Search

Background: preoperative risk assessment of gastrointestinal stromal tumors (GISTS) is required for optimal and personalized treatment planning. Radiomics features are promising tools to predict risk assessment. The purpose of this study is to develop and validate an artificial intelligence classification algorithm, based on CT features, to define GIST’s prognosis as determined by the Miettinen classification. Methods: patients with histological diagnosis of GIST and CT studies were retrospectively enrolled. Eight morphologic and 30 texture CT features were extracted from each tumor and combined to obtain three models (morphologic, texture and combined). Data were analyzed using a machine learning classification (WEKA). For each classification process, sensitivity, specificity, accuracy and area under the curve were evaluated. Inter- and intra-reader agreement were also calculated. Results: 52 patients were evaluated. In the validation population, highest performances were obtained by the combined model (SE 85.7%, SP 90.9%, ACC 88.8%, and AUC 0.954) followed by the morphologic (SE 66.6%, SP 81.8%, ACC 76.4%, and AUC 0.742) and texture (SE 50%, SP 72.7%, ACC 64.7%, and AUC 0.613) models. Reproducibility was high of all manual evaluations. Conclusions: the AI-based radiomics model using a CT feature demonstrates good predictive performance for preoperative risk stratification of GISTs.

Objective To evaluate if an adequate bowel preparation for CT colonography, can be achieved without diet restriction, using a reduced amount of cathartic agent and fecal tagging. To investigate the influence of patients’ characteristics on bowel preparation and the impact on patients’ compliance. Methods In total, 1446 outpatients scheduled for elective CT colonography were prospectively enrolled. All patients had the same bowel preparation based on a reduced amount of cathartic agent (120 g of macrogol in 1.5 l of water) the day before the exam and a fecal tagging agent (60 ml of hyperosmolar oral iodinated agent) the day of the exam. No dietary restrictions were imposed before the exam. The bowel preparation was evaluated using a qualitative and quantitative score. Patients were grouped by age, gender, and presence of diverticula in both scores. Patients’ compliance has been evaluated with a questionnaire after the end of the exam and with a phone-calling interview the day after the exam. Results According to the qualitative score, adequate bowel preparation was achieved in 1349 patients (93.29%) and no statistical differences were observed among the subgroups of patients. Quantitative scores demonstrated that colon distension was significantly better in younger patients and without diverticula. A good patients’ compliance was observed and most patients (96.5%) were willing to repeat it. Conclusions The lack of diet restriction does not affect the quality of CTC preparation and good patient’s compliance could potentially increase the participation rate in CRC screening programs. Key Points • An adequate quality bowel preparation for CT colonography can be achieved without diet restriction, using a reduced amount of cathartic agent (120 g of macrogol in 1.5 l of water) and fecal tagging (60 ml of hyperosmolar oral iodinated agent). • A bowel preparation based on the combination of a reduced amount of cathartic agent and fecal tagging, without diet restriction, allows obtaining good quality in more than 90% of patients. • The bowel preparation scheme proposed reduces the distress and discomfort experienced by the patients improving adherence to CTC.

Fitz-Hugh-Curtis Syndrome is a rare disorder manifesting as a complication associated with Pelvic Inflammatory Disease. The initial presentation generally consists of concomitant right upper quadrant and lower abdominal pain. This syndrome is characterized by inflammation of the peritoneum with the involvement of hepatic capsule and the tissues surrounding the liver. Intrahepatic involvement is rare and not yet well investigated. An accurate interpretation of Computed Tomography and Magnetic Resonance Imaging findings is missing in the literature. This report presents a case of Fitz-Hugh-Curtis Syndrome in which Computed Tomography and Magnetic Resonance Imaging showed a region of heterogeneously decreased enhancement and abnormal signal intensity within the liver mimicking a lesion.

To determine whether the quality of a low-volume reduced bowel preparation (LV-RBP) for CT Colonography (CTC) is noninferior to full-volume reduced bowel preparation (FV-RBP) regimen. In this randomized controlled trial, consecutive participants referred for CTC were randomly assigned to receive LV-RBP (52.5 g of PMF104 in 500 mL of water) or FV-RBP (105 g of PMF104 in 1000 mL of water). Images were independently reviewed by five blinded readers who rated the quality of bowel preparation from 0 (best score) to 3 (worst score). The primary outcome was the noninferiority of LV-RBP to FV-RBP in the proportion of colonic segments scored 0 for cleansing quality, with noninferiority margin of 10%. Volume of residual fluids, colonic distension, lesions and polyps detection rates and patient tolerability were secondary outcomes. From March 2019 to January 2020, 110 participants (mean age 65 years ± 14 [standard deviation]; 74 women) were allocated to LV-RBP (n = 55) or FV-RBP (n = 55) arms. There were 92% segment scored 0 in colon cleansing quality in LV-RBP and 94% in FV-RBP for prone scans, and 94% vs 92% for supine scans. Risk difference was – 2.1 (95% CI −5.9 to 1.7) and 1.5 (95% CI −2.4 to 5.4) for prone and supine positions, respectively. Residual fluids and colonic distension were also noninferior in LV-RBP. LV-RBP was associated with a lower number of evacuations during preparation (7 ± 5 vs 10 ± 6, p = 0.002). The LV-RBP for CTC demonstrated noninferior quality of colon cleansing with improved gastrointestinal tolerability compared to FV-RBP regimen.

