Chest X-Ray-Based Telemedicine Platform for Pediatric Tuberculosis Diagnosis in Low-Resource Settings: Development and Validation Study.

BACKGROUND: Tuberculosis (TB) remains a major cause of morbidity and death worldwide, with a significant impact on children, especially those under the age of 5 years. The complex diagnosis of pediatric TB, compounded by limited access to more accurate diagnostic tests, underscores the need for improved tools to enhance diagnosis and care in resource-limited settings. OBJECTIVE: This study aims to present a telemedicine web platform, BITScreen PTB (Biomedical Image Technologies Screen for Pediatric Tuberculosis), aimed at improving the evaluation of pulmonary TB in children based on digital chest x-ray (CXR) imaging and clinical information in resource-limited settings. METHODS: The platform was evaluated by 3 independent expert readers through a retrospective assessment of a data set with 218 imaging examinations of children under 3 years of age, selected from a previous study performed in Mozambique. The key aspects assessed were the usability through a standardized questionnaire, the time needed to complete the assessment through the platform, the performance of the readers to identify TB cases based on the CXR, the association between the TB features identified in the CXRs and the initial diagnostic classification, and the interreader agreement of the global assessment and the radiological findings. RESULTS: The platform's usability and user satisfaction were evaluated using a questionnaire, which received an average rating of 4.4 (SD 0.59) out of 5. The average examination completion time ranged from 35 to 110 seconds. In addition, the study on CXR showed low sensitivity (16.3%-28.2%) but high specificity (91.1%-98.2%) in the assessment of the consensus case definition of pediatric TB using the platform. The CXR finding having a stronger association with the initial diagnostic classification was air space opacification (χ21>20.38, P<.001). The study found varying levels of interreader agreement, with moderate/substantial agreement for air space opacification (κ=0.54-0.67) and pleural effusion (κ=0.43-0.72). CONCLUSIONS: Our findings support the promising role of telemedicine platforms such as BITScreen PTB in enhancing pediatric TB diagnosis access, particularly in resource-limited settings. Additionally, these platforms could facilitate the multireader and systematic assessment of CXR in pediatric TB clinical studies.

Evaluation of the Performance of a 3D-Printed Smartphone-Based Retinal Imaging Device as a Screening Tool for Retinal Pathology in Mozambique.

Low-income countries carry approximately 90% of the global burden of visual impairment, and up to 80% of this could be prevented or cured. However, there are only a few studies on the prevalence of retinal disease in these countries. Easier access to retinal information would allow differential diagnosis and promote strategies to improve eye health, which are currently scarce. This pilot study aims to evaluate the functionality and usability of a tele-retinography system for the detection of retinal pathology, based on a low-cost portable retinal scanner, manufactured with 3D printing and controlled by a mobile phone with an application designed ad hoc. The study was conducted at the Manhiça Rural Hospital in Mozambique. General practitioners, with no specific knowledge of ophthalmology or previous use of retinography, performed digital retinographies on 104 hospitalized patients. The retinographies were acquired in video format, uploaded to a web platform, and reviewed centrally by two ophthalmologists, analyzing the image quality and the presence of retinal lesions. In our sample there was a high proportion of exudates and hemorrhages-8% and 4%, respectively. In addition, the presence of lesions was studied in patients with known underlying risk factors for retinal disease, such as HIV, diabetes, and/or hypertension. Our tele-retinography system based on a smartphone coupled with a simple and low-cost 3D printed device is easy to use by healthcare personnel without specialized ophthalmological knowledge and could be applied for the screening and initial diagnosis of retinal pathology.

Enhancing physicians' radiology diagnostics of COVID-19's effects on lung health by leveraging artificial intelligence.

