Geographical distance predicts psychiatric treatment retention for Hispanic women with comorbid major depression and breast cancer.

PURPOSE: Depression is among the most common comorbid psychiatric disorders of patients with breast cancer. Depression decreases patient quality of life and, if untreated, can adversely affect cancer treatment. We sought to identify treatment barriers for women with breast cancer receiving psychotherapy for depression. Findings may help policy makers and researchers determine funding and design of future studies involving this population, especially in communities with high rates of health disparities. METHODS: We used data from a randomized trial for women with breast cancer and current DSM-IV non-psychotic unipolar major depressive disorder (MDD). Patients were randomly assigned to 12 weeks of one of three psychotherapies and attrition was assessed by whether subjects completed 12 weekly treatment sessions. We used descriptive analyses and logistic regression to identify treatment barriers. R shiny was used to determine study patient residences. RESULTS: Of 134 randomized patients, 84 (62.7%) were Hispanic. Fifty-nine patients (44%) either did not start or dropped out of treatment, 49 (83.1%) of them being Hispanic. Being a Hispanic woman, less educated, and geographically distant from treatment significantly predicted attrition. Single Hispanic mothers had significantly higher attrition risk than married and/or childless women. CONCLUSION: Identifying barriers to treatment is important to improve treatment adherence for patients with concurrent diagnoses of breast cancer and MDD, especially for traditionally underserved minorities. Additional support such as affordable tele-medicine, multi-language assistance, financial aid for transportation and child-care, and allocation of more funds to address some identified barriers deserve consideration to improve treatment adherence and outcomes.

Developing a digital informed consent app: opportunities and challenges of a new format to inform and obtain consent in public health research.

BACKGROUND: Informed consent procedures for large population-based cohort studies should be comprehensive and easy-to-use. This is particularly challenging when participants from different socio-economic groups and multicultural ethnic backgrounds are involved. Recently, more and more studies have tried to use multimedia in informed consent procedures. We describe the development and testing of a digital informed consent app and elaborate on whether this may contribute to a comprehensive and practical procedure to obtain informed consent for public health research. METHODS: In a sample of parents with young children, we used a mixed method approach to study the user experience of an informed consent app and evaluate whether it can be used to adequately inform people and register their consent. Through semi-structured interviews we investigated participants' experiences with and opinions about the app, with a special focus on comprehensibility of the content and the usability of the app. Information retention questions were asked to evaluate to what extent participants could recall key aspects of the provided study information. RESULTS: The 30 participants in this study used the app between 4 and 15 min to give their consent. Overall, they found the app well-designed, informative and easy to use. To learn more about the study for which informed consent is asked, most of the participants chose to watch the animated film, which was generally found to convey information in a clear manner. The identification process was met with mixed reactions, with some feeling it as a secure way to give consent, while for others it contradicted their view of using data anonymously. Information retention questions showed that while all participants remembered various aspects of the study, fewer than half answered all four questions satisfactorily. CONCLUSION: Our study shows that a well-designed informed consent app can be an effective tool to inform eligible participants and to record consents. Still, some issues remain, including trust barriers towards the identification procedure and lack of information retention in some participants. When implementing consent procedures that incorporate digital formats, it may be beneficial to also invest in a complementary face-to-face recruitment approach.

Prevalence of problematic feeding in young children born prematurely: a meta-analysis.

BACKGROUND: Difficulties related to eating are often reported in children born preterm. The objective of this study was to quantitatively synthesize available data on the prevalence of problematic feeding in children under 4 years of age who were born preterm. METHODS: Literature was identified from PubMed, CINAHL, and PsycInfo. The search was limited to English language and publication years 2000-2020. To be included in the meta-analysis, the article had to report the prevalence of problematic oral feeding within a population of children born prematurely (< 37 weeks' gestation), and the child age at the time of study had to be between full-term corrected age and 48 months. For studies meeting inclusion criteria, the following data were extracted: sample size and subsamples by gestational age and/or child age at time of study; definition of problematic feeding; measures used for assessment of feeding; gestational age at time of birth of sample; child age at time of study; exclusion criteria for the study; and prevalence of problematic feeding. Random-effects meta-analyses were performed to estimate the prevalence of problematic feeding across all studies, by gestational age at birth, and by child age at time of study. RESULTS: There were 22 studies that met inclusion criteria. Overall prevalence of problematic feeding (N = 4381) was 42% (95% CI 33-51%). Prevalence was neither significantly different across categories of gestational age nor by child age at the time of study. Few studies used psychometrically-sound assessments of feeding. CONCLUSION: Problematic feeding is highly prevalent in prematurely-born children in the first 4 years of life regardless of degree of prematurity. Healthcare providers of children born preterm should consider screening for problematic feeding throughout early childhood as a potential complication of preterm birth. SYSTEMATIC REVIEW REGISTRATION NUMBER: Not applicable.

