Specific nanoprobe design for MRI: Targeting laminin in the blood-brain barrier to follow alteration due to neuroinflammation

by Juan F. Zapata-Acevedo, Mónica Losada-Barragán, Johann F. Osma, Juan C. Cruz, Andreas Reiber, Klaus G. Petry, Amael Caillard, Audrey Sauldubois, Daniel Llamosa Pérez, Aníbal José Morillo Zárate, Sonia Bermúdez Muñoz, Agustín Daza Moreno, Rafaela V. Silva, Carmen Infante-Duarte, William Chamorro-Coral, Rodrigo E. González-Reyes, Karina Vargas-Sánchez

Chronic neuroinflammation is characterized by increased blood-brain barrier (BBB) permeability, leading to molecular changes in the central nervous system that can be explored with biomarkers of active neuroinflammatory processes. Magnetic resonance imaging (MRI) has contributed to detecting lesions and permeability of the BBB. Ultra-small superparamagnetic particles of iron oxide (USPIO) are used as contrast agents to improve MRI observations. Therefore, we validate the interaction of peptide-88 with laminin, vectorized on USPIO, to explore BBB molecular alterations occurring during neuroinflammation as a potential tool for use in MRI. The specific labeling of NPS-P88 was verified in endothelial cells (hCMEC/D3) and astrocytes (T98G) under inflammation induced by interleukin 1β (IL-1β) for 3 and 24 hours. IL-1β for 3 hours in hCMEC/D3 cells increased their co-localization with NPS-P88, compared with controls. At 24 hours, no significant differences were observed between groups. In T98G cells, NPS-P88 showed similar nonspecific labeling among treatments. These results indicate that NPS-P88 has a higher affinity towards brain endothelial cells than astrocytes under inflammation. This affinity decreases over time with reduced laminin expression. In vivo results suggest that following a 30-minute post-injection, there is an increased presence of NPS-P88 in the blood and brain, diminishing over time. Lastly, EAE animals displayed a significant accumulation of NPS-P88 in MRI, primarily in the cortex, attributed to inflammation and disruption of the BBB. Altogether, these results revealed NPS-P88 as a biomarker to evaluate changes in the BBB due to neuroinflammation by MRI in biological models targeting laminin.

Development of an explainable artificial intelligence model for Asian vascular wound images

Abstract

Chronic wounds contribute to significant healthcare and economic burden worldwide. Wound assessment remains challenging given its complex and dynamic nature. The use of artificial intelligence (AI) and machine learning methods in wound analysis is promising. Explainable modelling can help its integration and acceptance in healthcare systems. We aim to develop an explainable AI model for analysing vascular wound images among an Asian population. Two thousand nine hundred and fifty-seven wound images from a vascular wound image registry from a tertiary institution in Singapore were utilized. The dataset was split into training, validation and test sets. Wound images were classified into four types (neuroischaemic ulcer [NIU], surgical site infections [SSI], venous leg ulcers [VLU], pressure ulcer [PU]), measured with automatic estimation of width, length and depth and segmented into 18 wound and peri-wound features. Data pre-processing was performed using oversampling and augmentation techniques. Convolutional and deep learning models were utilized for model development. The model was evaluated with accuracy, F1 score and receiver operating characteristic (ROC) curves. Explainability methods were used to interpret AI decision reasoning. A web browser application was developed to demonstrate results of the wound AI model with explainability. After development, the model was tested on additional 15 476 unlabelled images to evaluate effectiveness. After the development on the training and validation dataset, the model performance on unseen labelled images in the test set achieved an AUROC of 0.99 for wound classification with mean accuracy of 95.9%. For wound measurements, the model achieved AUROC of 0.97 with mean accuracy of 85.0% for depth classification, and AUROC of 0.92 with mean accuracy of 87.1% for width and length determination. For wound segmentation, an AUROC of 0.95 and mean accuracy of 87.8% was achieved. Testing on unlabelled images, the model confidence score for wound classification was 82.8% with an explainability score of 60.6%. Confidence score was 87.6% for depth classification with 68.0% explainability score, while width and length measurement obtained 93.0% accuracy score with 76.6% explainability. Confidence score for wound segmentation was 83.9%, while explainability was 72.1%. Using explainable AI models, we have developed an algorithm and application for analysis of vascular wound images from an Asian population with accuracy and explainability. With further development, it can be utilized as a clinical decision support system and integrated into existing healthcare electronic systems.