Integrating Demographics and Imaging Features for Various Stages of Dementia Classification: Feed Forward Neural Network Multi-Class Approach.

BACKGROUND: MRI magnetization-prepared rapid acquisition (MPRAGE) is an easily available imaging modality for dementia diagnosis. Previous studies suggested that volumetric analysis plays a crucial role in various stages of dementia classification. In this study, volumetry, radiomics and demographics were integrated as inputs to develop an artificial intelligence model for various stages, including Alzheimer's disease (AD), mild cognitive decline (MCI) and cognitive normal (CN) dementia classifications. METHOD: The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset was separated into training and testing groups, and the Open Access Series of Imaging Studies (OASIS) dataset was used as the second testing group. The MRI MPRAGE image was reoriented via statistical parametric mapping (SPM12). Freesurfer was employed for brain segmentation, and 45 regional brain volumes were retrieved. The 3D Slicer software was employed for 107 radiomics feature extractions from within the whole brain. Data on patient demographics were collected from the datasets. The feed-forward neural network (FFNN) and the other most common artificial intelligence algorithms, including support vector machine (SVM), ensemble classifier (EC) and decision tree (DT), were used to build the models using various features. RESULTS: The integration of brain regional volumes, radiomics and patient demographics attained the highest overall accuracy at 76.57% and 73.14% in ADNI and OASIS testing, respectively. The subclass accuracies in MCI, AD and CN were 78.29%, 89.71% and 85.14%, respectively, in ADNI testing, as well as 74.86%, 88% and 83.43% in OASIS testing. Balanced sensitivity and specificity were obtained for all subclass classifications in MCI, AD and CN. CONCLUSION: The FFNN yielded good overall accuracy for MCI, AD and CN categorization, with balanced subclass accuracy, sensitivity and specificity. The proposed FFNN model is simple, and it may support the triage of patients for further confirmation of the diagnosis.

AI Deployment on GBM Diagnosis: A Novel Approach to Analyze Histopathological Images Using Image Feature-Based Analysis.

BACKGROUND: Glioblastoma (GBM) is one of the most common malignant primary brain tumors, which accounts for 60-70% of all gliomas. Conventional diagnosis and the decision of post-operation treatment plan for glioblastoma is mainly based on the feature-based qualitative analysis of hematoxylin and eosin-stained (H&E) histopathological slides by both an experienced medical technologist and a pathologist. The recent development of digital whole slide scanners makes AI-based histopathological image analysis feasible and helps to diagnose cancer by accurately counting cell types and/or quantitative analysis. However, the technology available for digital slide image analysis is still very limited. This study aimed to build an image feature-based computer model using histopathology whole slide images to differentiate patients with glioblastoma (GBM) from healthy control (HC). METHOD: Two independent cohorts of patients were used. The first cohort was composed of 262 GBM patients of the Cancer Genome Atlas Glioblastoma Multiform Collection (TCGA-GBM) dataset from the cancer imaging archive (TCIA) database. The second cohort was composed of 60 GBM patients collected from a local hospital. Also, a group of 60 participants with no known brain disease were collected. All the H&E slides were collected. Thirty-three image features (22 GLCM and 11 GLRLM) were retrieved from the tumor volume delineated by medical technologist on H&E slides. Five machine-learning algorithms including decision-tree (DT), extreme-boost (EB), support vector machine (SVM), random forest (RF), and linear model (LM) were used to build five models using the image features extracted from the first cohort of patients. Models built were deployed using the selected key image features for GBM diagnosis from the second cohort (local patients) as model testing, to identify and verify key image features for GBM diagnosis. RESULTS: All five machine learning algorithms demonstrated excellent performance in GBM diagnosis and achieved an overall accuracy of 100% in the training and validation stage. A total of 12 GLCM and 3 GLRLM image features were identified and they showed a significant difference between the normal and the GBM image. However, only the SVM model maintained its excellent performance in the deployment of the models using the independent local cohort, with an accuracy of 93.5%, sensitivity of 86.95%, and specificity of 99.73%. CONCLUSION: In this study, we have identified 12 GLCM and 3 GLRLM image features which can aid the GBM diagnosis. Among the five models built, the SVM model proposed in this study demonstrated excellent accuracy with very good sensitivity and specificity. It could potentially be used for GBM diagnosis and future clinical application.

