Precise pulmonary scanning and reducing medical radiation exposure by developing a clinically applicable intelligent CT system: Toward improving patient care

Abstract

Background: Interstitial lung disease requires frequent re-examination, which directly causes excessive cumulative radiation exposure. To date, AI has not been applied to CT for enhancing clinical care; thus, we hypothesize AI may empower CT with intelligence to realize automatic and accurate pulmonary scanning, thus dramatically decrease medical radiation exposure without compromising patient care. Methods: Facial boundary detection was realized by recognizing adjacent jaw position through training and testing a region proposal network (RPN) on 76,882 human faces using a preinstalled 2-dimensional camera; the lung-fields was then segmented by V-Net on another training set with 314 subjects and calculated the moving distance of the scanning couch based on a pre-generated calibration table. A multi-cohort study, including 1,186 patients was used for validation and radiation dose quantification under three clinical scenarios. Findings: A U-HAPPY (United imaging Human Automatic Planbox for PulmonarY) scanning CT was designed. Error distance of RPN was 4¢46 §0¢02 pixels with a success rate of 98¢7% in training set and 2¢23 §0¢10 pixels with 100% success rate in testing set. Average Dice's coefficient was 0¢99 in training set and 0¢96 in testing set. A calibration table with 1,344,000 matches was generated to support the linkage between camera and scanner. This real-time automation makes an accurate plan-box to cover exact location and area needed to scan, thus reducing amounts of radiation exposures significantly (all, P<0¢001). Interpretation: U-HAPPY CT designed for pulmonary imaging acquisition standardization is promising for reducing patient risk and optimizing public health expenditures.

Wearable Sensing and Telehealth Technology with Potential Applications in the Coronavirus Pandemic

“…To date, many CT imaging devices have deployed computer vision techniques to track patients, and measure their position, shape, height and width contours using 3D optical or infrared cameras, and to automatically align the anatomical location of the patients with the isocenter of the bore. The AI-enabled U-HAPPY (United imaging Human Automatic Planbox for PulmonarY) scanning CT designed by Wang et al presents one example of such automatic and accurate CT scanning technologies [183]. In that study, the performance of automatic localization and radiation doses were evaluated in three scenarios, i.e., fully automatic, semi-automatic, and manual scanning, and it demonstrated that the fully automatic scenario significantly outperformed the others (Fig.…”

“…12. Intelligent CT performance testing, (a-d) full automatic results, (e-h) manual results, and (i-j) comparison of the scanning length error and radiation dose among the full, semi and manual scenarios [183]. been used in Wuhan during the COVID-19 outbreak, has prevented cross infections among medical staff and infected patients, and provided doctors a robust foundation to work on.…”

A comparison between manual and artificial intelligence-based automatic positioning in CT imaging for COVID-19 patients

“…By virtue of 3D visual sensors, AI can identify the pose and shape of patients and realize an automated contactless image acquisition work ow. Yang Wang et al (2020) reported that U-HAPPY (United imaging Human Automatic Planbox for PulmonarY) CT has a function with automatic positioning and scanning, which helps to reduce the radiation dose [6]. Booij et al [7] and Saltybaeva et al [8] also reported the patient centering accuracy in CT using 3D cameras that relies on deep neural network for image contouring.…”

Artificial intelligence-based patient positioning for faster, more accurate and efficient CT imaging for COVID-19 patients

“…By virtue of visual sensors, AI can identify the pose and shape of patients and realize an automated contactless image acquisition work ow. Yang Wang et al (2020) reported that U-HAPPY (United imaging Human Automatic Planbox for PulmonarY) CT has a function with automatic positioning and scanning, which helps to reduce the radiation dose [6]. Recently, GE Healthcare also introduced a Revolution Maxima CT, which relies on deep learning algorithms and real-time depth sensing technology to center patients, locate desired anatomies and perform scan automatically.…”