GANDA: A deep generative adversarial network predicts the spatial distribution of nanoparticles in tumor pixelly
This work addresses the challenge of predicting intratumoral nanoparticle distribution, which is crucial for optimizing nanomedicine in imaging and treatment, particularly for personalized cancer therapy.
This paper introduces GANDA, a deep generative adversarial network, to predict the spatial distribution of nanoparticles within tumors. The model, trained on 27,775 image patches, can conditionally generate nanoparticle distribution images with a minimal mean squared error of 1.871 and an intraclass correlation of 0.94.
Intratumoral nanoparticles (NPs) distribution is critical for the success of nanomedicine in imaging and treatment, but computational models to describe the NPs distribution remain unavailable due to the complex tumor-nano interactions. Here, we develop a Generative Adversarial Network for Distribution Analysis (GANDA) to describe and conditionally generates the intratumoral quantum dots (QDs) distribution after i.v. injection. This deep generative model is trained automatically by 27 775 patches of tumor vessels and cell nuclei decomposed from whole-slide images of 4T1 breast cancer sections. The GANDA model can conditionally generate images of intratumoral QDs distribution under the constraint of given tumor vessels and cell nuclei channels with the same spatial resolution (pixels-to-pixels), minimal loss (mean squared error, MSE = 1.871) and excellent reliability (intraclass correlation, ICC = 0.94). Quantitative analysis of QDs extravasation distance (ICC = 0.95) and subarea distribution (ICC = 0.99) is allowed on the generated images without knowing the real QDs distribution. We believe this deep generative model may provide opportunities to investigate how influencing factors affect NPs distribution in individual tumors and guide nanomedicine optimization for molecular imaging and personalized treatment.