Deep-Manager: a versatile tool for optimal feature selection in live-cell imaging analysis.

One of the major problems in bioimaging, often highly underestimated, is whether features extracted for a discrimination or regression task will remain valid for a broader set of similar experiments or in the presence of unpredictable perturbations during the image acquisition process. Such an issue is even more important when it is addressed in the context of deep learning features due to the lack of a priori known relationship between the black-box descriptors (deep features) and the phenotypic properties of the biological entities under study. In this regard, the widespread use of descriptors, such as those coming from pre-trained Convolutional Neural Networks (CNNs), is hindered by the fact that they are devoid of apparent physical meaning and strongly subjected to unspecific biases, i.e., features that do not depend on the cell phenotypes, but rather on acquisition artifacts, such as brightness or texture changes, focus shifts, autofluorescence or photobleaching. The proposed Deep-Manager software platform offers the possibility to efficiently select those features having lower sensitivity to unspecific disturbances and, at the same time, a high discriminating power. Deep-Manager can be used in the context of both handcrafted and deep features. The unprecedented performances of the method are proven using five different case studies, ranging from selecting handcrafted green fluorescence protein intensity features in chemotherapy-related breast cancer cell death investigation to addressing problems related to the context of Deep Transfer Learning. Deep-Manager, freely available at https://github.com/BEEuniroma2/Deep-Manager , is suitable for use in many fields of bioimaging and is conceived to be constantly upgraded with novel image acquisition perturbations and modalities.

Machine learning phenomics (MLP) combining deep learning with time-lapse-microscopy for monitoring colorectal adenocarcinoma cells gene expression and drug-response.

High-throughput phenotyping is becoming increasingly available thanks to analytical and bioinformatics approaches that enable the use of very high-dimensional data and to the availability of dynamic models that link phenomena across levels: from genes to cells, from cells to organs, and through the whole organism. The combination of phenomics, deep learning, and machine learning represents a strong potential for the phenotypical investigation, leading the way to a more embracing approach, called machine learning phenomics (MLP). In particular, in this work we present a novel MLP platform for phenomics investigation of cancer-cells response to therapy, exploiting and combining the potential of time-lapse microscopy for cell behavior data acquisition and robust deep learning software architectures for the latent phenotypes extraction. A two-step proof of concepts is designed. First, we demonstrate a strict correlation among gene expression and cell phenotype with the aim to identify new biomarkers and targets for tailored therapy in human colorectal cancer onset and progression. Experiments were conducted on human colorectal adenocarcinoma cells (DLD-1) and their profile was compared with an isogenic line in which the expression of LOX-1 transcript was knocked down. In addition, we also evaluate the phenotypic impact of the administration of different doses of an antineoplastic drug over DLD-1 cells. Under the omics paradigm, proteomics results are used to confirm the findings of the experiments.

Discovering the hidden messages within cell trajectories using a deep learning approach for in vitro evaluation of cancer drug treatments.

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.

The influence of spatial and temporal resolutions on the analysis of cell-cell interaction: a systematic study for time-lapse microscopy applications.

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.

Control de calidad de la citología ginecológica: programa de calidad de la Sociedad Española de Citología. Resultados de la segunda ronda / The Spanish Society of Cytology: quality control program of gynecological cytology

Introducción. Las recomendaciones del cribado de cáncer de cérvix en España incluyen la participación en programas de control de calidad externos a los laboratorios de citología. La Sociedad Española de Citología (SEC) ha iniciado un programa de control de calidad de la citología ginecológica (CG). Objetivo. Presentar y analizar los resultados de la segunda ronda del control de calidad de la SEC. Material y métodos. Se incluyeron casos procesados mediante citología en medio líquido. Se escanearon las laminillas mediante la plataforma Aperio. Se seleccionaron 23 muestras procedentes de un banco de casos con al menos un 75% de acuerdo entre 4 expertos citopatólogos. Los diagnósticos de los casos para estudio incluyeron: uno negativo, 15 lesiones de bajo grado (4 ASCUS y 11 LSIL) y 7 lesiones de alto grado (uno ASCH y 6 HSIL). La CML correspondía a ThinPrep® en 16 casos y a SurePath® en 7. Se realizó el estudio de la correlación diagnóstica interobservador. Resultados. Participaron 16 hospitales. Las concordancias medias fueron: global 70,6% y por tipo de lesión 63,1%. En negativo 71,9%, en ASCUS 56,2%, en LSIL 69,5% y en HSIL 82,8%. Los casos discordantes correspondían con mayor frecuencia a negativos y a ASCUS. Se observó discordancia severa (HSIL/ASCH frente a negativo) en un 4,4% de los casos. Conclusiones. Nuestros resultados son similares a los descritos en la literatura, encontrando muy escasas discordancias severas (AU)

