Baoxin Li’s research while affiliated with Arizona State University and other places

Objective This systematic literature review of the integration of artificial intelligence (AI) applications in surgical practice through hand and instrument tracking provides an overview of recent advancements and analyzes current literature on the intersection of surgery with AI. Distinct AI algorithms and specific applications in surgical practice are also examined. Methods An advanced search using medical subject heading terms was conducted in Medline (via PubMed), SCOPUS, and Embase databases for articles published in English. A strict selection process was performed, adhering to PRISMA guidelines. Results A total of 225 articles were retrieved. After screening, 77 met inclusion criteria and were included in the review. Use of AI algorithms in surgical practice was uncommon during 2013–2017 but has gained significant popularity since 2018. Deep learning algorithms (n = 62) are increasingly preferred over traditional machine learning algorithms (n = 15). These technologies are used in surgical fields such as general surgery (n = 19), neurosurgery (n = 10), and ophthalmology (n = 9). The most common functional sensors and systems used were prerecorded videos (n = 29), cameras (n = 21), and image datasets (n = 7). The most common applications included laparoscopic (n = 13), robotic-assisted (n = 13), basic (n = 12), and endoscopic (n = 8) surgical skills training, as well as surgical simulation training (n = 8). Conclusion AI technologies can be tailored to address distinct needs in surgical education and patient care. The use of AI in hand and instrument tracking improves surgical outcomes by optimizing surgical skills training. It is essential to acknowledge the current technical and social limitations of AI and work toward filling those gaps in future studies.

Background Amyloid PET (Positron Emission Tomography) is crucial in detecting amyloid burden within the brain. However, the diversity of amyloid tracers and the scarcity of paired data significantly challenge the collaboration between cross‐center studies. In this research, we introduce a novel patch‐based 3D end‐to‐end image transformation model. This model works as a harmonization strategy, transferring the amyloid PET images from one tracer type to another. Method 51 florbetapir (FBP) and 604 PiB images from the Australian Imaging, Biomarkers and Lifestyle Study of Ageing (AIBL) were processed using established pipelines to extract regional standard uptake value ratios (SUVRs), mean cortical SUVRs (mcSUVRs), and SUVR images. 3D Cycle‐Consistent Generative Adversarial Networks (CycleGAN) was used to learn the end‐to‐end 3D image transformation using adversarial training strategies in conjunction with Resnet generators and multilayer discriminators within different tracer domains. Data augmentation techniques were applied to process the FBP images to balance the training samples and patch‐based learning was used throughout the experiment. The trained CycleGAN model was then applied to an independent dataset with 46 paired images from www.gaain.org/centiloid‐project for performance evaluation. Correlation analyses were conducted voxel‐wise and on mcSUVR, comparing the FBP/synthetic PiB to the true PiB data. The Structural Similarity Index Measure (SSIM) and Peak Signal‐to‐Noise Ratio (PSNR) were also evaluated between the synthetic and real PiB SUVR images. Result The synthetic PiB SUVR images were visually more similar to real PiB SUVR images than FBP. Voxel‐wise correlation improved from 0.942 between FBP and real PiB to 0.958 between the virtual and real PiB SUVR image (p < 0.0001). The agreement of mcSUVR improved from r = 0.909 to r = 0.954 (p<0.001) in the independent test dataset. The SSIM and PSNR between synthetic and real PiB are 0.762 and 25.370 in the independent dataset. Conclusion We proposed a novel end‐to‐end image transformation model for 3D PET image synthesis. The model finds the nonlinear mapping between different tracers and eliminates the requirement for paired training images. The result was confirmed using an independent dataset to demonstrate its effectiveness.

Objective: Deep learning enables precise hand tracking without the need for physical sensors, allowing for unsupervised quantitative evaluation of surgical motion and tasks. We quantitatively assessed the hand motions of experienced cerebrovascular neurosurgeons during simulated microvascular anastomosis using deep learning. We explored the extent to which surgical motion data differed among experts. Methods: A deep learning detection system tracked 21 landmarks corresponding to digit joints and the wrist on each hand of 5 expert cerebrovascular neurosurgeons. Tracking data for each surgeon was analyzed over long and short time intervals to examine gross movements and micromovements, respectively. Quantitative algorithms assessed the economy and flow of motion by calculating mean movement distances from the baseline median landmark coordinates and median times between sutures, respectively. Results: Tracking data correlated with specific surgical actions observed in microanastomosis video analysis. Economy of motion during suturing was calculated as 19, 26, 29, 27, and 28 pixels for surgeons 1, 2, 3, 4, and 5, respectively. Flow of motion during microanastomosis was 31.96, 29.40, 28.90, 7.37, and 47.21 secs for surgeons 1, 2, 3, 4, and 5, respectively. Conclusions: Hand tracking data showed similarities among experts, with low movements from baseline, minimal excess motion, and rhythmic suturing patterns. The data revealed unique patterns related to each expert’s habits and techniques. The results showed that surgical motion can be correlated with hand motion and assessed using mathematical algorithms. We also demonstrated the feasibility and potential of deep learning–based motion detection to enhance surgical training.