Clinical, radiological and ultrasonographic findings related to knee pain in osteoarthritis.

BACKGROUND: Pain is the predominant symptom of knee osteoarthritis (OA) and the main reason of disability. Ultrasound is now one of the new imaging modality in Musculoskeletal medicine and its role in assessing the pain severity in the knee osteoarthritis is evaluated in this study. OBJECTIVES: (1) To study the correlation between ultrasonographic (US) findings and pain score and (2) whether ultrasonographic findings show a better association of pain level than conventional X-rays in patients suffering from primary knee osteoarthritis. METHODS: In this multi-center study, 193 patients with primary knee OA were asked to score their average knee pain using the Western Ontario and McMaster Universities Arthritis (WOMAC) questionnaire;patients would then go for a radiological and an US evaluation of their painful knee. Findings from both imaging modalities will be studied with the associated pain score. RESULTS: Ultrasound showed that knee effusion has positive correlation with pain score upon walking (r = 0.217) and stair climbing (r = 0.194). Presence of suprapatellar synovitis had higher pain score on sitting (Spearman's Rank correlation  = 0.355). The medial(r = 0.170) and lateral meniscus protrusion (r = 0.201) were associated with pain score upon stair climbing. CONCLUSIONS: Our study found that both imaging modalities shown some significant association with the aspect of pain; neither one is clearly better but rather complementary to each other. A trend is found in both modalities: walking pain is related to pathologies of the either the lateral or medial tibiofemoral joint(TFJ)while stair climbing pain is related to both tibiofemoral joint pathologies and also to the patellofemoral joint (PFJ) pathology. This suggested that biomechanical derangement is an important aspect in OA knee pain.

FosPeg® PDT alters the EBV miRNAs and LMP1 protein expression in EBV positive nasopharyngeal carcinoma cells.

Nasopharyngeal carcinoma (NPC) is one of the top ten cancers highly prevalent in Hong Kong and South China. Epstein-Barr virus (EBV) infection contributes to the tumorigenesis of NPC through the expression of different viral proteins. Among these, Latent Membrane Protein 1(LMP1) is the major oncoprotein expressed by EBV. Foscan® (Biolitec AG), m-tetrahydroxyphenylchlorin (mTHPC)-based photosensitizing drug, has been used in the photodynamic therapy (PDT) for head and neck cancers. FosPeg® (Biolitec AG) is a new formulation of mTHPC contained in PEGylated liposomes with optimized distribution properties. In this in vitro study, the potential of FosPeg®-PDT on human EBV positive NPC cell (c666-1) and EBV negative cells (HK1 and CNE2) were investigated. Effects of FosPeg®-PDT on the expression of EBV BART miRNAs (EBV miRNA BART 1-5p, BART 16, and BART 17-5p), LMP1 mRNA and proteins on c666-1 cells were also elucidated. The killing efficacy of FosPeg®-PDT on NPC cells were determined by MTT assay after LED activation. Effects of FosPeg®-PDT on the expression of LMP1 mRNA and protein were examined by real time PCR and western blot analysis. FosPeg®-PDT demonstrated its antitumor effect on c666-1 cells in a drug and light dose dependent manner. LD30, LD50 and LD70 were achieved by applying LED activation (3J/cm(2)) at 4h post incubated cells with 0.05µg/ml, 0.07µg/ml and 0.3µg/ml FosPeg®, respectively. Up-regulation of both LMP1 mRNA and protein were observed after FosPeg®-PDT in a dose dependent manner. FosPeg®-PDT exerted antitumor effect on c666-1 cells through up-regulation of LMP1 protein. Understanding the mechanism of FosPeg®-PDT may help to develop better strategies for the treatment of NPC.