Artificial Intelligence-Guided Segmentation and Path Planning Software for Transthoracic Lung Biopsy.

PURPOSE: To validate the sensitivity and specificity of a 3-dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) software for lung lesion detection and to establish concordance between AI-generated needle paths and those used in actual biopsy procedures. MATERIALS AND METHODS: This was a retrospective study using computed tomography (CT) scans from 3 hospitals. Inclusion criteria were scans with 1-5 nodules of diameter ≥5 mm; exclusion criteria were poor-quality scans or those with nodules measuring <5mm in diameter. In the lesion detection phase, 2,147 nodules from 219 scans were used to develop and train the deep learning 3D-CNN to detect lesions. The 3D-CNN was validated with 235 scans (354 lesions) for sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. In the path planning phase, Bayesian optimization was used to propose possible needle trajectories for lesion biopsy while avoiding vital structures. Software-proposed needle trajectories were compared with actual biopsy path trajectories from intraprocedural CT scans in 150 patients, with a match defined as an angular deviation of <5° between the 2 trajectories. RESULTS: The model achieved an overall AUC of 97.4% (95% CI, 96.3%-98.2%) for lesion detection, with mean sensitivity of 93.5% and mean specificity of 93.2%. Among the software-proposed needle trajectories, 85.3% were feasible, with 82% matching actual paths and similar performance between supine and prone/oblique patient orientations (P = .311). The mean angular deviation between matching trajectories was 2.30° (SD ± 1.22); the mean path deviation was 2.94 mm (SD ± 1.60). CONCLUSIONS: Segmentation, lesion detection, and path planning for CT-guided lung biopsy using an AI-guided software showed promising results. Future integration with automated robotic systems may pave the way toward fully automated biopsy procedures.

Phantom and Animal Study of a Robot-Assisted, CT-Guided Targeting System using Image-Only Navigation for Stereotactic Needle Insertion without Positional Sensors.

PURPOSE: To evaluate the feasibility and accuracy of a robotic system to integrate and map computed tomography (CT) and robotic coordinates, followed by automatic trajectory execution by a robotic arm. The system was hypothesized to achieve a targeting error of <5 mm without significant influence from variations in angulation or depth. MATERIALS AND METHODS: An experimental study was conducted using a robotic system (Automated Needle Targeting device for CT [ANT-C]) for needle insertions into a phantom model on both moving patient table and moving gantry CT scanners. Eight spherical markers were registered as targets for 90 insertions at different trajectories. After a single ANT-C registration, the closed-loop software targeted multiple markers via the insertion of robotically aligned 18-gauge needles. Accuracy (distance from the needle tip to the target) was assessed by postinsertion CT scans. Similar procedures were repeated to guide 10 needle insertions into a porcine lung. A regression analysis was performed to test the effect of needle angulation and insertion depth on the accuracy of insertion. RESULTS: In the phantom model, all needle insertions (median trajectory depth, 64.8 mm; range, 46.1-153 mm) were successfully performed in single attempts. The overall accuracy was 1.36 mm ± 0.53, which did not differ between the 2 types of CT scanners (1.39 mm ± 0.54 [moving patient table CT] vs 1.33 mm ± 0.52 [moving gantry CT]; P = .54) and was not significantly affected by the needle angulation and insertion depth. The accuracy for the porcine model was 9.09 mm ± 4.21. CONCLUSIONS: Robot-assisted needle insertion using the ANT-C robotic device was feasible and accurate for targeting multiple markers in a phantom model.

Automated Needle Targeting with X-ray (ANT-X) - Robot-assisted device for percutaneous nephrolithotomy (PCNL) with its first successful use in human.

INTRODUCTION: To make percutaneous access easier in PCNL, we developed Automated Needle Targeting with X-ray (ANT-X). METHOD: ANT-X uses an image registration software with a closed loop feedback system to autoalign the puncture needle to the desired calyx using the bullseye technique. We tried percutaneous punctures on a live pig model and compared the results with free-hand technique. We then performed our first PCNL in a human subject with the aid of ANT-X. Our patient was a 48 year-old gentleman with a 1.4cm left lower pole stone. RESULTS: Initial results for live animal trial showed radiation exposure for robot-assisted arm during puncture was reduced by 26% compared to the free-hand technique (8.2mGy vs 11.2mGy). In the human trial, obtaining percutaneous access was successful at first attempt. CONCLUSION: ANT-X system can help surgeons feel confident and potentially reduce complications, hence enabling more surgeons to adopt this procedure.

The development and validation of a prototype mobility tracker for assessing the life space mobility and activity participation of older adults.

BACKGROUND: There is increasing interest in examining the life space mobility and activity participation of older adults in the community using sensor technology. Objective data from these technologies may overcome the limitations of self-reported surveys especially in older adults with age-associated cognitive impairment. This paper describes the development and validation of a prototype hybrid mobility tracker for assessing life space mobility and out-of-home activities amongst 33 community-ambulant older adults in Singapore. METHODS: A hybrid mobility tracker was developed by combining a passive Global Positioning System logger, tri-axial accelerometer and radio-frequency identification. Objective measures of life space, derived from 1 week of tracking data using Geographic Information Systems, were the maximum Euclidean distance from home (Max Euclid) and the area of the minimum convex polygon surrounding all GPS waypoints (MCP area). Out-of-home activities were quantified by visually identifying the total number of activity nodes, or places where participants spent ≥5 min, from mobility tracks. Self-reported measure of life space in 4 weeks was obtained using the University of Alabama at Birmingham Study of Life Space Assessment (UAB-LSA) questionnaire. Self-reported out-of-home activities were recorded daily in a travel diary for 1 week. Bivariate correlations were used to examine convergent validity between objective and subjective measures of life space and out-of-home activities. RESULTS: The mean age of participants was 69.2 ± 7.1 years. The mean UAB-LSA total score was 79.1 ± 17.4. The median (range) Max Euclid was 2.44 km (0.26-7.50) per day, and the median (range) MCP area was 3.31 km2 (0.03-34.23) per day. The UAB-LSA total score had good correlation with Max Euclid (r = 0.51, p = 0.002), and moderate correlation with MCP area (r = 0.46, p = 0.007). The median (range) total number of activity nodes measured by tracker of 20 (8-47) per week had a good correlation with the total activity count recorded in the travel diaries of 15 (6-40) per week (r = 0.52, p = 0.002). CONCLUSIONS: The tracking system developed to understand out-of-home travel was feasible and reliable. Comparisons with the UAB-LSA and travel diaries showed that it provided reliable and valid spatiotemporal data to assess the life space mobility and activity participation of older adults.