Search

The incremented uptake provided by time-lapse microscopy in Organ-on-a-Chip (OoC) devices allowed increased attention to the dynamics of the co-cultured systems. However, the amount of information stored in long-time experiments may constitute a serious bottleneck of the experimental pipeline. Forward long-term prediction of cell trajectories may reduce the spatial–temporal burden of video sequences storage. Cell trajectory prediction becomes crucial especially to increase the trustworthiness in software tools designed to conduct a massive analysis of cell behavior under chemical stimuli. To address this task, we transpose here the exploitation of the presence of “social forces” from the human to the cellular level for motion prediction at microscale by adapting the potential of Social Generative Adversarial Network predictors to cell motility. To demonstrate the effectiveness of the approach, we consider here two case studies: one related to PC-3 prostate cancer cells cultured in 2D Petri dishes under control and treated conditions and one related to an OoC experiment of tumor-immune interaction in fibrosarcoma cells. The goodness of the proposed strategy has been verified by successfully comparing the distributions of common descriptors (kinematic descriptors and mean interaction time for the two scenarios respectively) from the trajectories obtained by video analysis and the predicted counterparts.

We describe a novel method to achieve a universal, massive, and fully automated analysis of cell motility behaviours, starting from time-lapse microscopy images. The approach was inspired by the recent successes in application of machine learning for style recognition in paintings and artistic style transfer. The originality of the method relies i) on the generation of atlas from the collection of single-cell trajectories in order to visually encode the multiple descriptors of cell motility, and ii) on the application of pre-trained Deep Learning Convolutional Neural Network architecture in order to extract relevant features to be used for classification tasks from this visual atlas. Validation tests were conducted on two different cell motility scenarios: 1) a 3D biomimetic gels of immune cells, co-cultured with breast cancer cells in organ-on-chip devices, upon treatment with an immunotherapy drug; 2) Petri dishes of clustered prostate cancer cells, upon treatment with a chemotherapy drug. For each scenario, single-cell trajectories are very accurately classified according to the presence or not of the drugs. This original approach demonstrates the existence of universal features in cell motility (a so called “motility style”) which are identified by the DL approach in the rationale of discovering the unknown message in cell trajectories.

Cell-cell interactions are an observable manifestation of underlying complex biological processes occurring in response to diversified biochemical stimuli. Recent experiments with microfluidic devices and live cell imaging show that it is possible to characterize cell kinematics via computerized algorithms and unravel the effects of targeted therapies. We study the influence of spatial and temporal resolutions of time-lapse videos on motility and interaction descriptors with computational models that mimic the interaction dynamics among cells. We show that the experimental set-up of time-lapse microscopy has a direct impact on the cell tracking algorithm and on the derived numerical descriptors. We also show that, when comparing kinematic descriptors in two diverse experimental conditions, too low resolutions may alter the descriptors’ discriminative power, and so the statistical significance of the difference between the two compared distributions. The conclusions derived from the computational models were experimentally confirmed by a series of video-microscopy acquisitions of co-cultures of unlabelled human cancer and immune cells embedded in 3D collagen gels within microfluidic devices. We argue that the experimental protocol of acquisition should be adapted to the specific kind of analysis involved and to the chosen descriptors in order to derive reliable conclusions and avoid biasing the interpretation of results.

The dynamic contrast-enhanced MR imaging plays a crucial role in evaluating the effectiveness of neoadjuvant chemotherapy (NAC) even since its early stage through the prediction of the final pathological complete response (pCR). In this study, we proposed a transfer learning approach to predict if a patient achieved pCR (pCR) or did not (non-pCR) by exploiting, separately or in combination, pre-treatment and early-treatment exams from I-SPY1 TRIAL public database. First, low-level features, i.e., related to local structure of the image, were automatically extracted by a pre-trained convolutional neural network (CNN) overcoming manual feature extraction. Next, an optimal set of most stable features was detected and then used to design an SVM classifier. A first subset of patients, called fine-tuning dataset (30 pCR; 78 non-pCR), was used to perform the optimal choice of features. A second subset not involved in the feature selection process was employed as an independent test (7 pCR; 19 non-pCR) to validate the model. By combining the optimal features extracted from both pre-treatment and early-treatment exams with some clinical features, i.e., ER, PgR, HER2 and molecular subtype, an accuracy of 91.4% and 92.3%, and an AUC value of 0.93 and 0.90, were returned on the fine-tuning dataset and the independent test, respectively. Overall, the low-level CNN features have an important role in the early evaluation of the NAC efficacy by predicting pCR. The proposed model represents a first effort towards the development of a clinical support tool for an early prediction of pCR to NAC.

