ABSTRACT
Brain tumors can have fatal consequences, affecting many body functions. For this reason, it is essential to detect brain tumor types accurately and at an early stage to start the appropriate treatment process. Although convolutional neural networks (CNNs) are widely used in disease detection from medical images, they face the problem of overfitting in the training phase on limited labeled and insufficiently diverse datasets. The existing studies use transfer learning and ensemble models to overcome these problems. When the existing studies are examined, it is evident that there is a lack of models and weight ratios that will be used with the ensemble technique. With the framework proposed in this study, several CNN models with different architectures are trained with transfer learning and fine-tuning on three brain tumor datasets. A particle swarm optimization-based algorithm determined the optimum weights for combining the five most successful CNN models with the ensemble technique. The results across three datasets are as follows: Dataset 1, 99.35% accuracy and 99.20 F1-score; Dataset 2, 98.77% accuracy and 98.92 F1-score; and Dataset 3, 99.92% accuracy and 99.92 F1-score. We achieved successful performances on three brain tumor datasets, showing that the proposed framework is reliable in classification. As a result, the proposed framework outperforms existing studies, offering clinicians enhanced decision-making support through its high-accuracy classification performance.
ABSTRACT
BACKGROUND: Maternal and neonatal health are regarded as important indicators of health in most countries. Death auditing through, for example, the Maternal and Perinatal Death Surveillance and Response (MPDSR) is viewed as key to preventing maternal and newborn mortality. However, little is known about the implications of implementing perinatal auditing for healthcare professionals in low-income contexts. This study aimed to explore the ethical and practical consequences clinicians experience concerning MPDSR reporting practices in Ethiopia. METHODS: Qualitative semi-structured in-depth individual interviews were conducted with 16 healthcare workers across professions at selected facilities in Ethiopia. The interview questions were related to clinicians' experiences with, and perceptions of, death auditing. Their strategies for coping with newborn losses and the related reporting practices were also explored. The material was analyzed following systematic text condensation, and the NVivo11 software was used for organizing and coding the data material. RESULTS: Participants experienced fear of punishment and blame in relation to the perinatal death auditing process. They found that auditing did not contribute to reducing perinatal deaths and that their motivation to stick to the obligation was negatively affected by this. Performing audits without available resources to provide optimal care or support in the current system was perceived as unfair. Some hid information or misreported information in order to avoid accusations of misconduct when they felt they were not to blame for the baby's death. Coping strategies such as engaging in exceedingly larger work efforts, overtreating patients, or avoiding complicated medical cases were described. CONCLUSIONS: Experiencing perinatal death and death reporting constitutes a double burden for the involved healthcare workers. The preventability of perinatal death is perceived as context-dependent, and both clinicians and the healthcare system would benefit from a safe and blame-free reporting environment. To support these healthcare workers in a challenging clinical reality, guidelines and action plans that are specific to the Ethiopian context are needed.
