Purpose
Radiomics is a growing field of image quantitation, but it lacks stable and high‐quality software systems. We extended the capabilities of the Computational Environment for Radiological ...Research (CERR) to create a comprehensive, open‐source, MATLAB‐based software platform with an emphasis on reproducibility, speed, and clinical integration of radiomics research.
Method
The radiomics tools in CERR were designed specifically to quantitate medical images in combination with CERR's core functionalities of radiological data import, transformation, management, image segmentation, and visualization. CERR allows for batch calculation and visualization of radiomics features, and provides a user‐friendly data structure for radiomics metadata. All radiomics computations are vectorized for speed. Additionally, a test suite is provided for reconstruction and comparison with radiomics features computed using other software platforms such as the Insight Toolkit (ITK) and PyRadiomics. CERR was evaluated according to the standards defined by the Image Biomarker Standardization Initiative. CERR's radiomics feature calculation was integrated with the clinically used MIM software using its MATLAB® application programming interface.
Results
The CERR provides a comprehensive computational platform for radiomics analysis. Matrix formulations for the compute‐intensive Haralick texture resulted in speeds that are superior to the implementation in ITK 4.12. For an image discretized into 32 bins, CERR achieved a speedup of 3.5 times over ITK. The CERR test suite enabled the successful identification of programming errors as well as genuine differences in radiomics definitions and calculations across the software packages tested.
Conclusion
The CERR's radiomics capabilities are comprehensive, open‐source, and fast, making it an attractive platform for developing and exploring radiomics signatures across institutions. The ability to both choose from a wide variety of radiomics implementations and to integrate with a clinical workflow makes CERR useful for retrospective as well as prospective research analyses.
•Deep learning can be used to contour organs at risk for numerous patients.•Deep learning outperforms atlas based auto-segmentation in head and neck organs at risk contouring.•Subjective analysis ...indicated no need manual corrections in many deep learning generated contours.•Deep learning auto-contouring has the potential to decrease the clinical burden.
Adequate head and neck (HN) organ-at-risk (OAR) delineation is crucial for HN radiotherapy and for investigating the relationships between radiation dose to OARs and radiation-induced side effects. The automatic contouring algorithms that are currently in clinical use, such as atlas-based contouring (ABAS), leave room for improvement. The aim of this study was to use a comprehensive evaluation methodology to investigate the performance of HN OAR auto-contouring when using deep learning contouring (DLC), compared to ABAS.
The DLC neural network was trained on 589 HN cancer patients. DLC was compared to ABAS by providing each method with an independent validation cohort of 104 patients, which had also been manually contoured. For each of the 22 OAR contours – glandular, upper digestive tract and central nervous system (CNS)-related structures – the dice similarity coefficient (DICE), and absolute mean and max dose differences (|Δmean-dose| and |Δmax-dose|) performance measures were obtained. For a subset of 7 OARs, an evaluation of contouring time, inter-observer variation and subjective judgement was performed.
DLC resulted in equal or significantly improved quantitative performance measures in 19 out of 22 OARs, compared to the ABAS (DICE/|Δmean dose|/|Δmax dose|: 0.59/4.2/4.1 Gy (ABAS); 0.74/1.1/0.8 Gy (DLC)). The improvements were mainly for the glandular and upper digestive tract OARs. DLC significantly reduced the delineation time for the inexperienced observer. The subjective evaluation showed that DLC contours were more often preferable to the ABAS contours overall, were considered to be more precise, and more often confused with manual contours. Manual contours still outperformed both DLC and ABAS; however, DLC results were within or bordering the inter-observer variability for the manual edited contours in this cohort.
The DLC, trained on a large HN cancer patient cohort, outperformed the ABAS for the majority of HN OARs.
To investigate the impact of setup and range uncertainties, breathing motion, and interplay effects using scanning pencil beams in robustly optimized intensity modulated proton therapy (IMPT) for ...stage III non-small cell lung cancer (NSCLC).
Three-field IMPT plans were created using a minimax robust optimization technique for 10 NSCLC patients. The plans accounted for 5- or 7-mm setup errors with ±3% range uncertainties. The robustness of the IMPT nominal plans was evaluated considering (1) isotropic 5-mm setup errors with ±3% range uncertainties; (2) breathing motion; (3) interplay effects; and (4) a combination of items 1 and 2. The plans were calculated using 4-dimensional and average intensity projection computed tomography images. The target coverage (TC, volume receiving 95% of prescribed dose) and homogeneity index (D2 - D98, where D2 and D98 are the least doses received by 2% and 98% of the volume) for the internal clinical target volume, and dose indexes for lung, esophagus, heart and spinal cord were compared with that of clinical volumetric modulated arc therapy plans.
