TY - JOUR
T1 - Magnetic resonance imaging (MRI) compared with computed tomography (CT) for interobserver agreement of gross tumor volume delineation in pancreatic cancer
T2 - a multi-institutional contouring study on behalf of the AIRO group for gastrointestinal cancers
AU - Caravatta, Luciana
AU - Cellini, Francesco
AU - Simoni, Nicola
AU - Rosa, Consuelo
AU - Niespolo, Rita Marina
AU - Lupattelli, Marco
AU - Picardi, Vincenzo
AU - Macchia, Gabriella
AU - Sainato, Aldo
AU - Mantello, Giovanna
AU - Dionisi, Francesco
AU - Rosetto, Maria Elena
AU - Fusco, Vincenzo
AU - Navarria, Federico
AU - De Paoli, Antonino
AU - Guido, Alessandra
AU - Vecchi, Claudio
AU - Basilico, Raffaella
AU - Cianci, Roberta
AU - Delli Pizzi, Andrea
AU - Di Nicola, Marta
AU - Mattiucci, Gian Carlo
AU - Valentini, Vincenzo
AU - Morganti, Alessio Giuseppe
AU - Genovesi, Domenico
PY - 2019/4
Y1 - 2019/4
N2 - 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 cm3 and 17.2 ± 6.0 cm3, respectively for Case 1, and 31.3 ± 15.6 cm3 and 33.2 ± 20.2 cm3, 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.
AB - 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 cm3 and 17.2 ± 6.0 cm3, respectively for Case 1, and 31.3 ± 15.6 cm3 and 33.2 ± 20.2 cm3, 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.
KW - Aged
KW - Female
KW - Follow-Up Studies
KW - Gastrointestinal Neoplasms/diagnostic imaging
KW - Humans
KW - Magnetic Resonance Imaging/methods
KW - Male
KW - Observer Variation
KW - Pancreatic Neoplasms/diagnostic imaging
KW - Prognosis
KW - Radiotherapy Planning, Computer-Assisted
KW - Retrospective Studies
KW - Tomography, X-Ray Computed/methods
KW - Tumor Burden
U2 - 10.1080/0284186X.2018.1546899
DO - 10.1080/0284186X.2018.1546899
M3 - Article
C2 - 30632876
VL - 58
SP - 439
EP - 447
JO - Acta Oncologica
JF - Acta Oncologica
SN - 0001-6381
IS - 4
ER -