Introduction: This study aimed to develop an individualized artificial intelligence model to help radiologists assess the severity of COVID-19's effects on patients' lung health. Methods: Data was collected from medical records of 1103 patients diagnosed with COVID-19 using RT- qPCR between March and June 2020, in Hospital Madrid-Group (HM-Group, Spain). By using Convolutional Neural Networks, we determine the effects of COVID-19 in terms of lung area, opacities, and pulmonary air density. We then combine these variables with age and sex in a regression model to assess the severity of these conditions with respect to fatality risk (death or ICU). Results: Our model can predict high effect with an AUC of 0.736. Finally, we compare the performance of the model with respect to six physicians' diagnosis, and test for improvements on physicians' performance when using the prediction algorithm. Discussion: We find that the algorithm outperforms physicians (39.5% less error), and thus, physicians can significantly benefit from the information provided by the algorithm by reducing error by almost 30%.

Integration of longitudinal deep-radiomics and clinical data improves the prediction of durable benefits to anti-PD-1/PD-L1 immunotherapy in advanced NSCLC patients.

BACKGROUND: Identifying predictive non-invasive biomarkers of immunotherapy response is crucial to avoid premature treatment interruptions or ineffective prolongation. Our aim was to develop a non-invasive biomarker for predicting immunotherapy clinical durable benefit, based on the integration of radiomics and clinical data monitored through early anti-PD-1/PD-L1 monoclonal antibodies treatment in patients with advanced non-small cell lung cancer (NSCLC). METHODS: In this study, 264 patients with pathologically confirmed stage IV NSCLC treated with immunotherapy were retrospectively collected from two institutions. The cohort was randomly divided into a training (n = 221) and an independent test set (n = 43), ensuring the balanced availability of baseline and follow-up data for each patient. Clinical data corresponding to the start of treatment was retrieved from electronic patient records, and blood test variables after the first and third cycles of immunotherapy were also collected. Additionally, traditional radiomics and deep-radiomics features were extracted from the primary tumors of the computed tomography (CT) scans before treatment and during patient follow-up. Random Forest was used to implementing baseline and longitudinal models using clinical and radiomics data separately, and then an ensemble model was built integrating both sources of information. RESULTS: The integration of longitudinal clinical and deep-radiomics data significantly improved clinical durable benefit prediction at 6 and 9 months after treatment in the independent test set, achieving an area under the receiver operating characteristic curve of 0.824 (95% CI: [0.658,0.953]) and 0.753 (95% CI: [0.549,0.931]). The Kaplan-Meier survival analysis showed that, for both endpoints, the signatures significantly stratified high- and low-risk patients (p-value< 0.05) and were significantly correlated with progression-free survival (PFS6 model: C-index 0.723, p-value = 0.004; PFS9 model: C-index 0.685, p-value = 0.030) and overall survival (PFS6 models: C-index 0.768, p-value = 0.002; PFS9 model: C-index 0.736, p-value = 0.023). CONCLUSIONS: Integrating multidimensional and longitudinal data improved clinical durable benefit prediction to immunotherapy treatment of advanced non-small cell lung cancer patients. The selection of effective treatment and the appropriate evaluation of clinical benefit are important for better managing cancer patients with prolonged survival and preserving quality of life.

Use of semi-synthetic data for catheter segmentation improvement.

In the era of data-driven machine learning algorithms, data is the new oil. For the most optimal results, datasets should be large, heterogeneous and, crucially, correctly labeled. However, data collection and labeling are time-consuming and labor-intensive processes. In the field of medical device segmentation, present during minimally invasive surgery, this leads to a lack of informative data. Motivated by this drawback, we developed an algorithm generating semi-synthetic images based on real ones. The concept of this algorithm is to place a randomly shaped catheter in an empty heart cavity, where the shape of the catheter is generated by forward kinematics of continuum robots. Having implemented the proposed algorithm, we generated new images of heart cavities with various artificial catheters. We compared the results of deep neural networks trained purely on real datasets with respect to networks trained on both real and semi-synthetic datasets, highlighting that semi-synthetic data improves catheter segmentation accuracy. A modified U-Net trained on combined datasets performed the segmentation with a Dice similarity coefficient of 92.6 ± 2.2%, while the same model trained only on real images achieved a Dice similarity coefficient of 86.5 ± 3.6%. Therefore, using semi-synthetic data allows for the decrease of accuracy spread, improves model generalization, reduces subjectivity, shortens the labeling routine, increases the number of samples, and improves the heterogeneity.

