Increased delivery and cytotoxicity of doxorubicin in HeLa cells using the synthetic cationic peptide pEM-2 functionalized liposomes.

HYPOTHESIS: Due to the inability of nano-carriers to passively cross the cell membrane, cell penetration enhancers are used to accelerate cytoplasmic delivery of antineoplastic drugs. In this regard, snake venom phospholipase A2 peptides are known for their ability to destabilize natural and artificial membranes. In this context, functionalized liposomes with peptide pEM-2 should favor the incorporation of doxorubicin and increase its cytotoxicity in HeLa cells compared to free doxorubicin, and doxorubicin encapsulated in non-functionalized liposomes. EXPERIMENTS: Several characteristics were monitored, including doxorubicin loading capacity of the liposomes, as well as the release and uptake before and after functionalization. Cell viability and half-maximal inhibition concentrations were determined in HeLa cells. FINDINGS: In vitro studies showed that functionalization of doxorubicin-loaded PC-NG liposomes with pEM-2 not only improved the amount of doxorubicin delivered compared to free doxorubicin or other doxorubicin-containing formulations, but also showed enhanced cytotoxicity against HeLa cells. The PC-NG liposomes loaded with doxorubicin improved treatment efficacy by reducing the IC50 value and incubation time. This increase in cell toxicity was directly related to the concentration of pEM-2 peptide bound to the liposomes. We conclude that the cytotoxicity observed in HeLa cells due to the action of doxorubicin was strongly favored when encapsulated in synthetic liposomes and functionalized with the pEM-2 peptide.

Optimising computer aided detection to identify intra-thoracic tuberculosis on chest x-ray in South African children.

Diagnostic tools for paediatric tuberculosis remain limited, with heavy reliance on clinical algorithms which include chest x-ray. Computer aided detection (CAD) for tuberculosis on chest x-ray has shown promise in adults. We aimed to measure and optimise the performance of an adult CAD system, CAD4TB, to identify tuberculosis on chest x-rays from children with presumptive tuberculosis. Chest x-rays from 620 children <13 years enrolled in a prospective observational diagnostic study in South Africa, were evaluated. All chest x-rays were read by a panel of expert readers who attributed each with a radiological reference of either 'tuberculosis' or 'not tuberculosis'. Of the 525 chest x-rays included in this analysis, 80 (40 with a reference of 'tuberculosis' and 40 with 'not tuberculosis') were allocated to an independent test set. The remainder made up the training set. The performance of CAD4TB to identify 'tuberculosis' versus 'not tuberculosis' on chest x-ray against the radiological reference read was calculated. The CAD4TB software was then fine-tuned using the paediatric training set. We compared the performance of the fine-tuned model to the original model. Our findings were that the area under the receiver operating characteristic curve (AUC) of the original CAD4TB model, prior to fine-tuning, was 0.58. After fine-tuning there was an improvement in the AUC to 0.72 (p = 0.0016). In this first-ever description of the use of CAD to identify tuberculosis on chest x-ray in children, we demonstrate a significant improvement in the performance of CAD4TB after fine-tuning with a set of well-characterised paediatric chest x-rays. CAD has the potential to be a useful additional diagnostic tool for paediatric tuberculosis. We recommend replicating the methods we describe using a larger chest x-ray dataset from a more diverse population and evaluating the potential role of CAD to replace a human-read chest x-ray within treatment-decision algorithms for paediatric tuberculosis.

The importance of estradiol for body weight regulation in women.

Obesity in women of reproductive age has a number of adverse metabolic effects, including Type II Diabetes (T2D), dyslipidemia, and cardiovascular disease. It is associated with increased menstrual irregularity, ovulatory dysfunction, development of insulin resistance and infertility. In women, estradiol is not only critical for reproductive function, but they also control food intake and energy expenditure. Food intake is known to change during the menstrual cycle in humans. This change in food intake is largely mediated by estradiol, which acts directly upon anorexigenic and orexigenic neurons, largely in the hypothalamus. Estradiol also acts indirectly with peripheral mediators such as glucagon like peptide-1 (GLP-1). Like estradiol, GLP-1 acts on receptors at the hypothalamus. This review describes the physiological and pathophysiological mechanisms governing the actions of estradiol during the menstrual cycle on food intake and energy expenditure and how estradiol acts with other weight-controlling molecules such as GLP-1. GLP-1 analogs have proven to be effective both to manage obesity and T2D in women. This review also highlights the relationship between steroid hormones and women's mental health. It explains how a decline or imbalance in estradiol levels affects insulin sensitivity in the brain. This can cause cerebral insulin resistance, which contributes to the development of conditions such as Parkinson's or Alzheimer's disease. The proper use of both estradiol and GLP-1 analogs can help to manage obesity and preserve an optimal mental health in women by reducing the mechanisms that trigger neurodegenerative disorders.