Introduction. In Spain, the guidelines for cervical cancer screening include a recommendation to enroll in external quality control programs. The Spanish Society of Cytology (SEC) has initiated its own quality control program of gynecological cytology (QCPGC). Aim. To describe and discuss the results of the second round of SEC¿s QCPGC. Material and method. The cases are selected by a group of expert cytologists. The cases with an agreement of 75% of four cytopathologists were used. The cases were scanned with Aperio. The scanned cases not available were excluded. We included a total of 23 cases, 1 negative, 15 low grade lesions (4 ASCUS and 11 LSIL) and 7 high grade lesions (1 ASCH and 6 HSIL). Sixteen cases were studied with ThinPrep™ platform and in 7 cases the SurePath™ platform was used. Results. Sixteen hospitals participated. The global mean concordance was 70.6%. The mean concordance in the type of lesion was 63.1%. The concordance was 71.9% in negative diagnoses, 56.2% in ASCUS, 69.5% in LSIL and 82.8% in HSIL The discordant cases were diagnosed more frequently as negative and ASCUS. 4.4% of cases had major discordances (HSIL or ASCH versus negatives). Conclusions: Our results are similar to those reported in the literature, with very little severe discordance. The method of exchanging slides does not allows continuous training, since the review of discordant cases can not be made. Therefore, methodological corrections are contemplated for future rounds (AU)

[The Spanish Society of Cytology: Quality control program of gynecological cytology]. / Control de calidad de la citología ginecológica: programa de calidad de la Sociedad Española de Citología. Resultados de la segunda ronda.

INTRODUCTION: In Spain, the guidelines for cervical cancer screening include a recommendation to enroll in external quality control programs. The Spanish Society of Cytology (SEC) has initiated its own quality control program of gynecological cytology (QCPGC). AIM: To describe and discuss the results of the second round of SECs QCPGC. MATERIAL AND METHOD: The cases are selected by a group of expert cytologists. The cases with an agreement of 75% of four cytopathologists were used. The cases were scanned with Aperio. The scanned cases not available were excluded. We included a total of 23 cases, 1 negative, 15 low grade lesions (4 ASCUS and 11 LSIL) and 7 high grade lesions (1 ASCH and 6 HSIL). Sixteen cases were studied with ThinPrep™ platform and in 7 cases the SurePath™ platform was used. RESULTS: Sixteen hospitals participated. The global mean concordance was 70.6%. The mean concordance in the type of lesion was 63.1%. The concordance was 71.9% in negative diagnoses, 56.2% in ASCUS, 69.5% in LSIL and 82.8% in HSIL The discordant cases were diagnosed more frequently as negative and ASCUS. 4.4% of cases had major discordances (HSIL or ASCH versus negatives). CONCLUSIONS: Our results are similar to those reported in the literature, with very few severe discordances.

One-year psychosocial functioning in patients in the early vs. late stage of bipolar disorder.

OBJECTIVE: The aim of this 1-year follow-up study was to compare functional outcome as well as clinical differences between patients with first- and multiple-episode bipolar disorder. METHOD: Bipolar disorder patients with first (n = 60) and multiple episodes (n = 59) were recruited from two hospitals in Spain. The Functioning Assessment Short Test (FAST) was used to assess functioning. The Hamilton Depression Rating Scale (HAMD) and the Young Mania Rating Scale (YMRS) were administered to assess mood symptoms. RESULTS: As expected, patients with first episode experienced a greater functioning compared to patients with multiple episodes (11.26 ± 10.94 vs. 26.91 ± 13.96; t = 6.436, P < 0.001). There were significant demographic and clinical differences between both groups. Baseline depressive symptoms (F = 9.553, df = 4, 102; P < 0.001) and age (F = 14.145, df = 4, 103; P < 0.001) were significantly associated with poor functional recovery at 6-month and 12-month assessment, respectively, in a group of patients with multiple episodes. CONCLUSION: Our data give support to the model of staging in bipolar disorder, showing that the enduring neurotoxicity of repeated episodes may contribute to sustained impairment in multiple areas of psychosocial functioning.