Anemia; Microfluídica; Enfermedad de células falciformes Anèmia; Microfluídica; Malaltia de cèl·lules falciformes Anaemia; Microfluidics; Sickle cell disease Combining microfluidics technology with machine learning represents an innovative approach to conduct massive quantitative cell behavior study and implement smart decision-making systems in support of clinical diagnostics. The spleen plays a key-role in rare hereditary hemolytic anemia (RHHA), being the organ responsible for the premature removal of defective red blood cells (RBCs). The goal is to adapt the physiological spleen filtering strategy for in vitro study and monitoring of blood diseases through RBCs shape analysis. Then, a microfluidic device mimicking the slits of the spleen red pulp area and video data analysis are combined for the characterization of RBCs in RHHA. This microfluidic unit is designed to evaluate RBC deformability by maintaining them fixed in planar orientation, allowing the visual inspection of RBC’s capacity to restore their original shape after crossing microconstrictions. Then, two cooperative learning approaches are used for the analysis: the majority voting scheme, in which the most voted label for all the cell images is the class assigned to the entire video; and the maximum sum of scores to decide the maximally scored class to assign. The proposed platform shows the capability to discriminate healthy controls and patients with an average efficiency of 91%, but also to distinguish between RHHA subtypes, with an efficiency of 82%. This work was supported by Networking Biomedical Research Center (CIBER), Spain. CIBER is an initiative funded by the VI National R&D&i Plan 2008–2011, Iniciativa Ingenio 2010, Consolider Program, CIBER Actions, and the Instituto de Salud Carlos III (RD16/0006/0012), with the support of the European Regional Development Fund. This work was funded by the European Commission H2020-MSCA-ITN-2019, Grant Agreement N860436, “EVIDENCE” and by the CERCA Programme and by the Commission for Universities and Research of the Department of Innovation, Universities, and Enterprise of the Generalitat de Catalunya (2017 SGR 1079), it has been developed in the context of AdvanceCat with the support of ACCIÓ (Catalonia Trade and Investment; Generalitat de Catalunya) under the Catalonian ERDF operational program (European Regional Development Fund) 2014–2020.

Summary One of the most challenging frontiers in biological systems understanding is fluorescent label-free imaging. We present here the NeuriTES platform that revisits the standard paradigms of video analysis to detect unlabeled objects and adapt to the dynamic evolution of the phenomenon under observation. Object segmentation is reformulated using robust algorithms to assure regular cell detection and transfer entropy measures are used to study the inter-relationship among the parameters related to the evolving system. We applied the NeuriTES platform to the automatic analysis of neurites degeneration in presence of amyotrophic lateral sclerosis (ALS) and to the study of the effects of a chemotherapy drug on living prostate cancer cells (PC3) cultures. Control cells have been considered in both the two cases study. Accuracy values of 93% and of 92% are achieved, respectively. NeuriTES not only represents a tool for investigation in fluorescent label-free images but demonstrates to be adaptable to individual needs., Highlights • Monitoring of cell phenotype changes by fluorescence label-free time-lapse microscopy • Adaptive semantic segmentation for the robust detection of cell shape • TE to correlate morphological and textural soma descriptors along time • Directed TE graph for the representation of mutual relationship among descriptors, The bigger picture One of the most challenging frontiers for the automatic understanding of biological systems is fluorescent label-free imaging in which the behavior changes of living being are characterized without cell staining. To this aim, we present here the NeuriTES platform that revisits standard paradigms of video analysis to detect unlabeled objects and correlate the analysis to phenotype evolution of the mechanisms under observation. Through the exploitation of adaptive algorithms and of transfer entropy measures, the platform assures regular cell detection and the possibility to extract reliable parameters related to the evolving cell system. As a proof-of-concept, NeuriTES is applied to two fascinating phenotype investigation scenarios, amyotrophic lateral sclerosis (ALS) disease mechanism and the study of the effects of a chemotherapy drug on living prostate cancer cells (PC3) cultures. Directed graphs assist the biologists with a visual understanding of the mechanisms identified., Nowadays, observational traits (phenotype) of biological entities complement with genomics offering the possibility to monitor phenomenon evolutions and underlying mechanism (neurodegeneration, cancer cell replication, etc.). By complementing video, data analysis, and machine learning approaches with label-free time-lapse microscopy, NeuriTES tool allows automatically analyzing such traits and extracting as outcomes proof of concepts and visual graph-based representation of the phenotypical rationale behind.