Herramienta de Detección de Maltrato Infantil para la Clínica Odontológica

RESUMEN: El maltrato infantil es una grave vulneración a los derechos humanos de los niños, que afecta su salud física, mental y emocional, y que puede provocar además graves consecuencias en su vida adulta. El odontólogo tiene la responsabilidad de detectar los posibles casos de maltrato infantil y tomar acciones para detenerlo en una etapa temprana. Sin embargo, muchas veces la decisión de intervenir y/o denunciar un caso se hace difícil, pues no se posee las herramientas para objetivar la sospecha. Aplicando el método Delphi, con el apoyo de destacados expertos nacionales, se desarrolló un breve formulario de auto-aplicación para el odontólogo, en el que se definieron siete puntos clave que se deben examinar al enfrentarse a un niño lesionado que llega a la clínica odontológica. Este formulario guía al cirujano dentista en el reconocimiento de las señales y signos clínicos de abuso, y le permite determinar cuándo un caso presenta suficientes elementos que apuntan a posible maltrato infantil y se hace recomendable su denuncia, tal como indica la ley. La aplicación del formulario mejorará la pesquisa de los casos, que es el primer paso para asegurar el bienestar de las niñas y los niños maltratados.

ABSTRACT: Child abuse is a serious violation of children's human rights, that affects their physical, mental and emotional health, and can, furthermore, have serious consequences in their adult life. Dentists have the responsibility to detect possible cases of child abuse and take actions to put a stop to it at an early stage. However, often the decision to report a case is made difficult due to a lack of tools to express an objective suspicion. Applying the Delphi method with the support of prominent national experts, a short self-application questionnaire was developed to be applied by odontologists in the dental clinic, defining seven key points that should be examined when handling the case of an injured child. The questionnaire guides dentists in recognizing the signs of abuse and deciding when a case has enough elements suggesting possible child abuse that it is advisable to report it, as required by law. Applying this questionnaire will improve the detections of cases, which is the first step to ensure the wellbeing of abused children.

Chronic Stress and Ovulatory Dysfunction: Implications in Times of COVID-19.

Stress is known to be associated with adverse health outcomes. The COVID-19 pandemic and its associated lockdowns are examples of chronic stressors. Lockdown measures inadvertently caused significant psychological distress and became a powerful source of anxiety/stress, sleep disturbances, nutritional changes and weight gain. Stress is known to impact women's health specifically, through hypothalamic-pituitary-gonadal (HPG) axis dysfunction and resultant ovulatory dysfunction. Such dysfunction may manifest in menstrual irregularities and/or infertility due to hypothalamic hypogonadism. Here, we review the key physiological mediators of stress and associated ovulatory dysfunction. The kisspeptinergic system is comprised of sets of neurons located in the hypothalamus, the rostral periventricular region of the third ventricle (RP3V) and the arcuate nucleus (ARC). This system links nutrition, reproductive signals and stress. It plays a key role in the function of the HPG axis. During chronic stress, the kisspeptinergic system affects the HPG axis, GnRH pulsatility, and, therefore, ovulation. Leptin, insulin and corticotrophin-releasing hormone (CRH) are thought to be additional key modulators in the behavioral responses to chronic stress and may contribute to stress-related ovulatory dysfunction. This mini-review also summarizes and appraises the available evidence on the negative impact of chronic stress as a result of the COVID-19 pandemic lockdowns. It proposes physiological mechanisms to explain the observed effects on women's reproductive health and well-being. The review suggests areas for future research.

A New Smoothened Antagonist Bearing the Purine Scaffold Shows Antitumour Activity In Vitro and In Vivo.

