Machine learning based skin lesion segmentation method with novel borders and hair removal techniques.

The effective segmentation of lesion(s) from dermoscopic skin images assists the Computer-Aided Diagnosis (CAD) systems in improving the diagnosing rate of skin cancer. The results of the existing skin lesion segmentation techniques are not up to the mark for dermoscopic images with artifacts like varying size corner borders with color similar to lesion(s) and/or hairs having low contrast with surrounding background. To improve the results of the existing skin lesion segmentation techniques for such kinds of dermoscopic images, an effective skin lesion segmentation method is proposed in this research work. The proposed method searches for the presence of corner borders in the given dermoscopc image and removes them if found otherwise it starts searching for the presence of hairs on it and eliminate them if present. Next, it enhances the resultant image using state-of-the-art image enhancement method and segments lesion from it using machine learning technique namely, GrabCut method. The proposed method was tested on PH2 and ISIC 2018 datasets containing 200 images each and its accuracy was measured with two evaluation metrics, i.e., Jaccard index, and Dice index. The evaluation results show that our proposed skin lesion segmentation method obtained Jaccard Index of 0.77, 0.80 and Dice index of 0.87, 0.82 values on PH2, and ISIC2018 datasets, respectively, which are better than state-of-the-art skin lesion segmentation techniques.

Factors related to depression symptoms among working women in Menoufia, Egypt.

BACKGROUND: Lifetime prevalence rates for any psychological disorder are higher than previously thought. Depression in the workplace may lower work productivity and increase maladjustment in daily professional life. AIM OF THE STUDY: The study aimed to investigate the prevalence of depression symptoms and the work-related risk factors in Egyptian working women. PATIENTS AND METHODS: A cross-sectional study was carried out on 600 working women in family health facilities in Tala district, Menoufia governorate in 2015. Two questionnaires were used: one of them was an Arabic translated form of the questionnaire found in the Egyptian Practice Guidelines established by the Ministry of Health and population for family physicians to use in assessing the prevalence of depression symptoms. The second one was a predesigned questionnaire used to assess risk factors concerning demographic characteristics and the work environment related to depression symptoms. RESULTS: The prevalence rate of depression symptoms among working women was 37.5%. Multiple logistic regression analyses reveal that the following work-related factors were associated with an increased likelihood of exhibiting positive depression symptoms: work-related activities continued during home time, such as telephone calls or messages [odds ratio (OR)=5.10; 95% confidence interval (CI): 1.69-15.39], when work problems affect concentration and interactions with family (OR=148.67; 95% CI: 50.04-441.71), and difficulty with household chores (OR=6.63; 95% CI: 1.64-26.73). In addition, the following sociodemographic factors were significant: being divorced or widowed (OR=4.10; 95% CI: 2.28-7.36), no enough income (OR=2.59; 95% CI: 1.68-3.97), and rural residence (OR=1.74; 95% CI: 1.08-2.78). CONCLUSION: Reported depression symptoms were high among working women in Menoufia. Both unfavorable employment conditions and background characteristics such as being divorced/widow, low income, and rural residence were factors determining depression symptoms. It is necessary to establish preventive strategies for female workers to control the negative effect of depression in the workplace.