RESUMO
Background and purpose: Image-guided adapted brachytherapy (IGABT) is superior to other radiotherapy techniques in the treatment of locally advanced cervical cancer (LACC). We aimed to investigate the benefit of interstitial needles (IN) for a combined intracavitary/interstitial (IC/IS) approach using IGABT over the intracavitary approach (IC) alone in patients with LACC after concomitant external beam radiotherapy (EBRT) and chemotherapy. Materials and methods: We included consecutive patients with LACC who were treated with IC/IS IGABT after radiochemotherapy (RCT) in our retrospective, observational study. Dosimetric gain and sparing of organs at risk (OAR) were investigated by comparing the IC/IS IGABT plan with a simulated plan without needle use (IC IGABT plan) and the impact of other clinical factors on the benefit of IC/IS IGABT. Results: Ninety-nine patients were analyzed, with a mean EBRT dose of 45.5 ± 1.7 Gy; 97 patients received concurrent chemotherapy. A significant increase in median D90% High Risk Clinical target volume (HR-CTV) was found for IC/IS (82.8 Gy) vs IC (76.2 Gy) (p < 10-4). A significant decrease of the delivered dose for all OAR was found for IC/IS vs IC for median D2cc to the bladder (77.2 Gy), rectum (68 Gy), sigmoid (53.2 Gy), and small bowel (47 Gy) (all p < 10-4). Conclusion: HR-CTV coverage was higher with IC/IS IGABT than with IC IGABT, with lower doses to the OAR in patients managed for LACC after RCT. Interstitial brachytherapy in the management of LACC after radiotherapy provides better coverage of the target volumes, this could contribute to better local control and improved survival of patients.
RESUMO
Brain tumor is one of the leading causes of cancer death. The high-grade brain tumors are easier to recurrent even after standard treatment. Therefore, developing a method to predict brain tumor recurrence location plays an important role in the treatment planning and it can potentially prolong patient's survival time. There is still little work to deal with this issue. In this paper, we present a deep learning-based brain tumor recurrence location prediction network. Since the dataset is usually small, we propose to use transfer learning to improve the prediction. We first train a multi-modal brain tumor segmentation network on the public dataset BraTS 2021. Then, the pre-trained encoder is transferred to our private dataset for extracting the rich semantic features. Following that, a multi-scale multi-channel feature fusion model and a nonlinear correlation learning module are developed to learn the effective features. The correlation between multi-channel features is modeled by a nonlinear equation. To measure the similarity between the distributions of original features of one modality and the estimated correlated features of another modality, we propose to use Kullback-Leibler divergence. Based on this divergence, a correlation loss function is designed to maximize the similarity between the two feature distributions. Finally, two decoders are constructed to jointly segment the present brain tumor and predict its future tumor recurrence location. To the best of our knowledge, this is the first work that can segment the present tumor and at the same time predict future tumor recurrence location, making the treatment planning more efficient and precise. The experimental results demonstrated the effectiveness of our proposed method to predict the brain tumor recurrence location from the limited dataset.