The Smoothened (SMO) receptor is the most druggable target in the Hedgehog (HH) pathway for anticancer compounds. However, SMO antagonists such as vismodegib rapidly develop drug resistance. In this study, new SMO antagonists having the versatile purine ring as a scaffold were designed, synthesised, and biologically tested to provide an insight to their mechanism of action. Compound 4s was the most active and the best inhibitor of cell growth and selectively cytotoxic to cancer cells. 4s induced cell cycle arrest, apoptosis, a reduction in colony formation and downregulation of PTCH and GLI1 expression. BODIPY-cyclopamine displacement assays confirmed 4s is a SMO antagonist. In vivo, 4s strongly inhibited tumour relapse and metastasis of melanoma cells in mice. In vitro, 4s was more efficient than vismodegib to induce apoptosis in human cancer cells and that might be attributed to its dual ability to function as a SMO antagonist and apoptosis inducer.

Bryophytes of rotten logs from El Zafire biological station, Amazonas - Colombia / Briófitos de troncos en descomposición de la estación biológica el zafire, amazonas-colombia

RESUMEN En el presente trabajo se caracterizó la flora briofítica en troncos en descomposición en la estación meteorológica El Zafire, Amazonas-Colombia. Para ello se realizó un muestreo de 100 unidades muestrales en 20 troncos en diferente estado de descomposición y en dos tipos de bosque (tierra firme y varillal inundable). Se reportan 120 especies, 81 hepáticas y 39 musgos, pertenecientes a 55 géneros (33 hepáticas y 22 musgos) y 21 familias (nueve hepáticas y 12 musgos). Se registran cuatro especies nuevas para el país, 25 para la amazonia colombiana y 41 para el departamento del Amazonas. En términos de riqueza total, el bosque de varillal presentó un valor mayor al de tierra firme. Sin embargo, esta diferencia no es significativa (Kruskal Wallis X 2=0,199; p = 0,05); así mismo la diversidad fue mayor en el bosque de varillal inundable (Shanon = 3,93) en comparación con la del bosque de tierra firme (Shanon = 3,67). La composición de las comunidades de briófitos fue diferente entre los dos tipos de bosques (similitud igual a 40 %). En el estudio florístico de los dos tipos de bosques de la estación biológica, se evidenció una marcada dominancia de la familia Lejeunaceae, que representó el 55,5 % de las hepáticas y el 37,5 % del total de las especies de briófitos.

ABSTRACT The present study aims to characterize the bryophyte community on rotten logs in El Zafire biological station, Amazonas-Colombia. We sampled 100 plots on 20 trunks with different states of decomposition in two types of forest (terra firme and floodplain). 120 species are reported, 81 liverworts and 39 mosses, belonging to 55 genera (33 liverworts and 22 mosses) and 21 families (nine liverworts and 12 mosses). Four new species are registered for Colombia, 25 for the Colombia Amazon, and 41 for the department of Amazonas. In terms of richness, the floodplain presented a higher value than the terra firme forest. However, no significant difference was found between the two types of forests (Kruskal Wallis X 2c= 0.199, X 2t= 3.81). Diversity was higher in the floodplain (Shanon = 3.93) compared to the terra firme forest (Shanon = 3.67). The composition of the bryophyte communities shows differences between the two types of forests (similarity equal to 40 %). In the floristic study of the two types of forests of the biological station, the most common family was Lejeuneaceae, it represented 55.5 % of the liverworts sampled and 37.5 % of the total of the bryophyte species.

COVID-19 on Chest Radiographs: A Multireader Evaluation of an Artificial Intelligence System.

Background Chest radiography may play an important role in triage for coronavirus disease 2019 (COVID-19), particularly in low-resource settings. Purpose To evaluate the performance of an artificial intelligence (AI) system for detection of COVID-19 pneumonia on chest radiographs. Materials and Methods An AI system (CAD4COVID-XRay) was trained on 24 678 chest radiographs, including 1540 used only for validation while training. The test set consisted of a set of continuously acquired chest radiographs (n = 454) obtained in patients suspected of having COVID-19 pneumonia between March 4 and April 6, 2020, at one center (223 patients with positive reverse transcription polymerase chain reaction [RT-PCR] results, 231 with negative RT-PCR results). Radiographs were independently analyzed by six readers and by the AI system. Diagnostic performance was analyzed with the receiver operating characteristic curve. Results For the test set, the mean age of patients was 67 years ± 14.4 (standard deviation) (56% male). With RT-PCR test results as the reference standard, the AI system correctly classified chest radiographs as COVID-19 pneumonia with an area under the receiver operating characteristic curve of 0.81. The system significantly outperformed each reader (P < .001 using the McNemar test) at their highest possible sensitivities. At their lowest sensitivities, only one reader significantly outperformed the AI system (P = .04). Conclusion The performance of an artificial intelligence system in the detection of coronavirus disease 2019 on chest radiographs was comparable with that of six independent readers. © RSNA, 2020.

Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system.

There is a growing interest in the automated analysis of chest X-Ray (CXR) as a sensitive and inexpensive means of screening susceptible populations for pulmonary tuberculosis. In this work we evaluate the latest version of CAD4TB, a commercial software platform designed for this purpose. Version 6 of CAD4TB was released in 2018 and is here tested on a fully independent dataset of 5565 CXR images with GeneXpert (Xpert) sputum test results available (854 Xpert positive subjects). A subset of 500 subjects (50% Xpert positive) was reviewed and annotated by 5 expert observers independently to obtain a radiological reference standard. The latest version of CAD4TB is found to outperform all previous versions in terms of area under receiver operating curve (ROC) with respect to both Xpert and radiological reference standards. Improvements with respect to Xpert are most apparent at high sensitivity levels with a specificity of 76% obtained at a fixed 90% sensitivity. When compared with the radiological reference standard, CAD4TB v6 also outperformed previous versions by a considerable margin and achieved 98% specificity at the 90% sensitivity setting. No substantial difference was found between the performance of CAD4TB v6 and any of the various expert observers against the Xpert reference standard. A cost and efficiency analysis on this dataset demonstrates that in a standard clinical situation, operating at 90% sensitivity, users of CAD4TB v6 can process 132 subjects per day at an average cost per screen of $5.95 per subject, while users of version 3 process only 85 subjects per day at a cost of $8.38 per subject. At all tested operating points version 6 is shown to be more efficient and cost effective than any other version.

Computer-aided diagnosis for World Health Organization-defined chest radiograph primary-endpoint pneumonia in children.

BACKGROUND: The chest radiograph is the most common imaging modality to assess childhood pneumonia. It has been used in epidemiological and vaccine efficacy/effectiveness studies on childhood pneumonia. OBJECTIVE: To develop computer-aided diagnosis (CAD4Kids) for chest radiography in children and to evaluate its accuracy in identifying World Health Organization (WHO)-defined chest radiograph primary-endpoint pneumonia compared to a consensus interpretation. MATERIALS AND METHODS: Chest radiographs were independently evaluated by three radiologists based on WHO criteria. Automatic lung field segmentation was followed by manual inspection and correction, training, feature extraction and classification. Radiographs were filtered with Gaussian derivatives on multiple scales, extracting texture features to classify each pixel in the lung region. To obtain an image score, the 95th percentile score of the pixels was used. Training and testing were done in 10-fold cross validation. RESULTS: The radiologist majority consensus reading of 858 interpretable chest radiographs included 333 (39%) categorised as primary-endpoint pneumonia, 208 (24%) as other infiltrate only and 317 (37%) as no primary-endpoint pneumonia or other infiltrate. Compared to the reference radiologist consensus reading, CAD4Kids had an area under the receiver operator characteristic (ROC) curve of 0.850 (95% confidence interval [CI] 0.823-0.876), with a sensitivity of 76% and specificity of 80% for identifying primary-endpoint pneumonia on chest radiograph. Furthermore, the ROC curve was 0.810 (95% CI 0.772-0.846) for CAD4Kids identifying primary-endpoint pneumonia compared to other infiltrate only. CONCLUSION: Further development of the CAD4Kids software and validation in multicentre studies are important for future research on computer-aided diagnosis and artificial intelligence in paediatric radiology.

Author Correction: White Matter and Gray Matter Segmentation in 4D Computed Tomography.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has not been fixed in the paper.

RHOA GTPase Controls YAP-Mediated EREG Signaling in Small Intestinal Stem Cell Maintenance.

