30 April 2021 in IEEE Sensors Journal
With the increase of COVID-19 cases worldwide, an effective way is required to diagnose COVID-19 patients. The primary problem in diagnosing COVID-19 patients is the shortage and reliability of testing kits, due to the quick spread of the virus, medical practitioners are facing difficulty in identifying the positive cases. The second real-world problem is to share the data among the hospitals globally while keeping in view the privacy concerns of the organizations. Building a collaborative model and preserving privacy are the major concerns for training a global deep learning model. This paper proposes a framework that collects a small amount of data from different sources (various hospitals) and trains a global deep learning model using blockchain-based federated learning. Blockchain technology authenticates the data and federated learning trains the model globally while preserving the privacy of the organization. First, we propose a data normalization technique that deals with the heterogeneity of data as the data is gathered from different hospitals having different kinds of Computed Tomography (CT) scanners. Secondly, we use Capsule Network-based segmentation and classification to detect COVID-19 patients. Thirdly, we design a method that can collaboratively train a global model using blockchain technology with federated learning while preserving privacy. Additionally, we collected real-life COVID-19 patients’ data open to the research community. The proposed framework can utilize up-to-date data which improves the recognition of CT images. Finally, we conducted comprehensive experiments to validate the proposed method. Our results demonstrate better performance for detecting COVID-19 patients.
28 February 2019 in Child's Nervous System
30 September 2021 in Acta Neurologica Scandinavica
19 February 2026 in Neuroradiology
1 January 2025 in Acta Neurologica Scandinavica
Background: Epilepsy is a common symptom in patients with diffuse lower‐grade glioma (DLGG). However, the specific role of cortical alterations in glioma‐related epilepsy (GRE) remains unclear. This study is aimed at investigating the reorganization of cortical architecture and network changes associated with GRE. Materials and Methods: High‐resolution T1‐weighted and T2‐weighted images were acquired from patients with DLGG (GRE = 68, non‐GRE = 79) and 94 healthy controls (HCs). Cortical thickness and myelin content were calculated using the Human Connectome Project pipeline. Characteristics of structural covariance networks were computed using graph theory and network‐based statistic. Cortical thickness, myelin content, and network characteristics were compared among three groups. A GRE individual prediction model was constructed using an automated machine learning approach. Results: Compared with HCs, both GRE and non‐GRE groups exhibited cortical thinning in the tumor ipsilateral hemisphere, whereas there was cortical thickening in the contralateral hemisphere. Regarding the connectome characteristics, both GRE and non‐GRE groups showed decreased nodal efficiency and connections in multiple regions. When comparing GRE with non‐GRE, the GRE group exhibited more pronounced cortical thickening and demyelination in the contralateral orbitofrontal gyrus and superior frontal gyrus, with further decreased connections in the sensorimotor network, default mode network, and salience network. Finally, an XGBoost model based on cortical features enabled classification of GRE individuals with an accuracy of 0.80 and an AUC of 0.87. Conclusion: These findings deepen our understanding of the comprehensive cortical alterations in patients with DLGG and simultaneously provide novel insights into the potential pathophysiological mechanisms underlying GRE.