Weight gain in bipolar disorder: pharmacological treatment as a contributing factor.

OBJECTIVE: The aim of this paper was to review the association of most commonly used psychopharmacological drugs with weight gain in bipolar disorder. METHOD: Information was retrieved from a PubMed/Medline literature search reviewing weight gain in pharmacological studies in bipolar disorder. RESULTS: Obesity and overweight in bipolar disorder are partly related to prescribed drugs with a strong effect of clozapine and olanzapine. Lesser but still relevant weight gain is caused by quetiapine, risperidone, lithium, valproate, gabapentin and by some antidepressants. Ziprasidone, aripiprazole, carbamazepine and lamotrigine do not seem to cause significant overweight. CONCLUSION: Careful monitoring of weight changes in patients before and after drug prescription should be implemented in the clinical routine and drugs which potentially cause weight gain should be avoided in overweight patients with bipolar disorder. Furthermore, eating habits and daily activities should be targeted as they may also have a significant impact on overall health and weight-related issues.

Rapid-cycling bipolar I disorder: course and treatment outcome of a large sample across Europe.

OBJECTIVES: To evaluate the baseline characteristics and follow-up outcomes of rapid-cycling (RC) bipolar I patients in a large, prospective, observational study. METHODS: EMBLEM (European Mania in Bipolar Longitudinal Evaluation of Medication) is a long-term prospective observational study of in- and outpatients with an acute mania/mixed episode conducted in 14 European countries. Demographic and clinical variables were collected at baseline, including the presence or absence of DSM-IV rapid-cycling during the past year. Outcome measures included the 5-item Hamilton Depression Rating Scale (HAMD-5) and Young Mania Rating Scale (YMRS) over 12 weeks, as well as the Clinical Global Impressions-Bipolar Disorder Scale (CGI-BP overall, mania and depression) over 12 months. RESULTS: Of 3684 patients enrolled, 3089 patients provided reliable data to qualify for either RC (N=535, 17.3%) or non-RC (NRC, N=2554), according to DSM-IV. RC prevalence varied across countries (p<0.001). Baseline and 12 week outcomes on the YMRS and HAMD-5, 12 month ratings on the CGI-BP subscales and work impairment at 12 months were significantly different (p<0.001) between groups, being worse in RC. RC patients were more likely to receive antidepressants and lamotrigine (p<0.001). Using logistic regression, RC was associated to country (p<0.001), female sex (p=0.029), outpatients (p=0.035), more history of attempted suicide (p<0.001) and alcohol abuse (p<0.001). CONCLUSIONS: The EMBLEM results suggest that in naturalistic settings, patients with mania and RC differ from NRC in socio-demographic characteristics, treatment prescriptions and clinical outcome measures with a consistently worse occupational outcome and comorbidities. RC represents a longitudinally severe form of bipolar disorder, with poorly evidence-based diagnostic and therapeutic tools.

What really matters to bipolar patients' caregivers: sources of family burden.

BACKGROUND: Identifying and modifying burdensome aspects might reduce the level of burden and their negative effects both on caregivers and patients' outcome. Most studies evaluate acutely ill patients, whereas the most relevant problems may be related to subthreshold symptoms and long-term outcome. The aims of the present study were to assess caregiver's subjective burden, to analyse which were the most burdensome aspects for caregivers and to study which variables could explain the caregiver's subjective burden. METHODS: Caregivers of 86 euthymic bipolar patients completed the subjective burden subscale from an adapted version of the Social Behaviour Assessment Schedule. RESULTS: Caregivers showed a moderate level of subjective burden. The highest levels of distress were reported regarding the patient's behaviour; the most distressing behaviours were hyperactivity, irritability, sadness and withdrawal. Regarding the patient's role performance, the most worrying aspects were those associated with the patient's work or study and social relationships. Regarding adverse effects on others, caregivers were especially distressed by the way the illness had affected their emotional health and their life in general. Poorer social and occupational functioning, an episode in the last 2 years, history of rapid cycling and the caregiver being responsible for medication intake explained a quarter of the variance of the caregiver's subjective burden. LIMITATIONS: This was a cross-sectional study focused only on primary caregivers, there was no control group of non-bipolar patients. CONCLUSIONS: This study provides relevant data concerning the burden of caregivers of stable bipolar patients, pointing at potential targets for psychosocial interventions.

