BackgroundPompe disease is an autosomal recessive lysosomal glycogen storage disorder that has been reported in different ethnic populations which carry different common mutations of the acid alpha-glucosidase (GAA) gene. The GAA mutation pattern in mainland Chinese patients with late-onset Pompe disease is still not well understood.MethodsWe presented the clinical and genetic characteristics of 27 mainland Chinese late-onset Pompe patients from 24 families.ResultsGAA mutation analysis revealed 26 different mutations, including 10 that were novel. The allelic frequency of c.2238G > C (p.W746C) was found to be 27.08% in this patient group. Respiratory dysfunction was diagnosed in 10 of 11 patients who underwent pulmonary function evaluation, although only four required ventilator support at night.ConclusionsOur findings indicate that c.2238G > C (p.W746C) is the most common mutation in mainland Chinese late-onset Pompe patients, as observed in Taiwanese patients. The novel mutations identified in this study expand the genetic spectrum of late-onset Pompe disease, and the prevalence of respiratory dysfunction highlights the importance of monitoring pulmonary function in late-onset Pompe patients.

Being able to explain the prediction to clinical end-users is a necessity to leverage the power of artificial intelligence (AI) models for clinical decision support. For medical images, a feature attribution map, or heatmap, is the most common form of explanation that highlights important features for AI models' prediction. However, it is unknown how well heatmaps perform on explaining decisions on multi-modal medical images, where each image modality or channel visualizes distinct clinical information of the same underlying biomedical phenomenon. Understanding such modality-dependent features is essential for clinical users' interpretation of AI decisions. To tackle this clinically important but technically ignored problem, we propose the modality-specific feature importance (MSFI) metric. It encodes clinical image and explanation interpretation patterns of modality prioritization and modality-specific feature localization. We conduct a clinical requirement-grounded, systematic evaluation using computational methods and a clinician user study. Results show that the examined 16 heatmap algorithms failed to fulfill clinical requirements to correctly indicate AI model decision process or decision quality. The evaluation and MSFI metric can guide the design and selection of explainable AI algorithms to meet clinical requirements on multi-modal explanation.

No abstract

Primary brain tumors including gliomas continue to pose significant management challenges to clinicians. While the presentation, the pathology, and the clinical course of these lesions is variable, the initial investigations are usually similar. Patients who are suspected to have a brain tumor will be assessed with computed tomography (CT) and magnetic resonance imaging (MRI). The imaging findings are used by neurosurgeons to determine the feasibility of surgical resection and plan such an undertaking. Imaging studies are also an indispensable tool in tracking tumor progression or its response to treatment. As these imaging studies are non-invasive, relatively cheap and accessible to patients, there have been many efforts over the past two decades to increase the amount of clinically-relevant information that can be extracted from brain imaging. Most recently, artificial intelligence (AI) techniques have been employed to segment and characterize brain tumors, as well as to detect progression or treatment-response. However, the clinical utility of such endeavours remains limited due to challenges in data collection and annotation, model training, and in the reliability of AI-generated information.We provide a review of recent advances in addressing the above challenges. First, to overcome the challenge of data paucity, different image imputation and synthesis techniques along with annotation collection efforts are summarized. Next, various training strategies are presented to meet multiple desiderata, such as model performance, generalization ability, data privacy protection, and learning with sparse annotations. Finally, standardized performance evaluation and model interpretability methods have been reviewed. We believe that these technical approaches will facilitate the development of a fully-functional AI tool in the clinical care of patients with gliomas.

No abstract