A classifier-based expert system was developed to compare delivered and planned radiation therapy in prostate cancer patients. Its aim is to automatically identify patients that can benefit from an adaptive treatment strategy. The study predominantly addresses dosimetric uncertainties and critical issues caused by motion of hollow organs. 1200 MVCT images of 38 prostate adenocarcinoma cases were analyzed. An automatic daily re-contouring of structures (i.e. rectum, bladder and femoral heads), rigid/deformable registration and dose warping was carried out to simulate dose and volume variations during therapy. Support vector machine, K-means clustering algorithms and similarity index analysis were used to create an unsupervised predictive tool to detect incorrect setup and/or morphological changes as a consequence of inadequate patient preparation due to stochastic physiological changes, supporting clinical decision-making. After training on a dataset that was considered sufficiently dosimetrically stable, the system identified two equally sized macro clusters with distinctly different volumetric and dosimetric baseline properties and defined thresholds for these two clusters. Application to the test cohort resulted in 25% of the patients located outside the two macro clusters thresholds and which were therefore suspected to be dosimetrically unstable. In these patients, over the treatment course, mean volumetric changes of 30 and 40% for rectum and bladder were detected which possibly represents values justifying adjustment of patient preparation, frequent re-planning or a plan-of-the-day strategy. Based on our research, by combining daily IGRT images with rigid/deformable registration and dose warping, it is possible to apply a machine learning approach to the clinical setting obtaining useful information for a decision regarding an individualized adaptive strategy. Especially for treatments influenced by the movement of hollow organs, this could reduce inadequate treatments and possibly reduce toxicity, thereby increasing overall RT efficacy.
Genovesi (2019) Magnetic resonance imaging (MRI) compared with computed tomography (CT) for interobserver agreement of gross tumor volume delineation in pancreatic cancer: a multiinstitutional contouring study on behalf of the AIRO group for gastrointestinal cancers, Acta Oncologica, 58:4, 439-447, ABSTRACT Background: Due to the high soft tissue resolution, magnetic resonance imaging (MRI) could improve the accuracy of pancreatic tumor delineation in radiation treatment planning. A multi-institutional study was proposed to evaluate the impact of MRI on inter-observer agreement in gross tumor volume (GTV) and duodenum delineation for pancreatic cancer compared with computer tomography (CT). Material and Methods: Two clinical cases of borderline resectable (Case 1) and unresectable (Case 2) pancreatic cancer were selected. In two sequential steps, diagnostic contrast-enhanced CT scan and MRI sequences were sent to the participating centers. CT-GTVs were contoured while blinded to MRI data sets. DICE index was used to evaluate the spatial overlap accuracy. Results: Thirty-one radiation oncologists from different Institutions submitted the delineated volumes. CT-and MRI-GTV mean volumes were 21.6 ± 9.0 cm 3 and 17.2 ± 6.0 cm 3 , respectively for Case 1, and 31.3 ± 15.6 cm 3 and 33.2 ± 20.2 cm 3 , respectively for Case 2. Resulting MRI-GTV mean volume was significantly smaller than CT-GTV in the borderline resectable case (p < .05). A substantial agreement was shown by the median DICE index for CT-and MRI-GTV resulting as 0.74 (IQR: 0.67-0.75) and 0.61 (IQR: 0.57-0.67) for Case 1; a moderate agreement was instead reported for Case 2: 0.59 (IQR:0.52-0.66) and 0.53 (IQR:0.42-0.62) for CT-and MRI-GTV, respectively. Conclusion: Diagnostic MRI resulted in smaller GTV in borderline resectable case with a substantial agreement between observers, and was comparable to CT scan in interobserver variability, in both cases. The greater variability in the unresectable case underlines the critical issues related to the outlining when vascular structures are more involved. The integration of MRI with contrast-enhancement CT, thanks to its high definition of tumor relationship with neighboring vessels, could offer a greater accuracy of target delineation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.