Advances in technical radiotherapy have resulted in significant sparing of organs at risk (OARs), reducing radiation-related toxicities for patients with cancer of the head and neck (HNC). Accurate delineation of target volumes (TVs) and OARs is critical for maximising tumour control and minimising radiation toxicities. When performed manually, variability in TV and OAR delineation has been shown to have significant dosimetric impacts for patients on treatment. Auto-segmentation (AS) techniques have shown promise in reducing both inter-practitioner variability and the time taken in TV and OAR delineation in HNC. Ultimately, this may reduce treatment planning and clinical waiting times for patients. Adaptation of radiation treatment for biological or anatomical changes during therapy will also require rapid re-planning; indeed, the time taken for manual delineation currently prevents adaptive radiotherapy from being implemented optimally. We are therefore standing on the doorstep of a transformation of routine radiotherapy planning via the use of artificial intelligence. In this article, we outline the current state-of-the-art for AS for HNC radiotherapy in order to predict how this will rapidly change with the introduction of artificial intelligence. We specifically focus on delineation accuracy and time saving. We argue that, if such technologies are implemented correctly, AS should result in better standardisation of treatment for patients and significantly reduce the time taken to plan radiotherapy.

Three linkage studies of bipolar disorder have implicated chromosome 12q24.3 with lod scores of over 3.0 and several other linkage studies have found lods between 2 and 3. Fine mapping within the original chromosomal linkage regions has identified several loci that show association with bipolar disorder. One of these is the P2RX7 gene encoding a central nervous system-expressed purinergic receptor. A non-synonymous single nucleotide polymorphism, rs2230912 (P2RX7-E13A, G allele) and a microsatellite marker NBG6 were both previously found to be associated with bipolar disorder (P = 0.00071 and 0.008, respectively). rs2230912 has also been found to show association with unipolar depression. The effect of the polymorphism is non-conservative and results in a glutamine to arginine change (Gln460Arg), which is likely to affect P2RX7 dimerization and protein-protein interactions. We have confirmed the allelic associations between bipolar disorder and the markers rs2230912 (P2RX7-E13A, G allele, P = 0.043) and NBG6 (P = 0.010) in a London-based sample of 604 bipolar cases and 560 controls. When we combined these data with the published case-control studies of P2RX7 and mood disorder (3586 individuals) the association between rs2230912 (Gln460Arg) and affective disorders became more robust (P = 0.002). The increase in Gln460Arg was confined to heterozygotes rather than homozygotes suggesting a dominant effect (odds ratio 1.302, CI = 1.129-1.503). Although further research is needed to prove that the Gln460Arg change has an aetiological role, it is so far the most convincing mutation to have been found with a role for increasing susceptibility to bipolar and genetically related unipolar disorders.

If there is only a modest increase in the risk of bacterial infection following allogeneic transfusion, autologous transfusion would result in improved outcomes at a cost of less than $50,000 per QALY. Autologous transfusion would be dominant above a relative risk of infection that is within the range of values observed in randomized controlled trials. However, if there is no increased risk of bacterial infection, autologous transfusion would be a very expensive strategy. Until more definitive data are available on the magnitude and costs of this risk, we advise against prematurely closing the debate about the cost-effectiveness of autologous transfusion.