Simple Summary An early prediction of Breast Cancer Recurrence (BCR) for patients undergoing neoadjuvant chemotherapy (NACT) could better guide clinicians in the identification of the most suitable combination treatments for individual patient scenarios. We proposed a transfer learning approach to give an early prediction of three-year BCR for patients undergoing NACT, using DCE-MRI exams from I-SPY1 TRIAL and BREAST-MRI-NACT-Pilot public databases. Because no technical expertise is required in the extraction of meaningful features from images, the predictive model qualifies as a user-friendly tool for any medical expert in support of therapeutic choices. Only pre-treatment and early-treatment MRI examinations were analyzed to allow for potential therapy changes at a very early stage of treatment. We tested the strength of the model on an independent test. The best predictive performances (accuracy of 85.2%, sensitivity of 84.6%, and AUC of 0.83) were achieved by combining the extracted features with some clinical factors: age, ER, PgR, HER2+. Abstract Cancer treatment planning benefits from an accurate early prediction of the treatment efficacy. The goal of this study is to give an early prediction of three-year Breast Cancer Recurrence (BCR) for patients who underwent neoadjuvant chemotherapy. We addressed the task from a new perspective based on transfer learning applied to pre-treatment and early-treatment DCE-MRI scans. Firstly, low-level features were automatically extracted from MR images using a pre-trained Convolutional Neural Network (CNN) architecture without human intervention. Subsequently, the prediction model was built with an optimal subset of CNN features and evaluated on two sets of patients from I-SPY1 TRIAL and BREAST-MRI-NACT-Pilot public databases: a fine-tuning dataset (70 not recurrent and 26 recurrent cases), which was primarily used to find the optimal subset of CNN features, and an independent test (45 not recurrent and 17 recurrent cases), whose patients had not been involved in the feature selection process. The best results were achieved when the optimal CNN features were augmented by four clinical variables (age, ER, PgR, HER2+), reaching an accuracy of 91.7% and 85.2%, a sensitivity of 80.8% and 84.6%, a specificity of 95.7% and 85.4%, and an AUC value of 0.93 and 0.83 on the fine-tuning dataset and the independent test, respectively. Finally, the CNN features extracted from pre-treatment and early-treatment exams were revealed to be strong predictors of BCR.

The blood-brain barrier (BBB) is a dynamic cellular barrier that regulates brain nutrient supply, waste efflux, and paracellular diffusion through specialized junctional complexes. Finding a system to mimic and monitor BBB integrity (i.e., to be able to assess the effect of certain compounds on opening or closing the barrier) is of vital importance in several pathologies. This work aims to overcome some limitations of current barrier integrity measuring techniques thanks to a multi-layer microfluidic platform with integrated electrodes and Multi-frequency Trans-Endothelial Electrical Resistance (MTEER) in synergy with machine learning algorithms. MTEER measurements are performed across the barrier in a range of frequencies up to 10 MHz highlighting the presence of information on different frequency ranges. Results show that the proposed platform can detect barrier formation, opening, and regeneration afterwards, correlating with the results obtained from immunostaining of junctional complexes. This model presents novel techniques for a future biological barrier in-vitro studies that could potentially help on elucidating barrier opening or sealing on treatments with different drugs., This work was supported by Networking Biomedical Research Center (CIBER), Spain. CIBER is an initiative funded by the VI National R&D&i Plan 2008–2011, Iniciativa Ingenio 2010, Consolider Program, CIBER Actions, and the Instituto de Salud Carlos III (RD16/0006/0012), with the support of the European Regional Development Fund. This work was funded by the CERCA Programme and by the Commission for Universities and Research of the Department of Innovation, Universities, and Enterprise of the Generalitat de Catalunya (2017 SGR 1079). This work has been developed in the context of AdvanceCat with the support of ACCIÓ (Catalonia Trade and Investment; Generalitat de Catalunya) under the Catalonian ERDF operational program (European Regional Development Fund) 2014–2020. This work was funded by the Spanish Ministry of Economy and Competitiveness (MINECO) through the projects MINDS (Proyectos I + D Excelencia + FEDER) TEC2015-70104-P, CTQ2016-75870-P, BIOBOT (Programa Explora Ciencia / Tecnología), TEC2015- 72718-EXP and RTI2018-097038-B-C21.

Background Optical technologies, relying on spectral analysis, are more and more implemented in portable devices for food analysis. Thereby, each food safety, quality or authenticity provision as well as each technology requires the generation of a dedicated spectral database with reference data. Currently, knowledge on how these databases might be connected or transferred across food commodities, targeted compounds or devices are very limited. Hence, repetitive work is conducted and technologies are not optimally used. Scope and approach This perspective focuses on the currently available technologies and approaches for data handling and database transfer across miniaturized devices and technologies for food safety, quality and authenticity assessments. Key findings and conclusions For almost every food commodity or target compound a miniaturized spectroscopic device can be applied with the respective database to compare findings. Recent developments in optical spectroscopy allow more possibilities for their use as well as facilitate the production of portable devices. A multifunctional device hyphenating several sensors and broadening the application range is still not marketed. Newly developed software architecture, accessing and extracting data, helps to overcome sample heterogenicity or spurious measured data. In addition, several data fusion approaches using machine learning and deep learning strategies are available to fuse spectroscopic data with itself or other non-spectroscopic data. Following the research results presented in this field, spectral data can possibly be re-used and shared across instruments and locations, highly increasing the applicability of data sets. Thereby, obstacles such as policy or confidentiality are taken into account.

