[Artificial intelligence in the diagnosis of breast cancer : Yesterday, today and tomorrow]. / Künstliche Intelligenz in der Mammadiagnostik : Gestern, heute und morgen.

BACKGROUND: Artificial intelligence (AI) is increasingly applied in the field of breast imaging. OBJECTIVES: What are the main areas where AI is applied in breast imaging and what AI and computer-aided diagnosis (CAD) systems are already available? MATERIALS AND METHODS: Basic literature and vendor-supplied information are screened for relevant information, which is then pooled, structured and discussed from the perspective of breast imaging. RESULTS: Original CAD systems in mammography date almost 25 years back. They are much more widely applied in the United States than in Europe. The initial CAD systems exhibited limited diagnostic abilities and disproportionally high rates of false positive results. Since 2012, deep learning mechanisms have been applied and expand the application possibilities of AI. CONCLUSION: To date there is no algorithm that has beyond doubt been proven to outperform double reporting by two certified breast radiologists. AI could, however, in the foreseeable future, take over the following tasks: preselection of abnormal examinations to substantially reduce workload of the radiologists by either excluding normal findings from human review or by replacing the double reader in screening. Furthermore, the establishment of radio-patho-genomic correlations and their translation into clinical practice is hardly conceivable without AI.

Blood-brain barrier in vitro models as tools in drug discovery: assessment of the transport ranking of antihistaminic drugs.

In the course of our validation program testing blood-brain barrier (BBB) in vitro models for their usability as tools in drug discovery it was evaluated whether an established Transwell model based on porcine cell line PBMEC/C1-2 was able to differentiate between the transport properties of first and second generation antihistaminic drugs. First generation antihistamines can permeate the BBB and act in the central nervous system (CNS), whereas entry to the CNS of second generation antihistamines is restricted by efflux pumps such as P-glycoprotein (P-gP) located in brain endothelial cells. P-gP functionality of PBMEC/C1-2 cells grown on Transwell filter inserts was proven by transport studies with P-gP substrate rhodamine 123 and P-gP blocker verapamil. Subsequent drug transport studies with the first generation antihistamines promethazine, diphenhydramine and pheniramine and the second generation antihistamines astemizole, ceterizine, fexofenadine and loratadine were accomplished in single substance as well as in group studies. Results were normalised to diazepam, an internal standard for the transcellular transport route. Moreover, effects after addition of P-gP inhibitor verapamil were investigated. First generation antihistamine pheniramine permeated as fastest followed by diphenhydramine, diazepam, promethazine and second generation antihistaminic drugs ceterizine, fexofenadine, astemizole and loratadine reflecting the BBB in vivo permeability ranking well. Verapamil increased the transport rates of all second generation antihistamines, which suggested involvement of P-gP during their permeation across the BBB model. The ranking after addition of verapamil was significantly changed, only fexofenadine and ceterizine penetrated slower than internal standard diazepam in the presence of verapamil. In summary, permeability data showed that the BBB model based on porcine cell line PBMEC/C1-2 was able to reflect the BBB in vivo situation for the transport of antihistaminc drugs and to distinguish between first and second generation antihistamines.

Serum-derived immunoglobulins alter amyloid beta transport across a blood-brain barrier in vitro model.

Since passive immunization with serum-derived immunoglobulins (intravenous immunoglobulins) showed several positive effects in some patients with Alzheimer's disease (AD), intravenous immunoglobulins (IVIG) are discussed as a possible treatment option. IVIG, an antibody product derived from human plasma, contains natural antibodies against amyloid beta(Abeta) peptide. Until now it is not known, how IVIG interferes with pathogenesis in AD, but several proposed mechanisms are in discussion. Receptor types which are involved in transport processes at the BBB are LRP, RAGE and hFcRn. We were looking for an in vitro BBB model expressing these receptors and studied the alteration of transport of Abeta peptides across this model under the influence of immunoglobulins. Cell line ECV304 was found to be suitable for our experiments. We found evidence for involvement of an improved clearance of Abeta across the BBB as well as a decreased Abeta influx from blood to the brain probably following complex formation of immunoglobulins with free Abeta in the periphery. Furthermore, we were able to confirm the activity of IVIG preparations which acted the same way but showed slightly less efficacy in comparison to monoclonal anti-Abeta antibodies. Based on these results we suggest multiple mechanisms responsible for the efficacy of immunotherapy in Alzheimer's disease.