Five Alternative Myosin Converter Domains Influence Muscle Power, Stretch Activation, and Kinetics.

Muscles have evolved to power a wide variety of movements. A protein component critical to varying power generation is the myosin isoform present in the muscle. However, how functional variation in muscle arises from myosin structure is not well understood. We studied the influence of the converter, a myosin structural region at the junction of the lever arm and catalytic domain, using Drosophila because its single myosin heavy chain gene expresses five alternative converter versions (11a-e). We created five transgenic fly lines, each forced to express one of the converter versions in their indirect flight muscle (IFM) fibers. Electron microscopy showed that the converter exchanges did not alter muscle ultrastructure. The four lines expressing converter versions (11b-e) other than the native IFM 11a converter displayed decreased flight ability. IFM fibers expressing converters normally found in the adult stage muscles generated up to 2.8-fold more power and displayed up to 2.2-fold faster muscle kinetics than fibers with converters found in the embryonic and larval stage muscles. Small changes to stretch-activated force generation only played a minor role in altering power output of IFM. Muscle apparent rate constants, derived from sinusoidal analysis of the chimeric converter fibers, showed a strong positive correlation between optimal muscle oscillation frequency and myosin attachment kinetics to actin, and an inverse correlation with detachment related cross-bridge kinetics. This suggests the myosin converter alters at least two rate constants of the cross-bridge cycle with changes to attachment and power stroke related kinetics having the most influence on setting muscle oscillatory power kinetics.

The Ethical, Legal, and Social Implications Program of the National Human Genome Research Institute: reflections on an ongoing experiment.

For more than 20 years, the Ethical, Legal, and Social Implications (ELSI) Program of the National Human Genome Research Institute has supported empirical and conceptual research to anticipate and address the ethical, legal, and social implications of genomics. As a component of the agency that funds much of the underlying science, the program has always been an experiment. The ever-expanding number of issues the program addresses and the relatively low level of commitment on the part of other funding agencies to support such research make setting priorities especially challenging. Program-supported studies have had a significant impact on the conduct of genomics research, the implementation of genomic medicine, and broader public policies. The program's influence is likely to grow as ELSI research, genomics research, and policy development activities become increasingly integrated. Achieving the benefits of increased integration while preserving the autonomy, objectivity, and intellectual independence of ELSI investigators presents ongoing challenges and new opportunities.

Evolving approaches to the ethical management of genomic data.

The ethical landscape in the field of genomics is rapidly shifting. Plummeting sequencing costs, along with ongoing advances in bioinformatics, now make it possible to generate an enormous volume of genomic data about vast numbers of people. The informational richness, complexity, and frequently uncertain meaning of these data, coupled with evolving norms surrounding the sharing of data and samples and persistent privacy concerns, have generated a range of approaches to the ethical management of genomic information. As calls increase for the expanded use of broad or even open consent, and as controversy grows about how best to handle incidental genomic findings, these approaches, informed by normative analysis and empirical data, will continue to evolve alongside the science.

Prefrontal cortex white matter tracts in prodromal Huntington disease.

