Imaging-Based Deep Learning for Predicting Desmoid Tumor Progression.

Desmoid tumors (DTs) are non-metastasizing and locally aggressive soft-tissue mesenchymal neoplasms. Those that become enlarged often become locally invasive and cause significant morbidity. DTs have a varied pattern of clinical presentation, with up to 50-60% not growing after diagnosis and 20-30% shrinking or even disappearing after initial progression. Enlarging tumors are considered unstable and progressive. The management of symptomatic and enlarging DTs is challenging, and primarily consists of chemotherapy. Despite wide surgical resection, DTs carry a rate of local recurrence as high as 50%. There is a consensus that contrast-enhanced magnetic resonance imaging (MRI) or, alternatively, computerized tomography (CT) is the preferred modality for monitoring DTs. Each uses Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST 1.1), which measures the largest diameter on axial, sagittal, or coronal series. This approach, however, reportedly lacks accuracy in detecting response to therapy and fails to detect tumor progression, thus calling for more sophisticated methods. The objective of this study was to detect unique features identified by deep learning that correlate with the future clinical course of the disease. Between 2006 and 2019, 51 patients (mean age 41.22 ± 15.5 years) who had a tissue diagnosis of DT were included in this retrospective single-center study. Each had undergone at least three MRI examinations (including a pretreatment baseline study), and each was followed by orthopedic oncology specialists for a median of 38.83 months (IQR 44.38). Tumor segmentations were performed on a T2 fat-suppressed treatment-naive MRI sequence, after which the segmented lesion was extracted to a three-dimensional file together with its DICOM file and run through deep learning software. The results of the algorithm were then compared to clinical data collected from the patients' medical files. There were 28 males (13 stable) and 23 females (15 stable) whose ages ranged from 19.07 to 83.33 years. The model was able to independently predict clinical progression as measured from the baseline MRI with an overall accuracy of 93% (93 ± 0.04) and ROC of 0.89 ± 0.08. Artificial intelligence may contribute to risk stratification and clinical decision-making in patients with DT by predicting which patients are likely to progress.

Novel Treatment Protocol for Combined Tear Trough Ligament Stretching and Injection.

BACKGROUND: Complex anatomical changes have been the main challenges for optimal treatment results of tear trough deformities through hyaluronic acid (HA) injections. The authors present a novel technique consisting of a preinjection tear trough ligament stretching (TTLS-I) leading to its release, and compared its efficacy, safety, and patient satisfaction to tear trough deformity injection (TTDI). METHODS: This was a 4-year, retrospective, single-center cohort study of 83 TTLS-I patients, with a follow-up period of 1 year. One hundred thirty-five TTDI patients served as a comparison group. Outcome analyses included the analysis of possible risk factors for adverse outcome and comparative statistics between the complication and satisfaction rates of the two groups. RESULTS: TTLS-I patients received significantly less HA (0.3 cc; range, 0.2 to 0.3 cc) than TTDI patients did (0.6 cc; range, 0.6 to 0.8 cc; P < 0.001). The injected HA amount was a significant predictive factor for complications ( P < 0.05). Complication rates assessed during the follow-up visit for hematomas, edema, and the need for corrective hyaluronidase injection were low in both groups, with no significant differences between the groups. TTDI patients had significantly higher rates (5.1%) of lump surface irregularities during follow-up, compared with 0% in the TTLS-I group ( P < 0.05). After 1 year of follow-up, 98.8% of TTLS-I patients were satisfied, whereas 95.6% of TTDI patients were satisfied, with no significant difference between groups. CONCLUSIONS: TTLS-I is a novel, safe, and effective treatment method, necessitating significantly less HA compared with TTDI. Moreover, it leads to very high satisfaction rates and very low complication rates. CLINICAL QUESTION/LEVEL OF EVIDENCE: Therapeutic, III.

Sarcopenia is a Predictor for Adverse Clinical Outcome in Pediatric Inflammatory Bowel Disease.

OBJECTIVES: Inflammatory bowel disease (IBD) has a high impact on nutritional status. Sarcopenia is related to higher risk of surgery and rescue therapy in adults with IBD; however, comparable data in pediatric populations are scarce. We evaluated muscle mass as a predictor of disease outcome in pediatric IBD. METHODS: All pediatric IBD patients who underwent magnetic resonance enterography (MRE) during 2008 to 2019 were included. Muscle mass was assessed by measuring the area of the psoas muscle at the upper level of L3 on MRE. The psoas area divided by the body surface area (BSA) yielded the psoas index. Clinical and radiological data, including disease location, activity, course, and medications were documented. The control group included non-IBD children who underwent an MR imaging study. RESULTS: We enrolled 101 IBD patients, 69 (68.3%) with Crohn disease (CD) and 32 (31.7%) with ulcerative colitis (UC) (mean age 15.03 ±â€Š3.27 years). The psoas index was significantly lower in the IBD patients compared with the 87 controls (326 vs 528, respectively, P < 0.001). Patients with a psoas index in the lowest quartile had significantly higher risk for biologic therapy (multivariate analysis, hazard ratio [HR] = 12.1, P = 0.046) and disease exacerbation (HR = 9, P = 0.047) independently of body mass index, compared with patients with a psoas index in the uppermost quartile. CONCLUSIONS: Sarcopenia correlates with the radiological severity of pediatric IBD and serves as a predictor for adverse clinical disease outcome. Muscle mass measurement in MRE studies may serve as a possible marker for disease outcome in this population.

Early cardio-renal interactions among apparently healthy individuals undergoing coronary CT.

BACKGROUND: Previously we found that cardiac chambers' volumes correlate with estimated glomerular filtration rate (eGFR) of hospitalized patients. Currently we aimed to demonstrate this relation among apparently healthy individuals. METHODS: Ambulatory participants who underwent electrocardiography-gated cardiac computed tomography angiography (CCTA) were included. Subjects with an eGFR<60 ml/min/1.73m2, cardiovascular risk factors, and co-morbidities or medications which may influence cardiac chambers' volumes were excluded. Chambers' sizes were obtained by automatic four chamber volumetric analysis of the CCTAs, and calcium score was assessed using the Agatston score. RESULTS: The cohort consisted of 89 apparently healthy individuals, mostly of male gender (70%), with a mean age of 51 years and a mean eGFR of 79.5 ml/min/1.73m2. A low calcium score (≤10HU) was found in 67.4%(n = 60) of the cohort. After adjustment for baseline characteristics, renal function was associated exclusively with the volume of the left atrium (LA; b-coefficient-0.15, 95%CI -0.3- -0.01, p = .041). A 15.9% (95%CI 0.3-33.9%, p = .045) increase in LA volume index (LAVI) was found among participants with eGFR of 80-90 when compared to those with eGFR>90 ml/min/1.73m2. Participants with a low calcium score showed an increase in LAVI only when eGFR was reduced from normal (>90 ml/min/1.73m2) to 70-80 ml/min/1.73m2 (and not to 80-90 ml/min/1.73m2), revealing a percentage increase of 24.7% (95%CI 5.5-47.4%, p = .011). CONCLUSIONS: Renal function is closely related to LA volume even in the absence of overt renal failure, demonstrating that minor changes in eGFR instigate an increase in volumes. Risk factors for this interaction should be identified and treated prior to the development of cardio-renal syndrome.