Largest diameter delineations can substitute 3D tumor volume delineations for radiomics prediction of human papillomavirus status on MRI's of oropharyngeal cancer.

PURPOSE: Laborious and time-consuming tumor segmentations are one of the factors that impede adoption of radiomics in the clinical routine. This study investigates model performance using alternative tumor delineation strategies in models predictive of human papillomavirus (HPV) in oropharyngeal squamous cell carcinoma (OPSCC). METHODS: Of 153 OPSCC patients, HPV status was determined using p16/p53 immunohistochemistry. MR-based radiomic features were extracted within 3D delineations by an inexperienced observer, experienced radiologist or radiation oncologist, and within a 2D delineation of the largest axial tumor diameter and 3D spheres within the tumor. First, logistic regression prediction models were constructed and tested separately for each of these six delineation strategies. Secondly, the model trained on experienced delineations was tested using these delineation strategies. The latter methodology was repeated with the omission of shape features. Model performance was evaluated using area under the curve (AUC), sensitivity and specificity. RESULTS: Models constructed and tested using single-slice delineations (AUC/Sensitivity/Specificity: 0.84/0.75/0.84) perform better compared to 3D experienced observer delineations (AUC/Sensitivity/Specificity: 0.76/0.76/0.71), where models based on 4 mm sphere delineations (AUC/Sensitivity/Specificity: 0.77/0.59/0.71) show similar performance. Similar performance was found when experienced and largest diameter delineations (AUC/Sens/Spec: 0.76/0.75/0.65 vs 0.76/0.69/0.69) was used to test the model constructed using experienced delineations without shape features. CONCLUSION: Alternative delineations can substitute labor and time intensive full tumor delineations in a model that predicts HPV status in OPSCC. These faster delineations may improve adoption of radiomics in the clinical setting. Future research should evaluate whether these alternative delineations are valid in other radiomics models.

Simple delineations cannot substitute full 3d tumor delineations for MR-based radiomics prediction of locoregional control in oropharyngeal cancer.

BACKGROUND AND PURPOSE: Manual delineation of head and neck tumor contours for radiomics analyses is tedious and time consuming. This study investigates if fast or readily available tumor contours can substitute full tumor contours by an experienced observer for an MR-based radiomics model to predict locoregional control (LRC) in oropharyngeal squamous cell carcinoma (OPSCC) tumors. MATERIALS AND METHODS: Radiomic features were extracted from postcontrast T1-weighted MRIs of 177 OPSCC primary tumors using six different manual delineation strategies. LRC prediction models based on recursive feature elimination combined with logistic regression were built. Models were trained and tested on data from each separate delineation. Additionally, the model derived from segmentations from the experienced reader was tested by each of the alternative delineations. Complementary, this was repeated with removal of size and shape features. Model performance was evaluated using area under the curve (AUC). RESULTS: Prediction performance of the experienced radiologist tumor delineation (AUC: 0.74) was superior compared to all other delineations when trained and tested (AUCs: 0.41-0.56) or trained on experienced delineations and tested (AUC: 0.56-0.67) on alternative segmentations. Removal of size and shape features considerably decreases prediction performance (AUC: 0.54). Applying the model based on expert delineations to spherical or single slice delineations makes prediction worthless since these models predict one class. CONCLUSION: Fast or readily available contours cannot substitute full expert tumor delineations in radiomics models predictive of LRC in OPSCC.

The use of deep learning on endoscopic images to assess the response of rectal cancer after chemoradiation.

