Objective. Dose distribution data plays a pivotal role in radiotherapy treatment planning. The data is typically represented using voxel grids, and its size ranges from 10^6--10^8. A concise representation of the treatment plan is of great value in facilitating treatment planning and downstream applications. This work aims to develop an implicit neural representation of 3D dose distribution data. Approach. Instead of storing the dose values at each voxel, in the proposed approach, the weights of a multilayer perceptron (MLP) are employed to characterize the dosimetric data for plan representation and subsequent applications. We train a coordinate-based MLP with sinusoidal activations to map the voxel spatial coordinates to the corresponding dose values. We identify the best architecture for a given parameter budget and use that to train a model for each patient. The trained MLP is evaluated at each voxel location to reconstruct the dose distribution. We perform extensive experiments on dose distributions of prostate, spine, and head and neck tumor cases to evaluate the quality of the proposed representation. We also study the change in representation quality by varying model size and activation function. Main Results. Using coordinate-based MLPs with sinusoidal activations, we can learn implicit representations that achieve a mean-squared error of 10^{-6} and peak signal-to-noise ratio greater than 50 dB at a target bitrate of ~1 across all the datasets, with a compression ratio of ~32. Our results also show that model sizes with a bitrate of 1--2 achieve optimal accuracy. For smaller bitrates, performance starts to drop significantly. Significance. The proposed model provides a low-dimensional, implicit, and continuous representation of 3D dose data. In summary, given a dose distribution, we systematically show how to find a compact model to fit the data accurately. This study lays the groundwork for future applications of neural representations of dose data in radiation oncology.

An analytical theory for the unconfined creep behavior of a cylindrical inclusion (simulating a soft tissue tumor) embedded in a cylindrical background sample (simulating normal tissue) is presented and analyzed in this paper. Both the inclusion and the background are considered as fluid-filled, porous materials, each of them being characterized by a set of mechanical parameters. Specifically, in this derivation, the inclusion is assumed to have significantly higher interstitial permeability than the background. The formulations of the effective Poisson's ratio (EPR) and fluid pressure in the inclusion and in the background are derived for the case of a sample subjected to a creep compression. The developed analytical expressions are validated using finite element models (FEM). Statistical comparison between the results obtained from the developed model and the results from FEM demonstrates accuracy of the proposed theoretical model higher than 99.4%. The model presented in this paper complements the one reported in the companion paper (Part I), which refers to the case of an inclusion having less interstitial permeability than the background.

No abstract

Mechanical and transport properties of cancers such as Young’s modulus (YM), Poisson’s ratio (PR), and vascular permeability (VP) have great clinical importance in cancer diagnosis, prognosis, and treatment. However, non-invasive estimation of these parameters in vivo is challenged by many practical factors. Elasticity imaging methods, such as “poroelastography”, require prolonged data acquisition, which can limit their clinical applicability. In this paper, we investigate a new method to perform poroelastography experiments, which results in shorter temporal acquisition windows. This method is referred to as “short-time poroelastography” (STPE). Finite element (FE) and ultrasound simulations demonstrate that, using STPE, it is possible to accurately estimate YM, PR (within 10% error) using windows of observation (WoOs) of length as short as 1 underlying strain Time Constant (TC). The error was found to be almost negligible (< 3%) when using WoOs longer than 2 strain TCs. In the case of VP estimation, WoOs of at least 2 strain TCs are required to obtain an error < 8% (in simulations). The stricter requirement for the estimation of VP with respect to YM and PR is due its reliance on the transient strain behavior while YM and PR depend on the steady state strain values only. In vivo experimental data are used as a proof-of-principle of the potential applicability of the proposed methodology in vivo . The use of STPE may provide a means to efficiently perform poroelastography experiments without compromising the accuracy of the estimated tissue properties.

Remarkable advances in single cell genomics have presented unique challenges and opportunities for interrogating a wealth of biomedical inquiries. High dimensional genomic data are inherently complex because of intertwined relationships among the genes. Existing methods, including emerging deep learning-based approaches, do not consider the underlying biological characteristics during data processing, which greatly compromises the performance of data analysis and hinders the maximal utilization of state-of-the-art genomic techniques. In this work, we develop an entropy-based cartography strategy to contrive the high dimensional gene expression data into a configured image format, referred to as genomap, with explicit integration of the genomic interactions. This unique cartography casts the gene-gene interactions into the spatial configuration of genomaps and enables us to extract the deep genomic interaction features and discover underlying discriminative patterns of the data. We show that, for a wide variety of applications (cell clustering and recognition, gene signature extraction, single cell data integration, cellular trajectory analysis, dimensionality reduction, and visualization), the proposed approach drastically improves the accuracies of data analyses as compared to the state-of-the-art techniques.