Deep-learning model for background parenchymal enhancement classification in contrast-enhanced mammography.

Background.Breast background parenchymal enhancement (BPE) is correlated with the risk of breast cancer. BPE level is currently assessed by radiologists in contrast-enhanced mammography (CEM) using 4 classes: minimal, mild, moderate and marked, as described inbreast imaging reporting and data system(BI-RADS). However, BPE classification remains subject to intra- and inter-reader variability. Fully automated methods to assess BPE level have already been developed in breast contrast-enhanced MRI (CE-MRI) and have been shown to provide accurate and repeatable BPE level classification. However, to our knowledge, no BPE level classification tool is available in the literature for CEM.Materials and methods.A BPE level classification tool based on deep learning has been trained and optimized on 7012 CEM image pairs (low-energy and recombined images) and evaluated on a dataset of 1013 image pairs. The impact of image resolution, backbone architecture and loss function were analyzed, as well as the influence of lesion presence and type on BPE assessment. The evaluation of the model performance was conducted using different metrics including 4-class balanced accuracy and mean absolute error. The results of the optimized model for a binary classification: minimal/mild versus moderate/marked, were also investigated.Results.The optimized model achieved a 4-class balanced accuracy of 71.5% (95% CI: 71.2-71.9) with 98.8% of classification errors between adjacent classes. For binary classification, the accuracy reached 93.0%. A slight decrease in model accuracy is observed in the presence of lesions, but it is not statistically significant, suggesting that our model is robust to the presence of lesions in the image for a classification task. Visual assessment also confirms that the model is more affected by non-mass enhancements than by mass-like enhancements.Conclusion.The proposed BPE classification tool for CEM achieves similar results than what is published in the literature for CE-MRI.

Clinical study on the association between keratinized mucosa and peri-implant health when external hexagon implants are installed in the posterior region of the maxilla and mandible: a cohort study.

This study evaluated the association between keratinized mucosa (KM) and peri-implant health of external hexagon implants in the posterior region in 84 patients with 242 implants. Modified plaque index (MPI), modified sulcular bleeding index (MSBI), probing depth (PD), keratinized mucosa (KM) width, and peri-implant bone loss were evaluated. The implants were divided according to the KM: (1) absence of KM, (2) KM width >0 and <2 mm, and (3) KM width ≥2 mm. Of the 242 implants evaluated, 63 (26.0%) had no KM band, 56 (23.1%) had KM width <2 mm, and 123 (50.8%) had KM width ≥2 mm. One hundred and sixty-seven (69.0%) were used in multiple unit restorations and 75 (31.0%) in single tooth restorations; 66.9% were placed in the mandible and 33.1% in the maxilla. For single tooth and multiple unit implant restorations, MPI (P=0.069 and P=0.387, respectively), MSBI (P=0.695 and P=0.947, respectively), PD (P=0.270 and P=0.258, respectively), and mesial bone loss (P=0.121 and P=0.239, respectively) were not affected by the KM width. On the distal surface, bone loss was influenced by the absence of KM when single tooth implant restorations were used (P=0.032). No association was found between KM width and the peri-implant tissue health.

Wearable pulmonary monitoring system with integrated functional lung imaging and chest sound recording: a clinical investigation in healthy subjects.

Objective.Current wearable respiratory monitoring devices provide a basic assessment of the breathing pattern of the examined subjects. More complex monitoring is needed for healthcare applications in patients with lung diseases. A multi-sensor vest allowing continuous lung imaging by electrical impedance tomography (EIT) and auscultation at six chest locations was developed for such advanced application. The aims of our study were to determine the vest's capacity to record the intended bio-signals, its safety and the comfort of wearing in a first clinical investigation in healthy adult subjects.Approach.Twenty subjects (age range: 23-65 years) were studied while wearing the vests during a 14-step study protocol comprising phases of quiet and deep breathing, slow and forced full expiration manoeuvres, coughing, breath-holding in seated and three horizontal postures. EIT, chest sound and accelerometer signals were streamed to a tablet using a dedicated application and uploaded to a back-end server. The subjects filled in a questionnaire on the vest properties using a Likert scale.Main results.All subjects completed the full protocol. Good to excellent EIT waveforms and functional EIT images were obtained in 89% of the subjects. Breathing pattern and posture dependent changes in ventilation distribution were properly detected by EIT. Chest sounds were recorded in all subjects. Detection of audible heart sounds was feasible in 44%-67% of the subjects, depending on the sensor location. Accelerometry correctly identified the posture in all subjects. The vests were safe and their properties positively rated, thermal and tactile properties achieved the highest scores.Significance.The functionality and safety of the studied wearable multi-sensor vest and the high level of its acceptance by the study participants were confirmed. Availability of personalized vests might further advance its performance by improving the sensor-skin contact.

