Pituitary adenomas are typically slowly progressing tumors of the anterior pituitary gland. They represent a wide spectrum of clinical behavior including invasion, regrowth, and persistence of hormone hypersecretion cause significant morbidity and mortality. Metastatic behavior of pituitary adenoma has also been shown in rare cases. Hence, the presence of significant heterogeneity among these patients poses a unique predictive challenge.
Currently, prediction of clinical behavior following surgical resection is routinely performed through immunohistochemical investigation of a variety of markers such as Ki-67, p21, p27, p53 and EGFR. Availability of large genomics, transcriptomics, and proteomics data sets has recently provided the opportunity to apply machine learning (ML) methods for diagnosis, as well prediction of early outcomes following specific treatment. ML which is a subfield of artificial intelligence (AI) employs algorithms to allow computers to learn directly from the data and subsequently perform predictions.
Within this Research Topic we encourage the submission of manuscripts related to pituitary adenoma, novel Biomarkers that predict invasiveness, novel targeted therapies, Pathophysiology basis of resistance to conventional treatments, and personalized treatment strategies.
This Research Topic includes, but is not limited to, the following examples:
- Genomic, transcriptomic and proteomics characterization of pituitary adenoma
- Machine learning methods to predict early postsurgical and long-term outcomes
- Novel molecular biomarkers of tumor invasiveness
- Molecular mechanisms of resistance to conventional therapies
- Targeted therapy
Pituitary adenomas are typically slowly progressing tumors of the anterior pituitary gland. They represent a wide spectrum of clinical behavior including invasion, regrowth, and persistence of hormone hypersecretion cause significant morbidity and mortality. Metastatic behavior of pituitary adenoma has also been shown in rare cases. Hence, the presence of significant heterogeneity among these patients poses a unique predictive challenge.
Currently, prediction of clinical behavior following surgical resection is routinely performed through immunohistochemical investigation of a variety of markers such as Ki-67, p21, p27, p53 and EGFR. Availability of large genomics, transcriptomics, and proteomics data sets has recently provided the opportunity to apply machine learning (ML) methods for diagnosis, as well prediction of early outcomes following specific treatment. ML which is a subfield of artificial intelligence (AI) employs algorithms to allow computers to learn directly from the data and subsequently perform predictions.
Within this Research Topic we encourage the submission of manuscripts related to pituitary adenoma, novel Biomarkers that predict invasiveness, novel targeted therapies, Pathophysiology basis of resistance to conventional treatments, and personalized treatment strategies.
This Research Topic includes, but is not limited to, the following examples:
- Genomic, transcriptomic and proteomics characterization of pituitary adenoma
- Machine learning methods to predict early postsurgical and long-term outcomes
- Novel molecular biomarkers of tumor invasiveness
- Molecular mechanisms of resistance to conventional therapies
- Targeted therapy