RHOA, a founding member of the Rho GTPase family, is critical for actomyosin dynamics, polarity, and morphogenesis in response to developmental cues, mechanical stress, and inflammation. In murine small intestinal epithelium, inducible RHOA deletion causes a loss of epithelial polarity, with disrupted villi and crypt organization. In the intestinal crypts, RHOA deficiency results in reduced cell proliferation, increased apoptosis, and a loss of intestinal stem cells (ISCs) that mimic effects of radiation damage. Mechanistically, RHOA loss reduces YAP signaling of the Hippo pathway and affects YAP effector epiregulin (EREG) expression in the crypts. Expression of an active YAP (S112A) mutant rescues ISC marker expression, ISC regeneration, and ISC-associated Wnt signaling, but not defective epithelial polarity, in RhoA knockout mice, implicating YAP in RHOA-regulated ISC function. EREG treatment or active ß-catenin Catnblox(ex3) mutant expression rescues the RhoA KO ISC phenotypes. Thus, RHOA controls YAP-EREG signaling to regulate intestinal homeostasis and ISC regeneration.

Abordaje Terapéutico de la Hipomineralización Molar - Incisal. Revisión Narrativa / Peripheral Odontogenic Fibroma: Case Report

RESUMEN: Hipomineralización Molar-Incisal (MIH) es un trastorno del desarrollo dentario asociado a factores sistémicos, producido por una incompleta mineralización y maduración del esmalte. La prevalencia en niños, a nivel mundial, varía en la literatura entre el 2,4 % y el 40,2 %. Este trastorno que implica al menos un primer molar permanente, pudiendo también verse afectados los incisivos, dependiendo del momento, la duración, la susceptibilidad del individuo y la gravedad de la injuria prenatal, perinatal o postnatal. El esmalte presenta un grado variable de alteración en la translucidez, siendo éste de un espesor normal y de color blanco, o café-amarillo. Si bien se encuentra intacto en el momento de la erupción, puede sufrir fracturas post eruptivas debido a las fuerzas de la masticación, dejando límites definidos. Por lo general, los molares gravemente afectados son extremadamente hipersensibles, propensos a lesiones de caries de rápida progresión, y pueden ser difíciles de tratar en pacientes jóvenes. La atención debe abordar el comportamiento y la ansiedad del niño, con el objetivo de proporcionar restauraciones duraderas en condiciones libres de dolor. La ejecución de medidas preventivas individuales puede posponer el inicio del tratamiento restaurador y reducir la incomodidad del paciente a largo plazo. El diagnóstico precoz permitirá el seguimiento y la instauración de dichas medidas preventivas tan pronto las superficies afectadas sean accesibles. Pese a que los enfoques de tratamiento para MIH han comenzado a ser más claros y los avances en los materiales dentales han proporcionado soluciones clínicas en los casos que se consideraban sin posibilidad de restauración en el pasado, deben llevarse a cabo ensayos clínicos a largo plazo para facilitar aún más el manejo clínico de este cuadro.

ABSTRACT: Molar Incisor Hypomineralization (MIH) is a tooth development disorder, which is associated with systemic factors, produced by incomplete enamel mineralization and maturation below the enamel surface that is intact at the time of eruption. In literature, the prevalence in children worldwide varies between 2.4 % and 40.2 %. This disorder which involves at least one first permanent molar, and depending on duration, the child's susceptibility as well as the severity of prenatal, perinatal or postnatal insult may also compromise incisors. The defect reveals a variable degree of alteration in the translucency of the enamel, that has initially normal thickness and can be white, yellow or brown. Enamel surface may breakdown after eruption, due to masticatory forces, leaving sharp borders. Usually, severely affected molars are extremely hypersensitive, prone to rapid caries development, and can be difficult to manage in young patients. The complex care involved must address the child's behavior and anxiety, aiming to provide pain free treatment and durable restorations. Intensive individually prescribed preventive programs may postpone the onset of restorative treatment and reduce patient discomfort in the long term. Early identification of such children will allow monitoring and implementation of preventive measures as soon as affected surfaces are accessible. Although treatment approaches for MIH have become more clear, and advances in dental materials have provided clinical solutions in cases that in the past were regarded as unrestorable, long-term clinical trials should be realized to further facilitate clinical management of this dental defect.

New imidoyl-indazole platinum (II) complexes as potential anticancer agents: Synthesis, evaluation of cytotoxicity, cell death and experimental-theoretical DNA interaction studies.