A microswitch cluster to enhance arm-lifting responses without dystonic head tilting by a child with multiple disabilities.

This study assessed whether a microswitch duster with favorite stimulation could help a 9.1-yr.-old child with multiple disabilities increase arm-lifting responses without dystonic, sideways head tilting. The microswitch cluster involved two microswitches, one at the child's arm to monitor the lifting response, and the other at the child's head to monitor whether it was tilted during arm lifting. Analysis showed that the percentage of arm-lifting responses occurring without head tilting increased most visibly when favorite stimulation focused on those (appropriate) responses.

Do cognitive complaints in euthymic bipolar patients reflect objective cognitive impairment?

BACKGROUND: In clinical practice, bipolar patients complain of cognitive deficits such as attentional or memory disturbances. The main aim of this study was to determine whether subjective cognitive complaints were associated with objective neuropsychological impairments. METHOD: Sixty euthymic bipolar patients were assessed through a neuropsychological battery. A structured clinical interview was used to determine subjective cognitive complaints in patients. Thirty healthy controls were also included in the study in order to compare the neuropsychological performance among groups. RESULTS: Bipolar patients with a higher number of episodes, especially the number of mixed episodes, longer duration of the illness and the onset of the illness at an earlier age showed more subjective complaints. Furthermore, bipolar patients with subjective complaints showed lower scores in several cognitive measures related to attention, memory and executive function compared with the control group. Nevertheless, patients without complaints also performed less well than controls in some neuropsychological measures. CONCLUSION: Bipolar patients who were aware of cognitive deficits were more chronic, had presented more previous episodes, especially mixed type, and their illness had started at an earlier age compared with patients who did not complain about cognitive problems. Moreover, patients with good cognitive insight also had a poorer social and occupational functioning as well as a poorer neuropsychological performance. However, the bipolar group without complaints also obtained lower scores in several tests compared with healthy controls. Cognitive status of bipolar patients should be routinely assessed, regardless of the patients awareness about their cognitive deficits.

Impact of a psychoeducational family intervention on caregivers of stabilized bipolar patients.

BACKGROUND: Environmental stress has an important role in the course of bipolar disorder. Some findings have shown that family beliefs about the illness could predict family burden, and this burden could influence the outcome of bipolar disorder. To the best of our knowledge, there is scant information about the effects of family intervention on the caregiver's burden in bipolar disorder. The aim of this study was to assess the effects of psychoeducational family intervention on bipolar patients' caregivers, including the assessment of the caregiver's burden. METHODS: 45 medicated euthymic bipolar outpatients were randomized into an experimental and a control group. Relatives of patients from the experimental group received 12 psychoeducational, 90-min sessions about bipolar disorder and coping skills. The caregivers' knowledge of bipolar disorder, the relationship subscales of the Family Environment Scale, and the family burden subscales from an adapted version of the Social Behavior Assessment Schedule were assessed for both caregiver groups before and after the intervention. RESULTS: Psycho-educated caregivers significantly improved their knowledge of bipolar disorder and reduced both the subjective burden and the caregiver's belief about the link between the objective burden and the patient. No significant differences were found in the objective burden nor in the family relationship subscales. CONCLUSIONS: These preliminary results suggest that psychoeducational intervention on caregivers of bipolar patients may improve the caregiver's knowledge of the illness, reduce their distress or subjective burden and alter their beliefs about the link between the disruptions in their life and the patient's illness.

[Treatment of bipolar II disorder with lamotrigine]. / Tratamiento del trastorno bipolar II con lamotrigina.

INTRODUCTION: This study analyzes the effectiveness and safety of lamotrigine in the treatment of bipolar II disorder. Patients and methods. Seventeen patients with DSM-IV bipolar II disorder with a history of poor response to lithium or other mood-stabilizers gave their consent to be treated with lamotrigine. Th ey we re followed-up for 6 months and assessed with the Young Mania Scale (YMRS), Hamilton Depression Rating Scale (HDRS-17) and the modified version of the Global Clinic Impresion Scale for Bipolar Disorder ( CG I-BP-M). RESULTS: Twelve patients completed the study. Three patients dropped out due to side effects (two because of mild rash, which vanished after treatment was discontinued and one because of vomiting) and two due to lack of efficacy. The mean dose of lamotrigine for patients completing the study was 202.1 64.4 mg/day. There was a significant improvement in HDRS-17 scores (p= 0.004) and the depressive (p=0.002) and overall (p= 0.002) subscales of the CGI-BP-M. CONCLUSIONS: This study confirms previous findings concerning the antidepressant profile of lamotrigine and its potential effectiveness in bipolar II disorder.

