Surgical-DINO: adapter learning of foundation models for depth estimation in endoscopic surgery.

PURPOSE: Depth estimation in robotic surgery is vital in 3D reconstruction, surgical navigation and augmented reality visualization. Although the foundation model exhibits outstanding performance in many vision tasks, including depth estimation (e.g., DINOv2), recent works observed its limitations in medical and surgical domain-specific applications. This work presents a low-ranked adaptation (LoRA) of the foundation model for surgical depth estimation. METHODS: We design a foundation model-based depth estimation method, referred to as Surgical-DINO, a low-rank adaptation of the DINOv2 for depth estimation in endoscopic surgery. We build LoRA layers and integrate them into DINO to adapt with surgery-specific domain knowledge instead of conventional fine-tuning. During training, we freeze the DINO image encoder, which shows excellent visual representation capacity, and only optimize the LoRA layers and depth decoder to integrate features from the surgical scene. RESULTS: Our model is extensively validated on a MICCAI challenge dataset of SCARED, which is collected from da Vinci Xi endoscope surgery. We empirically show that Surgical-DINO significantly outperforms all the state-of-the-art models in endoscopic depth estimation tasks. The analysis with ablation studies has shown evidence of the remarkable effect of our LoRA layers and adaptation. CONCLUSION: Surgical-DINO shed some light on the successful adaptation of the foundation models into the surgical domain for depth estimation. There is clear evidence in the results that zero-shot prediction on pre-trained weights in computer vision datasets or naive fine-tuning is not sufficient to use the foundation model in the surgical domain directly.

Efficient Photoelectrochemical Reduction of Carbon Dioxide to Formic Acid: A Functionalized Ionic Liquid as an Absorbent and Electrolyte.

Photoelectrochemical (PEC) reduction of carbon dioxide (CO2 ) is a potential method for production of fuels and chemicals from a C1 feedstock accumulated in the atmosphere. However, the low solubility of CO2 in water, and complicated processes associated with capture and conversion, render CO2 conversion inefficient. A new concept is proposed in which a PEC system is used to capture and convert CO2 into formic acid. The process is assisted by an ionic liquid (1-aminopropyl-3-methylimidazolium bromide) aqueous solution, which functions as an absorbent and electrolyte at ambient temperature and pressure. Within this PEC reduction strategy, the ionic liquid plays a critical role in promoting the conversion of CO2 to formic acid and suppressing the reduction of H2 O to H2 . At an applied voltage of 1.7 V, the Faradaic efficiency for formic acid production is as high as 94.1 % and the electro-to-chemical efficiency is 86.2 %.