Background: A Critical Shoulder Angle (CSA), evaluated on plain radiographs, greater than 35&deg, is considered predictive of rotator cuff tears. The present prospective comparative study aimed, firstly, to develop a formula to calculate the amount of acromion that should be resected performing a lateral acromioplasty and, secondly, verify whether lateral acromioplasty to reduce the CSA associated with arthroscopic cuff repair decreased the rate of recurrence of the tears, and impacted favorably on clinical postoperative outcomes. Methods: Patients undergoing arthroscopic rotator cuff repair (RCR) for rotator cuff tears with a CSA greater than 35&deg, were included in this study and divided into two groups, based on whether the CSA had been reduced by arthroscopic resection of the lateral portion of the acromion. A new mathematical formula was developed in order to quantify the amount of bone to be resected while performing the lateral acromioplasty. Patients with traumatic tears, previous surgery, osteoarthritis or plain radiographs, not classified as A1 according to Suter-Henninger, were excluded. Clinical and radiographic outcomes were assessed at a minimum of 2 years of follow-up considering the tear size. Results: 289 patients were included in this study. Thirty-seven were lost to follow-up. Group A (Lateral acromioplasty) patients included: 38 small tears, 30 medium tears, 28 large tears and 22 massive tears, Group B (control group) was composed of 40 small tears, 30 medium tears, 30 large tears and 23 massive tears. The Constants Score value and retear Rate were, respectively, significant higher (p = 0.007 and p = 0.004) and lower (p = 0.029 and p = 0.028) in Group A, both in the Small-and Medium-size subgroups. No complications were outlined. The mediolateral width of the acromion was reduced, according to the preoperatively calculated measure. Conclusion: Arthroscopic lateral acromioplasty decreased the CSA within the favorable range (30&deg, &ndash, 35&deg, ) in all patients treated, resecting the amount of bone predicted by the mathematical formula. Lateral acromioplasty is a safe and reproducible technique which may prevent recurrence of rotator cuff tears in patients with small and medium lesions. Level of evidence: II.

Cell motility is the brilliant result of cell status and its interaction with close environments. Its detection is now possible, thanks to the synergy of high-resolution camera sensors, time-lapse microscopy devices, and dedicated software tools for video and data analysis. In this scenario, we formulated a novel paradigm in which we considered the individual cells as a sort of sensitive element of a sensor, which exploits the camera as a transducer returning the movement of the cell as an output signal. In this way, cell movement allows us to retrieve information about the chemical composition of the close environment. To optimally exploit this information, in this work, we introduce a new setting, in which a cell trajectory is divided into sub-tracks, each one characterized by a specific motion kind. Hence, we considered all the sub-tracks of the single-cell trajectory as the signals of a virtual array of cell motility-based sensors. The kinematics of each sub-track is quantified and used for a classification task. To investigate the potential of the proposed approach, we have compared the achieved performances with those obtained by using a single-trajectory paradigm with the scope to evaluate the chemotherapy treatment effects on prostate cancer cells. Novel pattern recognition algorithms have been applied to the descriptors extracted at a sub-track level by implementing features, as well as samples selection (a good teacher learning approach) for model construction. The experimental results have put in evidence that the performances are higher when a further cluster majority role has been considered, by emulating a sort of sensor fusion procedure. All of these results highlighted the high strength of the proposed approach, and straightforwardly prefigure its use in lab-on-chip or organ-on-chip applications, where the cell motility analysis can be massively applied using time-lapse microscopy images.

Aflatoxins are fungal metabolites extensively produced by many different fungal species that may contaminate a wide range of agricultural food products. They have been studied extensively because of being associated with various chronic and acute diseases, especially immunosuppression and cancer, and their presence in food is strictly monitored and regulated worldwide. Aflatoxin detection and measurement relies mainly on chemical methods usually based on chromatography approaches, and recently developed immunochemical based assays that have advantages but also limitations, since these are expensive and destructive techniques. Nondestructive, optical approaches are recently being developed to assess presence of contamination in a cost and time effective way, maintaining acceptable accuracy and reproducibility. In this paper are presented the results obtained with a simple portable device for nondestructive detection of aflatoxins in almonds. The presented approach is based on the analysis of fluorescence spectra of slurried almonds under 375 nm wavelength excitation. Experiments were conducted with almonds contaminated in the range of 2.7–320.2 ng/g total aflatoxins B (AFB1 + AFB2) as determined by High Performance Liquid Chromatography with Fluorescence Detection (HPLC/FLD). After applying pre-processing steps, spectral analysis was carried out using a binary classification model based on Support Vector Machine (SVM) algorithm. A majority vote procedure was then performed on the classification results. In this way we could achieve, as best result, a classification accuracy of 94% (and false negative rate 5%) with a threshold set at 6.4 ng/g. These results illustrate the feasibility of such approach in the great challenge of aflatoxin detection for food and feed safety.

