Ethical decision-making in simultaneous heart-liver transplantation.

PURPOSE OF REVIEW: Simultaneous heart-liver (SHL) transplants are only a small proportion of overall heart and liver transplantation, they have been increasing in frequency and thus challenge the equitable allocation of organs. RECENT FINDINGS: The incidence of SHL transplants is reviewed along with the outcomes of SHL transplants and their impact on the waitlist, particularly in the context of solitary heart and liver transplantation. The ethical implications, most importantly the principles of utility and equity, of SHL transplant are addressed. In the context of utility, the distinction of a transplant being life-saving versus life-enhancing is investigated. The risk of hepatic decompensation for those awaiting both solitary and combined organ transplantation is an important consideration for the principle of equity. Lastly, the lack of standardization of programmatic approaches to SHL transplant candidates, the national approach to allocation, and the criteria by which programs are evaluated are reviewed. SUMMARY: As with all multiorgan transplantation, SHL transplantation raises ethical issues of utility and equity. Given the unique patient population, good outcomes, lack of alternatives, and overall small numbers, we feel there is continued ethical justification for SHL, but a more standardized nationwide approach to the evaluation, listing, and allocation of organs is warranted.

Structure and Intensity Unbiased Translation for 2D Medical Image Segmentation.

Data distribution gaps often pose significant challenges to the use of deep segmentation models. However, retraining models for each distribution is expensive and time-consuming. In clinical contexts, device-embedded algorithms and networks, typically unretrainable and unaccessable post-manufacture, exacerbate this issue. Generative translation methods offer a solution to mitigate the gap by transferring data across domains. However, existing methods mainly focus on intensity distributions while ignoring the gaps due to structure disparities. In this paper, we formulate a new image-to-image translation task to reduce structural gaps. We propose a simple, yet powerful Structure-Unbiased Adversarial (SUA) network which accounts for both intensity and structural differences between the training and test sets for segmentation. It consists of a spatial transformation block followed by an intensity distribution rendering module. The spatial transformation block is proposed to reduce the structural gaps between the two images. The intensity distribution rendering module then renders the deformed structure to an image with the target intensity distribution. Experimental results show that the proposed SUA method has the capability to transfer both intensity distribution and structural content between multiple pairs of datasets and is superior to prior arts in closing the gaps for improving segmentation.