Identification and analysis of stable breathing periods in electrical impedance tomography recordings.

Objective. In this paper, an automated stable tidal breathing period (STBP) identification method based on processing electrical impedance tomography (EIT) waveforms is proposed and the possibility of detecting and identifying such periods using EIT waveforms is analyzed. In wearable chest EIT, patients breathe spontaneously, and therefore, their breathing pattern might not be stable. Since most of the EIT feature extraction methods are applied to STBPs, this renders their automatic identification of central importance.Approach. The EIT frame sequence is reconstructed from the raw EIT recordings and the raw global impedance waveform (GIW) is computed. Next, the respiratory component of the raw GIW is extracted and processed for the automatic respiratory cycle (breath) extraction and their subsequent grouping into STBPs.Main results. We suggest three criteria for the identification of STBPs, namely, the coefficient of variation of (i) breath tidal volume, (ii) breath duration and (iii) end-expiratory impedance. The total number of true STBPs identified by the proposed method was 294 out of 318 identified by the expert corresponding to accuracy over 90%. Specific activities such as speaking, eating and arm elevation are identified as sources of false positives and their discrimination is discussed.Significance. Simple and computationally efficient STBP detection and identification is a highly desirable component in the EIT processing pipeline. Our study implies that it is feasible, however, the determination of its limits is necessary in order to consider the implementation of more advanced and computationally demanding approaches such as deep learning and fusion with data from other wearable sensors such as accelerometers and microphones.

Calvarial graft resorption index in the reconstruction of the maxillary sinus in patients with atrophic maxillas: a prospective clinical study.

The objective of this study was to assess the resorption index of particulate calvarial grafts in maxillary sinuses of patients undergoing total reconstruction of an atrophic maxilla with residual alveolar bone that was less than, or equal to, 3mm thick. Twenty-one maxillary sinus floor elevations were carried out using particulate calvarial grafts in 11 individuals with totally edentulous maxillas. All patients had computed tomography (CT) before (T0), and 48hours (T1) and six months after surgery (T2). For each CT scan, linear measurements were taken of sections of the anterior, medial, and posterior regions of the maxillary sinus. There was a significant increase in the height of the maxillary sinus floor when T0 was compared with T1 (p=0.001). There was a statistically significant reduction in all maxillary sinus measurements when T1 was compared with T2; the mean height reduction being 2.36mm (16.87%) in the anterior region, 3.53mm (22.47%) in the medial region, and 2.21mm (22.78%) in the posterior region (p=0.001). Mean resorption was 20.7%. Autogenous calvarial bone used alone is an option for graft material in pneumatised maxillary sinuses and in cases where there is limited alveolar bone.

Short-term use of an exposed polypropylene barrier in the preservation of alveolar bone after extraction: randomized clinical trial.

This study was performed to evaluate the short-term preservation of alveolar bone volume with or without a polypropylene barrier and exposure of the area after extractions. Thirty posterior tooth extraction sockets were distributed randomly to a control group (n=15; extraction and suture) and a barrier group (n=15; extraction, barrier, and suture). All sutures and barriers were removed 10 days postoperatively. Cone beam computed tomography scans taken with the aid of a tomographic guide were obtained preoperatively, immediately postoperative, and at 120 days postoperative. A visual analysis of the coronal sections of the alveolus was performed, and vertical loss in the mesial, distal, buccal, and lingual bone ridges and horizontal thickness were evaluated. The mean vertical loss after extraction did not differ significantly between the control and barrier groups (Student t-test: mesial P= 0.989, buccal P= 0.997, lingual/palatal P= 0.070, distal P= 0.107). The mean vertical loss at 120 days postoperative did not differ significantly between the control (0.65 mm) and barrier (0.52 mm) groups (P> 0.05), with an effect size of 0.13 mm. At 120 days, the barrier group presented a mean resorption in thickness (0.45 mm) that was significantly lower than that in the control group (0.76 mm) (P= 0.021), with an effect size of 0.31 mm. The polypropylene barrier reduced the horizontal resorption in sockets of posterior teeth after extraction.

Assessment of accessory canals of the canalis sinuosus: a study of 1000 cone beam computed tomography examinations.

