First-order radiomic features, such as metabolic tumor volume (MTV) and total lesion glycolysis (TLG), are associated with disease progression in early-stage classical Hodgkin lymphoma (HL). We ...hypothesized that a model incorporating first- and second-order radiomic features would more accurately predict outcome than MTV or TLG alone. We assessed whether radiomic features extracted from baseline PET scans predicted relapsed or refractory disease status in a cohort of 251 patients with stage I-II HL who were managed at a tertiary cancer center. Models were developed and tested using a machine-learning algorithm. Features extracted from mediastinal sites were highly predictive of primary refractory disease. A model incorporating 5 of the most predictive features had an area under the curve (AUC) of 95.2% and total error rate of 1.8%. By comparison, the AUC was 78% for both MTV and TLG and was 65% for maximum standardize uptake value (SUV
). Furthermore, among the patients with refractory mediastinal disease, our model distinguished those who were successfully salvaged from those who ultimately died of HL. We conclude that our PET radiomic model may improve upfront stratification of early-stage HL patients with mediastinal disease and thus contribute to risk-adapted, individualized management.
Accurate clinical target volume (CTV) delineation is essential to ensure proper tumor coverage in radiation therapy. This is a particularly difficult task for head-and-neck cancer patients where ...detailed knowledge of the pathways of microscopic tumor spread is necessary. This paper proposes a solution to auto-segment these volumes in oropharyngeal cancer patients using a two-channel 3D U-Net architecture. The first channel feeds the network with the patient's CT image providing anatomical context, whereas the second channel provides the network with tumor location and morphological information. Radiation therapy simulation computer tomography scans and their corresponding manually delineated CTV and gross tumor volume (GTV) delineations from 285 oropharyngeal patients previously treated at MD Anderson Cancer Center were used in this study. CTV and GTV delineations underwent rigorous group peer-review prior to the start of treatment delivery. The convolutional network's parameters were fine-tuned using a training set of 210 patients using 3-fold cross-validation. During hyper-parameter selection, we use a score based on the overlap (dice similarity coefficient (DSC)) and missed volumes (false negative dice (FND)) to minimize any possible under-treatment. Three auto-delineated models were created to estimate tight, moderate, and wide CTV margin delineations. Predictions on our test set (75 patients) resulted in auto-delineations with high overlap and close surface distance agreement (DSC > 0.75 on 96% of cases for tight and moderate auto-delineation models and 97% of cases having mean surface distance 5.0 mm) to the ground-truth. We found that applying a 5 mm uniform margin expansion to the auto-delineated CTVs would cover at least 90% of the physician CTV volumes for a large majority of patients; however, determination of appropriate margin expansions for auto-delineated CTVs merits further investigation.
Treatment for glioblastoma (GBM) includes surgical resection and adjuvant radiotherapy (RT) and chemotherapy. The optimal time interval between surgery and RT remains unclear. The National Cancer ...Database (NCDB) was queried for patients with GBM. Overall survival (OS) was estimated using Kaplan-Meier and log-rank tests. Univariate (UVA) and multivariable Cox regression (MVA) modeling was used to determine predictors of OS. A total of 45,942 patients were included. On MVA: younger age, female gender, black ethnicity, higher KPS, obtaining a gross total resection (GTR), MGMT promoter-methylated gene status, unifocal disease, higher RT dose, and RT delay of 4-8 weeks had improved OS. Patients who underwent a subtotal resection (STR) had worsened survival with RT delay ≤4 weeks and patients with GTR had worsened survival when RT was delayed >8 weeks. This analysis suggests that an interval of 4-8 weeks between resection and RT results in better survival. Delays >8 weeks in patients with a GTR and delays <4 weeks in patients with a STR/biopsy resulted in worse survival. This impact of time delay from surgery to RT, in conjunction with extent of resection, should be considered in the clinical management of patients and future designs of clinical trials.
Radiomics studies require many patients in order to power them, thus patients are often combined from different institutions and using different imaging protocols. Various studies have shown that ...imaging protocols affect radiomics feature values. We examined whether using data from cohorts with controlled imaging protocols improved patient outcome models. We retrospectively reviewed 726 CT and 686 PET images from head and neck cancer patients, who were divided into training or independent testing cohorts. For each patient, radiomics features with different preprocessing were calculated and two clinical variables-HPV status and tumor volume-were also included. A Cox proportional hazards model was built on the training data by using bootstrapped Lasso regression to predict overall survival. The effect of controlled imaging protocols on model performance was evaluated by subsetting the original training and independent testing cohorts to include only patients whose images were obtained using the same imaging protocol and vendor. Tumor volume, HPV status, and two radiomics covariates were selected for the CT model, resulting in an AUC of 0.72. However, volume alone produced a higher AUC, whereas adding radiomics features reduced the AUC. HPV status and one radiomics feature were selected as covariates for the PET model, resulting in an AUC of 0.59, but neither covariate was significantly associated with survival. Limiting the training and independent testing to patients with the same imaging protocol reduced the AUC for CT patients to 0.55, and no covariates were selected for PET patients. Radiomics features were not consistently associated with survival in CT or PET images of head and neck patients, even within patients with the same imaging protocol.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Radiomics has been widely investigated for non-invasive acquisition of quantitative textural information from anatomic structures. While the vast majority of radiomic analysis is performed on images ...obtained from computed tomography, magnetic resonance imaging (MRI)-based radiomics has generated increased attention. In head and neck cancer (HNC), however, attempts to perform consistent investigations are sparse, and it is unclear whether the resulting textural features can be reproduced. To address this unmet need, we systematically reviewed the quality of existing MRI radiomics research in HNC.
