The high incidence of rectal cancer in both sexes makes it one of the most common tumors, with significant morbidity and mortality rates. To define the best treatment option and optimize patient outcome, several rectal cancer biological variables must be evaluated. Currently, medical imaging plays a crucial role in the characterization of this disease, and it often requires a multimodal approach. Magnetic resonance imaging is the first-choice imaging modality for local staging and restaging and can be used to detect high-risk prognostic factors. Computed tomography is widely adopted for the detection of distant metastases. However, conventional imaging has recognized limitations, and many rectal cancer characteristics remain assessable only after surgery and histopathology evaluation. There is a growing interest in artificial intelligence applications in medicine, and imaging is by no means an exception. The introduction of radiomics, which allows the extraction of quantitative features that reflect tumor heterogeneity, allows the mining of data in medical images and paved the way for the identification of potential new imaging biomarkers. To manage such a huge amount of data, the use of machine learning algorithms has been proposed. Indeed, without prior explicit programming, they can be employed to build prediction models to support clinical decision making. In this review, current applications and future perspectives of artificial intelligence in medical imaging of rectal cancer are presented, with an imaging modality-based approach and a keen eye on unsolved issues. The results are promising, but the road ahead for translation in clinical practice is rather long.

In the management of several abdominal disorders, magnetic resonance imaging (MRI) has the potential to significantly improve patient’s outcome due to its diagnostic accuracy leading to more appropriate treatment choice. However, its clinical value heavily relies on the quality and quantity of diagnostic information that radiologists manage to convey through their reports. To solve issues such as ambiguity and lack of comprehensiveness that can occur with conventional narrative reports, the adoption of structured reporting has been proposed. Using a checklist and standardized lexicon, structured reports are designed to increase clarity while assuring that all key imaging findings related to a specific disorder are included. Unfortunately, structured reports have their limitations too, such as risk of undue report simplification and poor template plasticity. Their adoption is also far from widespread, and probably the ideal balance between radiologist autonomy and report consistency of has yet to be found. In this article, we aimed to provide an overview of structured reporting proposals for abdominal MRI and of works assessing its value in comparison to conventional free-text reporting. While for several abdominal disorders there are structured templates that have been endorsed by scientific societies and their adoption might be beneficial, stronger evidence confirming their imperativeness and added value in terms of clinical practice is needed, especially regarding the improvement of patient outcome.

No abstract

Purpose: Illustrate imaging findings of gastrinomas and non-functioning pancreatic endocrine tumors (NF-PNET) in a patient with multiple endocrine neoplasia type-1 (MEN-1) syndrome with a radiologic-pathologic correlation for both along with the results of a 13 yrs observational study. Methods: A 48 yrs old male patient with MEN-1 and a Zollinger-Ellison syndrome was submitted to a duodeno-cephalopancreatectomy (DCP) extended to the pancreatic body to remove several gastrinomas shown by an endoscopic-ultrasonography as well as a large (> 2 cm) hypo-vascular pancreatic nodule shown by a contrast-enhanced multi-detector CT (CE-MDCT). Further conventional (CT/MR) and functional imaging (68Ga-PET-DOTA-TOC) studies were performed over the next 13 years. Results: Up to 14 gastrin-positive NET-G1 (pT2,N1) as well as a single PNET-G2 (pT2,N0) were found at histo-pathology which also showed a NET-G1 in the uncinate process where CE-MDCT documented a 9 mm hyper-vascular nodule. A 7 mm pancreatic nodule with identical contrast-enhancement pattern was also shown at the level of the pancreatic tail which was left to preserve endocrine function. At this level, follow-up studies documented the occurence of a small (< 1 cm) hypo-vascular nodule which was metastatic at presentation and rapidly progressed under somastatin-analogs therapy whereas the hyper-vascular nodule remained stable over 13 years. Both the pancreatic lesion as well as the hepatic metastasis showed pathologic uptake of the radiotracer with a SUVmax of 6.3 and 29.5, respectively, allowing the patient to be scheduled for a Peptide Receptor Radionuclide Therapy performed with 29.6 GBq of 177Lu-Oxotreotide. Conclusions: Contrast-enhancement patterns are correlated with both the histological grade as well as the biological behaviour of PNETS.