Deep learning enables the differentiation between early and late stages of hip avascular necrosis.

OBJECTIVES: To develop a deep learning methodology that distinguishes early from late stages of avascular necrosis of the hip (AVN) to determine treatment decisions. METHODS: Three convolutional neural networks (CNNs) VGG-16, Inception ResnetV2, InceptionV3 were trained with transfer learning (ImageNet) and finetuned with a retrospectively collected cohort of (n = 104) MRI examinations of AVN patients, to differentiate between early (ARCO 1-2) and late (ARCO 3-4) stages. A consensus CNN ensemble decision was recorded as the agreement of at least two CNNs. CNN and ensemble performance was benchmarked on an independent cohort of 49 patients from another country and was compared to the performance of two MSK radiologists. CNN performance was expressed with areas under the curve (AUC), the respective 95% confidence intervals (CIs) and precision, and recall and f1-scores. AUCs were compared with DeLong's test. RESULTS: On internal testing, Inception-ResnetV2 achieved the highest individual performance with an AUC of 99.7% (95%CI 99-100%), followed by InceptionV3 and VGG-16 with AUCs of 99.3% (95%CI 98.4-100%) and 97.3% (95%CI 95.5-99.2%) respectively. The CNN ensemble the same AUCs Inception ResnetV2. On external validation, model performance dropped with VGG-16 achieving the highest individual AUC of 78.9% (95%CI 51.6-79.6%) The best external performance was achieved by the model ensemble with an AUC of 85.5% (95%CI 72.2-93.9%). No significant difference was found between the CNN ensemble and expert MSK radiologists (p = 0.22 and 0.092 respectively). CONCLUSION: An externally validated CNN ensemble accurately distinguishes between the early and late stages of AVN and has comparable performance to expert MSK radiologists. CLINICAL RELEVANCE STATEMENT: This paper introduces the use of deep learning for the differentiation between early and late avascular necrosis of the hip, assisting in a complex clinical decision that can determine the choice between conservative and surgical treatment. KEY POINTS: • A convolutional neural network ensemble achieved excellent performance in distinguishing between early and late avascular necrosis. • The performance of the deep learning method was similar to the performance of expert readers.

Performance of Ultrasonography in the Diagnosis of Acute Colonic Diverticulitis.

OBJECTIVES: Computed tomography is regarded as the reference-standard imaging modality for the assessment of acute left-sided colonic diverticulitis (ALCD). However, its utility may be impaired by cost issues, limited availability, radiation exposure, and contrast-related adverse effects. Ultrasonography is increasingly advocated as an alternative technique for evaluating ALCD, although there is variation regarding its accuracy in disease diagnosis and staging and in determining alternative diagnoses. The aim of this study was to assess the performance of ultrasonography in diagnosing ALCD, differentiating complicated from non-complicated disease and defining alternative diseases related to left lower quadrant pain. METHODS: Within a 2-year period, all consecutive adult patients with clinically suspected ALCD and available abdominal computed tomography were prospectively evaluated and planned to undergo an abdominal ultrasonographic examination, tailored to the assessment of left lower quadrant. Computed tomography (CT) was regarded as the reference standard. RESULTS: A total of 132 patients (60 males, 72 females; mean age: 61.3 ± 11 years) were included. The sensitivity, specificity, and area under curve of ultrasonography for diagnosing ALCD were 88.6, 84.9, and 86.8%, with positive and negative predictive values of 89.7 and 83.3%, respectively. The method had sensitivity, specificity, and area under curve of 77.8, 100, and 88.9%, respectively, for defining complicated disease. The area under the curve for the identification of alternative diseases in patients with left lower quadrant pain was 90.9%. CONCLUSIONS: Ultrasonography has high diagnostic accuracy for diagnosing ALCD, differentiating complicated from non-complicated disease and establishing alternative diagnoses related to left lower quadrant pain. A low threshold to get a CT should be maintained as not to miss cases that may mimic ALCD.

Performance of thoracic ultrasonography compared with chest radiography for the detection of rib fractures using computed tomography as a reference standard.

