Post-Radiotherapy PET Image Outcome Prediction by Deep Learning Under Biological Model Guidance: A Feasibility Study of Oropharyngeal Cancer Application

Abstract

PurposeTo develop a method of biologically guided deep learning for post-radiation 18FDG-PET image outcome prediction based on pre-radiation images and radiotherapy dose information.MethodsBased on the classic reaction–diffusion mechanism, a novel biological model was proposed using a partial differential equation that incorporates spatial radiation dose distribution as a patient-specific treatment information variable. A 7-layer encoder–decoder-based convolutional neural network (CNN) was designed and trained to learn the proposed biological model. As such, the model could generate post-radiation 18FDG-PET image outcome predictions with breakdown biological components for enhanced explainability. The proposed method was developed using 64 oropharyngeal patients with paired 18FDG-PET studies before and after 20-Gy delivery (2 Gy/day fraction) by intensity-modulated radiotherapy (IMRT). In a two-branch deep learning execution, the proposed CNN learns specific terms in the biological model from paired 18FDG-PET images and spatial dose distribution in one branch, and the biological model generates post-20-Gy 18FDG-PET image prediction in the other branch. As in 2D execution, 718/233/230 axial slices from 38/13/13 patients were used for training/validation/independent test. The prediction image results in test cases were compared with the ground-truth results quantitatively.ResultsThe proposed method successfully generated post-20-Gy 18FDG-PET image outcome prediction with breakdown illustrations of biological model components. Standardized uptake value (SUV) mean values in 18FDG high-uptake regions of predicted images (2.45 ± 0.25) were similar to ground-truth results (2.51 ± 0.33). In 2D-based Gamma analysis, the median/mean Gamma Index (<1) passing rate of test images was 96.5%/92.8% using the 5%/5 mm criterion; such result was improved to 99.9%/99.6% when 10%/10 mm was adopted.ConclusionThe developed biologically guided deep learning method achieved post-20-Gy 18FDG-PET image outcome predictions in good agreement with ground-truth results. With the breakdown biological modeling components, the outcome image predictions could be used in adaptive radiotherapy decision-making to optimize personalized plans for the best outcome in the future.

Radiomics on spatial‐temporal manifolds via Fokker–Planck dynamics

“…Our lab has developed and applied this method to the OPC dataset studied in this work. 32,46 The use of deep learning tools alone was common to assess treatment response using the pre-treatment images and dose distribution information as inputs (e.g., Wang et al).…”

“…Integration of radiomic analysis and other analytical tools that are mechanistically informed may increase both generalization and interpretation. [46][47][48][49][50] For example, radiomics-boosted deep learning models have been developed for diverse applications, such as COVID-19 pneumonia detection via chest radiographs, 51 post-resection survival prediction of patients with glioblastoma 50 and identification of radionecrosis following stereotactic radiosurgery (SRS) for brain metastases. 48 In each case, integration of radiomics and deep learning approaches serves to improve interpretability of deep learning models otherwise described as "black boxes".…”

“…For our data, dosimetry modeling was not a main concern, as patients were given a uniform dose under well‐defined prescriptions outlined in the clinical trial. Furthermore, prior work has demonstrated that dosimetry is a shallow feature in this dataset, and that all necessary useful information comes directly from the PET/CT images 46 . However, if our algorithm were to be applied to other disease sites, this phenomenon would need to be accounted for, as we could no longer guarantee dosimetric homogeneity.…”

A neural ordinary differential equation model for visualizing deep neural network behaviors in multi‐parametric MRI‐based glioma segmentation

“…The explainability ensures that the networks are driven by (1) deep features that are appropriate for clinical practice and (2) decisions that are clinically defensible. [39][40][41][42][43] Without such model explainability, deep learning algorithms remain a "black box" in implementation. The massive data computations in deep neural networks are beyond human logical and symbolic abilities for causality, 44 which raises technical issues of deep learning model development for medical imaging applications.…”

“…One major issue of currently available deep learning models is the lack of model explainability, that is, the extent to which the internal mechanics of a deep neural network can be explained in human terms from a clinical perspective. The explainability ensures that the networks are driven by (1) deep features that are appropriate for clinical practice and (2) decisions that are clinically defensible 39–43 . Without such model explainability, deep learning algorithms remain a "black box" in implementation.…”