Protocol Letter: A multi-institutional retrospective case-control cohort investigating PREDiction models for mandibular OsteoRadioNecrosis in head and neck cancer (PREDMORN).
Ontology highlight
ABSTRACT:
SUBMITTER: Humbert-Vidan L
PROVIDER: S-EPMC9727320 | biostudies-literature | 2022 Nov
REPOSITORIES: biostudies-literature
Publications
Protocol Letter: A multi-institutional retrospective case-control cohort investigating PREDiction models for mandibular OsteoRadioNecrosis in head and neck cancer (PREDMORN).
Humbert-Vidan Laia L Hansen Christian R CR Fuller Clifton D CD Petit Steven S van der Schaaf Arjen A van Dijk Lisanne V LV Verduijn Gerda M GM Langendijk Hans H Muñoz-Montplet Carles C Heemsbergen Wilma W Witjes Max M Mohamed Abdallah S R ASR Khan Abdul A AA Marruecos Querol Jordi J Oliveras Cancio Irene I Patel Vinod V King Andrew P AP Johansen Jørgen J Guerrero Urbano Teresa T
Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology 20220928
Similar Datasets
Project description:PurposeThis study aims to identify radiomic features extracted from contrast-enhanced CT scans that differentiate osteoradionecrosis (ORN) from normal mandibular bone in patients with head and neck cancer (HNC) treated with radiotherapy (RT).Materials and methodsContrast-enhanced CT (CECT) images were collected for 150 patients (80% train, 20% test) with confirmed ORN diagnosis at The University of Texas MD Anderson Cancer Center between 2008 and 2018. Using PyRadiomics, radiomic features were extracted from manually segmented ORN regions and the corresponding automated control regions, the later defined as the contralateral healthy mandible region. A subset of pre-selected features was obtained based on correlation analysis (r > 0.95) and used to train a Random Forest (RF) classifier with Recursive Feature Elimination. Model explainability SHapley Additive exPlanations (SHAP) analysis was performed on the 20 most important features identified by the trained RF classifier.ResultsFrom a total of 1316 radiomic features extracted, 810 features were excluded due to high collinearity. From a set of 506 pre-selected radiomic features, the optimal subset resulting on the best discriminative accuracy of the RF classifier consisted of 67 features. The RF classifier was well calibrated (Log Loss 0.296, ECE 0.125) and achieved an accuracy of 88% and a ROC AUC of 0.96. The SHAP analysis revealed that higher values of Wavelet-LLH First-order Mean and Median were associated with ORN of the jaw (ORNJ). Conversely, higher Exponential GLDM Dependence Entropy and lower Square First-order Kurtosis were more characteristic of normal mandibular tissue.ConclusionThis study successfully developed a CECT-based radiomics model for differentiating ORNJ from healthy mandibular tissue in HNC patients after RT. Future work will focus on the detection of subclinical ORNJ regions to guide earlier interventions.
| S-EPMC11419222 | biostudies-literature
Project description:BackgroundWe aimed to determine whether hypomagnesemia predicts osteoradionecrosis development in patients with squamous cell carcinoma of the oropharynx and oral cavity who received platinum-based concurrent chemoradiation with or without induction therapy.MethodsWe reviewed data from patients with head and neck cancers who had undergone chemoradiation with weekly cisplatin/carboplatin between January 1, 2010 and December 31, 2014 at our institution. Pathologic features, laboratory test results, disease stage, and social histories were recorded. The association between hypomagnesemia and osteoradionecrosis was analyzed controlling for known confounding factors.ResultsHypomagnesemia during cancer treatment was associated with osteoradionecrosis development (HR = 2.72, P = .037) independent of total radiation dose (HR = 1.07, P = .260) and smoking history (HR = 2.05, P = .056) among the patients who received platinum-based induction chemotherapy followed by concurrent chemoradiation.ConclusionsHypomagnesemia was predictive of the development of osteoradionecrosis in patients with cancers of the oropharynx and oral cavity receiving platinum-based induction followed by concurrent chemoradiation.