OBJECTIVE: Although there is growing evidence that ultrasonography is superior to X-ray for rib fractures' detection, X-ray is still indicated as the most appropriate method. This has partially been attributed to a lack of studies using an appropriate reference modality. We aimed to compare the diagnostic accuracy of ultrasonography and X-ray in the detection of rib fractures, considering CT as the reference standard. MATERIALS AND METHODS: Within a 2.5-year period, all consecutive patients with clinically suspected rib fracture(s) following blunt chest trauma and available posteroanterior/anteroposterior X-ray and thoracic CT were prospectively studied and planned to undergo thoracic ultrasonography, by a single operator. All imaging examinations were evaluated for cortical rib fracture(s), and their location was recorded. The cartilaginous rib portions were not assessed. CTs and X-rays were evaluated retrospectively. Concomitant thoracic/extra-thoracic injuries were assessed on CT. Comparisons were performed with the Mann-Whitney U test and Fisher's exact test. RESULTS: Fifty-nine patients (32 males, 27 females; mean age, 53.1 ± 16.6 years) were included. CT, ultrasonography, and X-ray (40 posteroanterior/19 anteroposterior views) diagnosed 136/122/42 rib fractures in 56/54/27 patients, respectively. Ultrasonography and X-ray had sensitivity of 100%/40% and specificity of 89.7%/30.9% for rib fractures' detection. Ultrasound accuracy was 94.9% compared to 35.4% for X-rays (P < .001) in detecting individual rib fractures. Most fractures involved the 4th-9th ribs. Upper rib fractures were most commonly overlooked on ultrasonography. Thoracic cage/spine fractures and haemothorax represented the most common concomitant injuries. CONCLUSION: Ultrasonography appeared to be superior to X-ray for the detection of rib fractures with regard to a reference CT.

Ultrasound-guided hydrodilatation for adhesive capsulitis: capsule-preserving versus capsule-rupturing technique.

OBJECTIVE: To compare the clinical efficacy of capsule-rupturing versus capsule-preserving ultrasound-guided hydrodilatation in patients with shoulder adhesive capsulitis (AC). To determine potential factors affecting the outcome over a 6-month follow-up. MATERIALS AND METHODS: Within a 2-year period, 149 consecutive patients with AC were prospectively enrolled and allocated into (i) group-CR, including 39 patients receiving hydrodilatation of the glenohumeral joint (GHJ) with capsular rupture and (ii) group-CP, including 110 patients treated with GHJ hydrodilatation with capsular preservation. Demographics, affected shoulder, and AC grade were recorded. Disabilities of the Arm, Shoulder and Hand (DASH) questionnaire and visual analog scale (VAS) were used for clinical assessment at baseline/1/3/6 months. Comparisons were performed with Mann-Whitney U test and Kolmogorov-Smirnov test. Linear regression was used to identify predictors of outcome. P value < 0.05 defined significance. RESULTS: DASH and VAS scores in both groups improved significantly compared to baseline (P < 0.001) and were significantly lower in the CP compared to CR group at all time-points following intervention (P < 0.001). Capsule rupture was a significant predictor of DASH score at all time-points (P < 0.001). DASH scores correlated to initial DASH score at all time-points (P < 0.001). DASH/VAS scores at 1 month were correlated to the AC grade (P = 0.025/0.02). CONCLUSION: GHJ hydrodilatation results in pain elimination and functional improvement till the mid-term in patients with AC, with improved outcome when adopting the capsule-preserving compared to the capsule-rupturing technique. Higher initial DASH score is predictive of impaired functionality in the mid-term.

Application of an in-hospital, surgeon-led anti-osteoporotic medication algorithm in patients with hip fractures improves persistence to medication and can prevent the second fragility fracture.

INTRODUCTION: Secondary fracture prevention is an essential part of hip fracture treatment. Despite this, many patients are discharged without the appropriate anti-osteoporotic medication. The aim of this study is to report the outcomes of the application of an in-hospital, surgeon-led anti-osteoporotic medication algorithm to patients with hip fractures. MATERIALS AND METHODS: This prospective cohort study followed patients with hip fractures who were treated at a tertiary referral hospital between 2020 and 2022. At discharge, anti-osteoporotic medication according to the Arbeitsgemeinschaft für Osteosynthesefragen (AO) Foundation algorithm was prescribed to all patients. Multivariate Cox regression analysis was used to investigate the risks of non-persistence to medication and of secondary fracture. RESULTS: Two hundred thirteen consecutive patients were prospectively followed. Mean follow-up was 17.2 ± 7.1 months. Persistence to medication at 2 years was 58% (95%CI 51-65%). A secondary osteoporotic fracture occurred in 1/126 (0.8%) persistent patients and 9/87 (11.4%) non-persistent patients. Multivariable Cox regression analysis confirmed that persistence to medication was significantly associated with a lower risk of secondary fracture (cause-specific hazard ratio [csHR] 0.05; 95%CI 0.01-0.45; p = 0.007). CONCLUSION: The application of the surgeon-led AO Foundation algorithm enables the in-hospital initiation of anti-osteoporotic treatment, leading to better persistence to medication and decreased incidence of secondary osteoporotic fractures.

