Deep learning architectures like ResNet and Inception have produced accurate predictions for classifying benign and malignant tumors in the healthcare domain. This enables healthcare institutions to make data-driven decisions and potentially enable early detection of malignancy by employing computer-vision-based deep learning algorithms. These CNN algorithms, in addition to requiring huge amounts of data, can identify higher- and lower-level features that are significant while classifying tumors into benign or malignant. However, the existing literature is limited in terms of the explainability of the resultant classification, and identifying the exact features that are of importance, which is essential in the decision-making process for healthcare practitioners. Thus, the motivation of this work is to implement a custom classifier on the ovarian tumor dataset, which exhibits high classification performance and subsequently interpret the classification results qualitatively, using various Explainable AI methods, to identify which pixels or regions of interest are given highest importance by the model for classification. The dataset comprises CT scanned images of ovarian tumors taken from to the axial, saggital and coronal planes. State-of-the-art architectures, including a modified ResNet50 derived from the standard pre-trained ResNet50, are implemented in the paper. When compared to the existing state-of-the-art techniques, the proposed modified ResNet50 exhibited a classification accuracy of 97.5 % on the test dataset without increasing the the complexity of the architecture. The results then were carried for interpretation using several explainable AI techniques. The results show that the shape and localized nature of the tumors play important roles for qualitatively determining the ability of the tumor to metastasize and thereafter to be classified as benign or malignant.

Dental articulation holds crucial and fundamental importance in the design of dental restorations and analysis of prosthetic or orthodontic occlusions. However, common traditional and digital articulators are difficult and cumbersome in use to effectively translate the dental cast model to the articulator workspace when using traditional facebows. In this study, we have developed a personalized virtual dental articulator that directly utilizes computed tomography (CT) data to mathematically model the complex jaw movement, providing a more efficient and accurate way of analyzing and designing dental restorations. By utilizing CT data, Frankfurt\'s horizontal plane was established for the mathematical modeling of virtual articulation, eliminating tedious facebow transfers. After capturing the patients\' CT images and tracking their jaw movements prior to dental treatment, the jaw-tracking information was incorporated into the articulation mathematical model. The validation and analysis of the personalized articulation approach were conducted by comparing the jaw movement between simulation data (virtual articulator) and real measurement data. As a result, the proposed virtual articulator achieves two important functions. Firstly, it replaces the traditional facebow transfer process by transferring the digital dental model to the virtual articulator through the anatomical relationship derived from the cranial CT data. Secondly, the jaw movement trajectory provided by optical tracking was incorporated into the mathematical articulation model to create a personalized virtual articulation with a small Fréchet distance of 1.7 mm. This virtual articulator provides a valuable tool that enables dentists to obtain diagnostic information about the temporomandibular joint (TMJ) and configure personalized settings of occlusal analysis for patients.

To determine whether the use of single or combined mechanical and virtual articulators, as well as facebows, jaw motion trackers, face scanners, and related devices, actually improve the efficacy of the prosthesis obtained in terms of lifespan and patient-related outcomes. To coin the terms Analogic and Digital Virtual Patients (AVP and DVP) as an attempt to analyze, clarify and synthesize terminology and workflows related to previously so-called devices.
A scoping review was accomplished involving different databases. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA-ScR) checklist and JBI guidance were followed to extract data regarding the Population, Context and Concept established.
Available literature on the efficacy of using devices and techniques related to both AVP and DVP workflows showed arguable study designs, great heterogeneity, and questionable quality.
The terms AVP and DVP have been coined as a first step to clarify and simplify concepts and workflows related to the use of both mechanical and virtual articulators, as well as facebows, or facial and intraoral scanners, among others. This scoping review cannot claim that an AVP approach leads to more effective and efficient prosthetic restorations.

Neurodegenerative diseases, tauopathies, constitute a serious global health problem. The etiology of these diseases is unclear and an increase in their incidence has been projected in the next 30 years. Therefore, the study of the molecular mechanisms that might stop these neurodegenerative processes is very relevant. Classification of neurodegenerative diseases using Machine and Deep Learning algorithms has been widely studied for medical imaging such as Magnetic Resonance Imaging. However, post-mortem immunofluorescence imaging studies of the brains of patients have not yet been used for this purpose. These studies may represent a valuable tool for monitoring aberrant chemical changes or pathological post-translational modifications of the Tau polypeptide. We propose a Convolutional Neural Network pipeline for the classification of Tau pathology of Alzheimer\'s disease and Progressive Supranuclear Palsy by analyzing post-mortem immunofluorescence images with different Tau biomarkers performed with models generated with the architecture ResNet-IFT using Transfer Learning. These models\' outputs were interpreted with interpretability algorithms such as Guided Grad-CAM and Occlusion Analysis. To determine the best classifier, four different architectures were tested. We demonstrated that our design was able to classify diseases with an accuracy of 98.41% on average whilst providing an interpretation concerning the proper classification involving different structural patterns in the immunoreactivity of the Tau protein in NFTs present in the brains of patients with Progressive Supranuclear Palsy and Alzheimer\'s disease.

