Beijing Rectum Hospital, Air Force Medical Center of People's Liberation Army of China, and Puyang Hospital of Traditional Chinese Medicine were enrolled from September 2016 to March 2018. By using a blocked randomization scheme, participants were assigned to two groups. The experimental group was treated with HSLI, while the control group was treated with Milligan-Morgan haemorrhoidectomy. The primary outcome was the clinical effect evaluated at 12 weeks after operation. The secondary outcomes included the number of haemorrhoids treated during the operation, pain scores, use of analgesics, postoperative oedema, wound healing, incidence of anal stenosis, anorectal manometry after operation, as well as surgical duration, length of stay and total hospitalization expenses. A safety evaluation was also conducted. RESULTS: In total, 246 eligible participants were enrolled, with 123 cases in each group. There was no significant difference in the clinical effect between the two groups (100.00% vs. 99.19%, P>0.05). Compared with the control group, the number of external haemorrhoids treated during the operation and the pain scores after operation were significantly reduced in the experimental group (P<0.05 or P<0.01); the patient number with wound healing at 2 weeks after operation and the functional length of anal canal at 12 weeks after operation were significantly increased in the experimental group (P<0.05). There was no significant difference in the incidence of anal stenosis, the numbers of patients using analgesics and patients with postoperative oedema between the two groups after operation (P>0.05). The surgical duration and length of stay in the experimental group were significantly longer than those in the control group, and the total hospitalization expense was significantly higher than that in the control group (all P<0.05). No adverse events were reported in either group during the whole trial or follow-up period. CONCLUSION: HSLI had the advantages of preserving the skin of anal canal completely, alleviating postsurgical pain and promoting rapid recovery after operation. (Registration No. ChiCTR1900022883).