Post-mortem CT radiomics for the prediction of time since death.

OBJECTIVES: Post-mortem interval (PMI) estimation has long been relying on sequential post-mortem changes on the body as a function of extrinsic, intrinsic, and environmental factors. Such factors are difficult to account for in complicated death scenes; thus, PMI estimation can be compromised. Herein, we aimed to evaluate the use of post-mortem CT (PMCT) radiomics for the differentiation between early and late PMI. METHODS: Consecutive whole-body PMCT examinations performed between 2016 and 2021 were retrospectively included (n = 120), excluding corpses without an accurately reported PMI (n = 23). Radiomics data were extracted from liver and pancreas tissue and randomly split into training and validation sets (70:30%). Following data preprocessing, significant features were selected (Boruta selection) and three XGBoost classifiers were built (liver, pancreas, combined) to differentiate between early (< 12 h) and late (> 12 h) PMI. Classifier performance was assessed with receiver operating characteristics (ROC) curves and areas under the curves (AUC), which were compared by bootstrapping. RESULTS: A total of 97 PMCTs were included, representing individuals (23 females and 74 males) with a mean age of 47.1 ± 23.38 years. The combined model achieved the highest AUC reaching 75% (95%CI 58.4-91.6%) (p = 0.03 compared to liver and p = 0.18 compared to pancreas). The liver-based and pancreas-based XGBoost models achieved AUCs of 53.6% (95%CI 34.8-72.3%) and 64.3% (95%CI 46.7-81.9%) respectively (p > 0.05 for the comparison between liver- and pancreas-based models). CONCLUSION: The use of radiomics analysis on PMCT examinations differentiated early from late PMI, unveiling a novel image-based method with important repercussions in forensic casework. CLINICAL RELEVANCE STATEMENT: This paper introduces the employment of radiomics in forensic diagnosis by presenting an effective automated alternative method of estimating post-mortem interval from targeted tissues, thus paving the way for improvement in speed and quality of forensic investigations. KEY POINTS: • A combined liver-pancreas radiomics model differentiated early from late post-mortem intervals (using a 12-h threshold) with an area under the curve of 75% (95%CI 58.4-91.6%). • XGBoost models based on liver-only or pancreas-only radiomics demonstrated inferior performance to the combined model in predicting the post-mortem interval.

Radiotranscriptomics of non-small cell lung carcinoma for assessing high-level clinical outcomes using a machine learning-derived multi-modal signature.

BACKGROUND: Multi-omics research has the potential to holistically capture intra-tumor variability, thereby improving therapeutic decisions by incorporating the key principles of precision medicine. The purpose of this study is to identify a robust method of integrating features from different sources, such as imaging, transcriptomics, and clinical data, to predict the survival and therapy response of non-small cell lung cancer patients. METHODS: 2996 radiomics, 5268 transcriptomics, and 8 clinical features were extracted from the NSCLC Radiogenomics dataset. Radiomics and deep features were calculated based on the volume of interest in pre-treatment, routine CT examinations, and then combined with RNA-seq and clinical data. Several machine learning classifiers were used to perform survival analysis and assess the patient's response to adjuvant chemotherapy. The proposed analysis was evaluated on an unseen testing set in a k-fold cross-validation scheme. Score- and concatenation-based multi-omics were used as feature integration techniques. RESULTS: Six radiomics (elongation, cluster shade, entropy, variance, gray-level non-uniformity, and maximal correlation coefficient), six deep features (NasNet-based activations), and three transcriptomics (OTUD3, SUCGL2, and RQCD1) were found to be significant for therapy response. The examined score-based multi-omic improved the AUC up to 0.10 on the unseen testing set (0.74 ± 0.06) and the balance between sensitivity and specificity for predicting therapy response for 106 patients, resulting in less biased models and improving upon the either highly sensitive or highly specific single-source models. Six radiomics (kurtosis, GLRLM- and GLSZM-based non-uniformity from images with no filtering, biorthogonal, and daubechies wavelets), seven deep features (ResNet-based activations), and seven transcriptomics (ELP3, ZZZ3, PGRMC2, TRAK1, ATIC, USP7, and PNPLA2) were found to be significant for the survival analysis. Accordingly, the survival analysis for 115 patients was also enhanced up to 0.20 by the proposed score-based multi-omics in terms of the C-index (0.79 ± 0.03). CONCLUSIONS: Compared to single-source models, multi-omics integration has the potential to improve prediction performance, increase model stability, and reduce bias for both treatment response and survival analysis.

