Protein-Decorated Microbubbles for Ultrasound-Mediated Cell Surface Manipulation.

Delivering cargo to the cell membranes of specific cell types in the body is a major challenge for a range of treatments, including immunotherapy. This study investigates employing protein-decorated microbubbles (MBs) and ultrasound (US) to "tag" cellular membranes of interest with a specific protein. Phospholipid-coated MBs were produced and functionalized with a model protein using a metallochelating complex through an NTA(Ni) and histidine residue interaction. Successful "tagging" of the cellular membrane was observed using microscopy in adherent cells and was promoted by US exposure. Further modification of the MB surface to enable selective binding to target cells was then achieved by functionalizing the MBs with a targeting protein (transferrin) that specifically binds to a receptor on the target cell membrane. Attachment and subsequent transfer of material from MBs functionalized with transferrin to the target cells significantly increased, even in the absence of US. This work demonstrates the potential of these MBs as a platform for the noninvasive delivery of proteins to the surface of specific cell types.

Beyond automatic medical image segmentation-the spectrum between fully manual and fully automatic delineation.

Semi-automatic and fully automatic contouring tools have emerged as an alternative to fully manual segmentation to reduce time spent contouring and to increase contour quality and consistency. Particularly, fully automatic segmentation has seen exceptional improvements through the use of deep learning in recent years. These fully automatic methods may not require user interactions, but the resulting contours are often not suitable to be used in clinical practice without a review by the clinician. Furthermore, they need large amounts of labelled data to be available for training. This review presents alternatives to manual or fully automatic segmentation methods along the spectrum of variable user interactivity and data availability. The challenge lies to determine how much user interaction is necessary and how this user interaction can be used most effectively. While deep learning is already widely used for fully automatic tools, interactive methods are just at the starting point to be transformed by it. Interaction between clinician and machine, via artificial intelligence, can go both ways and this review will present the avenues that are being pursued to improve medical image segmentation.

Interactive contouring through contextual deep learning.

PURPOSE: To investigate a deep learning approach that enables three-dimensional (3D) segmentation of an arbitrary structure of interest given a user provided two-dimensional (2D) contour for context. Such an approach could decrease delineation times and improve contouring consistency, particularly for anatomical structures for which no automatic segmentation tools exist. METHODS: A series of deep learning segmentation models using a Recurrent Residual U-Net with attention gates was trained with a successively expanding training set. Contextual information was provided to the models, using a previously contoured slice as an input, in addition to the slice to be contoured. In total, 6 models were developed, and 19 different anatomical structures were used for training and testing. Each of the models was evaluated for all 19 structures, even if they were excluded from the training set, in order to assess the model's ability to segment unseen structures of interest. Each model's performance was evaluated using the Dice similarity coefficient (DSC), Hausdorff distance, and relative added path length (APL). RESULTS: The segmentation performance for seen and unseen structures improved when the training set was expanded by addition of structures previously excluded from the training set. A model trained exclusively on heart structures achieved a DSC of 0.33, HD of 44 mm, and relative APL of 0.85 when segmenting the spleen, whereas a model trained on a diverse set of structures, but still excluding the spleen, achieved a DSC of 0.80, HD of 13 mm, and relative APL of 0.35. Iterative prediction performed better compared to direct prediction when considering unseen structures. CONCLUSIONS: Training a contextual deep learning model on a diverse set of structures increases the segmentation performance for the structures in the training set, but importantly enables the model to generalize and make predictions even for unseen structures that were not represented in the training set. This shows that user-provided context can be incorporated into deep learning contouring to facilitate semi-automatic segmentation of CT images for any given structure. Such an approach can enable faster de-novo contouring in clinical practice.