Huntington disease (HD) is most widely known for its selective degeneration of striatal neurons but there is also growing evidence for white matter (WM) deterioration. The primary objective of this research was to conduct a large-scale analysis using multisite diffusion-weighted imaging (DWI) tractography data to quantify diffusivity properties along major prefrontal cortex WM tracts in prodromal HD. Fifteen international sites participating in the PREDICT-HD study collected imaging and neuropsychological data on gene-positive HD participants without a clinical diagnosis (i.e., prodromal) and gene-negative control participants. The anatomical prefrontal WM tracts of the corpus callosum (PFCC), anterior thalamic radiations (ATRs), inferior fronto-occipital fasciculi (IFO), and uncinate fasciculi (UNC) were identified using streamline tractography of DWI. Within each of these tracts, tensor scalars for fractional anisotropy, mean diffusivity, radial diffusivity, and axial diffusivity coefficients were calculated. We divided prodromal HD subjects into three CAG-age product (CAP) groups having Low, Medium, or High probabilities of onset indexed by genetic exposure. We observed significant differences in WM properties for each of the four anatomical tracts for the High CAP group in comparison to controls. Additionally, the Medium CAP group presented differences in the ATR and IFO in comparison to controls. Furthermore, WM alterations in the PFCC, ATR, and IFO showed robust associations with neuropsychological measures of executive functioning. These results suggest long-range tracts essential for cross-region information transfer show early vulnerability in HD and may explain cognitive problems often present in the prodromal stage. Hum Brain Mapp 36:3717-3732, 2015. © 2015 Wiley Periodicals, Inc.

Diffusion weighted imaging of prefrontal cortex in prodromal Huntington's disease.

Huntington's disease (HD) is a devastating neurodegenerative disease with no effective disease-modifying treatments. There is considerable interest in finding reliable indicators of disease progression to judge the efficacy of novel treatments that slow or stop disease onset before debilitating signs appear. Diffusion-weighted imaging (DWI) may provide a reliable marker of disease progression by characterizing diffusivity changes in white matter (WM) in individuals with prodromal HD. The prefrontal cortex (PFC) may play a role in HD progression due to its prominent striatal connections and documented role in executive function. This study uses DWI to characterize diffusivity in specific regions of PFC WM defined by FreeSurfer in 53 prodromal HD participants and 34 controls. Prodromal HD individuals were separated into three CAG-Age Product (CAP) groups (16 low, 22 medium, 15 high) that indexed baseline progression. Statistically significant increases in mean diffusivity (MD) and radial diffusivity (RD) among CAP groups relative to controls were seen in inferior and lateral PFC regions. For MD and RD, differences among controls and HD participants tracked with baseline disease progression. The smallest difference was for the low group and the largest for the high group. Significant correlations between Trail Making Test B (TMTB) and mean fractional anisotropy (FA) and/or RD paralleled group differences in mean MD and/or RD in several right hemisphere regions. The gradient of effects that tracked with CAP group suggests DWI may provide markers of disease progression in future longitudinal studies as increasing diffusivity abnormalities in the lateral PFC of prodromal HD individuals.

Association between α4 integrin cytoplasmic tail and non-muscle myosin IIA regulates cell migration.

α4ß1 integrin regulates cell migration via cytoplasmic interactions. Here, we report an association between the cytoplasmic tail of α4 integrin (α4 tail) and non-muscle myosin IIA (MIIA), demonstrated by co-immunoprecipitation of the MIIA heavy chain (HC) with anti-α4-integrin antibodies and pull-down of MIIA-HC with recombinant α4 tail from cell lysates. The association between the α4 tail and MIIA does not require paxillin binding or phosphorylation at Ser988 in the α4 tail. We found that substituting Glu982 in the α4 tail with alanine (E982A) disrupts the α4-MIIA association without interfering with the paxillin binding or Ser988 phosphorylation. By comparing stably transfected CHO cells, we show that the E982A mutation reduces the ability of α4ß1 integrin to mediate cell spreading and to promote front-back polarization. In addition, we show that E982A impairs shear-flow-induced migration of the α4-integrin-expressing CHO cells by reducing their migration speed and directional persistence. The E982A mutation also leads to defects in the organization of MIIA filament bundles. Furthermore, when cells are plated on fibronectin and simulated with shear flow, α4ß1 integrin forms filament-like patterns that co-align with MIIA filament bundles. These results provide a new mechanism for linking integrins to the actomyosin cytoskeleton and for regulating cell migration by integrins and non-muscle myosin II.

White matter fractional anisotropy is inversely related to anxious symptoms in older adults with atherosclerosis.

