Learning-based motion artifact correction in the Z-spectral domain for chemical exchange saturation transfer MRI.

Purpose: To develop and evaluate a physics-driven, saturation contrast-aware, deep-learning-based framework for motion artifact correction in CEST MRI.

Methods: A neural network was designed to correct motion artifacts directly from a Z-spectrum frequency (Ω) domain rather than an image spatial domain. Motion artifacts were simulated by modeling 3D rigid-body motion and readout-related motion during k-space sampling.

Glycogen synthase kinase-3ß inhibitor use and prostate cancer incidence in Manitoba, Canada: A population-based nested case-control study.

Background: Little is known on the effect of glycogen synthase kinase-3ß inhibitors (GSK3Is), as a class, on prostate cancer (PC). We aimed to study this in the Canadian province of Manitoba, because mixed results have been reported on the effect of valproate.

Methods: We conducted a nested case-control study among cancer-free Manitobans with ≥ 5 years of medical history in which we matched all men 40 years or older diagnosed with PC between 2000 and 2018 (N = 11,189) on period, age, length of available drug information to cancer-free controls (N = 55,728).

Designing siRNA for silencing the human ERBB2 gene in cancer treatment: Evaluating intracellular delivery strategies.

The ERBB2 is one of the most studied genes in oncology for its significant role in human malignancies. The metastasis-associated properties that facilitate cancer metastasis can be enhanced by activating the ERBB2 receptor signaling pathways. Additionally, therapeutic resistance is conferred by ERBB2 overexpression via receptor-mediated antiapoptotic signals.

A machine learning approach identifies cellular senescence on transcriptome data of human cells in vitro.

Although cellular senescence has been recognized as a hallmark of aging, it is challenging to detect senescence cells (SnCs) due to their high level of heterogeneity at the molecular level. Machine learning (ML) is likely an ideal approach to address this challenge because of its ability to recognize complex patterns that cannot be characterized by one or a few features, from high-dimensional data. To test this, we evaluated the performance of four ML algorithms including support vector machines (SVM), random forest (RF), decision tree (DT), and Soft Independent Modelling of Class Analogy (SIMCA), in distinguishing SnCs from controls based on bulk RNA sequencing data.