Imaging of Anatomical Variants Around the Hip.

Considering the current widespread use of imaging as an integral part of managing hip pain, variable hip geometries and anatomical variants are increasingly being detected. These variants are commonly found in the acetabulum and proximal femur, as well as the surrounding capsule-labral tissues. The morphology of specific anatomical spaces confined by the proximal femur and the bony pelvis may also vary significantly among individuals. Familiarity with the spectrum of imaging appearances of the hip is necessary to identify variant hip morphologies with or without potential clinical relevance and reduce an unnecessary work-up and overdiagnosis. We describe anatomical variations and variable morphologies of the bony structures comprising the hip joint and the soft tissues, around the hip. The potential clinical significance of these findings is further analyzed in conjunction with the patient's profile.

Ultrasound-Guided Hydrodistension for Adhesive Capsulitis: Is There Any Adjunct Effect of Immediate Post-Procedural Manipulation Over Instructed Physical Therapy?

OBJECTIVES: To compare the additive value of immediate post-procedural manipulation versus physiotherapy, following ultrasound (US)-guided hydrodistention of the glenohumeral joint (GHJ) in patients with adhesive capsulitis (AC) and define predictors of outcome. METHODS: Within a 19-month period, 161 consecutive patients with AC were prospectively enrolled and allocated to two groups according to treatment, based on patients' individual preferences: 1) group-I, US-guided hydrodistension plus immediate post-procedural manipulations and 2) group-II, US-guided hydrodistension plus supervised physiotherapy program. The Disabilities of the Arm, Shoulder, and Hand (DASH) questionnaire and a visual analog scale (VAS) were used for clinical assessment at baseline (immediately after treatment), 1, 3, and 6 months. Comparisons were performed with Mann-Whitney U test and Kolmogorov-Smirnov test. Linear regression was used to identify predictors of outcome. P value <.05 defined significance. RESULTS: GHJ hydrodistension with manipulation or physiotherapy was linked to clinical improvement at all follow-up time-points. DASH scores of group-I remained constantly lower than DASH scores of group-II at all time-points (P < .001). VAS scores were lower in group-I than group-II at 1 and 3 months (P < .001 and P = .0019, respectively). Both groups had improved to a similar degree with respect to pain at 6 months (P = .29). The performance of post-interventional manipulations was predictive of improved shoulder functionality (as assessed with DASH scores) at all time-points, while low-grade disease and milder symptoms at presentation were associated with improved short-term pain. CONCLUSIONS: Immediate post-procedural manipulations appeared to be superior to physiotherapy following GHJ hydrodistension for AC in terms of shoulder functionality during a 6-month follow-up period. Post-interventional manipulations, the stage of AC and lower DASH and VAS scores at presentations were predictive of improved outcome.

Ultrasound-guided hydrodistension for adhesive capsulitis: a longitudinal study on the effect of diabetes on treatment outcomes.

OBJECTIVE: The effect of diabetes on adhesive capsulitis (AC) and its impact on the outcomes of ultrasound (US)-guided hydrodistension of the glenohumeral joint are still unclear. We aimed to identify predictors of US-guided hydrodistension outcomes, while assessing the performance of the method in diabetic compared to non-diabetic patients. MATERIALS AND METHODS: A total of 135 patients with AC who underwent US-guided hydrodistension were prospectively included. Demographics and factors linked to chronic inflammation and diabetes were recorded and patients were followed-up for 6 months. Functionality and pain were evaluated with the Disabilities of the Arm, Shoulder and Hand (DASH) and the Visual Analogue Scale (VAS) score. Statistical analysis was performed with Mann-Whitney U test, linear, and binary logistic regression. RESULTS: Diabetes was identified in 25/135 patients (18.5%). Diabetic patients had worse DASH and VAS score at presentation (P < 0.0001) and presented with a higher grade of AC (P < 0.0001) and lower range of motion (P < 0.01) compared to non-diabetics. Higher DASH (P = 0.025) and VAS scores (P = 0.039) at presentation were linked to worse functionality at 6 months. Presence and duration of diabetes, and the number of hydrodistension repeats, correlated with worse VAS and DASH scores at 6 months. The number of procedure repeats was the only independent predictor of complete pain resolution at 6 months (OR 0.418, P = 003). CONCLUSION: Diabetes is linked to more severe AC at presentation and worse outcomes in patients undergoing US-guided hydrodistension. In resistant cases, repeating the intervention is independently linked to worse outcomes for at least 6 months post-intervention.