Modern optical sensors coupled with time-lapse microscopy devices and dedicated software tools allow the miniaturization of laboratories for biological experiments leading to the Organ-On-Chip (OoC) framework. OoCs allow performing massive measurements on a large number of cells under the assumption of reproducibility conditions, permitting to investigate the cell dynamics in terms of motility and shape changes over time. In this work, we present the OoC platform used in a preliminary study of the Rare Haemolytic Anaemia (RHA) disease, a group of rare diseases characterized by haemolysis, which is the premature loss of red blood cells (RBCs). Preliminary results demonstrate the effectiveness of shape measurement for the diagnosis of RHA.

The performance of an Unsupervised Online feature Selection (UOS) algorithm was investigated for the selection of training features of multispectral images acquired from a dairy product (vanilla cream) stored under isothermal conditions. The selected features were further used as input in a support vector machine (SVM) model with linear kernel for the determination of the microbiological quality of vanilla cream. Model training (n = 65) was based on two batches of cream samples provided directly by the manufacturer and stored at different isothermal conditions (4, 8, 12, and 15 &deg, C), whereas model testing (n = 132) and validation (n = 48) were based on real life conditions by analyzing samples from different retail outlets as well as expired samples from the market. Qualitative analysis was performed for the discrimination of cream samples in two microbiological quality classes based on the values of total viable counts [TVC &le, 2.0 log CFU/g (fresh samples) and TVC &ge, 6.0 log CFU/g (spoiled samples)]. Results exhibited good performance with an overall accuracy of classification for the two classes of 91.7% for model validation. Further on, the model was extended to include the samples in the TVC range 2&ndash, 6 log CFU/g, using 1 log step to define the microbiological quality of classes in order to assess the potential of the model to estimate increasing microbial populations. Results demonstrated that high rates of correct classification could be obtained in the range of 2&ndash, 5 log CFU/g, whereas the percentage of erroneous classification increased in the TVC class (5,6) that was close to the spoilage level of the product. Overall, the results of this study demonstrated that the UOS algorithm in tandem with spectral data acquired from multispectral imaging could be a promising method for real-time assessment of the microbiological quality of vanilla cream samples.

Background and objective: Full-field digital mammography (FFDM) is the predominant breast cancer screening exam used. However, with the emergence of digital breast tomosynthesis (DBT) the radiologists could improve early recognition of breast cancer signs. In this scenario, the detection of architectural distortion (AD) is still a challenging task. ADs are very subtle contraction of the breast parenchyma that could represent the earliest manifestation of cancer, assessing at present 50% of missed cases. Methods: This paper proposes a new paradigm to detect AD in DBT exams by a cross-cutting approach exploiting the 3-dimensionality of the imaging modality. After locating AD candidates in each DBT slice, the suspicious spots are tracked in cross-slice direction and then characterized in terms of neighboring texture. In this approach, which mimics radiologist's scrolling down over zoomed slices, we reduce the amount of uninformative signs collected in DBT exams by preserving the large variability of AD appearance. Results: Using 37 sets of DBT slices containing at least one AD locus indicated by a radiologist, the proposed methodology reaches an AUC of 0.84, with only one false negative exam at sensitivity of 0.9. Conclusions: The results show that the proposed algorithm can be a promising tool for the automatic detection of AD locii. Future work will address the extension of the dataset of DBT slices as well the improvement of algorithm performance toward the application in the clinical practice.

Objective: The ability of cells to collectively move is essential in various biological contexts including cancer metastasis. In this paper, we propose an automatic video analysis tool to correlate the cell movement inhibition with replication block induced by dose-dependent chemotherapy administration. Methods: The novel approach combines individual and collective cell kinematic analysis performed over time-lapse microscopy video frames. Cells are first localized and tracked, and then kinematic descriptors are extracted for each track. Selective track identification is performed assuming diversified cell roles within the same cluster (spontaneously forming groups of cells), and finally individual results are grouped exploiting consensus of coordinated motility within cell clusters. Results: Recognition performance of three different experimental conditions (no drug, 0.5–5 μ M merged in the same condition, and 50 μ M) reached an average accuracy value of 88% over 958 different tracks collected in 36 clusters of diverse dimensions in eight independent experiments. Conclusion: An extensive application of this methodology could give a different point of view of the cancer mechanisms.

