Association between habitual snoring,middle ear disease,and speech problems in young children with non-syndromic cleft palate anomalies

The purpose of this study was to investigate the association between habitual snoring (HS), middle ear disease (MED), and speech problems in children with cleft palate. This cross-sectional study included children aged 2.0–7.9 years with non-syndromic cleft palate anomalies. Parents completed the Pediatric Sleep Questionnaire and a questionnaire about MED. Audiograms and speech assessment were also conducted. Ninety-five children were enrolled; 15.2% of families reported HS, 97.6% MED, and 17.1% speech problems. HS (37.5% vs 10.3%, P = 0.007) and early episodes of MED (92.3% vs 58.2%, P = 0.021) were more likely to be reported for children with isolated cleft palate when compared to those with cleft lip and palate. Children with cleft lip and palate had a higher frequency of MED with effusion compared to those with Robin sequence (86.4% vs 57.1%, P = 0.049). The odds ratio for HS in children with ≥1 episode of MED in the last year was 7.37 (95% confidence interval 1.55–35.15, P = 0.012). There was a trend for children with speech problems reported by parents to have HS (30.8% vs 11.5%, P= 0.076). Anatomical factors play a role in the frequency of upper airway symptoms in children with cleft palate. A recent history of at least one episode of MED was associated with an increased frequency of HS.     

Quantifying and leveraging predictive uncertainty for medical image assessment

The interpretation of medical images is a challenging task, often complicated by the presence of artifacts, occlusions, limited contrast and more. Most notable is the case of chest radiography, where there is a high inter-rater variability in the detection and classification of abnormalities. This is largely due to inconclusive evidence in the data or subjective definitions of disease appearance. An additional example is the classification of anatomical views based on 2D Ultrasound images. Often, the anatomical context captured in a frame is not sufficient to recognize the underlying anatomy. Current machine learning solutions for these problems are typically limited to providing probabilistic predictions, relying on the capacity of underlying models to adapt to limited information and the high degree of label noise. In practice, however, this leads to overconfident systems with poor generalization on unseen data. To account for this, we propose a system that learns not only the probabilistic estimate for classification, but also an explicit uncertainty measure which captures the confidence of the system in the predicted output. We argue that this approach is essential to account for the inherent ambiguity characteristic of medical images from different radiologic exams including computed radiography, ultrasonography and magnetic resonance imaging. In our experiments we demonstrate that sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC for various tasks, e.g., by 8% to 0.91 with an expected rejection rate of under 25% for the classification of different abnormalities in chest radiographs. In addition, we show that using uncertainty-driven bootstrapping to filter the training data, one can achieve a significant increase in robustness and accuracy. Finally, we present a multi-reader study showing that the predictive uncertainty is indicative of reader errors.     

A comprehensive method for calculating total body irradiation

PurposeTo provide means for calculating the dose received by various tissues of the patient, calculate lung shield, and verify received dose using a phantom as a tool for quality assurance for a planned Total Body Irradiation (TBI) procedure in radiotherapy.MethodUsing Microsoft Visual Basic, MATLAB, and Python, a program for Total Body Irradiation Calculation in Radiotherapy (TBICR) is constructed. It uses patient translation and beam zone method for total body irradiation calculations to compute the proper dose received by the patient and determine the lung shield thickness. There are three main user-friendly interfaces in the application. The first one allows the user to upload the TBI topography and estimate the distances needed for TBI calculations. The second one enables the user to count the number of beam zones needed for each point and estimate the effective area (A_eff) for each level. The third interface estimates the velocity required to deliver the relative dose depending on patient separation, Monitor Units (MU), couch speed and travel distance. It allows the user to compute the required lung shield thickness, read any patient's CT DICOM file and acquire dose in any distinct location using machine learning model to predict the dose.ResultsThe TBICR software has been successfully validated by reproducing all of the manual calculations in an exact and timely manner. TBICR generated more accurate results and confirmed the absorbed dose to patient through measurements on Anderson phantom.ConclusionsA computer program for the calculation of total body irradiation (TBI) is described in full. The dose received at each point on the patient, the calculation of lung shield and the determination of the velocity and time required for the couch movement are all made possible using the software. The ease of use, precision, data storage and printing are some important features of the present software.     

Primary and recurrent regional metastases for lateralized oral cavity squamous cell carcinoma

ObjectivesMap regional lymph node metastases for lateralized oral cavity squamous cell carcinoma (OCSCC) and evaluate factors associated with regional metastases and recurrence.Materials and methodsRetrospective cohort study of 715 patients with lateralized OCSCC surgically treated in 1997–2011. Analysis was performed using log-rank, Kaplan-Meier, and multivariable logistic and Cox regression.ResultsRegional metastases were identified in ipsilateral levels IIA (24%), IB (18%), III (13%), V (9%), IV (7%), IA (2%) and IIB (1%) and the contralateral neck (3%). Lymphovascular invasion (LVI) (Hazard Ratio [HR] 2.2, 95% Confidence Interval [CI] 1.2–3.9) and T category (T3 vs. T1: HR 4.1, 95% CI 1.9–9.3; T4 vs. T1: HR 2.3, 95% CI 1.2–4.3) were associated with regional metastases. Most (71%) isolated regional metastatic recurrences were in undissected levels of the neck, including 58% in levels IV and V. Tumors of the hard palate (HR 4.3, 95% CI 1.2–16.1), upper alveolus (HR 3.2, 95% CI 1.0–4.7) or with LVI (HR 2.0, 95% CI 1.0–3.9) were associated with isolated regional recurrence. For upper alveolar/hard palate tumors, depth of invasion (DOI) ≥4 mm (P = .003) and LVI (P = .04) were associated with regional metastases.ConclusionsFor lateralized OCSCC, elective neck dissection of level IIB or the contralateral neck may rarely be needed, but additional surgical or radiation treatment of levels IV and V may be considered based on patient risk factors, including T category 3–4 or LVI. For upper alveolar/hard palate tumors, DOI ≥4 mm is an appropriate threshold for elective neck dissection.