Technology

Pusan National University Introduces ASTRA-Net for Improved Lung Airway Mapping

Published

2 hours ago

August 6, 2026

ASTRA-Net helps reconstruct overlooked peripheral airways, creating more complete maps for bronchoscopy procedures

BUSAN, South Korea, Aug. 6, 2026 /PRNewswire/ — Lung cancer is the most diagnosed cancer globally and is one of the leading causes of cancer-related deaths. Early detection can improve survival. However, collecting tissue samples from small tumors located deep within the lungs remains a big challenge. As many of these lesions are found in the peripheral regions of the lungs, physicians must navigate through an intricate network of tiny branching airways to reach the target.

In these cases, clinicians rely on lung navigation systems that use three-dimensional airway maps reconstructed from computed tomography (CT) scans to guide instruments toward suspicious lesions. The accuracy of these navigation systems depends on the completeness of the airway maps. Creating these maps is again difficult, as the smallest peripheral airways are extremely thin and difficult to distinguish from the surrounding tissues. This restriction raises a concern that if artificial intelligence (AI) systems are trained using incomplete information, they may also overlook clinically important airways.

To address this challenge, researchers from Pusan National University in South Korea developed ASTRA-Net (Anatomical Segmentation with Tree-aware Refinement Attention), an AI framework designed to identify previously overlooked airway branches and generate more complete airway maps. The study was led by Dr. MinWoo Kim from the School of Biomedical Convergence Engineering, Pusan National University, and Dr. Hee Yun Seol from the Division of Pulmonary and Critical Care Medicine, Research Institute for Convergence of Biomedical Science and Technology, Pusan National University Yangsan Hospital, in collaboration with other researchers. The paper was published in IEEE Transactions on Medical Imaging (Volume 45, Issue 6) on June 1, 2026.

Unlike conventional models that may be limited by incomplete training annotations, ASTRA-Net was designed to identify anatomically plausible airway structures that may have been omitted from the original labels.

“ASTRANET is not simply another airway segmentation model. It was specifically designed to identify peripheral airways that may have been overlooked during manual annotation, thereby helping to create a more complete roadmap for bronchoscopy,” explains Dr. Kim.

ASTRA-Net utilizes a multi-stage deep learning architecture like those employed in advanced medical image analysis. A part of this network learns the overall structure of the lungs, whereas another refines regions where airway boundaries are unclear. An additional attention mechanism helps the model focus on regions where small peripheral airways are difficult to distinguish or may have been omitted from the annotations. This allows the reconstruction of airway branches that are often missing from CT annotations. By incorporating anatomical clues from the surrounding lung tissues and blood vessels, which often run alongside the airways, the system can infer the continuity of previously unrecognized airway pathways.

Researchers also evaluated the framework using multiple datasets as well as clinical CT scans obtained from Pusan National University Yangsan Hospital. This model demonstrated strong performance in identifying fine peripheral airways and remained robust even when CT scans varied in image quality and slice thickness. Additionally, expert review of the model predictions showed that some structures initially counted as false positives were genuine airway branches that had been omitted from the original annotations.

“By providing physicians with a more complete airway roadmap, we hope this technology will improve navigation to difficult-to-reach lung lesions and support the development of future AI-assisted and robotic bronchoscopy systems,” concludes Dr. Kim.

Reference

Title of original paper: Discovery of Peripheral Airway Beyond Incomplete CT Annotations for Navigational Bronchoscopy

Journal: IEEE Transactions on Medical Imaging

DOI: 10.1109/TMI.2026.3672178

About Pusan National University

Website: https://www.pusan.ac.kr/eng/Main.do

Contact:

Goon-Soo Kim

82 51 510 7928

420227@email4pr.com

View original content to download multimedia:https://www.prnewswire.com/news-releases/pusan-national-university-introduces-astra-net-for-improved-lung-airway-mapping-302844459.html

SOURCE Pusan National University

Technology

OneBill Software Launches CPQ360.ai, an AI-First CPQ Built to Work With Any Billing Stack

Published

15 minutes ago

August 6, 2026

SANTA CLARA, Calif., Aug. 6, 2026 /PRNewswire/ — OneBill Software today announced the launch of CPQ360.ai, an AI-first configure-price-quote product built to run on top of any billing platform to complete the quote-to-revenue lifecycle. CPQ360.ai governs every quote, rep-built or AI agent-built, under the same pricing rules, margin guardrails, and approval logic, then hands off clean, billing-ready terms through native connectors — live today for Stripe, with additional platforms in active development.

