Human-level comparable control volume mapping with a deep unsupervised-learning model for image-guided radiation therapy

PURPOSE

To develop a deep unsupervised learning method with control volume (CV) mapping from patient positioning daily CT (dCT) to planning computed tomography (pCT) for precise patient positioning.

METHODS

We propose an unsupervised learning framework, which maps CVs from dCT to pCT to automatically generate the couch shifts, including translation and rotation dimensions. The network inputs are dCT, pCT and CV positions in the pCT. The output is the transformation parameter of the dCT used to setup the head and neck cancer (HNC) patients. The network is trained to maximize image similarity between the CV in the pCT and the CV in the dCT. A total of 554 CT scans from 158 HNC patients were used for the evaluation of the proposed model. At different points in time, each patient had many CT scans. Couch shifts are calculated for the testing by averaging the translation and rotation from the CVs. The ground-truth of the shifts come from bone landmarks determined by an experienced radiation oncologist.

RESULTS

The system positioning errors of translation and rotation are less than 0.47 mm and 0.17°, respectively. The random positioning errors of translation and rotation are less than 1.13 mm and 0.29°, respectively. The proposed method enhanced the proportion of cases registered within a preset tolerance (2.0 mm/1.0°) from 66.67% to 90.91% as compared to standard registrations.

CONCLUSIONS

We proposed a deep unsupervised learning architecture for patient positioning with inclusion of CVs mapping, which weights the CVs regions differently to mitigate any potential adverse influence of image artifacts on the registration. Our experimental results show that the proposed method achieved efficient and effective HNC patient positioning.

Multicellular Spheroids as In Vitro Models of Oxygen Depletion During FLASH Irradiation

PURPOSE

The differential response of normal and tumor tissues to ultrahigh-dose-rate radiation (FLASH) has raised new hope for treating solid tumors but, to date, the mechanism remains elusive. One leading hypothesis is that FLASH radiochemically depletes oxygen from irradiated tissues faster than it is replenished through diffusion. The purpose of this study was to investigate these effects within hypoxic multicellular tumor spheroids through simulations and experiments.

METHODS AND MATERIALS

Physicobiological equations were derived to model (1) the diffusion and metabolism of oxygen within spheroids; (2) its depletion through reactions involving radiation-induced radicals; and (3) the increase in radioresistance of spheroids, modeled according to the classical oxygen enhancement ratio and linear-quadratic response. These predictions were then tested experimentally in A549 spheroids exposed to electron irradiation at conventional (0.075 Gy/s) or FLASH (90 Gy/s) dose rates. Clonogenic survival, cell viability, and spheroid growth were scored postradiation. Clonogenic survival of 2 other cell lines was also investigated.

RESULTS

The existence of a hypoxic core in unirradiated tumor spheroids is predicted by simulations and visualized by fluorescence microscopy. Upon FLASH irradiation, this hypoxic core transiently expands, engulfing a large number of well-oxygenated cells. In contrast, oxygen is steadily replenished during slower conventional irradiation. Experimentally, clonogenic survival was around 3-fold higher in FLASH-irradiated spheroids compared with conventional irradiation, but no significant difference was observed for well-oxygenated 2-dimensional cultured cells. This differential survival is consistent with the predictions of the computational model. FLASH irradiation of spheroids resulted in a dose-modifying factor of around 1.3 for doses above 10 Gy.

CONCLUSIONS

Tumor spheroids can be used as a model to study FLASH irradiation in vitro. The improved survival of tumor spheroids receiving FLASH radiation confirms that ultrafast radiochemical oxygen depletion and its slow replenishment are critical components of the FLASH effect.

Closing the Gap Between Deep Neural Network Modeling and Biomedical Decision-Making Metrics in Segmentation via Adaptive Loss Functions

Deep learning is becoming an indispensable tool for various tasks in science and engineering. A critical step in constructing a reliable deep learning model is the selection of a loss function, which measures the discrepancy between the network prediction and the ground truth. While a variety of loss functions have been proposed in the literature, a truly optimal loss function that maximally utilizes the capacity of neural networks for deep learning-based decision-making has yet to be established. Here, we devise a generalized loss function with functional parameters determined adaptively during model training to provide a versatile framework for optimal neural network-based decision-making in small target segmentation. The method is showcased by more accurate detection and segmentation of lung and liver cancer tumors as compared with the current state-of-the-art. The proposed formalism opens new opportunities for numerous practical applications such as disease diagnosis, treatment planning, and prognosis.

Modified U-Net (mU-Net) With Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images

Segmentation of livers and liver tumors is one of the most important steps in radiation therapy of hepatocellular carcinoma. The segmentation task is often done manually, making it tedious, labor intensive, and subject to intra-/inter- operator variations. While various algorithms for delineating organ-at-risks (OARs) and tumor targets have been proposed, automatic segmentation of livers and liver tumors remains intractable due to their low tissue contrast with respect to the surrounding organs and their deformable shape in CT images. The U-Net has gained increasing popularity recently for image analysis tasks and has shown promising results. Conventional U-Net architectures, however, suffer from three major drawbacks. First, skip connections allow for the duplicated transfer of low resolution information in feature maps to improve efficiency in learning, but this often leads to blurring of extracted image features. Secondly, high level features extracted by the network often do not contain enough high resolution edge information of the input, leading to greater uncertainty where high resolution edge dominantly affects the network's decisions such as liver and liver-tumor segmentation. Thirdly, it is generally difficult to optimize the number of pooling operations in order to extract high level global features, since the number of pooling operations used depends on the object size. To cope with these problems, we added a residual path with deconvolution and activation operations to the skip connection of the U-Net to avoid duplication of low resolution information of features. In the case of small object inputs, features in the skip connection are not incorporated with features in the residual path. Furthermore, the proposed architecture has additional convolution layers in the skip connection in order to extract high level global features of small object inputs as well as high level features of high resolution edge information of large object inputs. Efficacy of the modified U-Net (mU-Net) was demonstrated using the public dataset of Liver tumor segmentation (LiTS) challenge 2017. For liver-tumor segmentation, Dice similarity coefficient (DSC) of 89.72 %, volume of error (VOE) of 21.93 %, and relative volume difference (RVD) of - 0.49 % were obtained. For liver segmentation, DSC of 98.51 %, VOE of 3.07 %, and RVD of 0.26 % were calculated. For the public 3D Image Reconstruction for Comparison of Algorithm Database (3Dircadb), DSCs were 96.01 % for the liver and 68.14 % for liver-tumor segmentations, respectively. The proposed mU-Net outperformed existing state-of-art networks.