| S-EPMC10359096 | biostudies-literature
Project description:Objectives(i) To determine the influence of specimen collection protocol (timing and specimen quantity), primary disease process, and pre-existing antimicrobial or immunosuppressive therapy on blood culture (BC) positivity and (ii) To determine agreement between urine culture and BC results.Animals701 client-owned dogs.MethodsMulti-institutional retrospective study (2019-2022). Mixed-effect logistic regression was used to determine whether primary disease process, the number of BCs, or the timing of specimen collection was associated with BC positivity. Prediction plots were generated. Associations between urine culture and BC results were performed using logistic regression.ResultsDogs with a positive urine culture were more likely to have a positive BC (OR: 4.36, 95% CI: 2.12-8.97, p = 0.003). Dogs that had three BC specimens had the greatest odds of obtaining a positive BC result (adjusted predictive value: 0.44, 95% CI: 0.21-0.70), although this was not significant. Isolates from 38.5% of dogs with a positive BC had resistance to ≥3 antimicrobial classes. The timing between specimen collection had no significant association with BC positivity. Pre-existing antibiotic or immunosuppressive therapy had no significant association with BC positivity.Clinical relevanceDogs with a positive urine culture were more likely to have a positive BC result.
| S-EPMC10752604 | biostudies-literature
Project description:In radiation oncology, predicting patient risk stratification allows specialization of therapy intensification as well as selecting between systemic and regional treatments, all of which helps to improve patient outcome and quality of life. Deep learning offers an advantage over traditional radiomics for medical image processing by learning salient features from training data originating from multiple datasets. However, while their large capacity allows to combine high-level medical imaging data for outcome prediction, they lack generalization to be used across institutions. In this work, a pseudo-volumetric convolutional neural network with a deep preprocessor module and self-attention (PreSANet) is proposed for the prediction of distant metastasis, locoregional recurrence, and overall survival occurrence probabilities within the 10 year follow-up time frame for head and neck cancer patients with squamous cell carcinoma. The model is capable of processing multi-modal inputs of variable scan length, as well as integrating patient data in the prediction model. These proposed architectural features and additional modalities all serve to extract additional information from the available data when availability to additional samples is limited. This model was trained on the public Cancer Imaging Archive Head-Neck-PET-CT dataset consisting of 298 patients undergoing curative radio/chemo-radiotherapy and acquired from 4 different institutions. The model was further validated on an internal retrospective dataset with 371 patients acquired from one of the institutions in the training dataset. An extensive set of ablation experiments were performed to test the utility of the proposed model characteristics, achieving an AUROC of [Formula: see text], [Formula: see text] and [Formula: see text] for DM, LR and OS respectively on the public TCIA Head-Neck-PET-CT dataset. External validation was performed on a retrospective dataset with 371 patients, achieving [Formula: see text] AUROC in all outcomes. To test for model generalization across sites, a validation scheme consisting of single site-holdout and cross-validation combining both datasets was used. The mean accuracy across 4 institutions obtained was [Formula: see text], [Formula: see text] and [Formula: see text] for DM, LR and OS respectively. The proposed model demonstrates an effective method for tumor outcome prediction for multi-site, multi-modal combining both volumetric data and structured patient clinical data.
| S-EPMC8873259 | biostudies-literature
Project description:PurposeDeep-learning (DL) techniques have been successful in disease-prediction tasks and could improve the prediction of mandible osteoradionecrosis (ORN) resulting from head and neck cancer (HNC) radiation therapy. In this study, we retrospectively compared the performance of DL algorithms and traditional machine-learning (ML) techniques to predict mandible ORN binary outcome in an extensive cohort of patients with HNC.Methods and materialsPatients who received HNC radiation therapy at the University of Texas MD Anderson Cancer Center from 2005 to 2015 were identified for the ML (n = 1259) and DL (n = 1236) studies. The subjects were followed for ORN development for at least 12 months, with 173 developing ORN and 1086 having no evidence of ORN. The ML models used dose-volume histogram parameters to predict ORN development. These models included logistic regression, random forest, support vector machine, and a random classifier reference. The DL models were based on ResNet, DenseNet, and autoencoder-based architectures. The DL models used each participant's dose cropped to the mandible. The effect of increasing the amount of available training data on the DL models' prediction performance was evaluated by training the DL models using increasing ratios of the original training data.ResultsThe F1 score for the logistic regression model, the best-performing ML model, was 0.3. The best-performing ResNet, DenseNet, and autoencoder-based models had F1 scores of 0.07, 0.14, and 0.23, respectively, whereas the random classifier's F1 score was 0.17. No performance increase was apparent when we increased the amount of training data available for DL model training.ConclusionsThe ML models had superior performance to their DL counterparts. The lack of improvement in DL performance with increased training data suggests that either more data are needed for appropriate DL model construction or that the image features used in DL models are not suitable for this task.