Four new neutral N,N imidoyl-indazole ligands (L1, L3, L6, L7) and six new Pt(II)-based complexes (C1-5 and C7) were synthesized and characterized by spectroscopic and spectrometric techniques. Additionally, compounds L6, L7, C3, C5 and C7 were analyzed using X-ray diffraction. An evaluation of cytotoxicity and cell death in vitro for both ligands and complexes was performed by colorimetric assay and flow cytometry, in four cancer cell lines and VERO cells as the control, respectively. Cytotoxicity and selectivity demonstrated by each compound were dependent on the cancer cell line assayed. IC50 values of complexes C1-5 and C7 were lower than those exhibited for the reference drug cisplatin, and selectivity of these complexes was in general terms greater than cisplatin on three cancer cell lines studied. In HL60 cells, complexes C1 and C5 exhibited the lowest values of IC50 and were almost five times more selective than cisplatin. Flow cytometry results suggest that each complex predominantly induced necrosis, and its variant necroptosis, instead of apoptosis in all cancer cell lines studied. DNA binding assays, using agarose gel electrophoresis and UV-visible spectrophotometry studies, displayed a strong interaction only between C4 and DNA. In fact, theoretical calculations showed that C4-DNA binding complex was the most thermodynamic favorable interaction among the complexes in study. Overall, induction of cell death by dependent and independent-DNA-metal compound interactions were possible using imidoyl-indazole Pt(II) complexes as anticancer agents.

White Matter and Gray Matter Segmentation in 4D Computed Tomography.

Modern Computed Tomography (CT) scanners are capable of acquiring contrast dynamics of the whole brain, adding functional to anatomical information. Soft tissue segmentation is important for subsequent applications such as tissue dependent perfusion analysis and automated detection and quantification of cerebral pathology. In this work a method is presented to automatically segment white matter (WM) and gray matter (GM) in contrast- enhanced 4D CT images of the brain. The method starts with intracranial segmentation via atlas registration, followed by a refinement using a geodesic active contour with dominating advection term steered by image gradient information, from a 3D temporal average image optimally weighted according to the exposures of the individual time points of the 4D CT acquisition. Next, three groups of voxel features are extracted: intensity, contextual, and temporal. These are used to segment WM and GM with a support vector machine. Performance was assessed using cross validation in a leave-one-patient-out manner on 22 patients. Dice coefficients were 0.81 ± 0.04 and 0.79 ± 0.05, 95% Hausdorff distances were 3.86 ± 1.43 and 3.07 ± 1.72 mm, for WM and GM, respectively. Thus, WM and GM segmentation is feasible in 4D CT with good accuracy.

Low Gene Dosage of Cdc42 Is Not Associated with Protein Dysfunction in Patients with Colorectal Cancer.

High incidence of Rho Cdc42-GTPase overexpression has been found in Colorectal Cancer (CRC) samples, suggesting its potential role in tumor development. However, no conclusive studies have shown the lack of mutations and/or copy number of Cdc42 gene in this type of samples. To understand mutation/deletion and copy number status of Cdc42 gene, CRC patients were evaluated for both parameters. More than Cdc42 mutants, single-nucleotide variants were found. Analysis of regions flanking the Cdc42 gene showed allelic imbalance; 58.7% were loss of heterozygosity (LOH) positive and 14.8% presented microsatellite instability. The highest LOH percentage was located between microsatellite markers D1S199 and D1S2674, where the Cdc42 gene is located. No association between gender, age, and tumor stage was found. LOH validation through gene dosage analysis showed most CRC patients with allelic imbalance also presented a low gene dosage of Cdc42, although equal amounts of Cdc42 mRNA were detected in all samples. Although changes in Cdc42 expression were not found in any condition, Cdc42 activation was different between high and normal gene dosage samples, but not between samples with normal and low copy number. Low dosage of Cdc42 was also not related to changes in methylation status at the Cdc42 promoter region. Results suggest that low copy of Cdc42 gene is not associated with Cdc42 protein dysfunction in CRC patients.

An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information.

