Generalized nucleus segmentation techniques can contribute greatly to reducing the time to develop and validate visual biomarkers for new digital pathology datasets. We summarize the results of MoNuSeg 2018 Challenge whose objective was to develop generalizable nuclei segmentation techniques in digital pathology. The challenge was an official satellite event of the MICCAI 2018 conference in which 32 teams with more than 80 participants from geographically diverse institutes participated. Contestants were given a training set with 30 images from seven organs with annotations of 21,623 individual nuclei. A test dataset with 14 images taken from seven organs, including two organs that did not appear in the training set was released without annotations. Entries were evaluated based on average aggregated Jaccard index (AJI) on the test set to prioritize accurate instance segmentation as opposed to mere semantic segmentation. More than half the teams that completed the challenge outperformed a previous baseline [1]. Among the trends observed that contributed to increased accuracy were the use of color normalization as well as heavy data augmentation. Additionally, fully convolutional networks inspired by variants of U-Net [2], FCN [3], and Mask- RCNN [4] were popularly used, typically based on ResNet [5] or VGG [6] base architectures. Watershed segmentation on predicted semantic segmentation maps was a popular post-processing strategy. Several of the top techniques compared favorably to an individual human annotator and can be used with confidence for nuclear morphometrics.

No abstract

BackgroundYears of education are inversely related to the prevalence of major depressive disorder (MDD), but the relationship between the clinical features of MDD and educational status is poorly understood. We investigated this in 1970 Chinese women with recurrent MDD identified in a clinical setting.MethodsClinical and demographic features were obtained from 1970 Han Chinese women with DSM-IV major depression between 30 and 60 years of age across China. Analysis of linear, logistic and multiple logistic regression models were used to determine the association between educational level and clinical features of MDD.ResultsSubjects with more years of education are more likely to have MDD, with an odds ratio of 1.14 for those with more than ten years. Low educational status is not associated with an increase in the number of episodes, nor with increased rates of co-morbidity with anxiety disorders. Education impacts differentially on the symptoms of depression: lower educational attainment is associated with more biological symptoms and increased suicidal ideation and plans to commit suicide.LimitationsFindings may not generalize to males or to other patient populations. Since the threshold for treatment seeking differs as a function of education there may an ascertainment bias in the sample.ConclusionsThe relationship between symptoms of MDD and educational status in Chinese women is unexpectedly complex. Our findings are inconsistent with the simple hypothesis from European and US reports that low levels of educational attainment increase the risk and severity of MDD.

BackgroundStudies in Western countries have repeatedly shown that women with a history of childhood sexual abuse (CSA) are at increased risk for developing major depression (MD). Would this relationship be found in China?MethodThree levels of CSA (non-genital, genital, and intercourse) were assessed by self-report in two groups of Han Chinese women: 1970 clinically ascertained with recurrent MD and 2597 matched controls. Diagnostic and other risk factor information was assessed at personal interview. Odds ratios (ORs) were calculated by logistic regression and regression coefficients by linear or Poisson regression.ResultsAny form of CSA was significantly associated with recurrent MD [OR 3.26, 95% confidence interval (CI) 1.95–5.45]. This association strengthened with increasing CSA severity: non-genital (OR 2.47, 95% CI 1.17–5.23), genital (OR 2.77, 95% CI 1.32–5.83) and intercourse (OR 13.35, 95% CI 1.83–97.42). The association between any form of CSA and MD remained significant after accounting for parental history of depression, childhood emotional neglect (CEN), childhood physical abuse (CPA) and parent–child relationship. Among the depressed women, those with CSA had an earlier age of onset, longer depressive episodes and an increased risk for generalized anxiety disorder (GAD; OR 1.92, 95% CI 1.39–2.66) and dysthymia (OR 2.16, 95% CI 1.52–3.09).ConclusionsIn Chinese women CSA is strongly associated with MD and this association increases with greater severity of CSA. Depressed women with CSA have an earlier age of onset, longer depressive episodes and increased co-morbidity with GAD and dysthymia. Although reporting biases cannot be ruled out, our results are consistent with the hypothesis that, as in Western countries, CSA substantially increases the risk for MD in China.

No abstract