MRI Assessment of Changes in Tumor Vascularization during Neoadjuvant Anti-Angiogenic Treatment in Locally Advanced Breast Cancer Patients.

Anti-VEGF (vascular endothelial growth factor) treatment improves response rates, but not progression-free or overall survival in advanced breast cancer. It has been suggested that subgroups of patients may benefit from this treatment; however, the effects of adding anti-VEGF treatment to a standard chemotherapy regimen in breast cancer patients are not well studied. Understanding the effects of the anti-vascular treatment on tumor vasculature may provide a selection of patients that can benefit. The aim of this study was to study the vascular effect of bevacizumab using clinical dynamic contrast-enhanced MRI (DCE-MRI). A total of 70 women were randomized to receive either chemotherapy alone or chemotherapy with bevacizumab for 25 weeks. DCE-MRI was performed at baseline and at 12 and 25 weeks, and in addition 25 of 70 patients agreed to participate in an early MRI after one week. Voxel-wise pharmacokinetic analysis was performed using semi-quantitative methods and the extended Tofts model. Vascular architecture was assessed by calculating the fractal dimension of the contrast-enhanced images. Changes during treatment were compared with baseline and between the treatment groups. There was no significant difference in tumor volume at any point; however, DCE-MRI parameters revealed differences in vascular function and vessel architecture. Adding bevacizumab to chemotherapy led to a pronounced reduction in vascular DCE-MRI parameters, indicating decreased vascularity. At 12 and 25 weeks, the difference between the treatment groups is severely reduced.

A Prospective Study of High Dose-Rate Brachytherapy or Stereotactic Body Radiotherapy of Intra-Prostatic Recurrence: Toxicity and Long Term Clinical Outcome.

Background: Up to half of patients with localized prostate cancer experience biochemical relapse within 10 years after definitive radiotherapy. The aim of this prospective study was to investigate the toxicity, dose to the organs at risk (OARs), and efficacy of dose-intensified focal salvage radiotherapy. Methods and Material: Thirty-three patients (median age 68.8 years) with histologically confirmed relapse after primary definitive radiotherapy were enrolled between 2012 and 2019. No patients had metastases at imaging or in bone marrow aspiration. Twenty-three patients were treated with high dose-rate brachytherapy to the recurrent tumor, defined at multiparametric MRI, with 3 fractions of 10 Gy with two weeks interval, and 10 patients by stereotactic body radiotherapy with 35 Gy to the local recurrence and 25 Gy to the whole prostate in 5 fractions. We used the RTOG-scoring system to grade genitourinary (GU) and gastrointestinal toxicity (GI) at three months (acute), and at 12, 24, and 36 months (late). Dose-volume histogram parameters to the local recurrence and the OARs were obtained and 2 Gy equivalent (EQD2) total dose was calculated using the linear-quadratic model with α/ß = 3 Gy. Efficacy was assessed by the progression-free interval and overall survival. Results: Median follow-up time was 81 months (range 21-115). The cumulative moderate to severe GI and GU toxicities were 3.0% (1/33) and 15.2% (5/33). Six patients had grade 1 acute GI toxicity, none had grade 2 or 3. One patient had grade 3 acute GU toxicity, two had grade 2, and fourteen had grade 1. One patient had late GI toxicity grade 2 and eight had grade 1. Four patients had late GU toxicity grade 2 and eight had grade 1. No patients had grade 3 late toxicity. The mean total D90 to the recurrent tumor was 77.7 ± 17.0 Gy. The mean total rectum D2cc was 17.0 ± 7.9 Gy and the mean total urethra D0.1cc was 29.1 ± 8.2 Gy. Twenty-eight patients had re-irradiation without androgen deprivation therapy (ADT). Nine of these are still relapse-free and 10 had a recurrence-free interval longer than 2 years. Conclusion: The toxicity of salvage radiotherapy was mild to moderate. One-third of the patients achieved long-term stable disease without ADT and one-third had a recurrence-free interval longer than 2 years. Some patients progressed rapidly and probably did not benefit from re-irradiation.

MRI pulse sequence integration for deep-learning-based brain metastases segmentation.