The TC and homogeneity index for all plans were within clinical limits when considering the breathing motion and interplay effects independently. The setup and range uncertainties had a larger effect when considering their combined effect. The TC decreased to <98% (clinical threshold) in 3 of 10 patients for robust 5-mm evaluations. However, the TC remained >98% for robust 7-mm evaluations for all patients. The organ at risk dose parameters did not significantly vary between the respective robust 5-mm and robust 7-mm evaluations for the 4 error types. Compared with the volumetric modulated arc therapy plans, the IMPT plans showed better target homogeneity and mean lung and heart dose parameters reduced by about 40% and 60%, respectively.
In robustly optimized IMPT for stage III NSCLC, the setup and range uncertainties, breathing motion, and interplay effects have limited impact on target coverage, dose homogeneity, and organ-at-risk dose parameters.
Purpose A relationship between mean heart dose (MHD) and acute coronary event (ACE) rate was reported in a study of patients with breast cancer (BC). The main objective of our cohort study was to ...validate this relationship and investigate if other dose-distribution parameters are better predictors for ACEs than MHD. Patients and Methods The cohort consisted of 910 consecutive female patients with BC treated with radiotherapy (RT) after breast-conserving surgery. The primary end point was cumulative incidence of ACEs within 9 years of follow-up. Both MHD and various dose-distribution parameters of the cardiac substructures were collected from three-dimensional computed tomography planning data. Results The median MHD was 2.37 Gy (range, 0.51 to 15.25 Gy). The median follow-up time was 7.6 years (range, 0.1 to 10.1 years), during which 30 patients experienced an ACE. The cumulative incidence of ACE increased by 16.5% per Gy (95% CI, 0.6 to 35.0; P = .042). Analysis showed that the volume of the left ventricle receiving 5 Gy (LV-V5) was the most important prognostic dose-volume parameter. The most optimal multivariable normal tissue complication probability model for ACEs consisted of LV-V5, age, and weighted ACE risk score per patient (c-statistic, 0.83; 95% CI, 0.75 to 0.91). Conclusion A significant dose-effect relationship was found for ACEs within 9 years after RT. Using MHD, the relative increase per Gy was similar to that reported in the previous study. In addition, LV-V5 seemed to be a better predictor for ACEs than MHD. This study confirms the importance of reducing exposure of the heart to radiation to avoid excess risk of ACEs after radiotherapy for BC.
To compare the clinical benefit of robust optimized Intensity Modulated Proton Therapy (minimax IMPT) with current photon Intensity Modulated Radiation Therapy (IMRT) and PTV-based IMPT for head and ...neck cancer (HNC) patients. The clinical benefit is quantified in terms of both Normal Tissue Complication Probability (NTCP) and target coverage in the case of setup and range errors.
For 10 HNC patients, PTV-based IMRT (7 fields), minimax and PTV-based IMPT (2, 3, 4, 5 and 7 fields) plans were tested on robustness. Robust optimized plans differed from PTV-based plans in that they target the CTV and penalize possible error scenarios, instead of using the static isotropic CTV-PTV margin. Perturbed dose distributions of all plans were acquired by simulating in total 8060 setup (±3.5 mm) and range error (±3%) combinations. NTCP models for xerostomia and dysphagia were used to predict the clinical benefit of IMPT versus IMRT.
The robustness criterion was met in the IMRT and minimax IMPT plans in all error scenarios, but this was only the case in 1 of 40 PTV-based IMPT plans. Seven (out of 10) patients had relatively large NTCP reductions in minimax IMPT plans compared to IMRT. For these patients, xerostomia and dysphagia NTCP values were reduced by 17.0% (95% CI; 13.0-21.1) and 8.1% (95% CI; 4.9-11.2) on average with minimax IMPT. Increasing the number of fields did not contribute to plan robustness, but improved organ sparing.
The estimated clinical benefit in terms of NTCP of robust optimized (minimax) IMPT is greater than that of IMRT and PTV-based IMPT in HNC patients. Furthermore, the target coverage of minimax IMPT plans in the presence of errors was comparable to IMRT plans.
