Automatic classification of spinal osteosarcoma and giant cell tumor of bone using optimized DenseNet.

Objective: This study aims to explore an optimized deep-learning model for automatically classifying spinal osteosarcoma and giant cell tumors. In particular, it aims to provide a reliable method for distinguishing between these challenging diagnoses in medical imaging. Methods: This research employs an optimized DenseNet model with a self-attention mechanism to enhance feature extraction capabilities and reduce misclassification in differentiating spinal osteosarcoma and giant cell tumors. The model utilizes multi-scale feature map extraction for improved classification accuracy. The paper delves into the practical use of Gradient-weighted Class Activation Mapping (Grad-CAM) for enhancing medical image classification, specifically focusing on its application in diagnosing spinal osteosarcoma and giant cell tumors. The results demonstrate that the implementation of Grad-CAM visualization techniques has improved the performance of the deep learning model, resulting in an overall accuracy of 85.61%. Visualizations of images for these medical conditions using Grad-CAM, with corresponding class activation maps that indicate the tumor regions where the model focuses during predictions. Results: The model achieves an overall accuracy of 80% or higher, with sensitivity exceeding 80% and specificity surpassing 80%. The average area under the curve AUC for spinal osteosarcoma and giant cell tumors is 0.814 and 0.882, respectively. The model significantly supports orthopedics physicians in developing treatment and care plans. Conclusion: The DenseNet-based automatic classification model accurately distinguishes spinal osteosarcoma from giant cell tumors. This study contributes to medical image analysis, providing a valuable tool for clinicians in accurate diagnostic classification. Future efforts will focus on expanding the dataset and refining the algorithm to enhance the model's applicability in diverse clinical settings.

Ultra-microhistological study of nonthermal irreversible electroporation on the esophagus.

BACKGROUND: Esophageal ulceration and even fistula are severe complications of pulmonary vein isolation using traditional thermal ablation. Nonthermal irreversible electroporation (NTIRE) is a new technique for pulmonary vein isolation in patients with atrial fibrillation. NTIRE has been shown to be a safe method for pulsed electroporation near the esophagus. NTIRE preserves the structural framework of the esophagus and allows for rapid recovery of the whole layers of the esophagus. OBJECTIVE: The purpose of this study was to elucidate the ultrastructural changes and cytological mechanisms of cell regeneration and tissue repair after esophageal electroporation. METHODS: The parameter combination of 2000 V/cm multiplied by 90-pulse output was directly applied to the esophagus in 60 New Zealand rabbits, and ultrastructure analysis of the esophagus was implemented subsequently. RESULTS: NTIRE predominantly triggered apoptosis of esophageal cells shortly after electroporation. Since the tissue structural framework was preserved, esophageal cells could regenerate through self-replication within 4 weeks. Complete anatomical repair can eventually be achieved through structural remodeling, and no lumen stenosis, ulcer, or fistula was observed in the ablated segment. CONCLUSION: Monophasic, bipolar NTIRE pulses delivered using plate electrodes in an esophageal model demonstrates no irreversible ultra-micropathological changes to the esophagus after 4 weeks.

Metabolic Syndrome is an Independent Risk Factor for Fuhrman Grade and TNM Stage of Renal Clear Cell Carcinoma.

BACKGROUND: More and more evidences show that metabolic syndrome (MS) is closely related to clear cell renal cell carcinoma (ccRCC), but the impact of MS on Fuhrman grade and TNM stage of ccRCC is rarely reported. PURPOSE: To explore the relationship between MS and its components of Fuhrman grade and TNM stage in ccRCC. OBJECTIVE: The clinical data of 247 patients with ccRCC diagnosed in our hospital from January 2016 to November 2020 were retrospectively collected and analyzed. Based on diagnostic criteria of MS, the patients were divided into MS and non-MS group. Logistic regression analysis was used to analyze the independent risk factors of ccRCC. RESULTS: The incidence of MS was 32.79% (81/247). There was no significant difference in age, gender, smoking and drinking between MS group and non-MS group (P > 0.05). In MS group, BMI ≥25kg/m2, hypertension, diabetes, hyperlipidemia, tumor diameter, poorly differentiated renal cancer, high-stage renal cancer, triglyceride, fasting blood glucose, glycated hemoglobin, fasting insulin and homeostasis model assessment index were significantly higher than those in non-MS group (P < 0.001), while in high density lipoprotein cholesterol (p < 0.005), islet beta cell secretory index (P < 0.001), well-differentiated renal cell carcinoma (P= 0.009), and low-stage renal cell carcinoma (P = 0.019) were significantly lower than that of non-MS group. Logistic regression analysis showed that hypertension (P = 0.005), diabetes (P = 0.012), hyperlipidemia (P = 0.021) are independent risk factors for Fuhrman grade of ccRCC, while diabetes (P = 0.002), hyperlipidemia (P = 0.007) are independent risk factors for TNM staging of ccRCC. CONCLUSION: The patients with ccRCC and MS had higher Fuhrman grade and TNM stage. MS is an independent risk factor for Fuhrman grade and TNM stage of ccRCC.