Literature search was conducted in accordance with guidelines established by Preferred Reporting Items for Systematic Reviews and Meta-Analyses. Electronic databases were examined from January 1990 through November 2017 for common radiomic keywords. Eligible completed studies were then scored using a standardized checklist that we developed from Enhancing the Quality and Transparency of Health Research guidelines for reporting machine-learning predictive model specifications and results in biomedical research, defined by Luo et al. (1). Descriptive statistics of checklist scores were populated, and a subgroup analysis of methodology items alone was conducted in comparison to overall scores.
Sixteen completed studies and four ongoing trials were selected for inclusion. Of the completed studies, the nasopharynx was the most common site of study (37.5%). MRI modalities varied with only four of the completed studies (25%) extracting radiomic features from a single sequence. Study sample sizes ranged between 13 and 118 patients (median of 40), and final radiomic signatures ranged from 2 to 279 features. Analyzed endpoints included either segmentation or histopathological classification parameters (44%) or prognostic and predictive biomarkers (56%). Liu et al. (2) addressed the highest number of our checklist items (total score: 48), and a subgroup analysis of methodology checklist items alone did not demonstrate any difference in scoring trends between studies Spearman's ρ = 0.94 (
< 0.0001).
Although MRI radiomic applications demonstrate predictive potential in analyzing diverse HNC outcomes, methodological variances preclude accurate and collective interpretation of data.
A major challenge in radiomics is assembling data from multiple centers. Sharing data between hospitals is restricted by legal and ethical regulations. Distributed learning is a technique, enabling ...training models on multicenter data without data leaving the hospitals ("privacy-preserving" distributed learning). This study tested feasibility of distributed learning of radiomics data for prediction of two year overall survival and HPV status in head and neck cancer (HNC) patients. Pretreatment CT images were collected from 1174 HNC patients in 6 different cohorts. 981 radiomic features were extracted using Z-Rad software implementation. Hierarchical clustering was performed to preselect features. Classification was done using logistic regression. In the validation dataset, the receiver operating characteristics (ROC) were compared between the models trained in the centralized and distributed manner. No difference in ROC was observed with respect to feature selection. The logistic regression coefficients were identical between the methods (absolute difference <10
). In comparison of the full workflow (feature selection and classification), no significant difference in ROC was found between centralized and distributed models for both studied endpoints (DeLong p > 0.05). In conclusion, both feature selection and classification are feasible in a distributed manner using radiomics data, which opens new possibility for training more reliable radiomics models.
Clustering is the task of identifying groups of similar subjects according to certain criteria. The AJCC staging system can be thought as a clustering mechanism that groups patients based on their ...disease stage. This grouping drives prognosis and influences treatment. The goal of this work is to evaluate the efficacy of machine learning algorithms to cluster the patients into discriminative groups to improve prognosis for overall survival (OS) and relapse free survival (RFS) outcomes. We apply clustering over a retrospectively collected data from 644 head and neck cancer patients including both clinical and radiomic features. In order to incorporate outcome information into the clustering process and deal with the large proportion of censored samples, the feature space was scaled using the regression coefficients fitted using a proxy dependent variable, martingale residuals, instead of follow-up time. Two clusters were identified and evaluated using cross validation. The Kaplan Meier (KM) curves between the two clusters differ significantly for OS and RFS (p-value < 0.0001). Moreover, there was a relative predictive improvement when using the cluster label in addition to the clinical features compared to using only clinical features where AUC increased by 5.7% and 13.0% for OS and RFS, respectively.