| S-EPMC9926206 | biostudies-literature
Project description:Accurate organ-at-risk (OAR) segmentation is critical to reduce radiotherapy complications. Consensus guidelines recommend delineating over 40 OARs in the head-and-neck (H&N). However, prohibitive labor costs cause most institutions to delineate a substantially smaller subset of OARs, neglecting the dose distributions of other OARs. Here, we present an automated and highly effective stratified OAR segmentation (SOARS) system using deep learning that precisely delineates a comprehensive set of 42 H&N OARs. We train SOARS using 176 patients from an internal institution and independently evaluate it on 1327 external patients across six different institutions. It consistently outperforms other state-of-the-art methods by at least 3-5% in Dice score for each institutional evaluation (up to 36% relative distance error reduction). Crucially, multi-user studies demonstrate that 98% of SOARS predictions need only minor or no revisions to achieve clinical acceptance (reducing workloads by 90%). Moreover, segmentation and dosimetric accuracy are within or smaller than the inter-user variation.
| S-EPMC9576793 | biostudies-literature
Project description:ImportanceProton radiation therapy (PRT) has reduced radiation-induced toxic effects, such as mucositis and xerostomia, over conventional photon radiation therapy, leading to significantly improved quality of life in patients with head and neck cancers. However, the prevalence of osteoradionecrosis (ORN) of the jaw following PRT in these patients is less clear.ObjectiveTo report the prevalence and clinical characteristics of ORN in patients with oral and oropharyngeal cancer (OOPC) treated with PRT.Design, setting, and participantsThis case series reports a single-institution experience (Memorial Sloan Kettering Cancer Center, New York, New York) between November 2013 and September 2019 and included 122 radiation therapy-naive patients with OOPC treated with PRT. Data were analyzed from 2013 to 2019.Main outcomes and measuresClinical parameters, including sex, age, comorbidities, tumor histology, concurrent chemotherapy, smoking, comorbidities, and preradiation dental evaluation, were obtained from the medical record. Patients with clinical or radiographic signs of ORN were identified and graded using the adopted modified Glanzmann and Grätz grading system. Characteristics of ORN, such as location, clinical presentation, initial stage at diagnosis, etiology, time to diagnosis, management, and clinical outcome at the last follow-up, were also collected.ResultsOf the 122 patients (mean [SD] age, 63 [13] years; 45 [36.9%] women and 77 [63.1%] men) included in this study, 13 (10.6%) developed ORN following PRT during a median (range) follow-up time of 40.6 (<1-101) months. All patients had spontaneous development of ORN. At the time of initial diagnosis, grade 0, grade 1, grade 2, and grade 3 ORN were seen in 2, 1, 9, and 1 patient, respectively. The posterior ipsilateral mandible within the radiation field that received the full planned PRT dose was the most involved ORN site. At a median (range) follow-up of 13.5 (0.2-58.0) months from the time of ORN diagnosis, complete resolution, stable condition, and progression of ORN were seen in 3, 6, and 4 patients, respectively. The 3-year rates of ORN and death in the total cohort were 5.2% and 21.5%, while the 5-year rates of ORN and death were 11.5% and 34.4%, respectively.Conclusions and relevanceIn this case series, the prevalence of ORN following PRT was found to be 10.6%, indicating that ORN remains a clinical challenge even in the era of highly conformal PRT. Clinicians treating patients with OOPC with PRT should be mindful of this complication.
| S-EPMC9912132 | biostudies-literature
Project description:Artificial intelligence (AI) and machine learning (ML) are becoming critical in developing and deploying personalized medicine and targeted clinical trials. Recent advances in ML have enabled the integration of wider ranges of data including both medical records and imaging (radiomics). However, the development of prognostic models is complex as no modeling strategy is universally superior to others and validation of developed models requires large and diverse datasets to demonstrate that prognostic models developed (regardless of method) from one dataset are applicable to other datasets both internally and externally. Using a retrospective dataset of 2,552 patients from a single institution and a strict evaluation framework that included external validation on three external patient cohorts (873 patients), we crowdsourced the development of ML models to predict overall survival in head and neck cancer (HNC) using electronic medical records (EMR) and pretreatment radiological images. To assess the relative contributions of radiomics in predicting HNC prognosis, we compared 12 different models using imaging and/or EMR data. The model with the highest accuracy used multitask learning on clinical data and tumor volume, achieving high prognostic accuracy for 2-year and lifetime survival prediction, outperforming models relying on clinical data only, engineered radiomics, or complex deep neural network architecture. However, when we attempted to extend the best performing models from this large training dataset to other institutions, we observed significant reductions in the performance of the model in those datasets, highlighting the importance of detailed population-based reporting for AI/ML model utility and stronger validation frameworks. We have developed highly prognostic models for overall survival in HNC using EMRs and pretreatment radiological images based on a large, retrospective dataset of 2,552 patients from our institution.Diverse ML approaches were used by independent investigators. The model with the highest accuracy used multitask learning on clinical data and tumor volume.External validation of the top three performing models on three datasets (873 patients) with significant differences in the distributions of clinical and demographic variables demonstrated significant decreases in model performance.SignificanceML combined with simple prognostic factors outperformed multiple advanced CT radiomics and deep learning methods. ML models provided diverse solutions for prognosis of patients with HNC but their prognostic value is affected by differences in patient populations and require extensive validation.