Lack of human resources and radiological interpretation expertise impair tuberculosis (TB) screening programmes in TB-endemic countries. Computer-aided detection (CAD) constitutes a viable alternative for chest radiograph (CXR) reading. However, no automated techniques that exploit the additional clinical information typically available during screening exist. To address this issue and optimally exploit this information, a machine learning-based combination framework is introduced. We have evaluated this framework on a database containing 392 patient records from suspected TB subjects prospectively recruited in Cape Town, South Africa. Each record comprised a CAD score, automatically computed from a CXR, and 12 clinical features. Comparisons with strategies relying on either CAD scores or clinical information alone were performed. Our results indicate that the combination framework outperforms the individual strategies in terms of the area under the receiving operating characteristic curve (0.84 versus 0.78 and 0.72), specificity at 95% sensitivity (49% versus 24% and 31%) and negative predictive value (98% versus 95% and 96%). Thus, it is believed that combining CAD and clinical information to estimate the risk of active disease is a promising tool for TB screening.

Automated detection of breast cancer in false-negative screening MRI studies from women at increased risk.

PURPOSE: To evaluate the performance of an automated computer-aided detection (CAD) system to detect breast cancers that were overlooked or misinterpreted in a breast MRI screening program for women at increased risk. METHODS: We identified 40 patients that were diagnosed with breast cancer in MRI and had a prior MRI examination reported as negative available. In these prior examinations, 24 lesions could retrospectively be identified by two breast radiologists in consensus: 11 were scored as visible and 13 as minimally visible. Additionally, 120 normal scans were collected from 120 women without history of breast cancer or breast surgery participating in the same MRI screening program. A fully automated CAD system was applied to this dataset to detect malignant lesions. RESULTS: At 4 false-positives per normal case, the sensitivity for the detection of cancer lesions that were visible or minimally visible in retrospect in prior-negative examinations was 0.71 (95% CI=0.38-1.00) and 0.31 (0.07-0.59), respectively. CONCLUSIONS: A substantial proportion of cancers that were misinterpreted or overlooked in an MRI screening program was detected by a CAD system in prior-negative examinations. It has to be clarified with further studies if such a CAD system has an influence on the number of misinterpreted and overlooked cancers in clinical practice when results are given to a radiologist.

Automatic detection of pleural effusion in chest radiographs.

Automated detection of Tuberculosis (TB) using chest radiographs (CXRs) is gaining popularity due to the lack of trained human readers in resource limited countries with a high TB burden. The majority of the computer-aided detection (CAD) systems for TB focus on detection of parenchymal abnormalities and ignore other important manifestations such as pleural effusion (PE). The costophrenic angle is a commonly used measure for detecting PE, but has limitations. In this work, an automatic method to detect PE in the left and right hemithoraces is proposed and evaluated on a database of 638 CXRs. We introduce a robust way to localize the costophrenic region using the chest wall contour as a landmark structure, in addition to the lung segmentation. Region descriptors are proposed based on intensity and morphology information in the region around the costophrenic recess. Random forest classifiers are trained to classify left and right hemithoraces. Performance of the PE detection system is evaluated in terms of recess localization accuracy and area under the receiver operating characteristic curve (AUC). The proposed method shows significant improvement in the AUC values as compared to systems which use lung segmentation and the costophrenic angle measurement alone.

On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis.

The major advantage of multiple-instance learning (MIL) applied to a computer-aided detection (CAD) system is that it allows optimizing the latter with case-level labels instead of accurate lesion outlines as traditionally required for a supervised approach. As shown in previous work, a MIL-based CAD system can perform comparably to its supervised counterpart considering complex tasks such as chest radiograph scoring in tuberculosis (TB) detection. However, despite this remarkable achievement, the uncertainty inherent to MIL can lead to a less satisfactory outcome if analysis at lower levels (e.g., regions or pixels) is needed. This issue may seriously compromise the applicability of MIL to tasks related to quantification or grading, or detection of highly localized lesions. In this paper, we propose to reduce uncertainty by embedding a MIL classifier within an active learning (AL) framework. To minimize the labeling effort, we develop a novel instance selection mechanism that exploits the MIL problem definition through one-class classification. We adapt this mechanism to provide meaningful regions instead of individual instances for expert labeling, which is a more appropriate strategy given the application domain. In addition, and contrary to usual AL methods, a single iteration is performed. To show the effectiveness of our approach, we compare the output of a MIL-based CAD system trained with and without the proposed AL framework. The task is to detect textural abnormalities related to TB. Both quantitative and qualitative evaluations at the pixel level are carried out. Our method significantly improves the MIL-based classification.