CPQ360.ai is built for the industries where quoting complexity is highest – telecom, hi-tech, manufacturing, and medical devices; where complex bundles, configurable pricing, and multi-party approvals make manual quoting unworkable.

Unlike CPQ tools that bolt AI onto an existing UI, CPQ360.ai is API-first, with REST APIs, webhooks, and Model Context Protocol (MCP) access built in from day one. It’s billing-platform agnostic by design, so the quote-to-revenue lifecycle completes on whatever CRM, contract, and billing stack a team already runs — Salesforce or HubSpot for CRM, any eSign tool, and any billing platform — without requiring teams to replace what’s already working.

“We set out to build an agentic-first CPQ that drops into any RevOps stack, on any billing platform,” said JK Chelladurai, Founder and CEO of OneBill Software. “Our team spent years running quote-to-revenue at scale inside OneBill. CPQ360.ai is built on that experience, so an AI agent and a human rep are held to the exact same rules, on any billing platform.”

CPQ360.ai is available now at www.cpq360.ai, where teams can book a personalized demo or start a free trial.

About CPQ360.ai

CPQ360.ai is a configure-price-quote product built for agentic execution on an API-first foundation, completing the quote-to-revenue lifecycle on whatever CRM, contract, and billing systems are already in place. CPQ360.ai is a OneBill Software company. Learn more at www.cpq360.ai

Media Contact: Ravi Condamoor | marketing@cpq360.ai | +1 (408) 505 – 4212

View original content to download multimedia:https://www.prnewswire.com/news-releases/onebill-software-launches-cpq360ai-an-ai-first-cpq-built-to-work-with-any-billing-stack-302844595.html

SOURCE OneBill Software

Technology

Central Alabama Water Selects Doxim to Enhance the Customer Payment Experience

Published

15 minutes ago

August 6, 2026

Doxim’s customer payment portal provides accessible, convenient payment options to streamline operations and improve efficiency for the utility.

INDIANAPOLIS, Aug. 6, 2026 /PRNewswire/ — Doxim® (http://www.doxim.com), the leading Customer Communications Management (CCM) and payments provider serving highly regulated markets, announced that Central Alabama Water, the largest water utility in the state, has selected Doxim’s customer payment solution and portal. It will unify with Doxim’s CCM solution already in place at the utility to offer greater flexibility to its customers through expanded payment access.

Central Alabama Water provides residents in five counties with safe and reliable drinking water. Through a strategic partnership with Doxim spanning customer communications, billing, and payments, the utility has established a streamlined meter-to-cash ecosystem that reduces vendor management complexity and enhances customer engagement. Building on a relationship of more than 20 years, the expanded partnership leverages a single-provider model to drive greater consistency, cost efficiencies, and a more modern payment experience for all customers.

Doxim will implement a customer-facing payment portal, which provides Central Alabama Water customers with omnichannel and personalized ways to make payment transactions. Methods include online and mobile payments, pay-by-text, pay by phone, and in-person payments made through an extensive network of retail locations, such as Walmart, CVS, and Dollar General.

“Making sure our customers have easy access to information about their account is key to building a world-class water utility,” said Jeffrey F. Thompson, CEO of Central Alabama Water. “This partnership with Doxim will bring a new customer portal and provide more locations where customers can pay in-person if they prefer that option. We look forward to providing more details to our customers when we roll out this exciting change.”

Doxim’s innovative payments solution will help Central Alabama Water improve its collections process and operational efficiency via a unified platform.

“Customers increasingly want convenience from their utility, and our clients benefit from a complete billing to payments solution that supports long-term payment goals,” says Scott Biel, Chief Revenue Officer at Doxim. “We’re thrilled to bring our payments portal to Central Alabama Water and help them improve customer experience through the availability of flexible payment options.”

Doxim’s Payments platform delivers a seamless, omnichannel billing-to-payment experience, enabling customers to pay anytime, anywhere. For utilities like Central Alabama Water, the integrated solution streamlines the entire billing and payment lifecycle, reducing operational complexity while improving efficiency and customer satisfaction.