Incontinence, hematuria, voiding frequency and pain during voiding are possible side effects of radiotherapy among patients treated for prostate cancer. The objective of this study was to develop ...multivariable NTCP models for these side effects.
This prospective cohort study was composed of 243 patients with localized or locally advanced prostate cancer (stage T1-3). Genito-urinary (GU) toxicity was assessed using a standardized follow-up program. The GU toxicity endpoints were scored using the Common Terminology Criteria for Adverse Events version 3.0 (CTCAE 3.0) scoring system. The full bladder and different anatomical subregions within the bladder were delineated. A least absolute shrinkage and selection operator (LASSO) logistic regression analysis was used to analyze dose volume effects on the four individual endpoints.
In the univariable analysis, urinary incontinence was significantly associated with dose distributions in the trigone (V55-V75, mean). Hematuria was significantly associated with the bladder wall dose (V40-V75, mean), bladder dose (V70-V75), cardiovascular disease and anticoagulants use. Pain during urinating was associated with the dose to the trigone (V50-V75, mean) and with trans transurethral resection of the prostate (TURP). In the final multivariable model urinary incontinence was associated with the mean dose of the trigone. Hematuria was associated with bladder wall dose (V75) and cardiovascular disease, while pain during urinating was associated with trigone dose (V75) and TURP. No significant associations were found for increase in voiding frequency.
Radiation-induced urinary side effects are associated with dose distributions to different organs as risk. Given the dose effect relationships found, decreasing the dose to the trigone and bladder wall may reduce the incidence of incontinence, pain during voiding and hematuria, respectively.
Tumor segmentation is a fundamental step for radiotherapy treatment planning. To define an accurate segmentation of the primary tumor (GTVp) of oropharyngeal cancer patients (OPC) each image volume ...is explored slice-by-slice from different orientations on different image modalities. However, the manual fixed boundary of segmentation neglects the spatial uncertainty known to occur in tumor delineation. This study proposes a novel deep learning-based method that generates probability maps which capture the model uncertainty in the segmentation task.
We included 138 OPC patients treated with (chemo)radiation in our institute. Sequences of 3 consecutive 2D slices of concatenated FDG-PET/CT images and GTVp contours were used as input. Our framework exploits inter and intra-slice context using attention mechanisms and bi-directional long short term memory (Bi-LSTM). Each slice resulted in three predictions that were averaged. A 3-fold cross validation was performed on sequences extracted from the axial, sagittal, and coronal plane. 3D volumes were reconstructed and single- and multi-view ensembling were performed to obtain final results. The output is a tumor probability map determined by averaging multiple predictions.
Model performance was assessed on 25 patients at different probability thresholds. Predictions were the closest to the GTVp at a threshold of 0.9 (mean surface DSC of 0.81, median HD
of 3.906 mm).
The promising results of the proposed method show that is it possible to offer the probability maps to radiation oncologists to guide them in a in a slice-by-slice adaptive GTVp segmentation.
•Heart dose volume parameters predicted the risk on cardiac toxicity.•Lung dose volume parameters predicted the risk on pulmonary toxicity.•Overall survival was associated with pulmonary but not ...cardiac toxicity.•Overall survival was best predicted by lung dose in amongst clinical parameters.
The aim of this study was to evaluate which clinical and treatment-related factors are associated with heart and lung toxicity in oesophageal cancer patients treated with chemoradiation (CRT). The secondary objective was to analyse whether these toxicities are associated with overall survival (OS).
The study population consisted of a retrospective cohort of 216 oesophageal cancer patients treated with curative CRT. Clinical and treatment related factors were analysed for OS and new pulmonary and cardiac events by multivariable regression analyses. The effect of these toxicities on OS was assessed by Kaplan Meyer analyses.
Multivariable analysis revealed that pulmonary toxicity was best predicted by the mean lung dose. Cardiac complications were diverse; the most frequently occurring complication was pericardial effusion. Several cardiac dose parameters correlated with this endpoint. Patients developing radiation pneumonitis had significantly worse OS than patients without radiation pneumonitis, while no difference was observed in OS between patients with and without pericardial effusion. OS was best predicted by the V45 of the lung and tumour stage. None of the cardiac dose parameters predicted OS in multivariable analyses.