PURPOSE: Magnetic resonance (MR) imaging is an essential diagnostic tool in clinical medicine. Recently, a variety of deep-learning methods have been applied to segmentation tasks in medical images, with promising results for computer-aided diagnosis. For MR images, effectively integrating different pulse sequences is important to optimize performance. However, the best way to integrate different pulse sequences remains unclear. In addition, networks trained with a certain subset of pulse sequences as input are unable to perform when given a subset of those pulse sequences. In this study, we evaluate multiple architectural features and characterize their effects in the task of metastasis segmentation while creating a method to robustly train a network to be able to work given any strict subset of the pulse sequences available during training. METHODS: We use a 2.5D DeepLabv3 segmentation network to segment metastases lesions on brain MR's with four pulse sequence inputs. To study how we can best integrate MR pulse sequences for this task, we consider (1) different pulse sequence integration schemas, combining our features at early, middle, and late points within a deep network, (2) different modes of weight sharing for parallel network branches, and (3) a novel integration level dropout layer, which will allow the networks to be robust to performing inference on input with only a subset of pulse sequences available at the training. RESULTS: We find that levels of integration and modes of weight sharing that favor low variance work best in our regime of small amounts of training data (n = 100). By adding an input-level dropout layer, we could preserve the overall performance of these networks while allowing for inference on inputs with missing pulse sequences. We illustrate not only the generalizability of the network but also the utility of this robustness when applying the trained model to data from a different center, which does not use the same pulse sequences. Finally, we apply network visualization methods to better understand which input features are most important for network performance. CONCLUSIONS: Together, these results provide a framework for building networks with enhanced robustness to missing data while maintaining comparable performance in medical imaging applications.

Handling missing MRI sequences in deep learning segmentation of brain metastases: a multicenter study.

The purpose of this study was to assess the clinical value of a deep learning (DL) model for automatic detection and segmentation of brain metastases, in which a neural network is trained on four distinct MRI sequences using an input-level dropout layer, thus simulating the scenario of missing MRI sequences by training on the full set and all possible subsets of the input data. This retrospective, multicenter study, evaluated 165 patients with brain metastases. The proposed input-level dropout (ILD) model was trained on multisequence MRI from 100 patients and validated/tested on 10/55 patients, in which the test set was missing one of the four MRI sequences used for training. The segmentation results were compared with the performance of a state-of-the-art DeepLab V3 model. The MR sequences in the training set included pre-gadolinium and post-gadolinium (Gd) T1-weighted 3D fast spin echo, post-Gd T1-weighted inversion recovery (IR) prepped fast spoiled gradient echo, and 3D fluid attenuated inversion recovery (FLAIR), whereas the test set did not include the IR prepped image-series. The ground truth segmentations were established by experienced neuroradiologists. The results were evaluated using precision, recall, Intersection over union (IoU)-score and Dice score, and receiver operating characteristics (ROC) curve statistics, while the Wilcoxon rank sum test was used to compare the performance of the two neural networks. The area under the ROC curve (AUC), averaged across all test cases, was 0.989 ± 0.029 for the ILD-model and 0.989 ± 0.023 for the DeepLab V3 model (p = 0.62). The ILD-model showed a significantly higher Dice score (0.795 ± 0.104 vs. 0.774 ± 0.104, p = 0.017), and IoU-score (0.561 ± 0.225 vs. 0.492 ± 0.186, p < 0.001) compared to the DeepLab V3 model, and a significantly lower average false positive rate of 3.6/patient vs. 7.0/patient (p < 0.001) using a 10 mm3 lesion-size limit. The ILD-model, trained on all possible combinations of four MRI sequences, may facilitate accurate detection and segmentation of brain metastases on a multicenter basis, even when the test cohort is missing input MRI sequences.

Responses in the diffusivity and vascular function of the irradiated normal brain are seen up until 18 months following SRS of brain metastases.

BACKGROUND: MRI may provide insights into longitudinal responses in the diffusivity and vascular function of the irradiated normal-appearing brain following stereotactic radiosurgery (SRS) of brain metastases. METHODS: Forty patients with brain metastases from non-small cell lung cancer (N = 26) and malignant melanoma (N = 14) received SRS (15-25 Gy). Longitudinal MRI was performed pre-SRS and at 3, 6, 9, 12, and 18 months post-SRS. Measures of tissue diffusivity and vascularity were assessed by diffusion-weighted and perfusion MRI, respectively. All maps were normalized to white matter receiving less than 1 Gy. Longitudinal responses were assessed in normal-appearing brain, excluding tumor and edema, in the LowDose (1-10 Gy) and HighDose (>10 Gy) regions. The Eastern Cooperative Oncology Group (ECOG) performance status was recorded pre-SRS. RESULTS: Following SRS, the diffusivity in the LowDose region increased continuously for 1 year (105.1% ± 6.2%; P < .001), before reversing toward pre-SRS levels at 18 months. Transient reductions in microvascular cerebral blood volume (P < .05), blood flow (P < .05), and vessel densities (P < .05) were observed in LowDose at 6-9 months post-SRS. Correspondingly, vessel calibers in LowDose transiently increased at 3-9 months (P < .01). The responses in HighDose displayed similar trends as in LowDose, but with larger interpatient variations. Vascular responses followed pre-SRS ECOG status. CONCLUSIONS: Our results imply that even low doses of radiation to normal-appearing brain following cerebral SRS induce increased diffusivity and reduced vascular function for up until 18 months. In particular, the vascular responses indicate the reduced ability of the normal-appearing brain tissue to form new capillaries. Assessing the potential long-term neurologic effects of SRS on the normal-appearing brain is warranted.