Automatic hepatic tumor segmentation in intra-operative ultrasound: a supervised deep-learning approach.

Purpose: Training and evaluation of the performance of a supervised deep-learning model for the segmentation of hepatic tumors from intraoperative US (iUS) images, with the purpose of improving the accuracy of tumor margin assessment during liver surgeries and the detection of lesions during colorectal surgeries. Approach: In this retrospective study, a U-Net network was trained with the nnU-Net framework in different configurations for the segmentation of CRLM from iUS. The model was trained on B-mode intraoperative hepatic US images, hand-labeled by an expert clinician. The model was tested on an independent set of similar images. The average age of the study population was 61.9 ± 9.9 years. Ground truth for the test set was provided by a radiologist, and three extra delineation sets were used for the computation of inter-observer variability. Results: The presented model achieved a DSC of 0.84 (p=0.0037), which is comparable to the expert human raters scores. The model segmented hypoechoic and mixed lesions more accurately (DSC of 0.89 and 0.88, respectively) than hyper- and isoechoic ones (DSC of 0.70 and 0.60, respectively) only missing isoechoic or >20 mm in diameter (8% of the tumors) lesions. The inclusion of extra margins of probable tumor tissue around the lesions in the training ground truth resulted in lower DSCs of 0.75 (p=0.0022). Conclusion: The model can accurately segment hepatic tumors from iUS images and has the potential to speed up the resection margin definition during surgeries and the detection of lesion in screenings by automating iUS assessment.

Imaging in interventional oncology, the better you see, the better you treat.

Imaging and image processing is the fundamental pillar of interventional oncology in which diagnostic, procedure planning, treatment and follow-up are sustained. Knowing all the possibilities that the different image modalities can offer is capital to select the most appropriate and accurate guidance for interventional procedures. Despite there is a wide variability in physicians preferences and availability of the different image modalities to guide interventional procedures, it is important to recognize the advantages and limitations for each of them. In this review, we aim to provide an overview of the most frequently used image guidance modalities for interventional procedures and its typical and future applications including angiography, computed tomography (CT) and spectral CT, magnetic resonance imaging, Ultrasound and the use of hybrid systems. Finally, we resume the possible role of artificial intelligence related to image in patient selection, treatment and follow-up.

Image-guided percutaneous ablation for the treatment of lung malignancies: current state of the art.

Image-guided percutaneous lung ablation has proven to be a valid treatment alternative in patients with early-stage non-small cell lung carcinoma or oligometastatic lung disease. Available ablative modalities include radiofrequency ablation, microwave ablation, and cryoablation. Currently, there are no sufficiently representative studies to determine significant differences between the results of these techniques. However, a common feature among them is their excellent tolerance with very few complications. For optimal treatment, radiologists must carefully select the patients to be treated, perform a refined ablative technique, and have a detailed knowledge of the radiological features following lung ablation. Although no randomized studies comparing image-guided percutaneous lung ablation with surgery or stereotactic radiation therapy are available, the current literature demonstrates equivalent survival rates. This review will discuss image-guided percutaneous lung ablation features, including available modalities, approved indications, possible complications, published results, and future applications.

A novel technique to restore access in patients with central venous occlusion using the Surfacer® Inside-Out® Access Catheter System.

Exhausted central venous access is a potentially life-threatening situation for patients dependent on haemodialysis. If standard guidewire recanalisation fails, unconventional venous access or central venous needle recanalisation can be considered but are often associated with higher rates of complications and/or dysfunction. Here, we report about two patients treated successfully with the Surfacer® Inside-Out® Access Catheter System (Bluegrass Vascular Technologies, San Antonio, TX, USA) to achieve transmediastinal central venous access.

Minimally invasive treatment of vascular complications after neoaortoiliac system reconstruction using autologous vein grafts.

Treatment of complications after neoaortoiliac system vein reconstruction is a complex clinical problem with poor results. Endovascular treatment might offer an acceptable outcome in selected cases. We report two rare complications after neoaortoiliac system vein reconstruction for an infected aortic graft. These complications were treated with minimally invasive endovascular techniques. A 54-year-old man presented with an arterioureteral fistula located between the right ureter and the right branch of the venous reconstruction. The second case describes a 71-year-old man who developed a large dilation proximally in the venous reconstruction.