Automatic segmentation and applicator reconstruction for CT-based brachytherapy of cervical cancer using 3D convolutional neural networks.
In this study, we present deep learning-based approaches to automatic segmentation and applicator reconstruction with high accuracy and efficiency in the planning computed tomography (CT) for cervical cancer brachytherapy (BT). A novel three-dimensional (3D) convolutional neural network (CNN) architecture was proposed and referred to as DSD-UNET. The dataset of 91 patients received CT-based BT of cervical cancer was used to train and test DSD-UNET model for auto-segmentation of high-risk clinical target volume (HR-CTV) and organs at risk (OARs). Automatic applicator reconstruction was achieved with DSD-UNET-based segmentation of applicator components followed by 3D skeletonization and polynomial curve fitting. Digitization of the channel paths for tandem and ovoid applicator in the planning CT was evaluated utilizing the data from 32 patients. Dice similarity coefficient (DSC), Jaccard Index (JI), and Hausdorff distance (HD) were used to quantitatively evaluate the accuracy. The segmentation performance of DSD-UNET was compared with that of 3D U-Net. Results showed that DSD-UNET method outperformed 3D U-Net on segmentations of all the structures. The mean DSC values of DSD-UNET method were 86.9%, 82.9%, and 82.1% for bladder, HR-CTV, and rectum, respectively. For the performance of automatic applicator reconstruction, outstanding segmentation accuracy was first achieved for the intrauterine and ovoid tubes (average DSC value of 92.1%, average HD value of 2.3 mm). Finally...
Conclusions: Extended treatment planning time for brachytherapy due to the changes in topography of small pelvis can lead to different dose in high-risk organs than previously planned. It seems that the most significant changes are related to rectum. PMID: 32395135 [PubMed]
Conclusions: The present study results show that all the dose parameters of HRCTV, bladder, and rectum with 60Co were comparable with those of 192Ir HDR source. The isodose distribution is more bulge out for 60Co in cranial-caudal direction compared to that of 192Ir. However, these differences can be reduced by treatment planning optimization techniques. The clinical plan evaluation in each slice and plane is necessary to explore the logistic and financial benefits of miniaturized 60Co source over 192Ir HDR source.
Conclusions: Dosimetric deviation for tumor and organs at risk is within acceptable limit while using CT image-based brachytherapy plan of the first fraction for treating successive fractions.
Conclusion: Optimal plans even with orthogonal radiographs may be generated by verifying the application based on the parameters mentioned in the present study and computed tomography-based plans could be utilized more effectively instead of doing automatic or manual optimization. Whereever orthogonal radiograph based or template based ICBT practices is performed this study may create a dataset to have an optimal treatment plan even without three-dimensional images.
Conclusion: Doses to both Manchester point A and ABS point A may be recorded during the transition period. However, ABS point A can be preferred over the Manchester point A as it conforms better with the desired dosimetric outcome and is found to be more static.
Conclusions: In 3D brachytherapy of cervical cancer, GO and IPSA optimizations do not present a significant difference in target dose coverage; nevertheless, IPSA may reduce the maximum dose to normal tissue when compared with GO. PMID: 31523240 [PubMed]
CONCLUSIONS: The first results of treatment with the Axxent eBT device are promising, as no recurrences have been observed and toxicity is very low. eBT is a good alternative for treating cervical cancer in centers without access to conventional HDR. PMID: 31183970 [PubMed - as supplied by publisher]
Conclusions: EQD2 of bladder, rectum, sigmoid, D90 CTVHR, and point A were similar with 5.5 Gy × 5 fractions, 6.5 Gy × 4 fractions, and 7 Gy × 4 fractions, whereas EQD2 of 9 Gy × 2 fractions was significantly unfavorable compared to other schedules. Further clinical studies are recommended to observe clinical outcomes. PMID: 31139229 [PubMed]
Publication date: Available online 3 May 2019Source: Medical Journal Armed Forces IndiaAuthor(s): Hari Mukundan, Kirti Tyagi, Deboleena Mukherjee, R.K. PatelAbstractBackgroundTwo-dimensional treatment planning using radiographs or simulator films was the standard in planning brachytherapy for patients with cervical cancer. Three-dimensional (3D) treatment planning has improved treatment efficacy. This retrospective study compares conventional and 3D treatment planning of brachytherapy in patients with cervical cancer and interfraction dose variation to bladder and rectum (D2cc).MethodsThe mean doses to bladder and rectum (...
Authors: Wali LM, Helal AM, Darwesh RM, Attar MA Abstract BACKGROUND: Cervical cancer radiotherapy is usually administrated through 3-Dimensional Conformal Radiation Therapy (3DCRT) followed by a brachytherapy (BT) boost. PURPOSE: To investigate whether Volumetric Modulated Arc Therapy (VMAT) can replace High Dose Rate (HDR) intracavitary BT boost for patients undergoing cervical cancer radiotherapy. MATERIALS AND METHODS: Computed Tomography (CT) images for ten patients with tandem and ovoids were included in this study. Target volumes, rectum, bladder, sigmoid, small bowel and both femoral heads were deli...