OBJECTIVE: Clinical anxiety disorders are associated with white matter hyperintensities and diffusion abnormalities measured using diffusion tensor imaging. However, it is not known if this association extends into individuals with mild anxious symptoms without formal diagnosis, in those who are older, or in those who have atherosclerosis. The current study explores whether white matter integrity and/or organization significantly associates with anxious symptoms in older adults with and without atherosclerosis. METHODS: We recruited older adults (ages 55-90 years); 35 with clinically diagnosed atherosclerotic vascular disease (AVD) and 22 without AVD. Anxious symptoms were measured using the validated Symptom Checklist-90-Revised. Fractional anisotropy (FA), a proxy for white matter organization and health, was measured in the white matter globally, by lobe, and in several smaller regions of interest suggested by the literature. Partial correlations between anxious symptoms and FA were calculated, controlling for significant covariates. RESULTS: Participants with and without AVD did not differ in severity of anxious symptom endorsement. There was a unique inverse relationship between white matter health and anxious symptoms in the AVD participants, but not in healthy comparisons. Significant relationships were observed in the superior longitudinal fasciculus (r = -0.476, df = 32, p = 0.004), as well as the cingulum bundle, the frontal lobes, and the parietal lobes. CONCLUSIONS: Anxiety symptoms uniquely correlated with low FA in older adults with atherosclerosis. These findings may have implications for future research on the topic of anxiety in aging and vascular disease and warrant replication.

The Genus Dacryodes Vahl.: Ethnobotany, Phytochemistry and Biological Activities.

Dacryodes Vahl. species, belonging to the Burseraceae family, are widely used in traditional medicine in tropical regions to treat a range of ailments including malaria, wounds, tonsillitis, and ringworms. This review discusses the distribution, ethnobotanical uses, phytochemistry, and bioactivities of Dacryodes species. The intent is to spur future research into isolating and identifying key active principles, secondary metabolites, and crude extracts, and evaluating their pharmacological and toxicological effects, as well as the mechanism of actions to understand their medicinal benefits. A systematic review of scientific electronic databases from 1963 to 2022 including Scifinder, Scopus, Pubmed, Springer Link, ResearchGate, Ethnobotany Research and Applications, Google Scholar, and ScienceDirect was conducted with a focus on Dacryodes edulis (G.Don) H.J. Lam and Dacryodes rostrata (Blume) H.J. Lam. Pharmacological data revealed that D. edulis isolates contain secondary metabolites and other phytochemical groups belonging to the terpenoids class with anti-microbial, anticancer, antidiabetic, antiinflammatory and hepatoprotective activities, highlighting its pharmacological potential in the therapy or management of diverse cancers, cardiovascular, and neurological diseases. Thus, phytochemicals and standardized extracts from D. edulis could offer safer and cost-effective chemopreventive and chemotherapeutic health benefits/regimen, or as alternative therapeutic remedy for several human diseases. Nevertheless, the therapeutic potential of most of the plants in the genus have not been exhaustively explored with regard to phytochemistry and pharmacology, but mostly complementary approaches lacking rigorous, scientific research-based knowledge. Therefore, the therapeutic potentials of the Dacryodes genus remain largely untapped, and comprehensive research is necessary to fully harness their medicinal properties.

The PI3K-Akt-mTOR and Associated Signaling Pathways as Molecular Drivers of Immune-Mediated Inflammatory Skin Diseases: Update on Therapeutic Strategy Using Natural and Synthetic Compounds.

The dysregulated phosphatidylinositol-3-kinase (PI3K)-Akt-mammalian target of rapamycin (mTOR) signaling pathway has been implicated in various immune-mediated inflammatory and hyperproliferative dermatoses such as acne, atopic dermatitis, alopecia, psoriasis, wounds, and vitiligo, and is associated with poor treatment outcomes. Improved comprehension of the consequences of the dysregulated PI3K/Akt/mTOR pathway in patients with inflammatory dermatoses has resulted in the development of novel therapeutic approaches. Nonetheless, more studies are necessary to validate the regulatory role of this pathway and to create more effective preventive and treatment methods for a wide range of inflammatory skin diseases. Several studies have revealed that certain natural products and synthetic compounds can obstruct the expression/activity of PI3K/Akt/mTOR, underscoring their potential in managing common and persistent skin inflammatory disorders. This review summarizes recent advances in understanding the role of the activated PI3K/Akt/mTOR pathway and associated components in immune-mediated inflammatory dermatoses and discusses the potential of bioactive natural products, synthetic scaffolds, and biologic agents in their prevention and treatment. However, further research is necessary to validate the regulatory role of this pathway and develop more effective therapies for inflammatory skin disorders.

The advantages of linear information processing for cerebellar computation.

