Deep and Domain Transfer Learning Aided Photoacoustic Microscopy: Acoustic Resolution to Optical Resolution

DOVE: Doodled vessel enhancement for photoacoustic angiography super resolution

Deep-learning-based super-resolution photoacoustic angiography (PAA) has emerged as a valuable tool for enhancing the resolution of blood vessel images and aiding in disease diagnosis. However, due to the scarcity of training samples, PAA super-resolution models do not generalize well, especially in the challenging in-vivo imaging of organs with deep tissue penetration. Furthermore, prolonged exposure to high laser intensity during the image acquisition process can lead to tissue damage and secondary infections. To address these challenges, we propose an approach doodled vessel enhancement (DOVE) that utilizes hand-drawn doodles to train a PAA super-resolution model. With a training dataset consisting of only 32 real PAA images, we construct a diffusion model that interprets hand-drawn doodles as low-resolution images. DOVE enables us to generate a large number of realistic PAA images, achieving a 49.375% fool rate, even among experts in photoacoustic imaging. Subsequently, we employ these generated images to train a self-similarity-based model for super-resolution. During cross-domain tests, our method, trained solely on generated images, achieves a structural similarity value of 0.8591, surpassing the scores of all other models trained with real high-resolution images. DOVE successfully overcomes the limitation of insufficient training samples and unlocks the clinic application potential of super-resolution-based biomedical imaging.

Advances in photoacoustic imaging aided by nano contrast agents: special focus on role of lymphatic system imaging for cancer theranostics

Photoacoustic imaging (PAI) is a successful clinical imaging platform for management of cancer and other health conditions that has seen significant progress in the past decade. However, clinical translation of PAI based methods are still under scrutiny as the imaging quality and clinical information derived from PA images are not on par with other imaging methods. Hence, to improve PAI, exogenous contrast agents, in the form of nanomaterials, are being used to achieve better image with less side effects, lower accumulation, and improved target specificity. Nanomedicine has become inevitable in cancer management, as it contributes at every stage from diagnosis to therapy, surgery, and even in the postoperative care and surveillance for recurrence. Nanocontrast agents for PAI have been developed and are being explored for early and improved cancer diagnosis. The systemic stability and target specificity of the nanomaterials to render its theranostic property depends on various influencing factors such as the administration route and physico-chemical responsiveness. The recent focus in PAI is on targeting the lymphatic system and nodes for cancer diagnosis, as they play a vital role in cancer progression and metastasis. This review aims to discuss the clinical advancements of PAI using nanoparticles as exogenous contrast agents for cancer theranostics with emphasis on PAI of lymphatic system for diagnosis, cancer progression, metastasis, PAI guided tumor resection, and finally PAI guided drug delivery.

Enhanced resolution and sensitivity acoustic-resolution photoacoustic microscopy with semi/unsupervised GANs

Acoustic-resolution photoacoustic microscopy (AR-PAM) enables visualization of biological tissues at depths of several millimeters with superior optical absorption contrast. However, the lateral resolution and sensitivity of AR-PAM are generally lower than those of optical-resolution PAM (OR-PAM) owing to the intrinsic physical acoustic focusing mechanism. Here, we demonstrate a computational strategy with two generative adversarial networks (GANs) to perform semi/unsupervised reconstruction with high resolution and sensitivity in AR-PAM by maintaining its imaging capability at enhanced depths. The b-scan PAM images were prepared as paired (for semi-supervised conditional GAN) and unpaired (for unsupervised CycleGAN) groups for label-free reconstructed AR-PAM b-scan image generation and training. The semi/unsupervised GANs successfully improved resolution and sensitivity in a phantom and in vivo mouse ear test with ground truth. We also confirmed that GANs could enhance resolution and sensitivity of deep tissues without the ground truth.