The aim of this study was to verify the presence, spatial location, and calibre of the accessory canals (AC) of the canalis sinuosus by cone beam computed tomography, and their relationship to the anterior maxilla. This retrospective analysis included the scans of 1000 subjects. Parameters registered were sex, age, number of AC, presence or absence of AC with a diameter <1.0mm, AC diameter (only for AC with a diameter >1.0mm), and AC location in relation to the adjacent teeth. Males showed a statistically higher frequency of AC than females. The difference in age distribution was not statistically significant. Twenty percent of all AC presented a diameter of a least 1.0mm. The end of the AC trajectory was most frequently located palatal to the anterior maxillary teeth. All relationships analyzed here were very weak (age vs. number of AC, age vs. AC diameter, number of AC vs. sex). Overall, the results of this study showed that AC of the canalis sinuosus are a common anatomical structure in the anterior maxilla, regardless of age and sex.

Perinatal outcome comparing triplets and singleton births at a reference maternity hospital.

OBJECTIVE: The objective of the present study was to evaluate adverse perinatal outcome in a group of high order pregnancies pared with singletons by BW and GA at birth. METHODS: Data was reviewed for all admissions of triplets and quadruplets in a 7 year period. For each study neonate we selected two singleton infants to constitute a control group. Variables analyzed included: respiratory distress syndrome, patent ductus arteriosus, intraventricular hemorrhage, necrotizing enterocolitis (NEC), bronchopulmonary dysplasia, retinopathy of prematurity and periventricular leukomalacia. RESULTS: We studied a total of 128 multiple and 260 singleton infants. Mean gestational age and birth weight were similar in both groups (31.3 ± 2,5 wks e 31.5 ± 2,8 wks; 1470 ± 461 g vs 1495 ± 540 g). There was no significant difference between the groups in the majority of main morbidities. The incidence of NEC was higher in triplets (6.3 vs 0.8%, p value <0.01). Mortality was higher in singletons (9.6 vs 3.1%, p value <0.037). CONCLUSIONS: Results show that major neonatal outcomes are very similar between multiples and singletons births when paired by gestational age and birth weight. NEC remained a significant morbidity in infants born from multiple gestations after adjustment for maternal and neonatal risk factors.

Integration of Different Risk Assessment Tools to Improve Stratification of Patients with Coronary Artery Disease.

Cardiovascular disease (CVD) causes unaffordable social and health costs that tend to increase as the European population ages. In this context, clinical guidelines recommend the use of risk scores to predict the risk of a cardiovascular disease event. Some useful tools have been developed to predict the risk of occurrence of a cardiovascular disease event (e.g. hospitalization or death). However, these tools present some drawbacks. These problems are addressed through two methodologies: (i) combination of risk assessment tools: fusion of naïve Bayes classifiers complemented with a genetic optimization algorithm and (ii) personalization of risk assessment: subtractive clustering applied to a reduced-dimensional space to create groups of patients. Validation was performed based on two ACS-NSTEMI patient data sets. This work improved the performance in relation to current risk assessment tools, achieving maximum values of sensitivity, specificity, and geometric mean of, respectively, 79.8, 83.8, and 80.9 %. Additionally, it assured clinical interpretability, ability to incorporate of new risk factors, higher capability to deal with missing risk factors and avoiding the selection of a standard CVD risk assessment tool to be applied in the clinical practice.

Personalization algorithms applied to cardiovascular disease risk assessment.

Cardiovascular disease (CVD) is the major cause of death in the world. Clinical guidelines recommend the use of risk assessment tools (scores) to identify the CVD risk of each patient as the correct stratification of patients may significantly contribute to the optimization of the health care strategies. This work further explores the personalization of CVD risk assessment, supported on the evidence that a specific CVD risk assessment tool may have good performance within a given group of patients and might perform poorly within other groups. Two main personalization methods based on the proper creation of groups of patients are presented: i) clustering patients approach; ii) similarity measures approach. These two methodologies were validated in a Portuguese population (460 Acute Coronary Syndrome with non-ST segment elevation (ACS-NSTEMI) patients). The similarity measures approach had the best performance, achieving maximum values of sensitivity, specificity and geometric mean of, respectively, 77.7%, 63.2%, 69.7%. These values represent an enhancement in relation to the best performance obtained with current CVD risk assessment tools applied in clinical practice (78.5%, 53.2%, 64.4%).

An effective wavelet strategy for the trend prediction of physiological time series with application to pHealth systems.

