Explore the vast range of titles available.

Background  Accurate segmentation of head and neck squamous cell cancer (HNSCC) is important for radiotherapy treatment planning. Manual segmentation of these tumors is time-consuming and vulnerable to inconsistencies between experts, especially in the complex head and neck region. The aim of this study is to introduce and evaluate an automatic segmentation pipeline for HNSCC using a multi-view CNN (MV-CNN). Methods The dataset included 220 patients with primary HNSCC and availability of T1-weighted, STIR and optionally contrast-enhanced T1-weighted MR images together with a manual reference segmentation of the primary tumor by an expert. A T1-weighted standard space of the head and neck region was created to register all MRI sequences to. An MV-CNN was trained with these three MRI sequences and evaluated in terms of volumetric and spatial performance in a cross-validation by measuring intra-class correlation (ICC) and dice similarity score (DSC), respectively. Results The average manual segmented primary tumor volume was 11.8±6.70 cm 3 with a median [IQR] of 13.9 [3.22-15.9] cm 3 . The tumor volume measured by MV-CNN was 22.8±21.1 cm 3 with a median [IQR] of 16.0 [8.24-31.1] cm 3 . Compared to the manual segmentations, the MV-CNN scored an average ICC of 0.64±0.06 and a DSC of 0.49±0.19. Improved segmentation performance was observed with increasing primary tumor volume: the smallest tumor volume group (<3 cm 3 ) scored a DSC of 0.26±0.16 and the largest group (>15 cm 3 ) a DSC of 0.63±0.11 ( p <0.001). The automated segmentation tended to overestimate compared to the manual reference, both around the actual primary tumor and in false positively classified healthy structures and pathologically enlarged lymph nodes. Conclusion An automatic segmentation pipeline was evaluated for primary HNSCC on MRI. The MV-CNN produced reasonable segmentation results, especially on large tumors, but overestimation decreased overall performance. In further research, the focus should be on decreasing false positives and make it valuable in treatment planning.

Background Decisions on head and neck squamous cell carcinoma (HNSCC) treatment are widely recognized as being difficult, due to high morbidity, often involving vital functions. Some patients may therefore decline standard, curative treatment. In addition doctors may propose alternative, nonstandard treatments. Little attention is devoted, both in literature and in daily practice, to understanding why and when HNSCC patients or their physicians decline standard, curative treatment modalities. Our objective is to determine factors associated with noncompliance in head and neck cancer treatment for both patients and physicians and to assess the influence of patient compliance on prognosis. Methods We did a retrospective study based on the medical records of 829 patients with primary HNSCC, who were eligible for curative treatment and referred to our hospital between 2010 and 2012. We analyzed treatment choice and reasons for nonstandard treatment decisions, survival, age, gender, social network, tumor site, cTNM classification, and comorbidity (ACE27). Multivariate analysis using logistic regression methods was performed to determine predictive factors associated with non-standard treatment following physician or patient decision. To gain insight in survival of the different groups of patients, we applied a Cox regression analysis. After checking the proportional hazards assumption for each variable, we adjusted the survival analysis for gender, age, tumor site, tumor stage, comorbidity and a history of having a prior tumor. Results 17 % of all patients with a primary HNSCC did not receive standard curative treatment, either due to nonstandard treatment advice (10 %) or due to the patient choosing an alternative (7 %). A further 3 % of all patients refused any type of therapy, even though they were considered eligible for curative treatment. Elderliness, single marital status, female gender, high tumor stage and severe comorbidity are predictive factors. Patients declining standard treatment have a lower overall 3-year survival (34 % vs. 70 %). Conclusions Predictive factors for nonstandard treatment decisions in head and neck cancer treatment differed between the treating physician and the patient. Patients who received nonstandard treatment had a lower overall 3-year survival. These findings should be taken into account when counselling patients in whom nonstandard treatment is considered.