Purkinje cells can encode the strength of parallel fiber inputs in their firing by using 2 fundamentally different mechanisms, either as pauses or as linear increases in firing rate. It is not clear which of these 2 encoding mechanisms is used by the cerebellum. We used the pattern-recognition capacity of Purkinje cells based on the Marr-Albus-Ito theory of cerebellar learning to evaluate the suitability of the linear algorithm for cerebellar information processing. Here, we demonstrate the simplicity and versatility of pattern recognition in Purkinje cells linearly encoding the strength of parallel fiber inputs in their firing rate. In contrast to encoding patterns with pauses, Purkinje cells using the linear algorithm could recognize a large number of both synchronous and asynchronous input patterns in the presence or absence of inhibitory synaptic transmission. Under all conditions, the number of patterns recognized by Purkinje cells using the linear algorithm was greater than that achieved by encoding information in pauses. Linear encoding of information also allows neurons of deep cerebellar nuclei to use a simple averaging mechanism to significantly increase the computational capacity of the cerebellum. We propose that the virtues of the linear encoding mechanism make it well suited for cerebellar computation.

Psychosocial and energetic factors on human female pubertal timing: a systematized review.

Childhood psychosocial stressors have been proposed to favour fast life history strategies promoting earlier puberty in females. However, studies demonstrating this association often do not elucidate causal mechanisms, nor account for greater childhood energetic availability - also known to promote rapid growth and earlier puberty. To assess the extent to which such confounding has been considered, we conducted a systematized review to identify studies examining measures of both prepubertal growth (e.g. weight, height) and psychosocial stressors (e.g. adversity, father absence) in relation to female pubertal timing. A total of 1069 non-duplicated studies were identified across five databases. Twenty studies met selection criteria for critical review following independent screening of titles, abstracts and manuscripts. Within these studies, measures indicative of rapid childhood growth were more consistently associated with earlier pubertal timing than were measures of psychosocial stress. We discuss future research directions to investigate the impact of psychosocial stress on pubertal timing more robustly, including methodological and mechanistic considerations, and contextualization of findings by socioecological environments.

Creation and validation of a chest X-ray dataset with eye-tracking and report dictation for AI development.

We developed a rich dataset of Chest X-Ray (CXR) images to assist investigators in artificial intelligence. The data were collected using an eye-tracking system while a radiologist reviewed and reported on 1,083 CXR images. The dataset contains the following aligned data: CXR image, transcribed radiology report text, radiologist's dictation audio and eye gaze coordinates data. We hope this dataset can contribute to various areas of research particularly towards explainable and multimodal deep learning/machine learning methods. Furthermore, investigators in disease classification and localization, automated radiology report generation, and human-machine interaction can benefit from these data. We report deep learning experiments that utilize the attention maps produced by the eye gaze dataset to show the potential utility of this dataset.

The functional equivalence of ascending and parallel fiber inputs in cerebellar computation.

At the center of the computational cerebellar circuitry are Purkinje cells, which integrate synaptic inputs from >150,000 granule cell inputs. Traditional theories of cerebellar function assume that all granule cell inputs are comparable. However, it has recently been suggested that the two anatomically distinct granule cell inputs, ascending and parallel fiber, have different functional roles. By systematically examining the efficacy of patches of granule cells with photostimulation, we found no differences in the efficacy of the two inputs in driving the activity of, or in producing postsynaptic currents in, Purkinje cells in cerebellar slices in vitro. We also found that the activity of Purkinje cells was significantly increased upon stimulation of lateral granule cells in vivo. Moreover, when we estimated parallel fiber and ascending apparent unitary EPSC amplitudes using photostimulation in cerebellar slices in vitro, we found them to be indistinguishable. These results are inconsistent with differential functional roles for these two inputs. Instead, our data support theories of cerebellar computation that consider granule cell inputs to be functionally comparable.

Decreases in the precision of Purkinje cell pacemaking cause cerebellar dysfunction and ataxia.

