One of the fundamental challenges in supervised learning for multimodal image registration is the lack of ground-truth for voxel-level spatial correspondence. This work describes a method to infer voxel-level transformation from higher-level correspondence information contained in anatomical labels. We argue that such labels are more reliable and practical to obtain for reference sets of image pairs than voxel-level correspondence. Typical anatomical labels of interest may include solid organs, vessels, ducts, structure boundaries and other subject-specific ad hoc landmarks. The proposed end-to-end convolutional neural network approach aims to predict displacement fields to align multiple labelled corresponding structures for individual image pairs during the training, while only unlabelled image pairs are used as the network input for inference. We highlight the versatility of the proposed strategy, for training, utilising diverse types of anatomical labels, which need not to be identifiable over all training image pairs. At inference, the resulting 3D deformable image registration algorithm runs in real-time and is fully-automated without requiring any anatomical labels or initialisation. Several network architecture variants are compared for registering T2-weighted magnetic resonance images and 3D transrectal ultrasound images from prostate cancer patients. A median target registration error of 3.6 mm on landmark centroids and a median Dice of 0.87 on prostate glands are achieved from cross-validation experiments, in which 108 pairs of multimodal images from 76 patients were tested with high-quality anatomical labels.

Whole-body STIR half-Fourier RARE MR imaging of pediatric and adolescent lymphoma can accurately depict nodal and extranodal disease and may provide an alternative nonionizing imaging method for anatomic disease assessment at initial staging.

The growing detection of papillary thyroid microcarcinomas (PTMCs) is paralleled by an increase in surgical procedures. Due to the frequent indolent nature, cost, and risk of surgery, active surveillance (AS) and ultrasound-guided minimally invasive treatments (MITs) are in suitable cases of incidental PTMC proposed as alternatives to thyroidectomy. Surgery and radioiodine are the established treatments for relapsing cervical differentiated thyroid carcinoma (DTC) metastases. But radioiodine refractoriness, risk of surgical complications, adverse influence on quality of life, or declining repeat surgery have led to AS and MIT being considered as alternatives for slow-growing DTC nodal metastases. Also, for distant radioiodine-refractory metastases not amenable to surgery, MIT is proposed as part of a multimodality therapeutic approach. The European Thyroid Association and the Cardiovascular and Interventional Radiological Society of Europe commissioned these guidelines for the appropriate use of MIT. Based on a systematic PubMed search, an evidence-based approach was applied, and both knowledge and practical experience of the panelists were incorporated to develop the manuscript and the specific recommendations. We recommend that when weighing between surgery, radioiodine, AS, or MIT for DTC, a multidisciplinary team including members with expertise in interventional radiology assess the demographic, clinical, histological, and imaging characteristics for appropriate selection of patients eligible for MIT. Consider TA in low-risk PTMC patients who are at surgical risk, have short life expectancy, relevant comorbidities, or are unwilling to undergo surgery or AS. As laser ablation, radiofrequency ablation, and microwave ablation are similarly safe and effective thermal ablation (TA) techniques, the choice should be based on the specific competences and resources of the centers. Use of ethanol ablation and high-intensity focused ultrasound is not recommended for PTMC treatment. Consider MIT as an alternative to surgical neck dissection in patients with radioiodine refractory cervical recurrences who are at surgical risk or decline further surgery. Factors that favor MIT are previous neck dissection, presence of surgical complications, small size metastases, and <4 involved latero-cervical lymph nodes. Consider TA among treatment options in patients with unresectable oligometastatic or oligoprogressive distant metastases to achieve local tumor control or pain palliation. Consider TA, in combination with bone consolidation and external beam radiation therapy, as a treatment option for painful bone metastases not amenable to other established treatments.

Our results confirm a strong reciprocal relationship between nodal ADC(mean) and SUV(max) in Hodgkin lymphoma;supporting the potential application of quantitative DWI as a functional biomarker of disease.

ObjectivesPainful chronic pancreatitis (CP) is often associated with main duct obstruction due to stones.Approaches to management are challenging, including surgery, extracorporeal shock wave lithotripsy, or endoscopic approaches. Here we report our experience of pancreatoscopy + electrohydraulic lithotripsy (EHL) for pancreatic duct (PD) stones using SpyGlass. MethodsWe retrospectively audited the use of SpyGlass (Legacy & DS™) + EHL. Indication, procedural details, and clinical outcome were assessed. Results118 SpyGlass + EHL procedures for stones were performed, of which 8 (7%) for pancreatic stones, in 6 patients (3 female, mean age 45 years ±7 years). All patients had painful CP, with radiological evidence of a dilated PD, and main duct stone disease. Surgical options had been considered in all cases. Stone fragmentation and PD decompression was achieved in 83% (n=5) without complications. Two patients required two EHL procedures to achieve clearance. One patient failed clearance, pancreatoscopy revealed a stone in the adjacent parenchyme and not in PD. All patients with successful EHL had pain relief/marked improvement at clinical review (mean follow-up 2.7 ±1.1 years). ConclusionPancreatoscopy + EHL may have a valuable role in treating obstructing pancreatic ductal stones, possibly avoiding the need for surgery in some patients.