Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI.

OBJECTIVE: The purpose of this study is to analyze the texture characteristics of chronic non-bacterial osteomyelitis (CNO) bone lesions, identified as areas of altered signal intensity on short tau inversion recovery (STIR) sequences, and to distinguish them from bone marrow growth-related changes through Machine Learning (ML) and Deep Learning (DL) analysis. MATERIALS AND METHODS: We included a group of 66 patients with confirmed diagnosis of CNO and a group of 28 patients with suspected extra-skeletal systemic disease. All examinations were performed on a 1.5 T MRI scanner. Using the opensource 3D Slicer software version 4.10.2, the ROIs on CNO lesions and on the red bone marrow were sampled. Texture analysis (TA) was carried out using Pyradiomics. We applied an optimization search grid algorithm on nine classic ML classifiers and a Deep Learning (DL) Neural Network (NN). The model's performance was evaluated using Accuracy (ACC), AUC-ROC curves, F1-score, Positive Predictive Value (PPV), Mean Absolute Error (MAE) and Root-Mean-Square Error (RMSE). Furthermore, we used Shapley additive explanations to gain insight into the behavior of the prediction model. RESULTS: Most predictive characteristics were selected by Boruta algorithm for each combination of ROI sequences for the characterization and classification of the two types of signal hyperintensity. The overall best classification result was obtained by the NN with ACC = 0.91, AUC = 0.93 with 95% CI 0.91-0.94, F1-score = 0.94 and PPV = 93.8%. Between classic ML methods, ensemble learners showed high model performance; specifically, the best-performing classifier was the Stack (ST) with ACC = 0.85, AUC = 0.81 with 95% CI 0.8-0.84, F1-score = 0.9, PPV = 90%. CONCLUSIONS: Our results show the potential of ML methods in discerning edema-like lesions, in particular by distinguishing CNO lesions from hematopoietic bone marrow changes in a pediatric population. The Neural Network showed the overall best results, while a Stacking classifier, based on Gradient Boosting and Random Forest as principal estimators and Logistic Regressor as final estimator, achieved the best results between the other ML methods.

Tracheal trifurcation: new cases and review of the literature.

BACKGROUND: Tracheal trifurcation is an uncommon and often unknown type of anomalous tracheobronchial arborization, characterized by three main bronchi originating at the level of the carina. Diagnosis is important due to its clinical implications. OBJECTIVE: To highlight the anatomical, clinical and diagnostic aspects of tracheal trifurcation by reporting our experience and reviewing the literature. MATERIALS AND METHODS: We retrospectively evaluated pediatric patients referred to our institution from January 2018 to May 2020 with a diagnosis of tracheal trifurcation. All patients underwent chest radiographs, computed tomography (CT) (with/without dynamic airway scanning) and bronchoscopy. Clinical and anatomical data were collected. RESULTS: Three patients with tracheal trifurcation were identified (1 female, median age: 7.6±0.4 months). All had associated anomalies: two had tetralogy of Fallot, one with esophageal atresia/tracheoesophageal fistula and one with an atrioventricular septal defect, and the other had skeletal ciliopathy. Chest radiographs were not diagnostic for tracheal trifurcation. Bronchoscopy could not fully evaluate the trachea and main bronchi in two cases. CT detected tracheal trifurcation in all of the patients and also demonstrated other lung parenchymal and congenital anomalies. Two of the three main bronchi were directed to the right lung in all cases. Ostial stenosis of either the central (two patients) or right upper bronchus (one patient) was present. No signs of tracheobronchomalacia were found. CONCLUSION: Tracheal trifurcation is rare and often associated with additional disorders, such as other tracheobronchial anomalies, cardiovascular defects or esophageal malformations, responsible for clinical manifestations and earlier detection. Bronchoscopy is often used for diagnosis, but is invasive and may be incomplete or inconclusive, while CT allows for a noninvasive and correct diagnosis, while also highlighting additional findings in the thorax.

Chronic nonbacterial osteomyelitis - clinical and magnetic resonance imaging features.