Amyloid PET imaging plays a crucial role in the diagnosis and research of Alzheimer's disease (AD), allowing non-invasive detection of amyloid-β plaques in the brain. However, the low spatial resolution of PET scans limits the accurate quantification of amyloid deposition due to partial volume effects (PVE). In this study, we propose a novel approach to addressing PVE using a latent diffusion model for resolution recovery (LDM-RR) of PET imaging. We leverage a synthetic data generation pipeline to create high-resolution PET digital phantoms for model training. The proposed LDM-RR model incorporates a weighted combination of L 1 , L 2 , and MS-SSIM losses at both noise and image scales to enhance MRI-guided reconstruction. We evaluated the model's performance in improving statistical power for detecting longitudinal changes and enhancing agreement between amyloid PET measurements from different tracers. The results demonstrate that the LDM-RR approach significantly improves PET quantification accuracy, reduces inter-tracer variability, and enhances the detection of subtle changes in amyloid deposition over time. We show that deep learning has the potential to improve PET quantification in AD, effectively contributing to the early detection and monitoring of disease progression.

Background In radiotherapy, 2D orthogonally projected kV images are used for patient alignment when 3D-on-board imaging (OBI) is unavailable. However, tumor visibility is constrained due to the projection of patient’s anatomy onto a 2D plane, potentially leading to substantial setup errors. In treatment room with 3D-OBI such as cone beam CT (CBCT), the field of view (FOV) of CBCT is limited with unnecessarily high imaging dose. A solution to this dilemma is to reconstruct 3D CT from kV images obtained at the treatment position. Methods We propose a dual-models framework built with hierarchical ViT blocks. Unlike a proof-of-concept approach, our framework considers kV images acquired by 2D imaging devices in the treatment room as the solo input and can synthesize accurate, full-size 3D CT within milliseconds. Results We demonstrate the feasibility of the proposed approach on 10 patients with head and neck (H&N) cancer using image quality (MAE: < 45HU), dosimetric accuracy (Gamma passing rate ((2%/2 mm/10%): > 97%) and patient position uncertainty (shift error: < 0.4 mm). Conclusions The proposed framework can generate accurate 3D CT faithfully mirroring patient position effectively, thus substantially improving patient setup accuracy, keeping imaging dose minimal, and maintaining treatment veracity.

Amyloid PET imaging plays a crucial role in the diagnosis and research of Alzheimer's disease (AD), allowing non-invasive detection of amyloid-β plaques in the brain. However, the low spatial resolution of PET scans limits accurate quantification of amyloid deposition due to partial volume effects (PVE). In this study, we propose a novel approach to addressing PVE using a latent diffusion model for resolution recovery (LDM-RR) of PET imaging. We leverage a synthetic data generation pipeline to create high-resolution PET digital phantoms for model training. The proposed LDM-RR model incorporates a weighted combination of L1, L2, and MS-SSIM losses at both noise and image scales to enhance MRI-guided reconstruction. We evaluated the model's performance in improving statistical power for detecting longitudinal changes and enhancing agreement between amyloid PET measurements from different tracers. Results demonstrate that the LDM-RR approach significantly improves PET quantification accuracy, reduces inter-tracer variability, and enhances the detection of subtle changes in amyloid deposition over time. We show that deep learning has the potential to improve PET quantification in AD, effectively contributing to early detection and monitoring of disease progression.

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both informative and non-informative tokens, suffers from inefficiency and inaccuracies. While sparse attention mechanisms have been introduced to mitigate these issues by pruning tokens involved in attention, they often lack context-awareness and intelligence. These mechanisms frequently apply a uniform token selection strategy across different inputs for batch training or optimize efficiency only for the inference stage. To overcome these challenges, we propose a novel algorithm: Select and Pack Attention (SPA). SPA dynamically selects informative tokens using a low-cost gating layer supervised by selection labels and packs these tokens into new batches, enabling a variable number of tokens to be used in parallelized GPU batch training and inference. Extensive experiments across diverse datasets and computer vision tasks demonstrate that SPA delivers superior performance and efficiency, including a 0.6 mAP improvement in object detection and a 16.4% reduction in computational costs.