Predicting necessity of daily online adaptive replanning based on wavelet image features for MRI guided adaptive radiation therapy

PURPOSE

Online adaptive replanning (OLAR) is generally labor-intensive and time-consuming during MRI-guided adaptive radiation therapy (MRgART). This work aims to develop a method to determine OLAR necessity during MRgART.

METHODS

A machine learning classifier was developed to predict OLAR necessity based on wavelet multiscale texture features extracted from daily MRIs and was trained and tested with data from 119 daily MRI datasets acquired during MRgART for 24 pancreatic cancer patients treated on a 1.5 T MR-Linac. Spearman correlations, interclass correlation (ICC), coefficient of variance (COV), t-test (p < 0.05), self-organized map (SOM) and maximum stable extremal region (MSER) algorithm were used to determine candidate features, which were used to build the prediction models using Bayesian classifiers. The model performance was judged using the AUC of the ROC curve.

RESULTS

Spearman correlation identified 123 features that were not redundant (r < 0.9). Of them 82 showed high ICC for repositioning > 0.6, 67 had a COV greater than 9% for OLAR. Among the 38 features passed the t-test, 25 passed the SOM and 12 passed the MSER. These final 12 features were used to build the classifier model. The combination of 2-3 features at a time was used to build the classifier models. The best performing model was a 3-feature combination, which can predict OLAR necessity with a CV-AUC of 0.98.

CONCLUSIONS

A machine learning classifier model based on the wavelet features extracted from daily MRI for pancreatic cancer was developed to automatically and objectively determine if OLAR is necessary for a treatment fraction avoiding unnecessary effort during MRgART.

Set-Up Errors, Organ Motion, Tumour Regression and its Implications on Internal Target Volume-Planning Target Volume During Cervical Cancer Radiotherapy: Results From a Prospective Study

AIMS

Uterocervical motions and organ filling during cervical cancer conformal radiotherapy is complex. This prospective, observational study investigated set-up margins (clinical target vo, ume [CTV] to planning target volume [PTV]) for pelvic nodal CTV and internal margin (CTV to internal target volume [ITV]) expansions for uterocervical movements during cervical cancer radiotherapy.

MATERIALS AND METHODS

During cervical cancer radiotherapy, a daily kilovoltage, cone-beam computed tomography (CBCT) scan was acquired. Bony anatomy-based rigid co-registration and matching to vessels/pelvic nodal region was carried out to document shifts, errors (systematic and random) and to calculate CTV to PTV margins. Subsequently, soft-tissue matching was carried out at the mid-cervical region and uterine fundus to record shifts, errors and to calculate CTV to ITV margins.

RESULTS

In 67 patients, 1380 CBCT scans were analysed. The mean (±standard deviation) couch shifts for CTV pelvic nodal region in all directions were within 4.5-5.3 mm, systematic and random errors 3.0-3.6 mm and set-up margins of within 10 mm (except anterior margin 10.3 mm). For the mid-cervical region, mean shifts were 4.5-5.5 mm, systematic and random errors 2-4 mm amounting to <10 mm internal margins (CTV-ITV for cervix) and for uterine fundus mean (±standard deviation) shifts were larger in the superior direction (12.1 mm) but 4.0-7.5 mm in other directions, systematic and random errors 2-7 mm amounting to anisotropic margins in various directions (10 mm in anterior-posterior and lateral directions, 12-20 mm in superior-inferior directions) (CTV-ITV for uterine fundus).

CONCLUSION

Our study suggests anisotropic CTV to ITV and CTV to PTV margins for cervical cancer radiotherapy.

Safety of image-guided radiotherapy in definitive radiotherapy for localized prostate cancer: a population-based analysis

Objectives:

Image-guided radiotherapy (IGRT) is a recommended advanced radiation technique that is associated with fewer acute and chronic toxicities. However, one Phase III trial showed worse overall survival in the IGRT arm. The purpose of this observational study is to evaluate the impact of IGRT on overall survival.

Methods:

We used the Taiwan Cancer Registry Database to enroll cT1-4N0M0 prostate cancer patients who received definitive radiotherapy between 2011 and 2015. We used inverse probability treatment weighting (IPW) to construct balanced IGRT and non-IGRT groups. We compared the overall survival of those in the IGRT and non-IGRT groups. Supplementary analyses (SA) were performed with alternative covariates in propensity score (PS) models and PS approaches. The incidence rates of prostate cancer mortality (IPCM), other cancer mortality (IOCM), and cardiovascular mortality (ICVM) were also evaluated.

Results:

There were 360 patients in the IGRT arm and 476 patients in the non-IGRT arm. The median follow-up time was 50 months. The 5-year overall survival was 88% in the IGRT arm and 86% in the non-IGRT arm (adjusted hazard ratio [HR] of death = 0.93; 95% CI, 0.61–1.45; p = 0.77). The SA also showed no significant differences in the overall survival between those in the IGRT and non-IGRT arms. Both groups did not significantly differ in terms of IPCM, IOCM, and ICVM.

Conclusions:

The overall survival of localized prostate cancer patients who underwent IGRT was not inferior to those who did not.

Advances in knowledge:

We demonstrated that the overall survival for prostate cancer patients with IGRT was not worse than those who did not undergo IGRT; this important outcome comparison has not been previously examined in the general population.

The Potential Value of MRI in External-Beam Radiotherapy for Cervical Cancer

The reference standard treatment for cervical cancer is concurrent chemoradiotherapy followed by magnetic resonance imaging (MRI)-guided brachytherapy. Improvements in brachytherapy have increased local control rates, but late toxicity remains high with rates of 11% grade ≥3. The primary clinical target volume (CTV) for external-beam radiotherapy includes the cervix and uterus, which can show significant inter-fraction motion. This means that generous margins are required to cover the primary CTV, increasing the radiation dose to organs at risk and, therefore, toxicity. A number of image-guided radiotherapy techniques (IGRT) have been developed, but motion can be random and difficult to predict prior to treatment. In light of the development of integrated MRI linear accelerators, this review discusses the potential value of MRI in external-beam radiotherapy. Current solutions for managing pelvic organ motion are reviewed, including the potential for online adaptive radiotherapy. The impacts of the use of MRI in tumour delineation and in the delivery of stereotactic ablative body radiotherapy (SABR) are highlighted. The potential role and challenges of using multi parametric MRI to guide radiotherapy are also discussed.

Problems and solutions in IGRT for cervical cancer

The contribution of Image-guided Radiotherapy (IGRT) to modern radiotherapy is undeniable, being the way to bring into daily practice the dosimetric benefits of Intensity-Modulated Radiotherapy (IMRT). Organ and target motion is constant and unpredictable at the pelvis, thus posing a challenge to the safe execution of IMRT. There are potential benefits of IMRT in the radical treatment of cervical cancer patients, both in terms of dose escalation and decrease of toxicity. But it is essential to find IGRT solutions to control the aspects that can lead to geographic miss targeting or organs at risk (OAR) overdose. This review seeks to describe the problems and possible solutions in the clinical implementation of IMRT/IGRT protocols to treat intact cervical cancer patients.