Does Aggregation of Therapeutic IgGs in PBS Offer a True Picture of What Happens in Models Derived from Human Body Fluids?

Therapeutic proteins such as monoclonal antibodies (mAb) are known to form aggregates due to various factors. Phosphate buffered saline (PBS), human serum, and human serum filtrate (HSF) are some of the models used to analyze mAb stability in physiologically relevant in-vitro conditions. In this study, aggregation of mAb in PBS and models derived from body fluids seeded with mAb samples subjected to various stresses were compared. Samples containing mAb subjected to pH, temperature, UV light, stirring, and interfacial agitation stress were seeded into different models for 2 case studies. In the first case study, %HMW (high molecular weight species) of mAb in PBS and HSF were compared using size exclusion chromatography. It was found that change in %HMW was higher in PBS compared to HSF. For example, PBS containing mAb that was subjected to UV light stress showed change in HMW by >10 % over 72 h, but the change was <5 % in HSF. In second case study, aggregates particles of FITC tagged mAb were monitored in PBS and serum using fluorescence microscope image processing. It was found that PBS and serum containing mAb subjected to stirring and interfacial agitation resulted in aggregates of >2 µm size, and average size and percentage number of particles having >10 µm size was higher in serum compared to PBS at all analysis time point. Overall, it was found that aggregation of mAb in PBS was different from that in human body fluids. Second case study also showed the importance of advanced strategies for further characterization of mAb in serum.

A Domain-Shift Invariant CNN Framework for Cardiac MRI Segmentation Across Unseen Domains.

The emergence of various deep learning approaches in diagnostic medical image segmentation has made machines capable of accomplishing human-level accuracy. However, the generalizability of these architectures across patients from different countries, Magnetic Resonance Imaging (MRI) scans from distinct vendors, and varying imaging conditions remains questionable. In this work, we propose a translatable deep learning framework for diagnostic segmentation of cine MRI scans. This study aims to render the available SOTA (state-of-the-art) architectures domain-shift invariant by utilizing the heterogeneity of multi-sequence cardiac MRI. To develop and test our approach, we curated a diverse group of public datasets and a dataset obtained from private source. We evaluated 3 SOTA CNN (Convolution neural network) architectures i.e., U-Net, Attention-U-Net, and Attention-Res-U-Net. These architectures were first trained on a combination of three different cardiac MRI sequences. Next, we examined the M&M (multi-center & mutli-vendor) challenge dataset to investigate the effect of different training sets on translatability. The U-Net architecture, trained on the multi-sequence dataset, proved to be the most generalizable across multiple datasets during validation on unseen domains. This model attained mean dice scores of 0.81, 0.85, and 0.83 for myocardial wall segmentation after testing on unseen MyoPS (Myocardial Pathology Segmentation) 2020 dataset, AIIMS (All India Institute of Medical Sciences) dataset and M&M dataset, respectively. Our framework achieved Pearson's correlation values of 0.98, 0.99, and 0.95 between the observed and predicted parameters of end diastole volume, end systole volume, and ejection fraction, respectively, on the unseen Indian population dataset.