Neoadjuvant chemo-radiotherapy (CRT) followed by total mesorectal excision (TME) represents the standard treatment for patients with locally advanced (≥ T3 or N+) rectal cancer (LARC). Approximately 15% of patients with LARC shows a complete response after CRT. The use of pre-treatment MRI as predictive biomarker could help to increase the chance of organ preservation by tailoring the neoadjuvant treatment. We present a novel machine learning model combining pre-treatment MRI-based clinical and radiomic features for the early prediction of treatment response in LARC patients. MRI scans (3.0 T, T2-weighted) of 72 patients with LARC were included. Two readers independently segmented each tumor. Radiomic features were extracted from both the “tumor core” (TC) and the “tumor border” (TB). Partial least square (PLS) regression was used as the multivariate, machine learning, algorithm of choice and leave-one-out nested cross-validation was used to optimize hyperparameters of the PLS. The MRI-Based “clinical-radiomic” machine learning model properly predicted the treatment response (AUC = 0.793, p = 5.6 × 10–5). Importantly, the prediction improved when combining MRI-based clinical features and radiomic features, the latter extracted from both TC and TB. Prospective validation studies in randomized clinical trials are warranted to better define the role of radiomics in the development of rectal cancer precision medicine.
Magnetic resonance imaging (MRI) allows to non-invasively evaluate rectal cancer staging and to assess the presence of “prognostic signs” such as the distance from the anorectal junction, the mesorectal fascia infiltration and the extramural vascular invasion. Moreover, MRI plays a crucial role in the assessment of treatment response after chemo-radiation therapy, especially considering the growing interest in the new conservative policy (wait and see, minimally invasive surgery). We present a practical overview regarding the state of the art of the MRI protocol, the main signs that radiologists should consider for their reports during their clinical activity and future perspectives.Teaching Points• MRI protocol for rectal cancer staging and re-staging.• MRI findings that radiologists should consider for reports during everyday clinical activity.• Perspectives regarding the development of latest technologies.
Anti-N-methyl-D-aspartate receptor (NMDAR) encephalitis (NMDARe) is the most common cause of nonviral encephalitis, mostly affecting young women and adolescents with a strong female predominance (F/M ratio of around 4:1). NMDARe is characterized by the presence of cerebrospinal fluid (CSF) antibodies against NMDARs, even though its pathophysiological mechanisms have not totally been clarified. The clinical phenotype of NMDARe is composed of both severe neurological and neuropsychiatric symptoms, including generalized seizures with desaturations, behavioral abnormalities, and movement disorders. NMDARe is often a paraneoplastic illness, mainly due to the common presence of concomitant ovarian teratomas in young women. Abdominal ultrasonography (US) is a key imaging technique that should always be performed in suspected patients. The timely use of abdominal US and the peculiar radiological features observed in NMDARe may allow for a quick diagnosis and a good prognosis, with rapid improvement after the resection of the tumor and the correct drug therapy.
Neoadjuvant chemo-radiotherapy (CRT) followed by total mesorectal excision (TME) represents the standard treatment for patients with locally advanced (³ T3 or N+) rectal cancer (LARC). Approximately 15% of patients with LARC shows a complete response after CRT. The use of pre-treatment MRI as predictive biomarker could help to increase the chance of organ preservation by tailoring the neoadjuvant treatment. We present a novel machine learning model combining pre-treatment MRI-based clinical and radiomic features for the early prediction of treatment response in LARC patients. MRI scans (3.0T, T2-weighted) of 72 patients with LARC were included. Two readers independently segmented each tumor. Radiomic features were extracted from both the “tumor core” (TC) and the “tumor border” (TB). Partial least square (PLS) regression was used as the multivariate, machine learning, algorithm of choice and leave-one-out nested cross-validation was used to optimize hyperparameters of the PLS. The MRI-Based “clinical-radiomic” machine learning model properly predicted the treatment response (AUC=0.793, p =5.6·10-5). Importantly, the prediction improved when combining MRI-based clinical features and radiomic features, the latter extracted from both TC and TB. Prospective validation studies in randomized clinical trials are warranted to better define the role of radiomics in the development of rectal cancer precision medicine.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.