Background Prediction in high dimensional settings is difficult due to the large number of variables relative to the sample size. We demonstrate how auxiliary ‘co-data’ can be used to improve the performance of a Random Forest in such a setting. Results Co-data are incorporated in the Random Forest by replacing the uniform sampling probabilities that are used to draw candidate variables by co-data moderated sampling probabilities. Co-data here are defined as any type information that is available on the variables of the primary data, but does not use its response labels. These moderated sampling probabilities are, inspired by empirical Bayes, learned from the data at hand. We demonstrate the co-data moderated Random Forest (CoRF) with two examples. In the first example we aim to predict the presence of a lymph node metastasis with gene expression data. We demonstrate how a set of external p -values, a gene signature, and the correlation between gene expression and DNA copy number can improve the predictive performance. In the second example we demonstrate how the prediction of cervical (pre-)cancer with methylation data can be improved by including the location of the probe relative to the known CpG islands, the number of CpG sites targeted by a probe, and a set of p -values from a related study. Conclusion The proposed method is able to utilize auxiliary co-data to improve the performance of a Random Forest.

Objective Present the results of the secondary obliteration of chronically discharging radical cavities using S53P4 bioactive glass (BAG). Study Design Retrospective cohort study. Setting Single‐center study. Methods A single‐center retrospective cohort study was conducted of all patients that underwent secondary obliteration of persistently draining radical cavities using S53P4 BAG between 2011 and 2022. Patients with middle ear cholesteatoma were excluded. The main outcome was postoperative otorrhea, as indicated by Merchant grading. Results In total, 97 patients were included. The median postoperative follow‐up time was 3.9 years (range 0.5‐10.4). Average time between the original canal wall down surgery and the secondary obliteration was 25.3 years (SD 11.7, range 2‐66). At the most recent follow‐up visit, a Merchant grade of 0 to 1 was observed in 95% of the cases. There were no cases of sensorineural hearing loss or facial palsy, one case developed a retro auricular skin defect and 1 patient developed CSF leakage. Minor complications were seen in 10 patients (10%). Ossicular chain reconstruction with a titanium prosthesis was performed in 42 cases, resulting in a median improvement of 11.2 dB in air conduction thresholds. In 9/42 cases (21%), closure of the postoperative air‐bone gap to ≤20 dB was achieved. Twenty‐five percent of cases could be discharged from out‐patient visits. Conclusion Revision of persistently draining radical cavities with BAG obliteration is feasible and results in a dry and safe ear in 95% of the patients, thereby enabling wearing of a conventional hearing aid. Out‐patient visits could be ceased in 25% of the cases.

Purpose To present the first pediatric study on the safety and efficacy of mastoid obliteration using S53P4 bioactive glass (BAG) for cholesteatoma surgery. Methods A single-center retrospective cohort study was conducted. Inclusion criteria were pediatric cases (≤ 18 years) and at least at least one year of follow-up including non-echo planar diffusion-weighted MRI to assess cholesteatoma recidivism. Both canal wall up (CWU) and canal wall down (CWD) procedures were evaluated. Results A total of 61 cases (56 patients) were included. Most cases had an otologic history before the development of the cholesteatoma. CWU procedure was performed in 18 cases (30%) and CWD procedure in 43 cases (70%). The cholesteatoma recidivism rate was 33% after a mean follow-up period of 58 months. Kaplan–Meier curve estimated a 5-year recidivism rate of 40%. Few complications were seen that were all minor and resolved spontaneously or after local or systemic treatment. Control of the infection (merchant grade 0–1) was achieved in 98% of the cases. Closure of the air–bone gap within 20 dB was achieved in 22% of the cases with complete audiometric evaluation. Conclusion In this MRI-controlled study, we show the safety and efficacy of S53P4 BAG for mastoid obliteration in a pediatric cholesteatoma cohort. Postoperative complications were both rare and minor, and a dry ear was achieved in almost all patients. Nevertheless, persistent hearing loss and the apparent high recidivism rate reflect the challenging nature of pediatric cholesteatoma.