Prediction of abdominal aortic aneurysm growth by artificial intelligence taking into account clinical, biologic, morphologic, and biomechanical variables.

OBJECTIVES: To develop a prediction model that could risk stratify abdominal aortic aneurysms (AAAs) into high and low growth rate groups, using machine learning algorithms based on variables from different pathophysiological fields. METHODS: A cohort of 40 patients with small AAAs (maximum diameter 32-53 mm) who had at least an initial and a follow-up CT scan (median follow-up 12 months, range 3-36 months) were included. 29 input variables from clinical, biological, morphometric, and biomechanical pathophysiological aspects extracted for predictive modeling. Collected data were used to build two supervised machine learning models. A gradient boosting (XGboost) and a support vector machines (SVM) algorithm were trained with 60% and tested with 40% of the data to predict which AAA would achieve a growth rate higher than the median of our study cohort. Receiver operating characteristics (ROC) curves and areas under the curve (AUC) were used for the evaluation of the developed algorithms. RESULTS: XGboost achieved the highest AUC in predicting high compared to low AAA growth rate with an AUC of 81.2% (95% CI from 61.1 to 100%). SVM achieved the second highest performance with an AUC of 68.8% (95% CI from 46.5 to 91%). Based on the best performing algorithm, variable importance was estimated. Diameter-diameter ratio (maximum diameter/neck diameter), Tortuosity from Renal arteries to aortic bifurcation, and maximum thickness of the intraluminal thrombus were found to be the most important factors for model predictions. Other factors were also found to play a significant but less important role. CONCLUSIONS: A prediction model that can risk stratify AAAs into high and low growth rate groups could be developed by analyzing several factors implicated in the multifactorial pathophysiology of this disease, with the use of machine learning algorithms. Future studies including larger patient cohorts and implementing additional risk markers may aid in the establishment of such methodology during AAA rupture risk estimation.

Machine learning identifies factors related to early joint space narrowing in dysplastic and non-dysplastic hips.

OBJECTIVES: To utilise machine learning, unsupervised clustering and multivariate modelling in order to predict severe early joint space narrowing (JSN) from anatomical hip parameters while identifying factors related to joint space width (JSW) in dysplastic and non-dysplastic hips. METHODS: A total of 507 hip CT examinations of patients 20-55 years old were retrospectively examined, and JSW, center-edge (CE) angle, alpha angle, anterior acetabular sector angle (AASA), and neck-shaft angle (NSA) were recorded. Dysplasia and severe JSN were defined with CE angle < 25o and JSW< 2 mm, respectively. A random forest classifier was developed to predict severe JSN based on anatomical and demographical data. Multivariate linear regression and two-step unsupervised clustering were performed to identify factors linked to JSW. RESULTS: In dysplastic hips, lateral or anterior undercoverage alone was not correlated to JSN. AASA (p < 0.005) and CE angle (p < 0.032) were the only factors significantly correlated with JSN in dysplastic hips. In non-dysplastic hips, JSW was inversely correlated to CE angle, AASA, and age and positively correlated to NSA (p < 0.001). A random forest classifier predicted severe JSN (AUC 69.9%, 95%CI 47.9-91.8%). TwoStep cluster modelling identified two distinct patient clusters one with low and one with normal JSW and different anatomical characteristics. CONCLUSION: Machine learning predicted severe JSN and identified population characteristics related to normal and abnormal joint space width. Dysplasia in one plane was found to be insufficient to cause JSN, highlighting the need for hip anatomy assessment on multiple planes. KEY POINTS: • Neither anterior nor lateral acetabular dysplasia was sufficient to independently reduce joint space width in a multivariate linear regression model of dysplastic hips. • A random forest classifier was developed based on measurements and demographic parameters from 507 hip joints, achieving an area under the curve of 69.9% in the external validation set, in predicting severe joint space narrowing based on anatomical hip parameters and age. • Unsupervised TwoStep cluster analysis revealed two distinct population groups, one with low and one with normal joint space width, characterised by differences in hip morphology.