Fetal MRI by Robust Deep Generative Prior Reconstruction and Diffeomorphic Registration.

Magnetic resonance imaging of whole fetal body and placenta is limited by different sources of motion affecting the womb. Usual scanning techniques employ single-shot multi-slice sequences where anatomical information in different slices may be subject to different deformations, contrast variations or artifacts. Volumetric reconstruction formulations have been proposed to correct for these factors, but they must accommodate a non-homogeneous and non-isotropic sampling, so regularization becomes necessary. Thus, in this paper we propose a deep generative prior for robust volumetric reconstructions integrated with a diffeomorphic volume to slice registration method. Experiments are performed to validate our contributions and compare with ifdefined tmiformat R2.5a state of the art method methods in the literature in a cohort of 72 fetal datasets in the range of 20-36 weeks gestational age. Results suggest improved image resolution Quantitative as well as radiological assessment suggest improved image quality and more accurate prediction of gestational age at scan is obtained when comparing to a state of the art reconstruction method methods. In addition, gestational age prediction results from our volumetric reconstructions compare favourably are competitive with existing brain-based approaches, with boosted accuracy when integrating information of organs other than the brain. Namely, a mean absolute error of 0.618 weeks ( R2=0.958 ) is achieved when combining fetal brain and trunk information.

Intrapericardial cardiosphere-derived cells hinder epicardial dense scar expansion and promote electrical homogeneity in a porcine post-infarction model.

The arrhythmic substrate of ventricular tachycardias in many structural heart diseases is located in the epicardium, often resulting in poor outcomes with currently available therapies. Cardiosphere-derived cells (CDCs) have been shown to modify myocardial scarring. A total of 19 Large White pigs were infarcted by occlusion of the mid-left anterior descending coronary artery for 150 min. Baseline cardiac magnetic resonance (CMR) imaging with late gadolinium enhancement sequences was obtained 4 weeks post-infarction and pigs were randomized to a treatment group (intrapericardial administration of 300,000 allogeneic CDCs/kg), (n = 10) and to a control group (n = 9). A second CMR and high-density endocardial electroanatomical mapping were performed at 16 weeks post-infarction. After the electrophysiological study, pigs were sacrificed and epicardial optical mapping and histological studies of the heterogeneous tissue of the endocardial and epicardial scars were performed. In comparison with control conditions, intrapericardial CDCs reduced the growth of epicardial dense scar and epicardial electrical heterogeneity. The relative differences in conduction velocity and action potential duration between healthy myocardium and heterogeneous tissue were significantly smaller in the CDC-treated group than in the control group. The lower electrical heterogeneity coincides with heterogeneous tissue with less fibrosis, better cardiomyocyte viability, and a greater quantity and better polarity of connexin 43. At the endocardial level, no differences were detected between groups. Intrapericardial CDCs produce anatomical and functional changes in the epicardial arrhythmic substrate, which could have an anti-arrhythmic effect.

Effects of Cardiac Stem Cell on Postinfarction Arrhythmogenic Substrate.

Clinical data suggest that cardiosphere-derived cells (CDCs) could modify post-infarction scar and ventricular remodeling and reduce the incidence of ventricular tachycardia (VT). This paper assesses the effect of CDCs on VT substrate in a pig model of postinfarction monomorphic VT. We studied the effect of CDCs on the electrophysiological properties and histological structure of dense scar and heterogeneous tissue (HT). Optical mapping and histological evaluation were performed 16 weeks after the induction of a myocardial infarction by transient occlusion of the left anterior descending (LAD) artery in 21 pigs. Four weeks after LAD occlusion, pigs were randomized to receive intracoronary plus trans-myocardial CDCs (IC+TM group, n: 10) or to a control group. Optical mapping (OM) showed an action potential duration (APD) gradient between HT and normal tissue in both groups. CDCs increased conduction velocity (53 ± 5 vs. 45 ± 6 cm/s, p < 0.01), prolonged APD (280 ± 30 ms vs. 220 ± 40 ms, p < 0.01) and decreased APD dispersion in the HT. During OM, a VT was induced in one and seven of the IC+TM and control hearts (p = 0.03), respectively; five of these VTs had their critical isthmus located in intra-scar HT found adjacent to the coronary arteries. Histological evaluation of HT revealed less fibrosis (p < 0.01), lower density of myofibroblasts (p = 0.001), and higher density of connexin-43 in the IC+TM group. Scar and left ventricular volumes did not show differences between groups. Allogeneic CDCs early after myocardial infarction can modify the structure and electrophysiology of post-infarction scar. These findings pave the way for novel therapeutic properties of CDCs.