Aflatoxin detection currently relies mainly on chemical methods usually based on chromatography approaches, and recently developed immunochemical based assays that are fairly accurate, however, they are time-consuming, expensive and destructive. Non-destructive, optical approaches are recently being developed in order to assess the presence of contamination in a cost and time-effective way, maintaining high levels of accuracy and reproducibility, but are usually based on the benchtop and expensive instruments. Here we will present the evolution of results of the analysis of fluorescence spectra of contaminated almond samples during the development of an optical multi-sensor device in the framework of PhasmaFOOD project. The aim of the project was to develop a low cost and portable instrument comprising multispectral and imaging capabilities, conjugated with a cloud reference database and analysis toolbox for food features analysis. One of the use cases of the project is the fast, reliable and non-destructive detection of mycotoxin (in particular aflatoxin) contamination in food products. For this use case, we used in particular fluorescence spectroscopy and different approaches to data analysis. After the first feasibility tests in the range of mg/g contamination range with a simple and effective analysis that led to highly reliable results, the work was focused on the detection limits with samples (almond) in the range of 0-291 ng/g acquired with a simple portable device and excitation light at 365 nm wavelength. An ad hoc processing strategy based on a feature selection steps coupled with a nonlinear classifier has been developed and test with two different datasets collected one month from the other another. The system performances have been evaluated training the classification model with one dataset and testing its with the other. The results have shown an accuracy higher than 80% with a threshold lower than 10ppb as contamination level.

In recent years, applications like Apple’s Siri or Microsoft’s Cortana have created the illusion that one can actually “chat” with a machine. However, a perfectly natural human-machine interaction is far from real as none of these tools can empathize. This issue has raised an increasing interest in speech emotion recognition systems, as the possibility to detect the emotional state of the speaker. This possibility seems relevant to a broad number of domains, ranging from man-machine interfaces to those of diagnostics. With this in mind, in the present work, we explored the possibility of applying a precision approach to the development of a statistical learning algorithm aimed at classifying samples of speech produced by children with developmental disorders(DD) and typically developing(TD) children. Under the assumption that acoustic features of vocal production could not be efficiently used as a direct marker of DD, we propose to apply the Emotional Modulation function(EMF) concept, rather than running analyses on acoustic features per se to identify the different classes. The novel paradigm was applied to the French Child Pathological & Emotional Speech Database obtaining a final accuracy of 0.79, with maximum performance reached in recognizing language impairment (0.92) and autism disorder (0.82).

Vision-based measurement of pain can provide significant advantage in patient care and cost reduction. The subjective nature of pain, however, poses metrological challenges yet to be addressed. With this work, we designed and validated a measurement architecture for automatically estimating intervals of pain over time based on the analysis of facial expressions. A reference measurement procedure was set up for labelling subjective levels of pain as observed by a set of independent evaluators. By means of a multi-label strategy, the system was calibrated for managing the uncertainty of the information provided by the evaluators at the ground-truth level. Results obtained for different coverage probability values support the efficacy of the proposed platform and motivate further investigations.

This paper proposes a method to reduce the number of false-positives (FP) in a computer-aided detection (CAD) scheme for automated detection of architectural distortion (AD) in digital mammography. AD is a subtle contraction of breast parenchyma that may represent an early sign of breast cancer. Due to its subtlety and variability, AD is more difficult to detect compared to microcalcifications and masses, and is commonly found in retrospective evaluations of false-negative mammograms. Several computer-based systems have been proposed for automated detection of AD in breast images. The usual approach is automatically detect possible sites of AD in a mammographic image (segmentation step) and then use a classifier to eliminate the false-positives and identify the suspicious regions (classification step). This paper focus on the optimization of the segmentation step to reduce the number of FPs that is used as input to the classifier. The proposal is to use statistical measurements to score the segmented regions and then apply a threshold to select a small quantity of regions that should be submitted to the classification step, improving the detection performance of a CAD scheme. We evaluated 12 image features to score and select suspicious regions of 74 clinical Full-Field Digital Mammography (FFDM). All images in this dataset contained at least one region with AD previously marked by an expert radiologist. The results showed that the proposed method can reduce the false positives of the segmentation step of the CAD scheme from 43.4 false positives (FP) per image to 34.5 FP per image, without increasing the number of false negatives.

Engineered nanomaterials play an even more relevant role in nanotechnology advances. However, care must be taken due to their suspected detrimental effects on human cells. Such alterations can be monitored through Atomic Force Microscopy (AFM) equipment and image digitalization. With the purpose to depict a metrological compliant scenario, a novel vision-based evaluation system is proposed with an evaluation unit based on a deep learning architecture. Inspired by the recent trends in trying to extend the standard concept of quantities to nominal properties and measurement to evaluation, we proposed here a platform for the evaluation of morphological alterations in AFM images of human cells exposed to different concentrations of carbon nanotubes. Results reveal the feasibility to automatically investigate such alterations with the aim to improve occupational medicine protocols and cells cataloguing procedures.

