http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Diagnosis of Alzheimer’s Disease using Wrapper Feature Selection Method
Vyshnavi Ramineni,권구락 (사)한국스마트미디어학회 2023 스마트미디어저널 Vol.12 No.3
Alzheimer’s disease (AD) symptoms are being treated by early diagnosis, where we can only slow the symptoms and research is still undergoing. In consideration, using T1-weighted images several classification models are proposed in Machine learning to identify AD. In this paper, we consider the improvised feature selection, to reduce the complexity by using wrapping techniques and Restricted Boltzmann Machine (RBM). This present work used the subcortical and cortical features of 278 subjects from the ADNI dataset to identify AD and sMRI. Multi-class classification is used for the experiment i.e., AD, EMCI, LMCI, HC. The proposed feature selection consists of Forward feature selection, Backward feature selection, and Combined PCA & RBM. Forward and backward feature selection methods use an iterative method starting being no features in the forward feature selection and backward feature selection with all features included in the technique. PCA is used to reduce the dimensions and RBM is used to select the best feature without interpreting the features. We have compared the three models with PCA to analysis. The following experiment shows that combined PCA &RBM, and backward feature selection give the best accuracy with respective classification model RF i.e., 88.65, 88.56% respectively.
A Comparative Study of the CNN Model for AD Diagnosis
Vyshnavi Ramineni,권구락 (사)한국스마트미디어학회 2023 스마트미디어저널 Vol.12 No.7
Alzheimer’s disease is one type of dementia, the symptoms can be treated by detecting the disease at its early stages. Recently, many computer-aided diagnosis using magnetic resonance image(MRI) have shown a good results in the classification of AD. Taken these MRI images and feed to Free surfer software to extra the features. In consideration, using T1-weighted images and classifying using the convolution neural network (CNN) model are proposed. In this paper, taking the subjects from ADNI of subcortical and cortical features of 190 subjects. Consider the study to reduce the complexity of the model by using the single layer in the Res-Net, VGG, and Alex Net. Multi-class classification is used to classify four different stages, CN, EMCI, LMCI, AD. The following experiment shows for respective classification Res-Net, VGG, and Alex Net with the best accuracy with VGG at 96%, Res-Net, GoogLeNet and Alex Net at 91%, 93% and 89% respectively.
Acellular Scaffolds as Innovative Biomaterial Platforms for the Management of Diabetic Wounds
Tallapaneni Vyshnavi,Kalaivani C.,Pamu Divya,Mude Lavanya,Singh Sachin Kumar,Karri Veera Venkata Satyanarayana Reddy 한국조직공학과 재생의학회 2021 조직공학과 재생의학 Vol.18 No.5
Diabetic wound (DW) is one of the leading complications of patients having a long history of uncontrolled diabetes. Moreover, it also imposes an economic burden on people suffering from wounds to manage the treatment. The major impending factors in the treatment of DW are infection, prolonged inflammation and decreased oxygen levels. Since these non-healing wounds are associated with an extended recovery period, the existing therapies provide treatment for a limited period only. The areas covered in this review are general sequential events of wound healing along with DW's pathophysiology, the origin of DW and success, as well as limitations of existing therapies. This systematic review's significant aspect is to highlight the fabrication, characterization and applications of various acellular scaffolds used to heal DW. In addition to that, cellular scaffolds are also described to a limited extent.
Harpreet Kaur,Gautham T Pranesh,Vyshnavi Rao,Kamini A Rao 대한산부인과학회 2024 Obstetrics & Gynecology Science Vol.67 No.2
Objective Controlled ovarian stimulation leads to profound changes in the endocrine characteristics of the ovarian cycle. Serum luteinising hormone (LH) levels on the day of trigger have been shown to correlate with oocyte quality and pregnancy rate in antagonist cycles. Methods This is an observational study of 86 women undergoing an antagonist in-vitro fertilisation cycle. Oocyte maturation trigger used was either Inj. human chorionic gonadotropin or Inj. triptorelin 0.2 mg s/c or a combination of both. Women were categorised into four groups based on serum LH levels on the day of trigger i.e., LH ≤0.5 (n=8), LH=0.6- 1.0 international units (IU)/L (n=12), LH=1.0-1.5 IU/L (n=13), and LH >1.6 IU/L (n=53) and the subgroup analysis was done based on type of trigger used. Results Mature oocyte (MII) retrieval rate did not show a significant relation with serum LH levels (87%, 89%, 77%, and 76% in groups with LH <0.5, 0.5-1.0, 1.0-1.5, and >1.5 IU/L respectively; P-value=0.243). There was no significant difference in the clinical pregnancy rate either when women were split according to the type of trigger given or according to trigger day LH levels. Women with low LH levels (<0.5 IU/L) required significantly more doses of gonadotropins compared to women with LH levels of 1.0-1.5 IU/L. (3,531+1,133 vs. 2,281+938; P-value=0.01). Conclusion Based on the observation from the current study, there was no significant association of serum LH levels with MII retrieval rate and clinical pregnancy rate. The group with low LH levels required slightly longer days of stimulation. Objective Controlled ovarian stimulation leads to profound changes in the endocrine characteristics of the ovarian cycle. Serum luteinising hormone (LH) levels on the day of trigger have been shown to correlate with oocyte quality and pregnancy rate in antagonist cycles.Methods This is an observational study of 86 women undergoing an antagonist <i>in-vitro</i> fertilisation cycle. Oocyte maturation trigger used was either Inj. human chorionic gonadotropin or Inj. triptorelin 0.2 mg s/c or a combination of both. Women were categorised into four groups based on serum LH levels on the day of trigger i.e., LH ≤0.5 (n=8), LH=0.6- 1.0 international units (IU)/L (n=12), LH=1.0-1.5 IU/L (n=13), and LH >1.6 IU/L (n=53) and the subgroup analysis was done based on type of trigger used.Results Mature oocyte (MII) retrieval rate did not show a significant relation with serum LH levels (87%, 89%, 77%, and 76% in groups with LH <0.5, 0.5-1.0, 1.0-1.5, and >1.5 IU/L respectively; <i>P</i>-value=0.243). There was no significant difference in the clinical pregnancy rate either when women were split according to the type of trigger given or according to trigger day LH levels. Women with low LH levels (<0.5 IU/L) required significantly more doses of gonadotropins compared to women with LH levels of 1.0-1.5 IU/L. (3,531+1,133 vs. 2,281+938; <i>P</i>-value=0.01).Conclusion Based on the observation from the current study, there was no significant association of serum LH levels with MII retrieval rate and clinical pregnancy rate. The group with low LH levels required slightly longer days of stimulation.