| S-EPMC10309070 | biostudies-literature
Project description:IntroductionSurgery is the primary treatment for resectable, non-metastatic recurrent head and neck squamous cell carcinoma (HNSCC). We explore the safety and oncologic benefit of intraoperative Cesium-131 (Cs-131) brachytherapy combined with salvage local and/or regional surgical resection.Methods and materialsFindings were reported from a single arm multi-institutional prospective phase 1/2 trial involving surgery plus Cs-131 (surgery + Cs-131) treatment. The results of two retrospective cohorts-surgery alone and surgery plus intensity modulated radiation therapy (surgery + ReIMRT)-were also described. Included patients had recurrent HNSCC and radiation history. Safety, tumor re-occurrence, and survival were evaluated.ResultsForty-nine patients were enrolled in the surgery + Cs-131 prospective study. Grade 1 to 3 adverse events (AEs) occurred in 18 patients (37%), and grade 4 AEs occurred in 2 patients. Postoperative percutaneous endoscopic gastrostomy (PEG) tubes were needed in 10 surgery + Cs-131 patients (20%), and wound and vascular complications were observed in 12 patients (24%). No cases of osteoradionecrosis were reported in the surgery + Cs-131 cohort. We found a 49% 2-year disease-free survival at the site of treatment with a substantial number of patients (31%) developing metastatic disease, which led to a 31% overall survival at 5 years.ConclusionsAmong patients with local/regional recurrent HNSCC status-post radiation, surgery + Cs-131 demonstrated acceptable safety with compelling oncologic outcomes, as compared to historic control cohorts.Clinical trial registrationClinicalTrials.gov, identifiers NCT02794675 and NCT02467738.
| S-EPMC8660666 | biostudies-literature
Project description:BackgroundTo evaluate factors associated with osteoradionecrosis of the jaw (ORNJ) in patients with head and neck squamous cell carcinoma (HNSCC), focusing on jaw-related dose-volume histogram (DVH) parameters.MethodsWe retrospectively reviewed the medical records of 616 patients with HNSCC treated with curative-intent or postoperative radiation therapy (RT) during 2008-2018. Patient-related (age, sex, history of smoking or alcohol use, diabetes mellitus, performance status, pre-RT dental evaluation, pre- or post-RT tooth extraction), tumor-related (primary tumor site, T-stage, nodal status), and treatment-related (pre-RT surgery, pre-RT mandible surgery, induction or concurrent chemotherapy, RT technique) variables and DVH parameters (relative volumes of the jaw exposed to doses of 10 Gy-70 Gy [V10-70]) were investigated and compared between patients with and without ORNJ. The Mann-Whitney U test was used to compare RT dose parameters. Univariate and multivariate Cox regression analyses were used to assess factors associated with ORNJ development. Kaplan-Meier analyses were performed for cumulative ORNJ incidence estimation.ResultsForty-six patients (7.5%) developed ORNJ. The median follow-up duration was 40 (range 3-145) months. The median time to ORNJ development was 27 (range 2-127) months. DVH analysis revealed that V30-V70 values were significantly higher in patients with than in those without ORNJ. In univariate analyses, primary tumor site, pre-RT mandible surgery, post-RT tooth extraction, and V60 > 14% were identified as important factors. In multivariate analyses, V60 > 14% (p = 0.0065) and primary tumor site (p = 0.0059) remained significant. The 3-year cumulative ORNJ incidence rates were 2.5% and 8.6% in patients with V60 ≤ 14% and > 14%, respectively (p < 0.0001), and 9.3% and 1.4% in patients with oropharyngeal or oral cancer and other cancers, respectively (p < 0.0001).ConclusionsV60 > 14% and oropharyngeal or oral cancer were found to be independent risk factors for ORNJ. These findings might be useful to minimize ORNJ incidence in HNSCC treated with curative RT.
| S-EPMC7786900 | biostudies-literature