Tratamiento del trastorno bipolar II con lamotrigina / Treatment of bipolar II disorder with lamotrigine

Introducción. Se analiza la efectividad y seguridad de la lamotrigina en el tratamiento de pacientes bipolares de tipo II.Pacientes y métodos. Un total de 17 pacientes con trastorno bipolar II según criterios DSM-IV con antecedentes de respuesta insuficiente al tratamiento con litio u otros eutimizantes dieron su consentimiento para recibir lamotrigina para el tratamiento de su enfermedad.La respuesta se evaluó con la Escala de Manía de Young (YMRS), Escala de Hamilton para la Depresión (HDRS-17) y la versión modificada de la Escala de Impresión Clínica Global para el Trastorno Bipolar (CGI-BP-M) a lo largo de 6 meses.Resultados. Completaron los 6 meses de seguimiento 12 pacientes. Hubo tres abandonos por efectos secundarios (dos por exantema de escasa gravedad que desapareció al interrumpir el tratamiento y uno por vómitos) y dos por falta de eficacia. La dosis media de lamotrigina de los pacientes que completaron el estudio fue de 202,1ñ 64,4 mg/día.Se produjo una mejoría significativa en las escalas HDRS-17 (p =0,004) y las subescalas de depresión (p= 0,002) y general (p=0,002) de la CGI-BP-M.Conclusiones. Este estudio confirma los hallazgos de estudios previos respecto al perfil predominantemente antidepresivo de la lamotrigina y su potencial terapéutico en el trastorno bipolar II (AU)

Inflammatory bowel disease in married couples: 10 cases in Nord Pas de Calais region of France and Liège county of Belgium.

Ten pairs of husband-wife couples are reported with inflammatory bowel disease who were seen in the same geographical area in Nord Pas de Calais region of France and in Liège county (Belgium). Among these 10 couples, four were concordant for Crohn's disease, two for ulcerative colitis, and four were discordant. In nine of 10 couples neither spouse had symptoms before marriage but inflammatory bowel disease subsequently developed in both. In one couple, one spouse had Crohn's disease before marriage and the other partner experienced symptoms afterwards. Eighteen children were born to eight of 10 couples. Five of them developed Crohn's disease but four belong to the same family. In all cases the affected children were born to parents who both developed Crohn's disease after they had married and were conceived at a time when parents did not yet have symptoms. It is proposed that this pattern of emergence of inflammatory bowel disease suggests a role for an infectious agent yet to be identified.

[Prevalence of hepatitis C, B and D markers and histopathological aspects in a group of intravenous drug addicts]. / Prévalence des marqueurs des hépatites C, B et D et aspects histopathologiques dans un groupe de toxicomanes intraveineux.

OBJECTIVES: The aim of this study was to assess the prevalence of infection by HCV, HBV, HDV and HIV and their biological and histopathological patterns in 104 intravenous drug users. METHODS AND RESULTS: Seventy-five patients (72%) had anti-HCV antibodies. Transmission was rapid because 33% of those who had been drug users for 6 months or less had anti-HCV antibodies. The contamination rate was very high because 90% of those who had been drug users for 2 years or less had anti-HCV antibodies. Thirty-four (33%) had an HBV marker, and 6 were HBs Ag carriers. None of the patients had anti-HDV antibodies. Only one patient had anti-HIV antibodies. Twenty-five anti-HCV antibody positive drug users underwent liver biopsy. Seven (28%) had normal ALAT levels and 18 (72%) had permanently or intermittently elevated ALAT levels. The mean histological activity on the Knodell index was 4.1 (range: 1-8). CONCLUSIONS: This study indicates that contamination by HCV is almost inevitable after 2 years of intravenous drug use. The low prevalence of HBV, HDV, and HIV infection might be explained by a low endemic state of these viruses in our area.