Renal structural image processing techniques: a systematic review.

BACKGROUND AND OBJECTIVE: Renal disease, such as nephritis and nephropathy, is very harmful to human health. Accordingly, how to achieve early diagnosis and enhance treatment for kidney disorders would be the important lesion. Nevertheless, the clues from the clinical data, such as biochemistry examination, serological examination, and radiological studies are quite indirect and limited. It is no doubt that pathological examination of kidney will supply the direct evidence. There is a requirement for greater understanding of image processing techniques for renal diagnosis to optimize treatment and patient care. METHODS: This study aims to systematically review the literature on publications that has been used image processing methods on pathological microscopic image for renal diagnosis. RESULTS: Nine included studies revealed image analysis techniques for the diagnosis of renal abnormalities on pathological microscopic image, renal image studies are clustered as follows: Glomeruli Segmentation and analysis of the Glomerular basement membrane (55/55%), Blood vessels and tubules classification and detection (22/22%) and The Grading of renal cell carcinomas (22/22%). CONCLUSIONS: A medical image analysis method should provide an auto-adaptive and no external-human action dependency. In addition, since medical systems should have special characteristics such as high accuracy and reliability then clinical validation is highly recommended. New high-quality studies based on Moore neighborhood contour tracking method for glomeruli segmentation and using powerful texture analysis techniques such as the local binary pattern are recommended.

Accurate emotion recognition using Bayesian model based EEG sources as dynamic graph convolutional neural network nodes.

Due to the effect of emotions on interactions, interpretations, and decisions, automatic detection and analysis of human emotions based on EEG signals has an important role in the treatment of psychiatric diseases. However, the low spatial resolution of EEG recorders poses a challenge. In order to overcome this problem, in this paper we model each emotion by mapping from scalp sensors to brain sources using Bernoulli-Laplace-based Bayesian model. The standard low-resolution electromagnetic tomography (sLORETA) method is used to initialize the source signals in this algorithm. Finally, a dynamic graph convolutional neural network (DGCNN) is used to classify emotional EEG in which the sources of the proposed localization model are considered as the underlying graph nodes. In the proposed method, the relationships between the EEG source signals are encoded in the DGCNN adjacency matrix. Experiments on our EEG dataset recorded at the Brain-Computer Interface Research Laboratory, University of Tabriz as well as publicly available SEED and DEAP datasets show that brain source modeling by the proposed algorithm significantly improves the accuracy of emotion recognition, such that it achieve a classification accuracy of 99.25% during the classification of the two classes of positive and negative emotions. These results represent an absolute 1-2% improvement in terms of classification accuracy over subject-dependent and subject-independent scenarios over the existing approaches.

A systematic review of EEG source localization techniques and their applications on diagnosis of brain abnormalities.

In recent years, multiple noninvasive imaging modalities have been used to develop a better understanding of the human brain functionality, including positron emission tomography, single-photon emission computed tomography, and functional magnetic resonance imaging, all of which provide brain images with millimeter spatial resolutions. Despite good spatial resolution, time resolution of these methods are poor and values are about seconds. Scalp electroencephalography recordings can be used to perform the inverse problem in order to specify the location of the dominant sources of the brain activity. In this paper, EEG source localization method, diagnosis of brain abnormalities using common EEG source localization methods, investigating the effect of the head model on EEG source imaging results have been studied. In this review we present enough evidence that provides motivation for consideration in the future research using EEG source localization methods.

Pregnancy after mumps: a case report.

INTRODUCTION: Oophoritis, a complication of mumps, is said to affect only 5% of all postpubertal women. In this report, we present a case of a 31-year-old Iranian woman with amenorrhea and infertility due to an infantile uterus and atrophic ovaries associated with contracting mumps at a young age. She later successfully carried a healthy baby to term. CASE PRESENTATION: The patient was diagnosed with oophoritis when she was 8 years of age. She had no menses before treatment. The patient underwent a low-dose contraceptive treatment from age 19 until she was 31 years of age. During this period, the size of her uterus was constantly monitored, which revealed constant yet slow uterine growth. At age 31, Drospil (containing 3 mg of drospirenone and 0.03 mg ethinyl estradiol) treatment was initiated and administered for 3 months, which led to substantial uterine growth and menses. After her uterus had reached a mature size, the patient was referred to an assisted reproductive technology clinic. There she received a donor oocyte that was fertilized with the sperm of her husband. She had a successful low-risk pregnancy after the second embryo transfer. CONCLUSION: Low-dose contraceptive treatment containing progesterone, followed by Drospil, which includes both estradiol and progesterone, had a synergistic effect that led to the growth of the patient's uterus.