RESUMEN
Objective and Impact Statement: Human epidermal growth factor receptor 2 (HER2) is a critical protein in cancer cell growth that signifies the aggressiveness of breast cancer (BC) and helps predict its prognosis. Here, we introduce a deep learning-based approach utilizing pyramid sampling for the automated classification of HER2 status in immunohistochemically (IHC) stained BC tissue images. Introduction: Accurate assessment of IHC-stained tissue slides for HER2 expression levels is essential for both treatment guidance and understanding of cancer mechanisms. Nevertheless, the traditional workflow of manual examination by board-certified pathologists encounters challenges, including inter- and intra-observer inconsistency and extended turnaround times. Methods: Our deep learning-based method analyzes morphological features at various spatial scales, efficiently managing the computational load and facilitating a detailed examination of cellular and larger-scale tissue-level details. Results: This approach addresses the tissue heterogeneity of HER2 expression by providing a comprehensive view, leading to a blind testing classification accuracy of 84.70%, on a dataset of 523 core images from tissue microarrays. Conclusion: This automated system, proving reliable as an adjunct pathology tool, has the potential to enhance diagnostic precision and evaluation speed, and might substantially impact cancer treatment planning.
RESUMEN
Background: The drug reaction with eosinophilia and systemic symptoms (DRESS) syndrome represents a severe hypersensitivity reaction. Up-to-date treatment is based on withdrawal of medication, supportive care, and immunosuppression using high-dose corticosteroid (CS) therapy. However, evidence-based data are lacking regarding second-line therapy for steroid-resistant or steroid-dependent patients. Objectives: We hypothesize that the interleukin (IL)-5 axis plays a critical role in the pathophysiology of DRESS; hence, inhibition of this signaling pathway could offer a potential therapy for steroid-dependent and/or steroid-resistant cases, and it may offer an alternative to CS therapy in certain patients more prone to CS toxicity. Methods: Herein, we collected worldwide data on DRESS cases treated with biological agents targeting the IL-5 axis. We reviewed all cases indexed in PubMed up to October 2022 and performed a total analysis including our center experience with two additional novel cases. Results: A review of the literature yielded 14 patients with DRESS who were treated with biological agents targeting the IL-5 axis as well as our two new cases. Reported patients are characterized by a female-to-male ratio of 1:1 and a mean age of 51.8 (17-87) years. The DRESS-inducing drugs, as expected from the prospective RegiSCAR study, were mostly antibiotics (7/16), as follows: vancomycin, trimethoprim-sulfamethoxazole, ciprofloxacin, piperacillin-tazobactam, and cefepime. DRESS patients were treated with anti-IL-5 agents (mepolizumab and reslizumab) or anti-IL-5 receptor (IL-5R) biologics (benralizumab). All patients have clinically improved under anti-IL-5/IL-5R biologics. Multiple doses of mepolizumab were needed to achieve clinical resolution, whereas a single dose of benralizumab was often sufficient. Relapse was noted in one patient receiving benralizumab treatment. One patient receiving benralizumab had a fatal outcome, although mortality was probably related to massive bleeding and cardiac arrest due to coronavirus disease 2019 (COVID-19) infection. Conclusion: Current treatment guidelines for DRESS are based on case reports and expert opinion. Understanding the central role of eosinophils in DRESS pathogenicity emphasizes the need for future implementation of IL-5 axis blockade as steroid-sparing agents, potential therapy to steroid-resistant cases, and perhaps an alternative to CS treatment in certain DRESS patients more prone to CS toxicity.
