Deep learning prediction of renal anomalies for prenatal ultrasound diagnosis.

Deep learning algorithms have demonstrated remarkable potential in clinical diagnostics, particularly in the field of medical imaging. In this study, we investigated the application of deep learning models in early detection of fetal kidney anomalies. To provide an enhanced interpretation of those models' predictions, we proposed an adapted two-class representation and developed a multi-class model interpretation approach for problems with more than two labels and variable hierarchical grouping of labels. Additionally, we employed the explainable AI (XAI) visualization tools Grad-CAM and HiResCAM, to gain insights into model predictions and identify reasons for misclassifications. The study dataset consisted of 969 ultrasound images from unique patients; 646 control images and 323 cases of kidney anomalies, including 259 cases of unilateral urinary tract dilation and 64 cases of unilateral multicystic dysplastic kidney. The best performing model achieved a cross-validated area under the ROC curve of 91.28% ± 0.52%, with an overall accuracy of 84.03% ± 0.76%, sensitivity of 77.39% ± 1.99%, and specificity of 87.35% ± 1.28%. Our findings emphasize the potential of deep learning models in predicting kidney anomalies from limited prenatal ultrasound imagery. The proposed adaptations in model representation and interpretation represent a novel solution to multi-class prediction problems.

The efficacy of systematic lymph node dissection in advanced epithelial ovarian cancer during interval debulking surgery performed after neoadjuvant chemotherapy.

BACKGROUND AND OBJECTIVE: The therapeutic role of systematic lymph node dissection (LND) remains unclear in advanced epithelial ovarian cancer (EOC), especially during interval debulking surgery (IDS) performed after neoadjuvant chemotherapy (NAC). We analyzed the therapeutic and prognostic roles of systematic LND in advanced EOC patients. METHODS: Data from consecutive patients with International Federation of Gynecology and Obstetrics (FIGO) stage IIIC-IV disease, who underwent optimal IDS (<1cm) after NAC, were obtained via a retrospective chart review. Patients were classified into a lymph node sampling (LNS; node count <20) group and an LND (node count ≥20) group. RESULTS: Among 133 study patients, 65 and 68 underwent LND and LNS, respectively, during IDS. Overall survival (OS) was significantly better in the LND group than in the LNS group. In subgroup analysis with negative lymphadenopathy on preoperative imaging, progression-free survival (PFS) and OS were significantly better in the LND group than in the LNS group. Follow-up of subsequent recurrences showed significantly lower nodal and peritoneal recurrence rates among patients who underwent LND. Multivariate analysis identified LND as an independent prognostic factor for PFS and OS. CONCLUSION: Systematic LND may have therapeutic value in advanced EOC patients treated with NAC and IDS.

[A review study on the strategies for concept analysis].

PURPOSE: Concept analysis is an essential part of theory development in nursing. Thus, many strategies or methods of concept analysis have been suggested in nursing literature. However, in Korea, only limited strategies were utilized, without much consideration on a wide range of strategies in choosing a method that coincides with the characteristics of each concept to analyze. The purpose of this article was to propose various strategies for concept analysis. METHOD: A literature review method was used. RESULT: Ten methods of concept analysis were identified in the literature, and they were evaluated for advantages and limitations. In addition to the method by Walker and Avant and a hybrid model, more advanced strategies, such as triangulation method, critical analysis and the feminist approach were introduced and described in detail. The examples used in each concept analysis method were presented in table to provide the extent of utilization of each method. CONCLUSION: This article provides a wide range of strategies in identifying, clarifying, or elaborating a concept. It might help in choosing a method that best fits the concept to analyze, thus enhancing quality of concept analysis research.