Prediction of Cardiac Resynchronization Therapy Response Using a Lead Placement Score Derived From 4-Dimensional Computed Tomography.

BACKGROUND: Cardiac resynchronization therapy (CRT) is an effective treatment for patients with heart failure; however, 30% of patients do not respond to the treatment. We sought to derive patient-specific left ventricle maps of lead placement scores (LPS) that highlight target pacing lead sites for achieving a higher probability of CRT response. METHODS: Eighty-two subjects recruited for the ImagingCRT trial (Empiric Versus Imaging Guided Left Ventricular Lead Placement in Cardiac Resynchronization Therapy) were retrospectively analyzed. All 82 subjects had 2 contrast-enhanced full cardiac cycle 4-dimensional computed tomography scans: a baseline and a 6-month follow-up scan. CRT response was defined as a reduction in computed tomography-derived end-systolic volume ≥15%. Eight left ventricle features derived from the baseline scans were used to train a support vector machine via a bagging approach. An LPS map over the left ventricle was created for each subject as a linear combination of the support vector machine feature weights and the subject's own feature vector. Performance for distinguishing responders was performed on the original 82 subjects. RESULTS: Fifty-two (63%) subjects were responders. Subjects with an LPS≤Q1 (lower-quartile) had a posttest probability of responding of 14% (3/21), while subjects with an LPS≥ Q3 (upper-quartile) had a posttest probability of responding of 90% (19/21). Subjects with Q1

Deep learning-based lesion subtyping and prediction of clinical outcomes in COVID-19 pneumonia using chest CT.

The main objective of this work is to develop and evaluate an artificial intelligence system based on deep learning capable of automatically identifying, quantifying, and characterizing COVID-19 pneumonia patterns in order to assess disease severity and predict clinical outcomes, and to compare the prediction performance with respect to human reader severity assessment and whole lung radiomics. We propose a deep learning based scheme to automatically segment the different lesion subtypes in nonenhanced CT scans. The automatic lesion quantification was used to predict clinical outcomes. The proposed technique has been independently tested in a multicentric cohort of 103 patients, retrospectively collected between March and July of 2020. Segmentation of lesion subtypes was evaluated using both overlapping (Dice) and distance-based (Hausdorff and average surface) metrics, while the proposed system to predict clinically relevant outcomes was assessed using the area under the curve (AUC). Additionally, other metrics including sensitivity, specificity, positive predictive value and negative predictive value were estimated. 95% confidence intervals were properly calculated. The agreement between the automatic estimate of parenchymal damage (%) and the radiologists' severity scoring was strong, with a Spearman correlation coefficient (R) of 0.83. The automatic quantification of lesion subtypes was able to predict patient mortality, admission to the Intensive Care Units (ICU) and need for mechanical ventilation with an AUC of 0.87, 0.73 and 0.68 respectively. The proposed artificial intelligence system enabled a better prediction of those clinically relevant outcomes when compared to the radiologists' interpretation and to whole lung radiomics. In conclusion, deep learning lesion subtyping in COVID-19 pneumonia from noncontrast chest CT enables quantitative assessment of disease severity and better prediction of clinical outcomes with respect to whole lung radiomics or radiologists' severity score.

Regional left ventricular endocardial strains estimated from low-dose 4DCT: Comparison with cardiac magnetic resonance feature tracking.