This manuscript describes a dataset of thoracic cavity segmentations and discrete pleural effusion segmentations we have annotated on 402 computed tomography (CT) scans acquired from patients with ...non‐small cell lung cancer. The segmentation of these anatomic regions precedes fundamental tasks in image analysis pipelines such as lung structure segmentation, lesion detection, and radiomics feature extraction. Bilateral thoracic cavity volumes and pleural effusion volumes were manually segmented on CT scans acquired from The Cancer Imaging Archive “NSCLC Radiomics” data collection. Four hundred and two thoracic segmentations were first generated automatically by a U‐Net based algorithm trained on chest CTs without cancer, manually corrected by a medical student to include the complete thoracic cavity (normal, pathologic, and atelectatic lung parenchyma, lung hilum, pleural effusion, fibrosis, nodules, tumor, and other anatomic anomalies), and revised by a radiation oncologist or a radiologist. Seventy‐eight pleural effusions were manually segmented by a medical student and revised by a radiologist or radiation oncologist. Interobserver agreement between the radiation oncologist and radiologist corrections was acceptable. All expert‐vetted segmentations are publicly available in NIfTI format through The Cancer Imaging Archive at https://doi.org/10.7937/tcia.2020.6c7y‐gq39. Tabular data detailing clinical and technical metadata linked to segmentation cases are also available. Thoracic cavity segmentations will be valuable for developing image analysis pipelines on pathologic lungs — where current automated algorithms struggle most. In conjunction with gross tumor volume segmentations already available from “NSCLC Radiomics,” pleural effusion segmentations may be valuable for investigating radiomics profile differences between effusion and primary tumor or training algorithms to discriminate between them.
The incidence of oropharyngeal squamous cell carcinoma (OPSCC) in the US is rapidly increasing, driven largely by the epidemic of human papillomavirus (HPV)-mediated OPSCC. Although survival for ...patients with HPV mediated OPSCC (HPV+ OPSCC) is generally better than that of patients with non-virally mediated OPSCC, this effect is not uniform. We hypothesized that tobacco exposure remains a critical modifier of survival for HPV+ OPSCC patients.
We conducted a retrospective analysis of 611 OPSCC patients with concordant p16 and HPV testing treated at a single institute (2002-2013). Survival analysis was performed using Kaplan-Meier analysis and Cox regression. Recursive partitioning analysis (RPA) was used to define tobacco exposure associated with survival (p < 0.05).
Tobacco exposure impacted overall survival (OS) for HPV+ patients on univariate and multivariate analysis (p = 0.002, p = 0.003 respectively). RPA identified 30 pack-years (PY) as a threshold at which survival became significantly worse in HPV+ patients. OS and disease-free survival (DFS) for HPV+ > 30 PY patients didn't differ significantly from HPV- patients (p = 0.72, p = 0.27, respectively). HPV+ > 30 PY patients had substantially lower 5-year OS when compared to their ≤30 PYs counterparts: 78.4% vs 91.6%; p = 0.03, 76% vs 88.3%; p = 0.07, and 52.3% vs 74%; p = 0.05, for stages I, II, and III (AJCC 8th Edition Manual), respectively.
Tobacco exposure can eliminate the survival benefit associated with HPV+ status in OPSCC patients. Until this effect can be clearly quantified using prospective datasets, de-escalation of treatment for HPV + OPSCC smokers should be avoided.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Purpose. Early animal studies suggest that parotid gland (PG) toxicity prediction could be improved by an accurate estimation of the radiation dose to sub-regions of the PG. Translation to clinical ...investigation requires voxel-level dose accumulation in this organ that responds volumetrically throughout treatment. To date, deformable image registration (DIR) has been evaluated for the PG using only surface alignment. We sought to develop and evaluate an advanced DIR technique capable of modeling these complex PG volume changes over the course of radiation therapy. Materials and methods. Planning and mid-treatment magnetic resonance images from 19 patients and computed tomography images from nine patients who underwent radiation therapy for head and neck cancer were retrospectively evaluated. A finite element model (FEM)-based DIR algorithm was applied between the corresponding pairs of images, based on boundary conditions on the PG surfaces only (Morfeus-spatial). To investigate an anticipated improvement in accuracy, we added a population model-based thermal expansion coefficient to simulate the dose distribution effect on the volume change inside the glands (Morfeus-spatialDose). The model accuracy was quantified using target registration error for magnetic resonance images, where corresponding anatomical landmarks could be identified. The potential clinical impact was evaluated using differences in mean dose, median dose, D98, and D50 of the PGs. Results. In the magnetic resonance images, the mean (±standard deviation) target registration error significantly reduced by 0.25 ± 0.38 mm (p = 0.01) when using Morfeus-spatialDose instead of Morfeus-spatial. In the computed tomography images, differences in the mean dose, median dose, D98, and D50 of the PGs reached 2.9 ± 0.8, 3.8, 4.1, and 3.8 Gy, respectively, between Morfeus-spatial and Morfeus-spatialDose. Conclusion. Differences between Morfeus-spatial and Morfeus-spatialDose may be impactful when considering high-dose gradients of radiation in the PGs. The proposed DIR model can allow more accurate PG alignment than the standard model and improve dose estimation and toxicity prediction modeling.