BACKGROUND: Accurate response evaluation is necessary to select complete responders (CRs) for a watch-and-wait approach. Deep learning may aid in this process, but so far has never been evaluated for this purpose. The aim was to evaluate the accuracy to assess response with deep learning methods based on endoscopic images in rectal cancer patients after neoadjuvant therapy. METHODS: Rectal cancer patients diagnosed between January 2012 and December 2015 and treated with neoadjuvant (chemo)radiotherapy were retrospectively selected from a single institute. All patients underwent flexible endoscopy for response evaluation. Diagnostic performance (accuracy, area under the receiver operator characteristics curve (AUC), positive- and negative predictive values, sensitivities and specificities) of different open accessible deep learning networks was calculated. Reference standard was histology after surgery, or long-term outcome (>2 years of follow-up) in a watch-and-wait policy. RESULTS: 226 patients were included for the study (117(52%) were non-CRs; 109(48%) were CRs). The accuracy, AUC, positive- and negative predictive values, sensitivity and specificity of the different models varied from 0.67-0.75%, 0.76-0.83%, 67-74%, 70-78%, 68-79% to 66-75%, respectively. Overall, EfficientNet-B2 was the most successful model with the highest diagnostic performance. CONCLUSIONS: This pilot study shows that deep learning has a modest accuracy (AUCs 0.76-0.83). This is not accurate enough for clinical decision making, and lower than what is generally reported by experienced endoscopists. Deep learning models can however be further improved and may become useful to assist endoscopists in evaluating the response. More well-designed prospective studies are required.

Improved outcome prediction of oropharyngeal cancer by combining clinical and MRI features in machine learning models.

OBJECTIVES: New markers are required to predict chemoradiation response in oropharyngeal squamous cell carcinoma (OPSCC) patients. This study evaluated the ability of magnetic resonance (MR) radiomics to predict locoregional control (LRC) and overall survival (OS) after chemoradiation and aimed to determine whether this has added value to traditional clinical outcome predictors. METHODS: 177 OPSCC patients were eligible for this study. Radiomic features were extracted from the primary tumor region in T1-weighted postcontrast MRI acquired before chemoradiation. Logistic regression models were created using either clinical variables (clinical model), radiomic features (radiomic model) or clinical and radiomic features combined (combined model) to predict LRC and OS 2-years posttreatment. Model performance was evaluated using area under the curve (AUC), 95 % confidence intervals were calculated using 500 iterations of bootstrap. All analyses were performed for the total population and the Human papillomavirus (HPV) negative tumor subgroup. RESULTS: A combined model predicted treatment outcome with a higher AUC (LRC: 0.745 [0.734-0.757], OS: 0.744 [0.735-0.753]) than the clinical model (LRC: 0.607 [0.594-0.620], OS: 0.708 [0.697-0.719]). Performance of the radiomic model was comparable to the combined model for LRC (AUC: 0.740 [0.729-0.750]), but not for OS prediction (AUC: 0.654 [0.646-0.662]). In HPV negative patients, the performance of all models was not sufficient with AUCs ranging from 0.587 to 0.660 for LRC and 0.559 to 0.600 for OS prediction. CONCLUSION: Predictive models that include clinical variables and radiomic tumor features derived from MR images of OPSCC better predict LRC after chemoradiation than models based on only clinical variables. Predictive models that include clinical variables perform better than models based on only radiomic features for the prediction of OS.

Clinical variables and magnetic resonance imaging-based radiomics predict human papillomavirus status of oropharyngeal cancer.

BACKGROUND: Human papillomavirus (HPV)-positive oropharyngeal squamous cell carcinoma (OPSCC) have better prognosis and treatment response compared to HPV-negative OPSCC. This study aims to noninvasively predict HPV status of OPSCC using clinical and/or radiological variables. METHODS: Seventy-seven magnetic resonance radiomic features were extracted from T1-weighted postcontrast images of the primary tumor of 153 patients. Logistic regression models were created to predict HPV status, determined with immunohistochemistry, based on clinical variables, radiomic features, and its combination. Model performance was evaluated using area under the curve (AUC). RESULTS: Model performance showed AUCs of 0.794, 0.764, and 0.871 for the clinical, radiomic, and combined models, respectively. Smoking, higher T-classification (T3 and T4), larger, less round, and heterogeneous tumors were associated with HPV-negative tumors. CONCLUSION: Models based on clinical variables and/or radiomic tumor features can predict HPV status in OPSCC patients with good performance and can be considered when HPV testing is not available.