Applying dual models on optimized LSTM with U-net segmentation for breast cancer diagnosis using mammogram images

Sivamurugan, J.; Sureshkumar, G.

doi:10.1016/j.artmed.2023.102626

Cited by 6 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the GSE95233 dataset can be applied to mining pathways and core genes related to the progression of sepsis over time. Specifically, time-constrained coefficient learning [61] or a classic deep learning model (suitable for datasets with large sample sizes and many time points) can be applied to model time series data [62].The attention mechanism can also be introduced to explore the changes in the importance of disease-related biomarkers over time, providing a reference for drug target discovery. Therefore, future studies can collect transcriptome data at different time points in sepsis patients, and mine pathways and hub genes related to the progression of sepsis over time.…”

Section: Discussionmentioning

confidence: 99%

Exploring the Role of Different Cell-Death-Related Genes in Sepsis Diagnosis Using a Machine Learning Algorithm

Wang,

Guo

et al. 2023

IJMS

View full text Add to dashboard Cite

Sepsis, a disease caused by severe infection, has a high mortality rate. At present, there is a lack of reliable algorithmic models for biomarker mining and diagnostic model construction for sepsis. Programmed cell death (PCD) has been shown to play a vital role in disease occurrence and progression, and different PCD-related genes have the potential to be targeted for the treatment of sepsis. In this paper, we analyzed PCD-related genes in sepsis. Implicated PCD processes include apoptosis, necroptosis, ferroptosis, pyroptosis, netotic cell death, entotic cell death, lysosome-dependent cell death, parthanatos, autophagy-dependent cell death, oxeiptosis, and alkaliptosis. We screened for diagnostic-related genes and constructed models for diagnosing sepsis using multiple machine-learning models. In addition, the immune landscape of sepsis was analyzed based on the diagnosis-related genes that were obtained. In this paper, 10 diagnosis-related genes were screened for using machine learning algorithms, and diagnostic models were constructed. The diagnostic model was validated in the internal and external test sets, and the Area Under Curve (AUC) reached 0.7951 in the internal test set and 0.9627 in the external test set. Furthermore, we verified the diagnostic gene via a qPCR experiment. The diagnostic-related genes and diagnostic genes obtained in this paper can be utilized as a reference for clinical sepsis diagnosis. The results of this study can act as a reference for the clinical diagnosis of sepsis and for target discovery for potential therapeutic drugs.

show abstract

Section: Discussionmentioning

confidence: 99%