Cardiac dose volume parameters predicted the risk of pericardial effusion and pulmonary dose volume parameters predicted the risk of radiation pneumonitis. However, in this patient cohort, pulmonary DVH parameters (V45) were more important for OS than cardiac DVH parameters. These results suggest that reducing the cardiac dose at the expense of the dose to the lungs might not always be a good strategy in oesophageal cancer patients.
BACKGROUND
The goal of this study was to comprehensively investigate the association of chemotherapy with trajectories of acute symptom development and late symptom recovery in patients with ...oropharyngeal cancer (OPC) by comparing symptom burden between induction chemotherapy followed by concurrent chemoradiotherapy (ICRT), concurrent chemo‐radiotherapy (CRT), or radiotherapy (RT) alone.
METHODS
Among a registry of 717 patients with OPC, the 28‐item patient‐reported MD Anderson Symptom Inventory–Head and Neck Module (MDASI‐HN) symptoms were collected prospectively at baseline, weekly during RT, and 1.5, 3 to 6, 12, and 18 to 24 months after RT. The effect of the treatment regimen (ICRT, CRT, and RT alone) was examined with mixed‐model analyses for the acute and late period. In the CRT cohort, the chemotherapy agent relationship with symptoms was investigated.
RESULTS
Chemoradiation (ICRT/CRT) compared with RT alone resulted in significantly higher acute symptom scores in the majority of MDASI‐HN symptoms (ie, 21 out of 28). No late symptom differences between treatment with or without chemotherapy were observed that were not attributable to ICRT. Nausea was lower for CRT with carboplatin than for CRT with cisplatin; cetuximab was associated with particularly higher scores for acute and late skin, mucositis, and 6 other symptoms. The addition of ICRT compared with CRT or RT alone was associated with a significant increase in numbness and shortness of breath.
CONCLUSION
The addition of chemotherapy to definitive RT for OPC patients was associated with significantly worse acute symptom outcomes compared with RT alone, which seems to attenuate in the late posttreatment period. Moreover, induction chemotherapy was specifically associated with worse numbness and shortness of breath during and after treatment.
LAY SUMMARY
Chemotherapy is frequently used in addition to radiotherapy cancer treatment, yet the (added) effect on treatment‐induced over time is not comprehensively investigated
This study shows that chemotherapy adds to the symptom severity reported by patients, especially during treatment
Induction/concurrent chemotherapy significantly augments patient‐reported symptom burden of radiotherapy among patients with oropharyngeal cancer, as worse acute symptom outcomes are observed compared with radiotherapy alone. Induction chemotherapy is associated with greater numbness and shortness of breath during and after treatment.
Radiation-induced acute coronary events (ACEs) may occur as a treatment-related late adverse effect of breast cancer (BC) radiation. However, the underlying mechanisms behind this radiation-induced ...cardiac disease remain to be determined. The objective of this study was to test the hypothesis that radiation dose to calcified atherosclerotic plaques in the left anterior descending coronary artery (LAD) is a better predictor for ACEs than radiation dose to the whole heart or left ventricle in patients with BC treated with radiation therapy.
The study cohort consisted of 910 patients with BC treated with postoperative radiation therapy after breast-conserving surgery. In total, 163 patients had an atherosclerotic plaque in the LAD. The endpoint was the occurrence of an ACE after treatment. For each individual patient, the mean heart dose, volume of the left ventricle receiving ≥5 Gy (LV-V5), mean LAD dose, and mean dose to calcified atherosclerotic plaques in the LAD, if present, were acquired based on planning computed tomography scans. Cox regression analysis was used to analyze the effects on the cumulative incidence of ACEs.
The median follow-up time was 9.2 years (range, 0.1-14.3 years). In total, 38 patients (4.2%) developed an ACE during follow-up. For patients with an atherosclerotic plaque (n = 163), the mean dose to the atherosclerotic plaque was the strongest predictor for ACEs, even after correction for cardiovascular risk factors (hazard ratio HR, 1.269; 95% CI, 1.090-1.477; P = .002). The LV-V5 was associated with ACEs in patients without atherosclerotic plaques in the LAD (n = 680) (HR, 1.021; 95% CI, 1.003-1.039; P = .023).
The results of this study suggest that radiation dose to pre-existing calcified atherosclerotic plaques in the LAD is strongly associated with the development of ACEs in patients with BC.