Research in Musculoskeletal Radiology: Setting Goals and Strategic Directions.

The future of musculoskeletal (MSK) radiology is being built on research developments in the field. Over the past decade, MSK imaging research has been dominated by advancements in molecular imaging biomarkers, artificial intelligence, radiomics, and novel high-resolution equipment. Adequate preparation of trainees and specialists will ensure that current and future leaders will be prepared to embrace and critically appraise technological developments, will be up to date on clinical developments, such as the use of artificial tissues, will define research directions, and will actively participate and lead multidisciplinary research. This review presents an overview of the current MSK research landscape and proposes tangible future goals and strategic directions that will fortify the future of MSK radiology.

Introduction of a new simple dynamic phantom for physical BOLD effect simulation.

OBJECTIVE: To propose a new method of simulating the BOLD contrast using a dynamic, easy to construct and operate, low-cost physical phantom. MATERIALS AND METHODS: A structure of thin pipelines passing through a gel volume was used to simulate blood vessels in human tissue. Quantitative T2*, R2* measurements were used to study the signal change of the phantom. BOLD fMRI experiments and analysis were performed to evaluate its potential use as an fMRI simulator. RESULTS: Experimental T2*, R2* measurements showed similar behavior with published references. BOLD contrast was successfully achieved with the proposed method. In addition, there were several proposed parameters, like the angle of the phantom relative to B0, which can easily adjust the signal change and the activation area. Coefficients of variation showed good reproducibility within a month period. Statistical t maps were produced with in-house software for the BOLD measurements. DISCUSSION: T2*maps and BOLD images confirm the potential use of this phantom as an fMRI simulator and also as a tool for studying sensitivity and specificity of BOLD sequences/algorithms.

MRI findings of acute anterior instability of the knee in the absence of recent trauma.

BACKGROUND: Anterior knee instability is usually encountered in the context of trauma, with the clinical examination and imaging focusing on anterior cruciate ligament (ACL) disruption. Limited data exist on magnetic resonance imaging (MRI) of acute anterior knee instability in the absence of recent trauma. PURPOSE: To provide the first comprehensive account of MRI findings in acute anterior knee laxity in the absence of acute trauma and to evaluate predictors of ACL integrity and pain. MATERIAL AND METHODS: A total of 84 consecutive patients with non-traumatic knee instability were prospectively studied. Instability was assessed with Lachman's, pivot shift, and Lelli's tests. MRI findings were recorded, and ACL integrity was surgically confirmed in all 24 cases of MRI suggesting tear and in 21/60 cases of MRI suggesting no tear. Binary logistic regression models were used to identify predictors of ACL tears and pain, and Mann-Whitney U test served for comparisons between continuous variables. The study was approved by the institutional review board. RESULTS: Osteoarthritis and notch bony outgrowth (NBO) were present in 44% and 42.9% of all knees, respectively. NBO did not correlate with osteoarthritis (P = 0.606). NBO (odds ratio [OR] = 4.157; P = 0.016) and ACL grafts (OR = 9.277; P = 0.01) predisposed to non-traumatic ACL tears (torn in 28.6% of total cases). Presence of osteoarthritis was predictive of pain (OR = 17.671; P < 0.001). CONCLUSION: We present a comprehensive analysis of MRI findings in clinically significant non-traumatic anterior instability, showing that NBO and ACL grafts predispose in non-traumatic ACL tears, whereas osteoarthritis is the only predictor of pain.

Radiomics and machine learning to predict aggressive type 2 endoleaks after endovascular aneurysm repair: a proof of concept.