The reliability and validity of three digital occlusion analysis methods was evaluated in vivo.
The three method evalueated were:scanning of articulating paper marks (SA), dental prescale occlusal analysis system (DP) and a virtual occlusion constructed method (VO). A conventional silicone transmission method (ST) was used as the standard for comparison. Each of the 20 enroled human subjects was tested with the four methods. Retest of each method was performed at 2-week intervals. Occlusal contact area (OCA) and occlusal contact numbers (OCN) were calculated for analyses. For reliability evaluation, intraclass correlation coefficients (ICC) of the OCA and OCN values obtained from each method were compared. For validity evaluation, Pearson correlations coefficients, paired t-tests, regression analysis and Bland-Altman analysis were examined.
The ICC values of OCA and OCN were in the order: ST>SA>DP>VO. The highest OCA and OCN values were found ST while the lowest values were obtained from DP. Paired t-test identified a significant difference when OCA values obtained from the three digital methods were compared with ST, and between the OCN values of DP and ST. Pearson correlation showed high coefficients between ST and three digital methods (0.583-0.885 for OCA; 0.779-0.836 for OCN). A significant linear correlation was found between the results from ST and those from SA or VO. Bland-Altman analysis showed good agreement between OCN values of SA and ST, and between those of VO and ST.
The three digital occlusal analysis methods showed good reliability and validity for in vivo clinical application.
The three digital occlusion analysis systems examined demonstrate good potential in in vivo quantitative analysis, with good reliability and validity. The use of these analytical methods should facilitate digital workflow in clinical practice.

Progressive brain atrophy is a key neuropathological hallmark of Alzheimer\'s disease (AD) dementia. However, atrophy patterns along the progression of AD dementia are diffuse and variable and are often missed by univariate methods. Consequently, identifying the major regional atrophy patterns underlying AD dementia progression is challenging. In the current study, we propose a method that evaluates the degree to which specific regional atrophy patterns are predictive of AD dementia progression, while holding all other atrophy changes constant using a total sample of 334 subjects. We first trained a dense convolutional neural network model to differentiate individuals with mild cognitive impairment (MCI) who progress to AD dementia versus those with a stable MCI diagnosis. Then, we retested the model multiple times, each time occluding different regions of interest (ROIs) from the model\'s testing set\'s input. We also validated this approach by occluding ROIs based on Braak\'s staging scheme. We found that the hippocampus, fusiform, and inferior temporal gyri were the strongest predictors of AD dementia progression, in agreement with established staging models. We also found that occlusion of limbic ROIs defined according to Braak stage III had the largest impact on the performance of the model. Our predictive model reveals the major regional patterns of atrophy predictive of AD dementia progression. These results highlight the potential for early diagnosis and stratification of individuals with prodromal AD dementia based on patterns of cortical atrophy, prior to interventional clinical trials.

The present in vitro study evaluated the reliability and validity of two computerised occlusion analysis systems.
Three occlusion analysis methods were evaluated. The methods included one traditional method (scanning of articulating paper marks (SAP)) and two computerised systems: (dental prescale occlusion analysis system (DPO) and a modified virtual occlusion construction method (VOC)). For reliability evaluation, the occlusion of an articulator-mounted anatomical dentoform was analysed ten times with each of the three methods. Occlusal contact areas and contact number values were obtained and the coefficient of variation (CoV) of each method was compared. For validity evaluation, resin casts of the dentition of 10 human subjects were used for analysis. Paired t-tests, regression analysis and Bland-Altman analysis were used to evaluate the difference and agreement amongst the three methods.
The CoV values of occlusal contact areas from the entire dentition were in the order: SAP (5.7%) < DPO (12.7%) < VOC (15.6%). Higher values was found in the anterior teeth (19.8-40.8%). Significant differences were identified in the occlusal contact areas of the entire dentition and posterior teeth obtained from SAP and DPO; a significant correlation was detected between the two methods (P < 0.01). Bland-Altman agreement analysis indicated good agreement between SAP and VOC.
Both DPO and VOC have good reliability and validity. They are potential alternatives for analysis of occlusal contacts.
The dental prescale occlusion analysis system and the modified virtual occlusion constructed method combine convenience with the objectivity of digital technology. These computerised occlusion analysis systems may be used for quantitative analysis of occlusal contacts in clinical practice, with good reliability and validity.

UNASSIGNED: Identifying the optimal method for occlusion analysis by comparing examination sensitivity of the static and dynamic occlusion using three systems: clinical occlusion analysis, semi-adjustable articulator and virtual articulator (3Shape, Denmark) occlusion analysis.
UNASSIGNED: The occlusion analysis of sixteen patients was performed using the three systems. In order to analyze the number of concordant and discordant points and trajectories, the clinical method was compared to the semi-adjustable articulator and to the computerized method.
UNASSIGNED: The greatest correspondence was obtained by comparing the clinical and the articulator methods, having a success rate of 85.25%, versus the clinical and the computerized method with a success rate of 73.25%. The propulsion registered the highest discrepancies: 35% in case of the semi-adjustable articulator comparison and 62% in case of the virtual articulator comparison.
UNASSIGNED: The semi-adjustable articulator was superior in static and dynamic occlusion analysis compared to the virtual articulator. The analysis of the dynamic occlusion is the most problematic due to its dependency on the individual anatomy of the glenoid fossa which cannot be exactly reproduced by any articulator.