BACKGROUND: Estimates of regional left ventricular (LV) strains provide additional information to global function parameters such as ejection fraction (EF) and global longitudinal strain (GLS) and are more sensitive in detecting abnormal regional cardiac function. The accurate and reproducible assessment of regional cardiac function has implications in the management of various cardiac diseases such as heart failure, myocardial ischemia, and dyssynchrony. PURPOSE: To develop a method that yields highly reproducible, high-resolution estimates of regional endocardial strains from 4DCT images. METHODS: A method for estimating regional LV endocardial circumferential ( ε c c ) $( {{\epsilon }_{cc}} )$ and longitudinal ( ε l l ${\epsilon }_{ll}$ ) strains from 4DCT was developed. Point clouds representing the LV endocardial surface were extracted for each time frame of the cardiac cycle from 4DCT images. 3D deformation fields across the cardiac cycle were obtained by registering the end diastolic point cloud to each subsequent point cloud in time across the cardiac cycle using a 3D point-set registration technique. From these deformation fields, ε c c and ε l l ${\epsilon }_{cc}\ {\rm{and\ }}{\epsilon }_{ll}$ were estimated over the entire LV endocardial surface by fitting an affine transformation with maximum likelihood estimation. The 4DCT-derived strains were compared with strains estimated in the same subjects by cardiac magnetic resonance (CMR); twenty-four subjects had CMR scans followed by 4DCT scans acquired within a few hours. Regional LV circumferential and longitudinal strains were estimated from the CMR images using a commercially available feature tracking software (cvi42). Global circumferential strain (GCS) and global longitudinal strain (GLS) were calculated as the mean of the regional strains across the entire LV for both modalities. Pearson correlation coefficients and Bland-Altman analyses were used for comparisons. Intraclass correlation coefficients (ICC) were used to assess the inter- and intraobserver reproducibility of the 4DCT-derived strains. RESULTS: The 4DCT-derived regional strains correlated well with the CMR-derived regional strains ( ε c c ${\epsilon }_{cc}$ : r = 0.76, p < 0.001; ε l l ${\epsilon }_{ll}$ : r = 0.64, p < 0.001). A very strong correlation was found between 4DCT-derived GCS and 4DCT-derived EF (r = -0.96; p < 0.001). The 4DCT-derived strains were also highly reproducible, with very low inter- and intraobserver variability (intraclass correlation coefficients in the range of [0.92, 0.99]). CONCLUSIONS: We have developed a novel method to estimate high-resolution regional LV endocardial circumferential and longitudinal strains from 4DCT images. Except for the definition of the mitral valve and LV outflow tract planes, the method is completely user independent, thus yielding highly reproducible estimates of endocardial strain. The 4DCT-derived strains correlated well with those estimated using a commercial CMR feature tracking software. The promising results reported in this study highlight the potential utility of 4DCT in the precise assessment of regional cardiac function for the management of cardiac disease.

Remote analysis of sputum smears for mycobacterium tuberculosis quantification using digital crowdsourcing.

Worldwide, TB is one of the top 10 causes of death and the leading cause from a single infectious agent. Although the development and roll out of Xpert MTB/RIF has recently become a major breakthrough in the field of TB diagnosis, smear microscopy remains the most widely used method for TB diagnosis, especially in low- and middle-income countries. This research tests the feasibility of a crowdsourced approach to tuberculosis image analysis. In particular, we investigated whether anonymous volunteers with no prior experience would be able to count acid-fast bacilli in digitized images of sputum smears by playing an online game. Following this approach 1790 people identified the acid-fast bacilli present in 60 digitized images, the best overall performance was obtained with a specific number of combined analysis from different players and the performance was evaluated with the F1 score, sensitivity and positive predictive value, reaching values of 0.933, 0.968 and 0.91, respectively.

Adaptive compounding speckle-noise-reduction filter for optical coherence tomography images.