BACKGROUND: Chronic nonbacterial osteomyelitis (CNO) is a rare autoinflammatory bone disorder. Little information exists on the use of imaging techniques in CNO. MATERIALS AND METHODS: We retrospectively reviewed clinical and MRI findings in children diagnosed with CNO between 2012 and 2018. Criteria for CNO included unifocal or multifocal inflammatory bone lesions, symptom duration >6 weeks and exclusion of infections and malignancy. All children had an MRI (1.5 tesla) performed at the time of diagnosis; 68 of these examinations were whole-body MRIs including coronal short tau inversion recovery sequences, with additional sequences in equivocal cases. RESULTS: We included 75 children (26 boys, or 34.7%), with mean age 10.5 years (range 0-17 years) at diagnosis. Median time from disease onset to diagnosis was 4 months (range 1.5-72.0 months). Fifty-nine of the 75 (78.7%) children presented with pain, with or without swelling or fever, and 17 (22.7%) presented with back pain alone. Inflammatory markers were raised in 46/75 (61.3%) children. Fifty-four of 75 (72%) had a bone biopsy. Whole-body MRI revealed a median number of 6 involved sites (range 1-27). Five children (6.7%) had unifocal disease. The most commonly affected bones were femur in 46 (61.3%) children, tibia in 48 (64.0%), pelvis in 29 (38.7%) and spine in 20 (26.7%). Except for involvement of the fibula and spine, no statistically significant differences were seen according to gender. CONCLUSION: Nearly one-fourth of the children presented with isolated back pain, particularly girls. The most common sites of disease were the femur, tibia and pelvic bones. Increased inflammatory markers seem to predict the number of MRI sites involved.

Low Dose versus Standard Single Heartbeat Acquisition Coronary Computed Tomography Angiography.

PURPOSE: The aim of this study was to compare image quality and mean radiation dose between two groups of patients undergoing coronary computed tomography angiography (CCTA) using a 640-slice CT scanner with two protocols with different noise level thresholds expressed as standard deviation (SD). MATERIALS AND METHODS: Two-hundred and sixty-eight patients underwent a CCTA with 640 slice CT scanner. In the experimental group (135 patients), an SD 51 protocol was employed; in the control group (133 patients), an SD 33 protocol was used. Mean effective dose and image quality with both objective and subjective measures were assessed. Image quality was subjectively assessed using a five-point scoring system. Segments scoring 2, 3, and 4 were considered having diagnostic quality, while segments scoring 0 and 1 were considered having nondiagnostic quality. Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) between the two groups as well as the effective radiation dose (ED) was finally assessed. RESULTS: Comparative analysis considering diagnostic quality (2, 3, and 4 score) and nondiagnostic (score 0 and 1) quality demonstrated that image quality of SD 51 group is not significantly lower than that of S33 group. The noise was significantly higher in the SD 51 group than in the SD 33 group (P < 0.0001). The SNR and CNR were higher in the SD 33 group than in SD 51 group (P < 0.0001). Mean effective dose was 49% lower in the SD 51 group than in SD 33 group; indeed mean effective dose was 1.43 mSv ± 0.67 in the SD 51 group while it was 2.8 mSv ± 0.57 in the SD 33 group. CONCLUSION: Comparative analysis shows that using a 640-slice CT with a 51 SD protocol, it is possible to reduce the mean radiation dose while maintaining good diagnostic image quality.

An Unusual Case of Ascending Pancreatitis with Mediastinal Involvement: A Case Report with CT and MRI Findings.

Fluid collections are common findings of pancreatitis and spread, more often, along preferential drainage pathways in the abdomen. In some rare cases, fluid collections may spread towards extra-abdominal sites like the mediastinum leading to the formation of mediastinal collections. We present the case of a 52-years-old man with pain in the right upper quadrant of the abdomen and mid-epigastrium lasting for some hours. Laboratory tests suggested a diagnosis of pancreatitis. CT and subsequent MRI revealed changes consistent with acute exacerbation on chronic pancreatitis spreading to the mediastinum and to the greater omentum. The patient received medical treatment and reported gradual improvement in his laboratory results and CT findings.

Magnetic resonance cholangiopancreatography in the diagnosis of haemobilia.

Haemobilia is a rare cause of unrecognized gastrointestinal bleeding and is hard to diagnose. Through the present case report we aim to corroborate magnetic resonance relevance in the evaluation of biliary system and bile features, investigating on its role in patients with acute biliary diseases. We report a case of a Caucasian 48-year-old man who was admitted due to abdominal pain and fever. After an ultrasonography exam we detected multiple cysts in the hepatic left lobe: imaging features, laboratory findings, and patient past work experience (woodcutter) suggested a diagnosis of hepatic Echinococcosis. Once surgery decision was taken, patient underwent an intervention of cystopericystectomy. On the 8th postoperative day, the procedure was complicated by black stool, jaundice, and severe anaemia. Acomputed tomography revealed an inhomogeneous collection with some air bubbles in the area of previous surgical intervention, but it was not able to solve the diagnosis question. At this stage a magnetic resonance study was mandatory. On T2-weighted images we observed an expanse gallbladder with hypointense intraluminal material and a considerable intrahepatic biliary system dilatation due to bloody material. On the basis of these examination results, we supposed haemobilia arising from previous surgical intervention. A therapeutic endoscopic retrograde cholangiopancreatography procedure led to decompression of biliary system through a major papilla sphincterotomy with spillage of bile mixed with blood clots.