ABSTRACT
Breast cancer is a significant health issue affecting women worldwide, and accurately detecting lymph node metastasis is critical in determining treatment and prognosis. While traditional diagnostic methods have limitations and complications, artificial intelligence (AI) techniques such as machine learning (ML) and deep learning (DL) offer promising solutions for improving and supplementing diagnostic procedures. Current research has explored state-of-the-art DL models for breast cancer lymph node classification from radiological images, achieving high performances (AUC: 0.71-0.99). AI models trained on clinicopathological features also show promise in predicting metastasis status (AUC: 0.74-0.77), whereas multimodal (radiomics + clinicopathological features) models combine the best from both approaches and also achieve good results (AUC: 0.82-0.94). Once properly validated, such models could greatly improve cancer care, especially in areas with limited medical resources. This comprehensive review aims to compile knowledge about state-of-the-art AI models used for breast cancer lymph node metastasis detection, discusses proper validation techniques and potential pitfalls and limitations, and presents future directions and best practices to achieve high usability in real-world clinical settings.
ABSTRACT
Purpose: The aim of this study was to compare the perioperative and postoperative respiratory complications between laryngeal mask (LM) airway and tracheal intubation (TI) in children undergoing percutaneous internal ring suturing (PIRS) for inguinal hernia. Patients and Methods: From October 2015 to February 2019, 135 pediatric patients (97 males and 38 females) with median age of 4 years, who underwent PIRS for inguinal hernia, were included in study. Patients were divided in two groups. In group I (n = 94) LM airway was used, and in group II (n = 41) TI was performed. Demographic data, surgical and anesthesia times, American Society of Anesthesiologists (ASA) classification, muscle relaxation, level of pneumoperitoneum, and complications of anesthesia were compared between the groups. Results: No significant differences among compared groups regarding age (P = .435), sex (P = .306), body mass index (P = .548), ASA classification (P = .506), level of pneumoperitoneum (P = .968), and duration of surgery (P = .968) were found. Duration of anesthesia was significantly shorter when LM was used compared to TI (25 minutes versus 36 minutes; P < .00001). During recovery from anesthesia, the incidences of desaturation (n = 1 versus n = 5; P = .003), laryngospasm (n = 2 versus n = 5; P = .015), and cough (n = 0 versus n = 4; P = .002) were significantly lower when LM airway was used for securing of the airway. Postoperative incidences of sore throat (P = .543), bronchospasm (P = .128), and aspiration (P = .128) did not differ between LM and TI. Conclusions: The use of LM in pediatric anesthesia results in a decrease in a number of common complications and significantly shortened patient anesthesia time. It is therefore a valuable device for the management of the pediatric airway for laparoscopic hernia repair in children.