SIGNIFICANCE: Speckle noise limits the diagnostic capabilities of optical coherence tomography (OCT) images, causing both a reduction in contrast and a less accurate assessment of the microstructural morphology of the tissue. AIM: We present a speckle-noise reduction method for OCT volumes that exploits the advantages of adaptive-noise wavelet thresholding with a wavelet compounding method applied to several frames acquired from consecutive positions. The method takes advantage of the wavelet representation of the speckle statistics, calculated properly from a homogeneous sample or a region of the noisy volume. APPROACH: The proposed method was first compared quantitatively with different state-of-the-art approaches by being applied to three different clinical dermatological OCT volumes with three different OCT settings. The method was also applied to a public retinal spectral-domain OCT dataset to demonstrate its applicability to different imaging modalities. RESULTS: The results based on four different metrics demonstrate that the proposed method achieved the best performance among the tested techniques in suppressing noise and preserving structural information. CONCLUSIONS: The proposed OCT denoising technique has the potential to adapt to different image OCT settings and noise environments and to improve image quality prior to clinical diagnosis based on visual assessment.

Influence of metabolic syndrome on post-stroke outcome, angiogenesis and vascular function in old rats determined by dynamic contrast enhanced MRI.

Stroke affects primarily aged and co-morbid people, aspects not properly considered to date. Since angiogenesis/vasculogenesis are key processes for stroke recovery, we purposed to determine how different co-morbidities affect the outcome and angiogenesis/vasculogenesis, using a rodent model of metabolic syndrome, and by dynamic enhanced-contrast imaging (DCE-MRI) to assess its non-invasive potential to determine these processes. Twenty/twenty-two month-old corpulent (JCR:LA-Cp/Cp), a model of metabolic syndrome and lean rats were used. After inducing the experimental ischemia by transient MCAO, angiogenesis was analyzed by histology, vasculogenesis by determination of endothelial progenitor cells in peripheral blood by flow cytometry and evaluating their pro-angiogenic properties in culture and the vascular function by DCE-MRI at 3, 7 and 28 days after tMCAO. Our results show an increased infarct volume, BBB damage and an impaired outcome in corpulent rats compared with their lean counterparts. Corpulent rats also displayed worse post-stroke angiogenesis/vasculogenesis, outcome that translated in an impaired vascular function determined by DCE-MRI. These data confirm that outcome and angiogenesis/vasculogenesis induced by stroke in old rats are negatively affected by the co-morbidities present in the corpulent genotype and also that DCE-MRI might be a technique useful for the non-invasive evaluation of vascular function and angiogenesis processes.

Automatic estimation of aortic and mitral valve displacements in dynamic CTA with 4D graph-cuts.

The location of the mitral and aortic valves in dynamic cardiac imaging is useful for extracting functional derived parameters such as ejection fraction, valve excursions, and global longitudinal strain, and when performing anatomical structures tracking using slice following or valve intervention's planning. Completely automatic segmentation methods are still challenging tasks because of their fast movements and the different positions that prevent good visibility of the leaflets along the full cardiac cycle. In this article, we propose a processing pipeline to track the displacement of the aortic and mitral valve annuli from high-resolution cardiac four-dimensional computed tomographic angiography (4D-CTA). The proposed method is based on the dynamic separation of left ventricle, left atrium and aorta using statistical shape modeling and an energy minimization algorithm based on graph-cuts and has been evaluated on a set of 15 electrocardiography-gated 4D-CTAs. We report a mean agreement distance between manual annotations and our proposed method of 2.52±1.06 mm for the mitral annulus and 2.00±0.69 mm for the aortic valve annulus based on valve locations detected from manual anatomical landmarks. In addition, we show the effect of detecting the valvular planes on derived functional parameters (ejection fraction, global longitudinal strain, and excursions of the mitral and aortic valves).

Intraoperative computed tomography imaging for dose calculation in intraoperative electron radiation therapy: Initial clinical observations.

