High-risk clinical target volume delineation in CT-guided cervical cancer brachytherapy: Impact of information from FIGO stage with or without systematic inclusion of 3D documentation of clinical gynecological examination

e17026 Background: A range of prognostic factors had been reported to be associated with clinical outcome of cervical cancer patients. However, most of these parameters were measured before the start of treatment but without consideration of tumor response to RT. We believed that it might be possible to provide locally advanced cervical cancer patients an opportunity to modify and guide the treatment strategies in the midway of treatment based on the early response evaluation during RT. To establish effective prognostic nomograms using clinical features including tumor volume and size mesured by MRI before treatment and after the completion of external beam radiotherapy (EBRT), and detailed dosimetry of brachytherapy dose for high-risk clinical target volume (HRCTV)D90 and Low-risk Clinical Target Volume(LR-CTV)D90. Methods: The nomogram for local control (LC) was based on a retrospective study of 316 patients who underwent IMRT at our hospital from 2010 to 2015. The predictive accuracy and discriminative ability of our nomogram models were determined by concordance index and calibration curve, and were compared with the nomogram models combining clinical features with FIGO stage. The results were validated using bootstrap resampling and a cohort study of 141 patients. The same data cohort was used to predict the progress-free survival (PFS) of cervical cancer with 3:1 training cohort (N = 310) and validation cohort (N = 155). Results: The following factors were assembled into our prognostic survival nomogram models: Age, tumor volume and size (TV & TS) before treatment, TV and TS after the completion of external beam radiotherapy (EBRT), brachytherapy dose of high-risk clinical target volume (HRCTV)D90 and Low-risk Clinical Target Volume(LR-CTV)D90. The calibration curves showed good agreement between nomogram-predicted and actual survival. Our nomogram models for LC and PFS, provided better results than the nomogram models combining clinical features with FIGO stage. Results were further confirmed in the validation set. Conclusions: Clinical features including tumor size and volume mesured before treatment and after EBRT, as well as detailed dosimetry of brachytherapy dose are able to improve the performance of prognostic nomograms for patients with cervical cancer.

Download Full-text

Automated Clinical Target Volume Delineation for Non-Small Cell Lung Cancer Patients Using Deep 3D Networks

International Journal of Radiation Oncology*Biology*Physics ◽

10.1016/j.ijrobp.2020.07.827 ◽

2020 ◽

Vol 108 (3) ◽

pp. e347

Author(s):

Y. Xie ◽

K. Kang ◽

Y. Wang ◽

F.K. Keane ◽

M.J. Khandekar ◽

...

Keyword(s):

Lung Cancer ◽

Cancer Patients ◽

Clinical Target Volume ◽

Target Volume ◽

Small Cell ◽

Small Cell Lung ◽

Target Volume Delineation ◽

Lung Cancer Patients ◽

Volume Delineation ◽

3D Networks

Download Full-text

CT based automatic clinical target volume delineation using a dense-fully connected convolution network for cervical Cancer radiation therapy

BMC Cancer ◽

10.1186/s12885-020-07595-6 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Zhongjian Ju ◽

Wen Guo ◽

Shanshan Gu ◽

Jin Zhou ◽

Wei Yang ◽

...

Keyword(s):

Cervical Cancer ◽

Cancer Patients ◽

Clinical Target Volume ◽

Target Volume ◽

Ct Images ◽

Clinical Samples ◽

Model Parameters ◽

Convolutional Network ◽

Volume Delineation ◽

Fully Connected

Abstract Background It is very important to accurately delineate the CTV on the patient’s three-dimensional CT image in the radiotherapy process. Limited to the scarcity of clinical samples and the difficulty of automatic delineation, the research of automatic delineation of cervical cancer CTV based on CT images for new patients is slow. This study aimed to assess the value of Dense-Fully Connected Convolution Network (Dense V-Net) in predicting Clinical Target Volume (CTV) pre-delineation in cervical cancer patients for radiotherapy. Methods In this study, we used Dense V-Net, a dense and fully connected convolutional network with suitable feature learning in small samples to automatically pre-delineate the CTV of cervical cancer patients based on computed tomography (CT) images and then we assessed the outcome. The CT data of 133 patients with stage IB and IIA postoperative cervical cancer with a comparable delineation scope was enrolled in this study. One hundred and thirteen patients were randomly designated as the training set to adjust the model parameters. Twenty cases were used as the test set to assess the network performance. The 8 most representative parameters were also used to assess the pre-sketching accuracy from 3 aspects: sketching similarity, sketching offset, and sketching volume difference. Results The results presented that the DSC, DC/mm, HD/cm, MAD/mm, ∆V, SI, IncI and JD of CTV were 0.82 ± 0.03, 4.28 ± 2.35, 1.86 ± 0.48, 2.52 ± 0.40, 0.09 ± 0.05, 0.84 ± 0.04, 0.80 ± 0.05, and 0.30 ± 0.04, respectively, and the results were greater than those with a single network. Conclusions Dense V-Net can correctly predict CTV pre-delineation of cervical cancer patients and can be applied in clinical practice after completing simple modifications.

Download Full-text