MRI-Based Deep Learning Segmentation and Radiomics of Sarcoma in Mice.

Small-animal imaging is an essential tool that provides noninvasive, longitudinal insight into novel cancer therapies. However, considerable variability in image analysis techniques can lead to inconsistent results. We have developed quantitative imaging for application in the preclinical arm of a coclinical trial by using a genetically engineered mouse model of soft tissue sarcoma. Magnetic resonance imaging (MRI) images were acquired 1 day before and 1 week after radiation therapy. After the second MRI, the primary tumor was surgically removed by amputating the tumor-bearing hind limb, and mice were followed for up to 6 months. An automatic analysis pipeline was used for multicontrast MRI data using a convolutional neural network for tumor segmentation followed by radiomics analysis. We then calculated radiomics features for the tumor, the peritumoral area, and the 2 combined. The first radiomics analysis focused on features most indicative of radiation therapy effects; the second radiomics analysis looked for features that might predict primary tumor recurrence. The segmentation results indicated that Dice scores were similar when using multicontrast versus single T2-weighted data (0.863 vs 0.861). One week post RT, larger tumor volumes were measured, and radiomics analysis showed greater heterogeneity. In the tumor and peritumoral area, radiomics features were predictive of primary tumor recurrence (AUC: 0.79). We have created an image processing pipeline for high-throughput, reduced-bias segmentation of multiparametric tumor MRI data and radiomics analysis, to better our understanding of preclinical imaging and the insights it provides when studying new cancer therapies.

The impact of respiratory gating on improving volume measurement of murine lung tumors in micro-CT imaging.

Small animal imaging has become essential in evaluating new cancer therapies as they are translated from the preclinical to clinical domain. However, preclinical imaging faces unique challenges that emphasize the gap between mouse and man. One example is the difference in breathing patterns and breath-holding ability, which can dramatically affect tumor burden assessment in lung tissue. As part of a co-clinical trial studying immunotherapy and radiotherapy in sarcomas, we are using micro-CT of the lungs to detect and measure metastases as a metric of disease progression. To effectively utilize metastatic disease detection as a metric of progression, we have addressed the impact of respiratory gating during micro-CT acquisition on improving lung tumor detection and volume quantitation. Accuracy and precision of lung tumor measurements with and without respiratory gating were studied by performing experiments with in vivo images, simulations, and a pocket phantom. When performing test-retest studies in vivo, the variance in volume calculations was 5.9% in gated images and 15.8% in non-gated images, compared to 2.9% in post-mortem images. Sensitivity of detection was examined in images with simulated tumors, demonstrating that reliable sensitivity (true positive rate (TPR) ≥ 90%) was achievable down to 1.0 mm3 lesions with respiratory gating, but was limited to ≥ 8.0 mm3 in non-gated images. Finally, a clinically-inspired "pocket phantom" was used during in vivo mouse scanning to aid in refining and assessing the gating protocols. Application of respiratory gating techniques reduced variance of repeated volume measurements and significantly improved the accuracy of tumor volume quantitation in vivo.

Bridging the translational gap: Implementation of multimodal small animal imaging strategies for tumor burden assessment in a co-clinical trial.

In designing co-clinical cancer studies, preclinical imaging brings unique challenges that emphasize the gap between man and mouse. Our group is developing quantitative imaging methods for the preclinical arm of a co-clinical trial studying immunotherapy and radiotherapy in a soft tissue sarcoma model. In line with treatment for patients enrolled in the clinical trial SU2C-SARC032, primary mouse sarcomas are imaged with multi-contrast micro-MRI (T1 weighted, T2 weighted, and T1 with contrast) before and after immune checkpoint inhibition and pre-operative radiation therapy. Similar to the patients, after surgery the mice will be screened for lung metastases with micro-CT using respiratory gating. A systems evaluation was undertaken to establish a quantitative baseline for both the MR and micro-CT systems against which others systems might be compared. We have constructed imaging protocols which provide clinically-relevant resolution and contrast in a genetically engineered mouse model of sarcoma. We have employed tools in 3D Slicer for semi-automated segmentation of both MR and micro-CT images to measure tumor volumes efficiently and reliably in a large number of animals. Assessment of tumor burden in the resulting images was precise, repeatable, and reproducible. Furthermore, we have implemented a publicly accessible platform for sharing imaging data collected during the study, as well as protocols, supporting information, and data analyses. In doing so, we aim to improve the clinical relevance of small animal imaging and begin establishing standards for preclinical imaging of tumors from the perspective of a co-clinical trial.