University College London Hospitals (UCLH)/UCL Comprehensive Biomedical Research Centre, UCLH Charities, National Institute for Health Research Health Technology Assessment programme, Ninewells Cancer Campaign, National Health and Medical Research Council, and German Federal Ministry of Education and Research.

SummaryBackground After breast-conserving surgery, 90% of local recurrences occur within the index quadrant despite the presence of multicentric cancers elsewhere in the breast. Thus, restriction of radiation therapy to the tumour bed during surgery might be adequate for selected patients. We compared targeted intraoperative radiotherapy with the conventional policy of whole breast external beam radiotherapy.

It is safe and feasible to deliver targeted intraoperative radiotherapy (Targit) for early breast cancer. We have begun a randomised trial--the first of its kind--comparing Targit with conventional six-week course of radiotherapy. If proven equivalent in terms of local recurrence and cosmesis, it could eliminate the need for the usual six-week course of post-operative radiotherapy.

Over the past few years, positron emission tomography/computed tomography (PET/CT) imaging for computer-aided diagnosis has received increasing attention. Supervised deep learning architectures are usually employed for the detection of abnormalities, with anatomical localization, especially in the case of CT scans. However, the main limitations of the supervised learning paradigm include (i) large amounts of data required for model training, and (ii) the assumption of fixed network weights upon training completion, implying that the performance of the model cannot be further improved after training. In order to overcome these limitations, we apply a few-shot learning (FSL) scheme. Contrary to traditional deep learning practices, in FSL the model is provided with less data during training. The model then utilizes end-user feedback after training to constantly improve its performance. We integrate FSL in a U-Net architecture for lung cancer lesion segmentation on PET/CT scans, allowing for dynamic model weight fine-tuning and resulting in an online supervised learning scheme. Constant online readjustments of the model weights according to the user’s feedback, increase the detection and classification accuracy, especially in cases where low detection performance is encountered. Our proposed method is validated on the Lung-PET-CT-DX TCIA database. PET/CT scans from 87 patients were included in the dataset and were acquired 60 minutes after intravenous 18F-FDG injection. Experimental results indicate the superiority of our approach compared to other state of the art methods.