Impact of Deep Learning Assistance on the Histopathologic Review of Lymph Nodes for Metastatic Breast Cancer.

Advances in the quality of whole-slide images have set the stage for the clinical use of digital images in anatomic pathology. Along with advances in computer image analysis, this raises the possibility for computer-assisted diagnostics in pathology to improve histopathologic interpretation and clinical care. To evaluate the potential impact of digital assistance on interpretation of digitized slides, we conducted a multireader multicase study utilizing our deep learning algorithm for the detection of breast cancer metastasis in lymph nodes.

Deletion or epigenetic silencing of AJAP1 on 1p36 in glioblastoma.

Glioblastoma is universally fatal because of its propensity for rapid recurrence due to highly migratory tumor cells. Unraveling the genomic complexity that underlies this migratory characteristic could provide therapeutic targets that would greatly complement current surgical therapy. Using multiple high-resolution genomic screening methods, we identified a single locus, adherens junctional associated protein 1 (AJAP1) on chromosome 1p36 that is lost or epigenetically silenced in many glioblastomas.