Nowadays, visual-based measurement (VBM) systems offer new possibilities of investigation for researchers and clinicians, using noninvasive–nondestructive approaches. In this paper, we present an atomic force microscopy (AFM)-based VBM for the study of cell-cerium oxide nanoparticle interactions. To provide a metrological characterization of the results obtained and with the aim to compare different strategies, we modeled four artifacts effects occurring in AFM acquisition within the random process theory and implemented a Monte Carlo simulation to repeatedly inject such variability in the original image. Empirical cumulative distribution function, confidence intervals, and average representative values, following Supplement 1 guidelines, were estimated for the final scores assigned by the operations unit to each cell. Area under the roc curve and accuracy of classification for two different machine learning approaches were compared in a metrological compliant methodology. Results clearly demonstrate the robustness of the presented VBM system and quantify the uncertainty expected for such kind of results.

The morphological changes induced by engineered nanomaterials (ENMs) in cellular samples are a key clue to evaluate the impact of these materials on human health. The investigation of the complexity of the interaction among nanoparticles and cellular molecules requires cutting-edge instrumentation and dedicated procedures. To this regard, atomic force microscopy (AFM) is a leading imaging technique that has the peculiarities of high resolution and direct relationship with 3D cellular morphology. Expert human operators, however, are still required to manage most of the AFM-based analysis, thus introducing subjective bias and allowing a limited number of trials. The modality of interaction and the resulting topographic differences are often not a priori known. Also, the presence of artefacts in AFM images may affect the derived conclusions. In this work, we propose a robust and flexible strategy to analyse AFM topography images with single click-select actions by the human operator. The proposed system allows for not only morphological studies and quantification of the changes occurring in cellular samples in the presence of nanomaterials, but also for the investigation of diversified experiments in more flexible application domains. As a proof of concepts, samples of human EA. hy926 endothelial cells exposed to carbon nanotubes are used to demonstrate the effectiveness of the proposed solution. The system is also tested against various AFM-artefact and noise scenarios and the robustness of its discrimination capability is verified. (C) 2017 Elsevier B.V. All rights reserved.

In clinical practice, the constructive consultation among experts improves the reliability of the diagnosis and leads to the definition of the treatment plan for the patient. Aggregation of the different opinions collected by many experts can be performed at the level of patient information, abnormality delineation, or final assessment. In this study, we present a novel cooperative strategy that exploits the dynamic contribution of the classification models composing the ensemble to make the final class assignment. As a proof of concept, we applied the proposed approach to the assessment of malignant infiltration in 103 vertebral compression fractures in magnetic resonance images. The results obtained with repeated random subsampling and receiver operating characteristic analysis indicate that the cooperative system statistically improved ( $$p

In this paper we discuss the applicability of numerical descriptors and statistical physics concepts to characterize complex biological systems observed at microscopic level through organ on chip approach. To this end, we employ data collected on a microfluidic platform in which leukocytes can move through suitably built channels toward their target. Leukocyte behavior is recorded by standard time lapse imaging. In particular, we analyze three groups of human peripheral blood mononuclear cells (PBMC): heterozygous mutants (in which only one copy of the FPR1 gene is normal), homozygous mutants (in which both alleles encoding FPR1 are loss-of-function variants) and cells from ‘wild type’ donors (with normal expression of FPR1). We characterize the migration of these cells providing a quantitative confirmation of the essential role of FPR1 in cancer chemotherapy response. Indeed wild type PBMC perform biased random walks toward chemotherapy-treated cancer cells establishing persistent interactions with them. Conversely, heterozygous mutants present a weaker bias in their motion and homozygous mutants perform rather uncorrelated random walks, both failing to engage with their targets. We next focus on wild type cells and study the interactions of leukocytes with cancerous cells developing a novel heuristic procedure, inspired by Lyapunov stability in dynamical systems.

We present a multistage approach to detection and classification of mammographic lesions that is independent of accurate extraction of their contours. The ultimate goal is to discriminate malignant tumors from benign lesions and normal parenchymal tissue in a realistic scenario of lesion candidates automatically detected in mammograms. Local analysis of the Gaussian curvature and of the phase response of multidirectional Gabor filters is performed for identification of suspicious focal areas. The detection of lesions and the classification of malignant tumors are performed in series, respectively, via a differential approach to analysis of the tissue surrounding the candidates and via quantification of nonstationarity and spatial dependence of pixel values within circular and annular regions of interest. A unified 3D free-response receiver operating characteristic framework is applied for global analysis of the two binary categorization problems in series. The system was tested on a total of 2105 full-field digital and screen-film mammograms from three different datasets, including abnormal mammograms with 560 malignant tumors and 639 benign lesions, masses, or architectural distortion, and 1010 normal mammograms. For sensitivity of detection of malignant tumors in the range of 0.70–0.81, the range of falsely detected malignant tumors was 0.82–3.47 per image, with a series of two stages of classification, including stepwise logistic regression for selection of features, Fisher linear discriminant analysis, and two-fold cross-validation.

