RESUMO
Kidney tumors represent a significant medical challenge, characterized by their often-asymptomatic nature and the need for early detection to facilitate timely and effective intervention. Although neural networks have shown great promise in disease prediction, their computational demands have limited their practicality in clinical settings. This study introduces a novel methodology, the UNet-PWP architecture, tailored explicitly for kidney tumor segmentation, designed to optimize resource utilization and overcome computational complexity constraints. A key novelty in our approach is the application of adaptive partitioning, which deconstructs the intricate UNet architecture into smaller submodels. This partitioning strategy reduces computational requirements and enhances the model's efficiency in processing kidney tumor images. Additionally, we augment the UNet's depth by incorporating pre-trained weights, therefore significantly boosting its capacity to handle intricate and detailed segmentation tasks. Furthermore, we employ weight-pruning techniques to eliminate redundant zero-weighted parameters, further streamlining the UNet-PWP model without compromising its performance. To rigorously assess the effectiveness of our proposed UNet-PWP model, we conducted a comparative evaluation alongside the DeepLab V3+ model, both trained on the "KiTs 19, 21, and 23" kidney tumor dataset. Our results are optimistic, with the UNet-PWP model achieving an exceptional accuracy rate of 97.01% on both the training and test datasets, surpassing the DeepLab V3+ model in performance. Furthermore, to ensure our model's results are easily understandable and explainable. We included a fusion of the attention and Grad-CAM XAI methods. This approach provides valuable insights into the decision-making process of our model and the regions of interest that affect its predictions. In the medical field, this interpretability aspect is crucial for healthcare professionals to trust and comprehend the model's reasoning.
RESUMO
CONTEXT: Skin thickness of type-2 diabetic insulin naïve adult patients. BACKGROUND: We have limited data on skin and subcutaneous tissue thickness of Indian type-2 diabetic population. Objective of this study was to assess skin and subcutaneous tissue thickness in insulin naïve type-2 diabetic patients as this information may be useful for insulin injection technique. AIMS: To assess the skin and subcutaneous tissue thickness at insulin injection sites in insulin naïve, type-2 diabetic adult population across different body mass index (BMI). SETTINGS AND DESIGN: Observational study carried out at our institute. MATERIALS AND METHODS: One hundred and one insulin naïve type-2 diabetic subjects underwent skin thickness measurement using ultrasound at insulin administration sites. Skin and subcutaneous tissue thickness were measured and prints taken. Though, the sample size to be taken for the study was not calculated, the results obtained clearly show that the power of the study was 80%. RESULTS: At arm and thigh, the mean skin thickness was more in males as compared to females in the BMI range <23 kg/m(2) (P < 0.05). At abdomen, skin thickness was more in males in the BMI range 19-23 kg/m(2) (P < 0.05). Across all the BMIs, mean skin plus subcutaneous thickness at arm was more in females (P < 0.05) except for BMI >25 kg/m(2) where thickness in males was comparable. At thigh, the skin plus subcutaneous tissue thickness was more in females (P < 0.05), across all BMI ranges. At abdomen, thickness was more in females for the BMI ranges 17-19 kg/m(2) and 23-25 kg/m(2), while it was comparable across all other BMI ranges (P > 0.05). CONCLUSIONS: Skin and subcutaneous tissue thickness can be estimated by BMI. In general it is higher in females.