About Doxim

Doxim is the customer communications management and engagement technology leader serving highly regulated markets, including financial services, utilities, and healthcare. Doxim provides omnichannel communications and payment solutions that maximize customer engagement and revenue while reducing costs. Its software and technology-enabled managed services address key digitization, operational efficiency, and customer experience challenges through a suite of plug-and-play, integrated SaaS software and technology solutions. Learn more at http://www.doxim.com.

View original content:https://www.prnewswire.com/news-releases/central-alabama-water-selects-doxim-to-enhance-the-customer-payment-experience-302845054.html

SOURCE Doxim

Technology

SolidRun and Leopard Imaging Collaborate to Accelerate Edge AI Vision Development

Published

15 minutes ago

August 6, 2026

ACRE, Israel and FREMONT, Calif., Aug. 6, 2026 /PRNewswire/ — SolidRun, a leading developer of embedded computing and edge AI solutions, and Leopard Imaging Inc., a global leader in embedded vision and camera technology, today announced a technology collaboration to simplify and accelerate the development of next-generation edge AI vision applications.

As AI-powered vision becomes increasingly important across industrial automation, robotics, intelligent transportation, security, and medical imaging, developers face growing pressure to reduce integration effort and shorten time-to-market. By combining Leopard Imaging’s industry-leading camera technology with SolidRun’s Hailo-15 AI platforms, the collaboration provides customers with a pre-validated solution that enables them to focus on application development rather than hardware integration.

Through this collaboration, Leopard Imaging’s MIPI CSI-2 camera modules have been validated and optimized for use with SolidRun’s Hailo-15 System-on-Module (SoM) and HummingBoard Hailo-15 AIOT platforms. The integrated solution combines advanced imaging, embedded AI processing, and production-ready hardware into a single platform for rapid development and deployment.

The solution currently supports Leopard Imaging camera modules based on Sony’s IMX678 and IMX334 image sensors. When paired with the Hailo-15 platform, developers benefit from dual 12-megapixel Image Signal Processors (ISP), AI-powered image enhancement, and up to 20 TOPS of edge AI performance for demanding real-time vision workloads.

The companies have jointly validated camera compatibility, image quality, and platform integration, helping customers reduce engineering risk, shorten development cycles, and accelerate the transition from prototype to production.

“Our mission has always been to simplify the development of advanced embedded AI systems,” said Dr. Atai Ziv, CEO of SolidRun. “By collaborating with Leopard Imaging, we are delivering a validated AI vision platform that removes much of the complexity of camera integration and allows developers to focus on creating innovative AI applications instead of solving hardware integration challenges.”

“Leopard Imaging is committed to delivering industry-leading embedded camera modules that provide the image quality, reliability, and performance required for demanding vision applications,” said Bill Pu, Co-founder and CEO of Leopard Imaging.

The combined solution is ideally suited for a broad range of edge AI applications, including:

Smart security and surveillanceIntelligent transportation systemsIndustrial automationRobotics and autonomous machinesSmart retailMedical imagingSmart city infrastructure

The joint solution is available today through SolidRun’s Hailo-15 System-on-Module, HummingBoard Hailo-15 AIOT, and evaluation kits. Developers can begin evaluating the platform immediately using production-ready hardware, software support, and documentation.

About SolidRun

SolidRun develops and manufactures high-performance System-on-Modules (SoMs), Single Board Computers (SBCs), industrial edge AI platforms, and embedded networking solutions for industrial, IoT, AI vision, and communications markets. The company’s open, scalable hardware platforms enable customers worldwide to accelerate the development of intelligent embedded systems.

About Leopard Imaging

Leopard Imaging Inc. is a global leader in embedded camera and AI vision technology, providing advanced camera modules and imaging solutions for robotics, industrial automation, autonomous systems, medical devices, and edge AI applications. The company partners with leading semiconductor manufacturers to deliver production-ready imaging solutions worldwide.

Media Contacts

Mirna Waldman
Business Development Manager
mirna.waldman@solid-run.com

Edge Computing Solutions – Modular & Scalable: SolidRun

Ariel Zhang
Marketing Strategist
arielz@leopardimaging.com

Leopard Imaging Inc.

View original content to download multimedia:https://www.prnewswire.com/news-releases/solidrun-and-leopard-imaging-collaborate-to-accelerate-edge-ai-vision-development-302844610.html

SOURCE SolidRun