This work proposes a wavelet decomposition based scheme to estimate the evolution trend of physiological time series. The scheme does not involve the explicit development of a model and is essentially supported on the hypothesis that future evolution of a biosignal can be estimated from similar historic patterns. The strategy considers an a-trous wavelet decomposition, where the most representative trends are extracted from the historic similar patterns. Then, a set of distance-based measures able to assess the prediction likelihood of each representative trend, is introduced. From these measures and through an optimization process, a subset of these trends is selected and aggregated to derive the required time series evolution trend. The effectiveness of the methodology is validated in the prediction of blood pressure signals collected in two telemonitoring studies: TEN-HMS and MyHeart. Additionally, Friedman and Nemenyi statistics tests are implemented to rank several methods, confirming the value of the proposed strategy.

Cardiovascular disease risk assessment innovative approaches developed in HeartCycle project.

Two innovative CVD event risk assessment strategies were developed in the scope of HeartCycle project: i) combination of individual risk assessment tools; ii) personalization of risk assessment based on grouping of patients. These approaches aimed to defeat some of the major limitations of the tools currently applied in the daily clinical practice, namely to: i) improve the risk prediction performance when comparing it to the one achieved by the individual current risk assessment tools; ii) consider the available knowledge provided by other risk assessment tools; iii) cope with missing risk factors; iv) incorporate additional clinical knowledge. Two different real patients' datasets were applied to validate the developed strategies: i) Santa Cruz Hospital, Portugal, N=460 ACS-NSTEMI1 patients; ii) Leiria Pombal Hospital Centre, Portugal, N=99 ACS-NSTEMI. Based on the gathered results, we propose a new strategy in order to improve patients' stratification.

HeartCycle: advanced sensors for telehealth applications.

Current treatment of Cardiovascular Disease (CVD)--the most frequent cause of hospitalization for people over 65--involves changes of diet and lifestyle, requiring in addition physical exercise to support these. Nowadays, patients receive sporadic feedback at doctor visits, or later on, when facing symptoms. The HeartCycle project aimed at providing 1) daily monitoring, 2) close follow up, 3) help on treatment routine and 4) decreasing non-compliance to treatment regimes. The present paper illustrates a new toolbox of advanced sensors developed within the HeartCycle project. Ongoing clinical studies support these developments.

Telehealth streams reduction based on pattern recognition techniques for events detection and efficient storage in EHR.

This work proposes a framework for telehealth streams analysis, founded on a pattern recognition technique that evaluates the similarity between multi-sensorial biosignals. The strategy combines the Haar wavelet with the Karhunen-Loève transforms to describe biosignals by means of a reduced set of parameters. These, that reflect the dynamic behavior of the biosignals, can support the detection of relevant clinical conditions. Moreover, the simplicity and fast execution of the proposed approach allow its application in real-time operation, as well as provide a practical way to manage historical electronic health records: i) common and uncommon behaviors can be distinguished; ii) the creation of different models, tailored to specific conditions can be efficiently stored. The efficiency of the methodology is assessed through its performance analysis, namely by computing the required number of operations and the compression rate. Its effectiveness is evaluated in the prediction of decompensation episodes using biosignals daily collected in the myHeart study (blood pressure, weight, respiration and heart rates).

Finite element analysis of stress distribution in anchor teeth in surgically assisted rapid palatal expansion.

The treatment of a transverse maxillary deficiency in skeletally mature individuals should include surgically assisted rapid palatal expansion. This study evaluated the distribution of stresses that affect the expander's anchor teeth using finite element analysis when the osteotomy is varied. Five virtual models were built and the surgically assisted rapid palatal expansion was simulated. Results showed tension on the lingual face of the teeth and alveolar bone, and compression on the buccal side of the alveolar bone. The subtotal Le Fort I osteotomy combined with intermaxillary suture osteotomy seemed to reduce the dissipation of tensions. Therefore, subtotal Le Fort I osteotomy without a step in the zygomaticomaxillary buttress, combined with intermaxillary suture osteotomy and pterygomaxillary disjunction may be the osteotomy of choice to reduce tensions on anchor teeth, which tend to move mesiobuccally (premolar) and distobuccally (molar).

Improvement of CVD risk assessment tools' performance through innovative patients' grouping strategies.

