Prediction of heart transplant rejection from routine pathology slides with self-supervised deep learning.

Aims: One of the most important complications of heart transplantation is organ rejection, which is diagnosed on endomyocardial biopsies by pathologists. Computer-based systems could assist in the diagnostic process and potentially improve reproducibility. Here, we evaluated the feasibility of using deep learning in predicting the degree of cellular rejection from pathology slides as defined by the International Society for Heart and Lung Transplantation (ISHLT) grading system.

Stain-Independent Deep Learning-Based Analysis of Digital Kidney Histopathology.

Convolutional neural network (CNN)-based image analysis applications in digital pathology (eg, tissue segmentation) require a large amount of annotated data and are mostly trained and applicable on a single stain. Here, a novel concept based on stain augmentation is proposed to develop stain-independent CNNs requiring only one annotated stain. In this benchmark study on stain independence in digital pathology, this approach is comprehensively compared with state-of-the-art techniques including image registration and stain translation, and several modifications thereof.

Adversarial attacks and adversarial robustness in computational pathology.

Artificial Intelligence (AI) can support diagnostic workflows in oncology by aiding diagnosis and providing biomarkers directly from routine pathology slides. However, AI applications are vulnerable to adversarial attacks. Hence, it is essential to quantify and mitigate this risk before widespread clinical use.

A T-cell engaging bispecific antibody with a tumor-selective bivalent folate receptor alpha binding arm for the treatment of ovarian cancer.

The use of T-cell engagers (TCEs) to treat solid tumors is challenging, and several have been limited by narrow therapeutic windows due to substantial on-target, off-tumor toxicities due to the expression of low levels of target antigens on healthy tissues. Here, we describe TNB-928B, a fully human TCE that has a bivalent binding arm for folate receptor alpha (FRα) to selectively target FRα overexpressing tumor cells while avoiding the lysis of cells with low levels of FRα expression. The bivalent design of the FRα binding arm confers tumor selectivity due to low-affinity but high-avidity binding to high FRα antigen density cells.