Background: To evaluate the diagnostic performance of a Machine Learning (ML) algorithm based on Texture Analysis (TA) parameters in the prediction of Pathological Complete Response (pCR) to Neoadjuvant Chemoradiotherapy (nChRT) in Locally Advanced Rectal Cancer (LARC) patients. Methods: LARC patients were prospectively enrolled to undergo pre- and post-nChRT 3T MRI for initial loco-regional staging. TA was performed on axial T2-Weighted Images (T2-WI) to extract specific parameters, including skewness, kurtosis, entropy, and mean of positive pixels. For the assessment of TA parameter diagnostic performance, all patients underwent complete surgical resection, which served as a reference standard. ROC curve analysis was carried out to determine the discriminatory accuracy of each quantitative TA parameter to predict pCR. A ML-based decisional tree was implemented combining all TA parameters in order to improve diagnostic accuracy. Results: Forty patients were considered for final study population. Entropy, kurtosis and MPP showed statistically significant differences before and after nChRT in patients with pCR; in particular, when patients with Pathological Partial Response (pPR) and/or Pathological Non-Response (pNR) were considered, entropy and skewness showed significant differences before and after nChRT (all p < 0.05). In terms of absolute value changes, pre- and post-nChRT entropy, and kurtosis showed significant differences (0.31 ± 0.35, in pCR, −0.02 ± 1.28 in pPR/pNR, (p = 0.04); 1.87 ± 2.19, in pCR, −0.06 ± 3.78 in pPR/pNR (p = 0.0005); 107.91 ± 274.40, in pCR, −28.33 ± 202.91 in pPR/pNR, (p = 0.004), respectively). According to ROC curve analysis, pre-treatment kurtosis with an optimal cut-off value of ≤3.29 was defined as the best discriminative parameter, resulting in a sensitivity and specificity in predicting pCR of 81.5% and 61.5%, respectively. Conclusions: TA parameters extracted from T2-WI MRI images could play a key role as imaging biomarkers in the prediction of response to nChRT in LARC patients. ML algorithms can be used to efficiently combine all TA parameters in order to improve diagnostic accuracy.

Radiological imaging is currently employed as the most effective technique for screening, diagnosis, and follow up of patients with breast cancer (BC), the most common type of tumor in women worldwide. However, the introduction of the omics sciences such as metabolomics, proteomics, and molecular genomics, have optimized the therapeutic path for patients and implementing novel information parallel to the mutational asset targetable by specific clinical treatments. Parallel to the “omics” clusters, radiological imaging has been gradually employed to generate a specific omics cluster termed “radiomics”. Radiomics is a novel advanced approach to imaging, extracting quantitative, and ideally, reproducible data from radiological images using sophisticated mathematical analysis, including disease-specific patterns, that could not be detected by the human eye. Along with radiomics, radiogenomics, defined as the integration of “radiology” and “genomics”, is an emerging field exploring the relationship between specific features extracted from radiological images and genetic or molecular traits of a particular disease to construct adequate predictive models. Accordingly, radiological characteristics of the tissue are supposed to mimic a defined genotype and phenotype and to better explore the heterogeneity and the dynamic evolution of the tumor over the time. Despite such improvements, we are still far from achieving approved and standardized protocols in clinical practice. Nevertheless, what can we learn by this emerging multidisciplinary clinical approach? This minireview provides a focused overview on the significance of radiomics integrated by RNA sequencing in BC. We will also discuss advances and future challenges of such radiomics-based approach.

The use of artificial intelligence (AI) and radiomics in the healthcare setting to advance disease diagnosis and management and facilitate the creation of new therapeutics is gaining popularity. Given the vast amount of data collected during cancer therapy, there is significant concern in leveraging the algorithms and technologies available with the underlying goal of improving oncologic care. Radiologists will attain better precision and effectiveness with the advent of AI technology, making machine-assisted medical services a valuable and important option for future oncologic medical care. As a result, it is critical to figure out which specific radiology activities are best positioned to gain from AI and radiomics models and methods of oncologic imaging, while also considering the algorithms' capabilities and constraints. Our purpose is to overview the current evidence and future prospects of AI and radiomics algorithms used in oncologic imaging efforts with an emphasis on the three most frequent cancers worldwide, i.e., lung cancer, breast cancer and colorectal cancer. We discuss how AI and radiomics could be used to detect and characterize cancers and assess therapy response.