BACKGROUND: Persistent type 2 endoleaks (T2EL) require lifelong surveillance to avoid potentially life-threatening complications. PURPOSE: To evaluate the performance of radiomic features (RF) derived from computed tomography angiography (CTA), for differentiating aggressive from benign T2ELs after endovascular aneurysm repair (EVAR). MATERIAL AND METHODS: A prospective study was performed on patients who underwent EVAR from January 2018 to January 2020. Analysis was performed in patients who were diagnosed with T2EL based on the CTA of the first postoperative month and were followed at six months and one year. Patients were divided into two groups according to the change of aneurysm sac dimensions. Segmentation of T2ELs was performed and RF were extracted. Feature selection for subsequent machine-learning analysis was evaluated by means of artificial intelligence. Two support vector machines (SVM) classifiers were developed to predict the aneurysm sac dimension changes at one year, utilizing RF from T2EL at one- and six-month CTA scans, respectively. RESULTS: Among the 944 initial RF of T2EL, 58 and 51 robust RF from the one- and six-month CTA scans, respectively, were used for the machine-learning model development. The SVM classifier trained on one-month signatures was able to predict sac expansion at one year with an area under curve (AUC) of 89.3%, presenting 78.6% specificity and 100% sensitivity. Similarly, the SVM classifier developed with six-month radiomics data showed an AUC of 95.5%, specificity of 90.9%, and sensitivity of 100%. CONCLUSION: Machine-learning algorithms utilizing CTA-derived RF may predict aggressive T2ELs leading to aneurysm sac expansion after EVAR.

Performance of Lung Ultrasound for Monitoring Interstitial Lung Disease.

OBJECTIVES: In this study, we sought to assess the validity of lung ultrasound (LUS) during the follow-up of patients with a wide spectrum of interstitial lung diseases (ILDs). METHODS: Twenty-four patients (13 males, 11 females; mean age ± SD, 65.4 ± 14.3 years; age range, 40-84 years) with a diagnosis of ILDs who were admitted to the Interstitial Lung Disease Unit were prospectively enrolled. Patients were examined with a 56-lung intercostal space LUS protocol in lateral decubitus position, at baseline, 6-months, and 1-year. The LUS score was defined as the sum of B-lines counted in each intercostal space. All patients underwent complete pulmonary function tests at baseline and follow-up time-points. High-resolution computed tomography (HRCT) was performed at baseline and during follow-up, according to personalized patients' needs. All HRCT studies were graded according to the Warrick scoring system (WS). RESULTS: Pooled data analysis showed a significant correlation between WS and LUS scores (P < .001). For separate time-point analysis, a significant correlation between LUS scores and WS was found at baseline (P < .001) and 1 year (P = .005). LUS scores negatively correlated with alveolar volume (VA) (P < .046) and diffusing capacity for carbon monoxide (DLCO) (P < .001) at 6 months and with transfer coefficient of the lung for carbon monoxide (KCO) (P < .031) and DLCO (P = .002) at 12-months. A multivariate regression model showed DLCO to be an independent predictor of LUS score at 1 year (P = .026). CONCLUSIONS: Our results highlight the validity and potential applicability of LUS for disease monitoring in a wide spectrum of ILDs.

Predicting long-term outcomes of ultrasound-guided percutaneous irrigation of calcific tendinopathy with the use of machine learning.

OBJECTIVE: To evaluate the performance of two machine learning models in predicting the long-term complete pain resolution in patients undergoing ultrasound-guided percutaneous irrigation of calcific tendinopathy (US-PICT). MATERIALS AND METHODS: Within a 3-year period, 100 consecutive patients who underwent US-PICT for rotator cuff disease were prospectively enrolled. The location, maximum diameter, and type of each calcification were recorded. The degree of calcium retrieval was graded as complete or incomplete. Shoulder pain was assessed with the visual analogue scale (VAS) at baseline, 1-week, 1-month, and 1-year post-treatment. Measurements related to procedural details, patient, and calcification characteristics were used to construct a machine learning model for the prediction of pain at 1-year post-US-PICT. Two distinct models were built, one including VAS data at 1 week and another additionally including pain data at 1-month post-treatment. Variable importance analysis was performed for the 1-week model. Model performance was evaluated by using receiver operating characteristics (ROC) curves and the respective areas under the curve (AUC). RESULTS: The model exhibited an AUC of 69.2% for the prediction of complete pain resolution at 1 year. The addition of VAS scores at 1 month did not significantly alter the performance of the algorithm. Age and baseline VAS scores were the most important variables for classification performance. CONCLUSION: The presented machine learning model exhibited an AUC of almost 70% in predicting complete pain resolution at 1 year. Pain data at 1 month do not appear to improve the performance of the algorithm.

Ultrasound-guided percutaneous irrigation of calcific tendinopathy: redefining predictors of treatment outcome.