Over 95% of head and neck cancers are squamous cell carcinoma (HNSCC). HNSCC is mostly diagnosed late, causing a poor prognosis despite the application of invasive treatment protocols. Tumor-educated platelets (TEPs) have been shown to hold promise as a molecular tool for early cancer diagnosis. We sequenced platelet mRNA isolated from blood of 101 patients with HNSCC and 101 propensity-score matched noncancer controls. Two independent machine learning classification strategies were employed using a training and validation approach to identify a cancer predictor: a particle swarm optimized support vector machine (PSO-SVM) and a least absolute shrinkage and selection operator (LASSO) logistic regression model. The best performing PSO-SVM predictor consisted of 245 platelet transcripts and reached a maximum area under the curve (AUC) of 0.87. For the LASSO-based prediction model, 1,198 mRNAs were selected, resulting in a median AUC of 0.84, independent of HPV status. Our data show that TEP RNA classification by different AI tools is promising in the diagnosis of HNSCC.

Prediction in high dimensional settings is difficult due to large by number of variables relative to the sample size. We demonstrate how auxiliary \"co-data\" can be used to improve the performance of a Random Forest in such a setting. Co-data are incorporated in the Random Forest by replacing the uniform sampling probabilities (used to draw candidate variables, the default for a Random Forest) by co-data moderated sampling probabilities. Co-data here is defined as any type information that is available on the variables of the primary data, but does not use its response labels. These moderated sampling probabilities are, inspired by empirical Bayes, learned from the data at hand. We demonstrate this co-data moderated Random Forest (CoRF) with one example. In the example we aim to predict a lymph node metastasis with gene expression data. We demonstrate how a set of external p-values, a gene signature, and the correlation between gene expression and DNA copy number can improve the predictive performance.

Motivation: Radiomics refers to the high-throughput mining of quantitative features from radiographic images. It is a promising field in that it may provide a non-invasive solution for screening and classification. Standard machine learning classification and feature selection techniques, however, tend to display inferior performance in terms of (the stability of) predictive performance. This is due to the heavy multicollinearity present in radiomic data. We set out to provide an easy-to-use approach that deals with this problem. Results: We developed a four-step approach that projects the original high-dimensional feature space onto a lower-dimensional latent-feature space, while retaining most of the covariation in the data. It consists of (i) penalized maximum likelihood estimation of a redundancy filtered correlation matrix. The resulting matrix (ii) is the input for a maximum likelihood factor analysis procedure. This two-stage maximum-likelihood approach can be used to (iii) produce a compact set of stable features that (iv) can be directly used in any (regression-based) classifier or predictor. It outperforms other classification (and feature selection) techniques in both external and internal validation settings regarding survival in squamous cell cancers.

In this study of ovarian clear-cell or endometrioid tumors, nearly half the samples had mutations in the ARID1A gene, which encodes a component of the SWI–SNF chromatin remodeling complex. Alterations in gene expression associated with abnormal chromatin remodeling may be linked with cancer. In the United States, ovarian cancer ranks as the fifth deadliest cancer among women. 1 Of the several subtypes of epithelial ovarian cancer, high-grade serous carcinomas are the most common, accounting for approximately 70% of all cases of epithelial ovarian cancer in North America. 2 Although ovarian clear-cell carcinoma is the second most common subtype in North America (accounting for 12% of cases and an even higher percentage in Japan 3 ) and is the second leading cause of death from ovarian cancer, 2 it is relatively understudied. Ovarian clear-cell carcinoma is defined on the basis of histopathological findings, including a predominance of clear . . .

The BRCA2 8765delAG mutation was previously reported in hereditary breast cancer families of French Canadian and Yemenite Jewish descent. Haplotype analysis, using six microsatellite markers that span BRCA2 and two intragenic polymorphisms, was performed on 8765delAG mutation carriers to determine if there was evidence that the mutations were identical by descent. The alleles of the microsatellite markers most closely flanking BRCA2 (D13S1697 and D13S1701) were found to be identical in state in all the mutation carriers. However, the disease-associated allele of one of the intragenic markers differed between the Yemenite Jews and French Canadian families, indicating that the 8765delAG mutation has independent origins in these two geographically and ethnically distinct populations.