7 August 2017 in European Radiology
1 January 2020 in Korean Journal of Radiology
TCthe Korean Society of Abdominal Radiology Study Group for Rectal Cancer
the Korean Society of Abdominal Radiology Study Group for Rectal Cancer
+5
Park SH, et al. Korean J Radiol. 2020 Jul;21(7):812-828. https://doi.org/10.3348/kjr.2020.0483
1 January 2015 in Journal of the Korean Medical Association
Sohn DK, et al. J Korean Med Assoc. 2015 May;58(5):420-432. http://dx.doi.org/10.5124/jkma.2015.58.5.420
17 December 2019 in IEEE Access
In preoperative imaging, the demarcation of rectal cancer with magnetic resonance images provides an important basis for cancer staging and treatment planning. Recently, deep learning has greatly improved the state-of-the-art method in automatic segmentation. However, limitations in data availability in the medical field can cause large variance and consequent overfitting to medical image segmentation networks. In this study, we propose methods to reduce the model variance of a rectal cancer segmentation network by adding a rectum segmentation task and performing data augmentation; the geometric correlation between the rectum and rectal cancer motivated the former approach. Moreover, we propose a method to perform a bias-variance analysis within an arbitrary region-of-interest (ROI) of a segmentation network, which we applied to assess the efficacy of our approaches in reducing model variance. As a result, adding a rectum segmentation task reduced the model variance of the rectal cancer segmentation network within tumor regions by a factor of 0.90; data augmentation further reduced the variance by a factor of 0.89. These approaches also reduced the training duration by a factor of 0.96 and a further factor of 0.78, respectively. Our approaches will improve the quality of rectal cancer staging by increasing the accuracy of its automatic demarcation and by providing rectum boundary information since rectal cancer staging requires the demarcation of both rectum and rectal cancer. Besides such clinical benefits, our method also enables segmentation networks to be assessed with bias-variance analysis within an arbitrary ROI, such as a cancerous region.
1 December 2018 in Journal of Surgical Research
4 November 2013 in Radiation Oncology
Background: To compare the short-term tumor response and long-term clinical outcome of two preoperative chemoradiotherapy (CRT) regimens for locally advanced rectal cancer. Methods: This study included 231 patients scheduled for preoperative CRT using two chemotherapeutic protocols from April 2003–August 2006. Pelvic radiotherapy (50.4 Gy) was delivered concurrently with capecitabine (n = 148) or capecitabine/irinotecan (n = 83). Surgery was performed 4–8 weeks after CRT completion. Tumor responses to CRT were assessed using both radiologic and pathologic measurements. Radiologic responses were evaluated by magnetic resonance volumetry, which was performed at the initial work-up and after completion of preoperative CRT just before surgery. Pathologic responses were assessed with downstaging (ypStage 0-1) and grading tumor regression. Clinical outcomes were evaluated in terms of local control, relapse-free survival, and overall survival rates. Results: Radiologic examination demonstrated that tumor volume decreased by 65.6% in the capecitabine group and 66.8% capecitabine/irinotecan group (p = 0.731). Postoperative pathologic stage determination showed that tumor downstaging occurred in 44.1% of the capecitabine group and 48.6% of the capecitabine/irinotecan group (p = 0.538). The sum of tumor regression grade 3 (near complete response) and 4 (complete response) after CRT were 28.6% in the capecitabine group and 37.5% in the capecitabine/irinotecan group (p = 0.247). There were no significant differences between the two groups in 5-year local control (91.7% vs. 92.5%; p = 0.875), relapse-free survival (80.8% vs. 77.2%; p = 0.685), and overall survival (88.4% vs. 90.4%; p = 0.723). Conclusions: This study revealed no differences in the short-term tumor response and long-term clinical outcome between preoperative capecitabine and capecitabine/irinotecan CRT regimens for locally advanced rectal cancer.