OBJECTIVES: To identify prognostic factors affecting the clinical outcome in patients treated with rotator cuff ultrasound-guided percutaneous irrigation of calcific tendinopathy (US-PICT), by evaluating the degree of calcium removal, the size and consistency of calcific deposits, and baseline level of shoulder pain and functionality. METHODS: From January 2017 to December 2019, 79 patients (23 males, 56 females; mean age, 45.7 years) who underwent US-PICT were prospectively enrolled. The calcifications' location, consistency, and size were evaluated. For US-PICT, local anesthesia, lavage of calcific material, and intrabursal steroid injection were performed. The degree of calcium removal was graded as total/partial. Shoulder pain and functionality were assessed with the visual analogue scale (VAS) in all and Constant score (CS) in a subset of patients, respectively, at 4 time-points. Mann-Whitney U test, Fisher's test, and linear and binary logistic regression were utilized for analysis. RESULTS: Pain improvement correlated with the presence of larger calcifications and lower baseline VAS score, at 1 week (p = 0.001, p < 0.001, respectively) and 1 year (p < 0.001, p = 0.002, respectively). Improved functionality correlated with total calcification retrieval, higher baseline CS, and fluid/soft calcific consistency at 1 week (p = 0.013, p = 0.003, p = 0.019, respectively). Increased calcification size, cystic appearance, and lower baseline VAS scores independently predicted complete pain resolution at 1 year. CONCLUSION: Large calcifications and low-grade pain at baseline correlated with short- and long-term pain improvement. The degree of calcium removal did not impact pain or functional improvement beyond 1 week. Increased calcification size, cystic appearance, and low-grade baseline pain predicted complete pain recovery at 1 year. KEY POINTS: • The presence of larger calcifications and lower-grade baseline pain appear to correlate with pain improvement at 1 week and 1 year after ultrasound-guided irrigation of rotator cuff calcific tendinopathy (US-PICT). • Total calcification retrieval, less affected baseline shoulder functionality, and presence of fluid/soft consistency of calcific deposits appear to correlate with improved shoulder functionality at 1 week post-treatment. • Baseline pain intensity and calcifications' morphologic characteristics, but not the degree of calcium retrieval, represent predictors of complete pain recovery at 1 year after US-PICT.

The Lisbon Agreement on femoroacetabular impingement imaging-part 2: general issues, parameters, and reporting.

OBJECTIVES: Imaging assessment for the clinical management of femoroacetabular impingement (FAI) is controversial because of a paucity of evidence-based guidance and notable variability among practitioners. Hence, expert consensus is needed because standardised imaging assessment is critical for clinical practice and research. We aimed to establish expert-based statements on FAI imaging by using formal methods of consensus building. METHODS: The Delphi method was used to formally derive consensus among 30 panel members from 13 countries. Forty-four questions were agreed upon, and relevant seminal literature was circulated and classified in major topics to produce answering statements. The level of evidence was noted for all statements, and panel members were asked to score their level of agreement (0-10). This is the second part of a three-part consensus series and focuses on 'General issues' and 'Parameters and reporting'. RESULTS: Forty-seven statements were generated and group consensus was reached for 45. Twenty-five statements pertaining to 'General issues' (9 addressing diagnosis, differential diagnosis, and postoperative imaging) and 'Parameters and reporting' (16 addressing femoral/acetabular parameters) were produced. CONCLUSIONS: The available evidence was reviewed critically, recommended criteria for diagnostic imaging highlighted, and the roles/values of different imaging parameters assessed. Radiographic evaluation (AP pelvis and a Dunn 45° view) is the cornerstone of hip-imaging assessment and the minimum imaging study that should be performed when evaluating adult patients for FAI. In most cases, cross-sectional imaging is warranted because MRI is the 'gold standard' imaging modality for the comprehensive evaluation, differential diagnosis assessment, and FAI surgical planning. KEY POINTS: • Diagnostic imaging for FAI is not standardised due to scarce evidence-based guidance on which imaging modalities and diagnostic criteria/parameters should be used. • Radiographic evaluation is the cornerstone of hip assessment and the minimum study that should be performed when assessing suspected FAI. Cross-sectional imaging is justified in most cases because MRI is the 'gold standard' modality for comprehensive FAI evaluation. • For acetabular morphology, coverage (Wiberg's angle and acetabular index) and version (crossover, posterior wall, and ischial spine signs) should be assessed routinely. On the femoral side, the head-neck junction morphology (α° and offset), neck morphology (NSA), and torsion should be assessed.