ELIC Publishes Paper Showing Open Source System Supports Deep Learning AI and Quantitative Imaging Analyses on Cloud-Based Datasets
08 / 15 / 23
The International Association for the Study of Lung Cancer (IASLC), Accumetra, and numerous international CT lung cancer screening researchers published a paper in the Journal of Thoracic Oncology (JTO) showing that the open source Early Lung
Imaging Confederation (ELIC) system can support deep learning AI and quantitative imaging analyses on diverse and globally distributed cloud-based datasets. This paper provides results from deep learning and quantitative imaging experiments performed on 697 lung cancer screening cases with two CT image acquisition time points each. ELIC is designed to support the computational study of large collections of early lung cancer cases, where image data stays on the cloud within local regions while AI and quantitative imaging algorithms are distributed to those data locations. To read more about how this new global infrastructure can advance medical AI visit: https://us06web.zoom.us/j/3456879728
Accumetra Publishes Method That Predicts The Bias and Precision Performance of CT Lung Nodule Volume Measurements
08 / 03 / 23
Lung imaging researchers from Accumetra, Mount Sinai, and Cleveland Clinic published a manuscript in July indicating for the first time that CT lung volume measurements can be reliably predicted using a new calibration-based analysis method. The
study showed that good volume measurement prediction results (bias, precision) could be obtained even when using low-cost reference objects, specifically three rolls of 3M Scotch Tape (TM). This novel approach, which formed the underlying computer-vision, math, and physics foundation of Accumetra's CTLX1 and CTLX2 phantoms, is being used internationally to improve lung nodule measurements. Numerous research projects have been launched as a result of this work, investigating improved methods to predict how a CT scanner will perform when requested to measure the volume of small objects near the limits of CT resolution. To read more, visit https://qims.amegroups.org/article/view/115487/html . Contact Accumetra at info@accumetra.com for information on how this new approach is being used to better monitor and optimize CT image acquisition for precise small lung nodule volume measurement in standard clinical care, lung cancer screening, and clinical trials.
Accumetra Presents a New Lung Nodule Measurement Approach at the 2023 I-ELCAP Meeting in Verona
07 / 17 / 23
Accumetra’s founder and CEO Ricardo Avila delivered a presentation on June 29th at the I-ELCAP meeting in Verona, Italy. This presentation announced our newest findings on how to use a combination of AI, computer vision, and
imaging physics/signal processing to improve quantitative CT measurement performance of small objects by more than 600% (see image). We call this new technical approach Artificial Intelligence Targeting and Measurement (AITAM). AITAM has the potential to greatly improve our ability to detect early lung cancer and help identify new CT imaging biomarkers.
Study Shows 80% Long-Term Survival Results of Low Dose CT Lung Cancer Screening
11 / 22 / 22
A 20-year study conducted by the global I-ELCAP team confirms that low dose CT lung cancer screening has an outstanding 80% long-term survival rate. In those 20 years, I-ELCAP has supported around 90,000 lung screening participants,
almost 300 publications and numerous international study confirmations. The I-ELCAP lung screening protocol represents a major advance in the war on cancer. To read more, visit https://www.auntminnie.com/index.aspx?sec=sup&sub=cto&pag=dis&ItemID=138686 Contact Accumetra at info@accumetra.com to learn how to deploy ScreeningPLUS, the commercially available version of the I-ELCAP lung cancer screening management system, at your institution.
Accumetra and RSNA/QIBA Launch QIBA Conformance Certification Services at RSNA 2018
11 / 19 / 18
RSNA's Quantitative Imaging Biomarkers Alliance (QIBA) and Accumetra have launched the first QIBA Conformance Certification Service for verification of CT small lung nodule volume measurements. This new paid service enables clinical sites to verify that their
CT scanners and software analysis tools are performing at a sufficient level to reliably measure the volume and change in volume of small solid lung nodules. A clinical site receives an institution-specific QIBA Conformance Certification Mark that can be used to communicate the site's small lung nodule performance achievement. CT scanner and nodule analysis software vendors can also achieve QIBA Conformance Certification for their FDA-approved products and achieve a product-specific QIBA Conformance Certification Mark to highlight the performance of their products. This launch comes after over a year of globally deploying and testing the new CTLX1 CT image quality phantom and a cloud-based and fully automated CT phantom analysis service. The map below shows the location of the 65 CTLX1 phantoms (yellow) that have been shipped and are being used to monitor and optimize CT image quality at clinical sites around the world, thanks to support from the Prevent Cancer Foundation. Cloud-based phantom analysis servers (purple) can analyze an uploaded CTLX1 scan and send back an automated CT image quality report containing fundamental CT image quality properties within 10 minutes. To learn more about these new services, visit us at the Accumetra/QIBA exhibit booth (South Hall Booth #1024) at the 2018 RSNA Annual meeting or visit the QIBA Conformance Certification web page.
Accumetra to Present a Hot Topic Scientific Presentation at the 4th Annual World Congress of Thoracic Imaging
03 / 09 / 17
Accumetra will give a Hot Topic scientific presentation on the “Clinical Implications of CT Image Quality Variation in Low Dose Lung Cancer Screening Scans” on Tuesday June 20, 2017 at the 4th Annual World Congress of Thoracic Imaging. The presentation
will provide information on the level of fundamental image quality variation present at 27 international lung cancer screening sites and the potential impact of this variation on CT lung nodule measurement performance. The clinical sites participated in a first-of-its-kind crowd-sourced image quality study based on CT scanning and analysis of three rolls of 3M Scotch tape. More information on the presentation and the conference will be available at the World Congress of Thoracic Imaging website.
Accumetra to Present at the 2017 Dialog For Action Conference
03 / 09 / 17
Accumetra will present “Crowd-Sourcing Quality in Imaging” on Thursday April 20, 2017 at the Prevent Cancer Foundation’s Dialog For Action conference. The presentation will provide an update on a recent crowd-sourced study showing that low cost and ubiquitously available reference
objects, demonstrated using rolls of 3M Scotch Tape, can be used to efficiently monitor the performance of global CT scanners and imaging protocols. More information on the presentation and the conference can be found on the Dialog For Action website
Accumetra to Present at the 2017 SPIE Medical Imaging Conference
02 / 01 / 17
Accumetra will present a poster on a new method for predicting CT lung nodule measurement performance on Wednesday February 15, 2017 at the SPIE Medical Imaging conference. The poster titled “A new method for predicting CT lung nodule volume measurement
performance,” describes an automated phantom analysis and simulation approach with promising early results. More information on the methods can be found at the SPIE Medical Imaging site.
Accumetra To Present at the IASLC’s 17th World Conference on Lung Cancer in Vienna, Austria
12 / 04 / 16
Accumetra will present a poster (Abstract #6317) on Monday December 5, 2016 at the IASLC’s World Conference on Lung Cancer 2016 that will review the results of the CT Lung Screening Protocol Challenge. The CT Lung Screening Protocol Challenge, conducted
in May and June of 2016, was the first crowd-sourced and ultra-low cost study to help the lung cancer and COPD imaging research communities determine the best CT scanners and protocols for the detection and measurement of lung cancer and COPD. Within the two month data collection period the study obtained CT image quality data from 27 healthcare institutions, 54 CT scanners, and 130 individual CT scans. This first of its kind study data is now helping shape imaging protocol recommendations for lung cancer screening and COPD. The challenge results and potential implications for globally improving the quality of future population screening initiatives will be presented.