We present the results of the first in-depth measurements of the linen cloth of the shroud of Arquata, a precious copy of the Shroud of Turin, which dates back to 1653. The measurements aimed at finding the nature of the faint and low-contrast body impressions on the linen cloth, which are not produced by drawings or paintings as in the other copies of the Shroud of Turin. In general, the optical analysis and the imaging of low-contrast stains on ancient textiles is a complex task, due to the irregular surface and the influence of spectrum, position and uniformity of the illuminating source on colour accuracy and rendition. A correct evaluation requires a multidisciplinary approach. We used noninvasive technologies, including imaging topological radar, laser induced fluorescence, absolute diffused reflectance and absorption spectra, which were previously used to study frescoes, paintings, antique papers, but were never exploited on ancient textiles. The combined results of our measurements and data elaboration allowed identifying the origins of the body impressions, of the stains simulating blood and of the other marks embedded on the linen cloth. Our results can be used to plan the proper long-term conservation of the linen cloth and of marks on it. © 2015 Elsevier Masson SAS.

Humans can communicate their emotions by modulating facial expressions or the tone of their voice. Albeit numerous applications exist that enable machines to read facial emotions and recognize the content of verbal messages, methods for speech emotion recognition are still in their infancy. Yet, fast and reliable applications for emotion recognition are the obvious advancement of present 'intelligent personal assistants', and may have countless applications in diagnostics, rehabilitation and research. Taking inspiration from the dynamics of human group decision-making, we devised a novel speech emotion recognition system that applies, for the first time, a semi-supervised prediction model based on consensus. Three tests were carried out to compare this algorithm with traditional approaches. Labeling performances relative to a public database of spontaneous speeches are reported. The novel system appears to be fast, robust and less computationally demanding than traditional methods, allowing for easier implementation in portable voice-analyzers (as used in rehabilitation, research, industry, etc.) and for applications in the research domain (such as real-time pairing of stimuli to participants' emotional state, selective/differential data collection based on emotional content, etc.).

The interpretation of diagnostic images is often conditioned by the specific properties of the instrument that generated the image. This makes particularly complicated to develop universal recognition algorithms that can facilitate the diagnosis in case of massive population screenings. Mammography is a typical example where such an algorithm is required. Although the technological advances in medical imaging increases the accuracy of interpretation of images, the improved resolution may not facilitate the identification of breast cancer at a very early stage due to the many confounding factors related, for instance, to differences in instrument settings or breast positioning by the operator. Being impossible an exact standardization, the problem of reducing the effects of different instruments and operators can be faced with a proper algorithm that can extract from each image the relevant information in an unsupervised manner, thus limiting the influence of instrumental and positioning issues. For this scope, in this paper we investigated the properties of a classifier based on an ensemble of Adaptive Artificial Immune Networks (A2INET) applied to original mammography image indicators aimed at diagnosing bilateral asymmetry that is known to be correlated with increased breast cancer risk. Classification models were trained using a set of descriptors measuring the degree of similarity of paired regions of the left and right breasts. Noteworthy, the ensemble of A2INET models achieved very high classification rates even when training and testing were made on two completely independent and heterogeneous datasets. The obtained results are promising (maximum accuracy level of 0.90, sensitivity of 0.93 and specificity of 0.87) and they prefigure to apply automatic diagnostic tools in clinical practice exploiting a network of different instrument databases.

Multimodal emotion recognition is a challenging topic that aims at determining the affective state of a subject by combining audio-visual and physiological signals acquired in a naturalistic environment. This procedure can be used to monitor the emotional state of a subject affected by mental disorder or under medical treatment. Common attempts principally learn a unique complex machine learning system on descriptors collected from different subjects. The novel paradigm of single-subject multimodal regression model (SSMRM) that we propose in this study is embedded in a averaging-based merging strategy that aggregates the responses provided by each model during the test of a new subject. This new approach presents a flexible architecture able to continuously embed new models without global re-training.

We hypothesize that quantification of structural similarity or dissimilarity between paired mammographic regions can be effective in detecting asymmetric signs of breast cancer. Bilateral masking procedures are applied for this purpose by using automatically detected anatomical landmarks. Changes in structural information of the extracted regions are investigated using spherical semivariogram descriptors and correlation-based structural similarity indices in the spatial and complex wavelet domains. The spatial distribution of grayscale values as well as of the magnitude and phase responses of multidirectional Gabor filters are used to represent the structure of mammographic density and of the directional components of breast tissue patterns, respectively. A total of 188 mammograms from the DDSM and mini-MIAS databases, consisting of 47 asymmetric cases and 47 normal cases, were analyzed. For the combined dataset of mammograms, areas under the receiver operating characteristic curves of 0.83, 0.77, and 0.87 were obtained, respectively, with linear discriminant analysis, the Bayesian classifier, and an artificial neural network with radial basis functions, using the features selected by stepwise logistic regression and leave-one-patient-out cross-validation. Two-view analysis provided accuracy up to 0.94, with sensitivity and specificity of 1 and 0.88, respectively.