In intraoperative electron radiation therapy (IOERT) the energy of the electron beam is selected under the conventional assumption of water-equivalent tissues at the applicator end. However, the treatment field can deviate from the theoretic flat irradiation surface, thus altering dose profiles. This patient-based study explored the feasibility of acquiring intraoperative computed tomography (CT) studies for calculating three-dimensional dose distributions with two factors not included in the conventional assumption, namely the air gap from the applicator end to the irradiation surface and tissue heterogeneity. In addition, dose distributions under the conventional assumption and from preoperative CT studies (both also updated with intraoperative data) were calculated to explore whether there are other alternatives to intraoperative CT studies that can provide similar dose distributions. The IOERT protocol was modified to incorporate the acquisition of intraoperative CT studies before radiation delivery in six patients. Three studies were not valid to calculate dose distributions due to the presence of metal artefacts. For the remaining three cases, the average gamma pass rates between the doses calculated from intraoperative CT studies and those obtained assuming water-equivalent tissues or from preoperative CT studies were 73.4% and 74.0% respectively. The agreement increased when the air gap was included in the conventional assumption (98.1%) or in the preoperative CT images (98.4%). Therefore, this factor was the one mostly influencing the dose distributions of this study. Our experience has shown that intraoperative CT studies are not recommended when the procedure includes the use of shielding discs or surgical retractors unless metal artefacts are removed. IOERT dose distributions calculated under the conventional assumption or from preoperative CT studies may be inaccurate unless the air gap (which depends on the surface irregularities of the irradiated volume and on the applicator pose) is included in the calculations.

Classification of Interstitial Lung Abnormality Patterns with an Ensemble of Deep Convolutional Neural Networks.

Subtle interstitial changes in the lung parenchyma of smokers, known as Interstitial Lung Abnormalities (ILA), have been associated with clinical outcomes, including mortality, even in the absence of Interstitial Lung Disease (ILD). Although several methods have been proposed for the automatic identification of more advanced Interstitial Lung Disease (ILD) patterns, few have tackled ILA, which likely precedes the development ILD in some cases. In this context, we propose a novel methodology for automated identification and classification of ILA patterns in computed tomography (CT) images. The proposed method is an ensemble of deep convolutional neural networks (CNNs) that detect more discriminative features by incorporating two, two-and-a-half and three- dimensional architectures, thereby enabling more accurate classification. This technique is implemented by first training each individual CNN, and then combining its output responses to form the overall ensemble output. To train and test the system we used 37424 radiographic tissue samples corresponding to eight different parenchymal feature classes from 208 CT scans. The resulting ensemble performance including an average sensitivity of 91,41% and average specificity of 98,18% suggests it is potentially a viable method to identify radiographic patterns that precede the development of ILD.

Remote Monitoring of Treatment Response in Parkinson's Disease: The Habit of Typing on a Computer.

OBJECTIVE: The recent advances in technology are opening a new opportunity to remotely evaluate motor features in people with Parkinson's disease (PD). We hypothesized that typing on an electronic device, a habitual behavior facilitated by the nigrostriatal dopaminergic pathway, could allow for objectively and nonobtrusively monitoring parkinsonian features and response to medication in an at-home setting. METHODS: We enrolled 31 participants recently diagnosed with PD who were due to start dopaminergic treatment and 30 age-matched controls. We remotely monitored their typing pattern during a 6-month (24 weeks) follow-up period before and while dopaminergic medications were being titrated. The typing data were used to develop a novel algorithm based on recursive neural networks and detect participants' responses to medication. The latter were defined by the Unified Parkinson's Disease Rating Scale-III (UPDRS-III) minimal clinically important difference. Furthermore, we tested the accuracy of the algorithm to predict the final response to medication as early as 21 weeks prior to the final 6-month clinical outcome. RESULTS: The score on the novel algorithm based on recursive neural networks had an overall moderate kappa agreement and fair area under the receiver operating characteristic (ROC) curve with the time-coincident UPDRS-III minimal clinically important difference. The participants classified as responders at the final visit (based on the UPDRS-III minimal clinically important difference) had higher scores on the novel algorithm based on recursive neural networks when compared with the participants with stable UPDRS-III, from the third week of the study onward. CONCLUSIONS: This preliminary study suggests that remotely gathered unsupervised typing data allows for the accurate detection and prediction of drug response in PD. © 2019 International Parkinson and Movement Disorder Society.