Introduction A more structured role of radiographers is advisable to speed up the management of patients with suspected COVID-19. The purpose of our study was to evaluate the diagnostic performance of radiographers in the detection of COVID-19 pneumonia on chest CT using CO-RADS descriptors. Methods CT images of patients who underwent RT-PCR and chest CT due to COVID-19 suspicion between March and July 2020 were analysed retrospectively. Six readers, including two radiologists, two highly experienced radiographers and two less experienced radiographers, independently scored each CT using the CO-RADS lexicon. ROC curves were used to investigate diagnostic accuracy, and Fleiss’κ statistics to evaluate inter-rater agreement. Results 714 patients (419 men; 295 women; mean age: 64 years ±19SD) were evaluated. CO-RADS> 3 was identified as optimal diagnostic threshold. Highly experienced radiographers achieved an average sensitivity of 58.7% (95%CI: 52.5–64.7), an average specificity of 81.8% (95%CI: 77.9–85.2), and a mean AUC of 0.72 (95%CI: 0.68–0.75). Among less experienced radiographers, an average sensitivity of 56.3% (95%CI: 50.1–62.2) and an average specificity of 81.5% (95%CI: 77.6–84.9) were observed, with a mean AUC of 0.71 (95%CI: 0.68–0.74). Consultant radiologists achieved an average sensitivity of 60.0% (95%CI: 53.7–65.8), an average specificity of 81.7% (95%CI: 77.8–85.1), and a mean AUC of 0.73 (95%CI: 0.70–0.77). Conclusion Radiographers can adequately recognise the classic appearances of COVID-19 on CT, as described by the CO-RADS assessment scheme, in a way comparable to expert radiologists. Implications for practice Radiographers, as the first healthcare professionals to evaluate CT images in patients with suspected SARS-CoV-2 infection, could diagnose COVID-19 pneumonia by means of a categorical reporting scheme at CT in a reliable way, hence playing a primary role in the early management of these patients.

Objective To conduct a multireader validation study to evaluate the interobserver variability and the diagnostic accuracy for the lung involvement by COVID-19 of COVID-19 Reporting and Data System (CO-RADS) score. Methods This retrospective study included consecutive symptomatic patients who underwent chest CT and reverse transcriptase-polymerase chain reaction (RT-PCR) from March 2020 to May 2020 for suspected COVID-19. Twelve readers with different levels of expertise independently scored each CT using the CO-RADS scheme for detecting pulmonary involvement by COVID-19. Receiver operating characteristic (ROC) curves were computed to investigate diagnostic yield. Fleiss’ kappa statistics was used to evaluate interreader agreement. Results A total of 572 patients (mean age, 63 ± 20 [standard deviation]; 329 men; 142 patients with COVID-19 and 430 patients without COVID-19) were evaluated. There was a moderate agreement for CO-RADS rating among all readers (Fleiss’ K = 0.43 [95% CI 0.42–0.44]) with a substantial agreement for CO-RADS 1 category (Fleiss’ K = 0.61 [95% CI 0.60–0.62]) and moderate agreement for CO-RADS 5 category (Fleiss’ K = 0.60 [95% CI 0.58–0.61]). ROC analysis showed the CO-RADS score ≥ 4 as the optimal threshold, with a cumulative area under the curve of 0.72 (95% CI 66–78%), sensitivity 61% (95% CI 52–69%), and specificity 81% (95% CI 77–84%). Conclusion CO-RADS showed high diagnostic accuracy and moderate interrater agreement across readers with different levels of expertise. Specificity is higher than previously thought and that could lead to reconsider the role of CT in this clinical setting. Key Points • COVID-19 Reporting and Data System (CO-RADS) demonstrated a good diagnostic accuracy for lung involvement by COVID-19 with an average AUC of 0.72 (95% CI 67–75%). • When a threshold of ≥ 4 was used, sensitivity and specificity were 61% (95% CI 52–69%) and 81% (95% CI 76–84%), respectively. • There was an overall moderate agreement for CO-RADS rating across readers with different levels of expertise (Fleiss’ K = 0.43 [95% CI 0.42–0.44]). Electronic supplementary material The online version of this article (10.1007/s00330-020-07273-y) contains supplementary material, which is available to authorized users.

The typical findings on CT in patients affected by novel COVID-19 (coronavirus disease 2019) pneumonia are characterized by ground-glass opacities and/or air space consolidation mainly bilateral and peripherical in distribution, including crazy paving pattern and reversed halo sign. We hereby describe a case of an adolescent male tested positive for COVID-19 with mild respiratory symptoms and presenting with pneumomediastinum as the only CT finding.