The 6D pose estimation of an object from an image is a central problem in many domains of Computer Vision (CV) and researchers have struggled with this issue for several years. Traditional pose estimation methods (1) leveraged on geometrical approaches, exploiting manually annotated local features, or (2) relied on 2D object representations from different points of view and their comparisons with the original image. The two methods mentioned above are also known as Feature-based and Template-based, respectively. With the diffusion of Deep Learning (DL), new Learning-based strategies have been introduced to achieve the 6D pose estimation, improving traditional methods by involving Convolutional Neural Networks (CNN). This review analyzed techniques belonging to different research fields and classified them into three main categories: Template-based methods, Feature-based methods, and Learning-Based methods. In recent years, the research mainly focused on Learning-based methods, which allow the training of a neural network tailored for a specific task. For this reason, most of the analyzed methods belong to this category, and they have been in turn classified into three sub-categories: Bounding box prediction and Perspective-n-Point (PnP) algorithm-based methods, Classification-based methods, and Regression-based methods. This review aims to provide a general overview of the latest 6D pose recovery methods to underline the pros and cons and highlight the best-performing techniques for each group. The main goal is to supply the readers with helpful guidelines for the implementation of performing applications even under challenging circumstances such as auto-occlusions, symmetries, occlusions between multiple objects, and bad lighting conditions.

The aim of “Precision Surgery” is to reduce the impact of surgeries on patients’ global health. In this context, over the last years, the use of three-dimensional virtual models (3DVMs) of organs has allowed for intraoperative guidance, showing hidden anatomical targets, thus limiting healthy-tissue dissections and subsequent damage during an operation. In order to provide an automatic 3DVM overlapping in the surgical field, we developed and tested a new software, called “ikidney”, based on convolutional neural networks (CNNs). From January 2022 to April 2023, patients affected by organ-confined renal masses amenable to RAPN were enrolled. A bioengineer, a software developer, and a surgeon collaborated to create hyper-accurate 3D models for automatic 3D AR-guided RAPN, using CNNs. For each patient, demographic and clinical data were collected. A total of 13 patients were included in the present study. The average anchoring time was 11 (6–13) s. Unintended 3D-model automatic co-registration temporary failures happened in a static setting in one patient, while this happened in one patient in a dynamic setting. There was one failure; in this single case, an ultrasound drop-in probe was used to detect the neoplasm, and the surgery was performed under ultrasound guidance instead of AR guidance. No major intraoperative nor postoperative complications (i.e., Clavien Dindo > 2) were recorded. The employment of AI has unveiled several new scenarios in clinical practice, thanks to its ability to perform specific tasks autonomously. We employed CNNs for an automatic 3DVM overlapping during RAPN, thus improving the accuracy of the superimposition process.

Background: Addressing intraoperative bleeding remains a significant challenge in the field of robotic surgery. This research endeavors to pioneer a groundbreaking solution utilizing convolutional neural networks (CNNs). The objective is to establish a system capable of forecasting instances of intraoperative bleeding during robot-assisted radical prostatectomy (RARP) and promptly notify the surgeon about bleeding risks. Methods: To achieve this, a multi-task learning (MTL) CNN was introduced, leveraging a modified version of the U-Net architecture. The aim was to categorize video input as either “absence of blood accumulation” (0) or “presence of blood accumulation” (1). To facilitate seamless interaction with the neural networks, the Bleeding Artificial Intelligence-based Detector (BLAIR) software was created using the Python Keras API and built upon the PyQT framework. A subsequent clinical assessment of BLAIR’s efficacy was performed, comparing its bleeding identification performance against that of a urologist. Various perioperative variables were also gathered. For optimal MTL-CNN training parameterization, a multi-task loss function was adopted to enhance the accuracy of event detection by taking advantage of surgical tools’ semantic segmentation. Additionally, the Multiple Correspondence Analysis (MCA) approach was employed to assess software performance. Results: The MTL-CNN demonstrated a remarkable event recognition accuracy of 90.63%. When evaluating BLAIR’s predictive ability and its capacity to pre-warn surgeons of potential bleeding incidents, the density plot highlighted a striking similarity between BLAIR and human assessments. In fact, BLAIR exhibited a faster response. Notably, the MCA analysis revealed no discernible distinction between the software and human performance in accurately identifying instances of bleeding. Conclusion: The BLAIR software proved its competence by achieving over 90% accuracy in predicting bleeding events during RARP. This accomplishment underscores the potential of AI to assist surgeons during interventions. This study exemplifies the positive impact AI applications can have on surgical procedures.