Episodic ataxia type-2 (EA2) is caused by mutations in P/Q-type voltage-gated calcium channels that are expressed at high densities in cerebellar Purkinje cells. Because P/Q channels support neurotransmitter release at many synapses, it is believed that ataxia is caused by impaired synaptic transmission. Here we show that in ataxic P/Q channel mutant mice, the precision of Purkinje cell pacemaking is lost such that there is a significant degradation of the synaptic information encoded in their activity. The irregular pacemaking is caused by reduced activation of calcium-activated potassium (K(Ca)) channels and was reversed by pharmacologically increasing their activity with 1-ethyl-2-benzimidazolinone (EBIO). Moreover, chronic in vivo perfusion of EBIO into the cerebellum of ataxic mice significantly improved motor performance. Our data support the hypothesis that the precision of intrinsic pacemaking in Purkinje cells is essential for motor coordination and suggest that K(Ca) channels may constitute a potential therapeutic target in EA2.

Symptoms of Gastroesophageal Reflux in Healthy, Full-Term Infants Younger Than 7 Months Old.

OBJECTIVE: To describe the range of symptoms of gastroesophageal reflux in healthy, full-term infants in the first 7 months of life. DESIGN: Cross-sectional, descriptive study. Median and percentile scores for the Infant Gastroesophageal Reflux Questionnaire-Revised (I-GERQ-R) were calculated for each of the following age groups of infants: 0 to 2, 2 to 4, 4 to 6, and 6 to 7 months. Psychometric properties, including internal consistency reliability and concurrent validity of the I-GERQ-R, were also tested. SETTING: Online. PARTICIPANTS: Primary caregivers of 559 healthy, full-term (≥37 weeks gestational age) infants younger than 7 months. MEASUREMENTS: Participants were asked to answer questions about themselves, their family, and their infant and to complete the I-GERQ-R, the Infant Gastrointestinal Symptoms Questionnaire, and the Neonatal Eating Assessment Tool. RESULTS: Symptoms of gastroesophageal reflux decreased over the first 7 months of life. Scores in the 95th percentile decreased from 19 in infants 0 to 2 months old to 16.7 in infants 6 to 7 months old. Internal consistency reliability of the I-GERQ-R was acceptable (Cronbach's α = .71). The I-GERQ-R had evidence of concurrent validity with the Infant Gastrointestinal Symptoms Questionnaire (rs = .69, p < .001) and Neonatal Eating Assessment Tool-Breastfeeding Gastroesophageal Function subscale (rs = .52, p < .001). CONCLUSIONS: Authors of prior studies used a cutoff score of 16 for the diagnosis of gastroesophageal reflux disease in infants younger than 18 months. Our results indicate that symptoms of reflux change with age over the first 7 months of life and that using more age-specific reference values may be more appropriate. Health care providers can use these age-specific percentile scores, together with clinical assessment, to identify significant symptomatology related to gastroesophageal reflux disease.

Combining Deep Learning and Knowledge-driven Reasoning for Chest X-Ray Findings Detection.

The application of deep learning algorithms in medical imaging analysis is a steadily growing research area. While deep learning methods are thriving in the medical domain, they seldom utilize the rich knowledge associated with connected radiology reports. The knowledge derived from these reports can be utilized to enhance the performance of deep learning models. In this work, we used a comprehensive chest X-ray findings vocabulary to automatically annotate an extensive collection of chest X-rays using associated radiology reports and a vocabulary-driven concept annotation algorithm. The annotated X-rays are used to train a deep neural network classifier for finding detection. Finally, we developed a knowledge-driven reasoning algorithm that leverages knowledge learned from X-ray reports to improve upon the deep learning module's performance on finding detection. Our results suggest that combining deep learning and knowledge from radiology reports in a hybrid framework can significantly enhance overall performance in the CXR finding detection.

Extracting and Learning Fine-Grained Labels from Chest Radiographs.

Chest radiographs are the most common diagnostic exam in emergency rooms and intensive care units today. Recently, a number of researchers have begun working on large chest X-ray datasets to develop deep learning models for recognition of a handful of coarse finding classes such as opacities, masses and nodules. In this paper, we focus on extracting and learning fine-grained labels for chest X-ray images. Specifically we develop a new method of extracting fine-grained labels from radiology reports by combining vocabulary-driven concept extraction with phrasal grouping in dependency parse trees for association of modifiers with findings. A total of457finegrained labels depicting the largest spectrum of findings to date were selected and sufficiently large datasets acquired to train a new deep learning model designed for fine-grained classification. We show results that indicate a highly accurate label extraction process and a reliable learning of fine-grained labels. The resulting network, to our knowledge, is the first to recognize fine-grained descriptions offindings in images covering over nine modifiers including laterality, location, severity, size and appearance.