There are available in the clinical community several practical risk tools to assess the risk of occurrence of a cardiovascular event. Although valuable, these tools typically present some lack of performance (low sensitivity/low specificity) when applied to a general (average) patient. This flaw is addressed in this work through an innovative personalization strategy that is supported on the evidence that current risk assessment tools perform differently among different populations/groups of patients. The proposed methodology is based on two main hypotheses: i) patients are grouped through a proper dimension reduction technique complemented with an unsupervised learning algorithm, ii) for each group the most suitable risk assessment tool can be selected improving the risk prediction performance. As a result, risk personalization is simply achieved by the identification of the group that patients belong to. The validation of the strategy is carried out through the combination of three current risk assessment tools (GRACE, TIMI, PURSUIT) developed to predict the risk of an event in coronary artery disease patients. The combination of these tools is validated with a real patient testing dataset: Santa Cruz Hospital, Portugal, N=460 ACS-NSTEMI patients. Considering the obtained results with the available dataset it is possible to state that the main objective of this work was achieved.

Clinicopathological analysis of head and neck chondrosarcoma: three case reports and literature review.

Chondrosarcoma (CHS) is a malignant neoplasm characterized by the formation of cartilaginous matrix by neoplastic cells, with a high propensity for local recurrences. Head and neck CHS is rare, accounting for less than 12% of all cases of CHS, usually affecting the maxilla. The majority of affected patients are in the fourth decade of life, with a slight predilection for male patients. A painless swelling is commonly the most frequent complaint. Surgery with wide en-bloc resection is the preferred treatment for CHS; radiotherapy and chemotherapy are usually palliative options. Owing to its rarity, there are few clinical series evaluating the biological behaviour of head and neck CHS. The aim of this study is to analyse the clinicopathological characteristics of head and neck CHS by reporting 3 new cases of this neoplasia affecting the jaw bones and reviewing the clinical series previously published in the English literature.

Long term cardiovascular risk models' combination.

The correct diagnosis of cardiovascular disease is a key factor to reduce social and economic costs. In this context, cardiovascular disease risk assessment tools are of fundamental importance. This work addresses two major drawbacks of the current cardiovascular risk score systems: reduced number of risk factors considered by each individual tool and the inability of these tools to deal with incomplete information. To achieve these goals a two phase strategy was followed. In the first phase, a common representation procedure, based on a Naïve-Bayes classifier methodology, was applied to a set of current risk assessment tools. Classifiers' individual parameters and conditional probabilities were initially evaluated through a frequency estimation method. In a second phase, a combination scheme was proposed exploiting the particular features of Bayes probabilistic reasoning, followed by conditional probabilities optimization based on a genetic algorithm approach. This strategy was applied to describe and combine ASSIGN and Framingham models. Validation results were obtained based on individual models, assuming their statistical correctness. The achieved results are very promising, showing the potential of the strategy to accomplish the desired goals.

Fusion of risk assessment models with application to coronary artery disease patients.

Several risk score models are available in literature to predict death/myocardial infarction event for coronary artery disease (CAD) patients, within a short period of time. However, the choice of the most adequate model is not straightforward since there might not be a consensus about the best model to use in clinical practice Moreover, individually, these models present some weaknesses, such as the inability to deal with missing information. This work addresses these problems, proposing a Bayesian classifier strategy enabling the simultaneous use of several models (models' fusion). Thus, a higher number of risk factors can be used in the common model, while it can deal with missing information. The validation of the strategy is carried out through the combination of three current risk score models (GRACE, TIMI, PURSUIT). Results were obtained based on a dataset that comprises 460 consecutive patients admitted to the Cardiology Department of Santa Cruz Hospital, Lisbon, from 1999 to 2001. A comparison with the voting scheme, which considers exclusively the outputs of models to combine (models output combination) is also carried out. The proposed Bayesian approach had very satisfactory results, confirming the potential of its application to the clinical practice.

Cardiovascular risk and status assessment.

This work focuses on the development of models to support the assessment of a patient's global cardiovascular condition. Three types of models, based on different types of information, have been developed: long term cardiovascular risk models, that evaluate the risk of occurring of cardiovascular event within a long period of time (years); short term cardiovascular risk models, to assess the risk of death within a short period of time (months); cardiovascular status assessment models, to estimate the current cardiovascular condition of a patient. Three major drawbacks of current cardiovascular tools are addressed: reduced number of risk factors considered by each individual tool, inappropriateness of these tools to incorporate empirical clinical expertise and incapacity of these tools to deal with incomplete information. Methodologies and preliminary results, obtained under FP7 HeartCycle project, as well as future directions of research are also presented in this paper.