Computer-aided detection has become the means to an unusual end for Median Technologies. The software firm, based in Biot, France, is building on a foundation of CAD technologies to develop a suite of software applications to quantify, volumetrically observe, and follow lesions over time.
Computer-aided detection has become the means to an unusual end for Median Technologies. The software firm, based in Biot, France, is building on a foundation of CAD technologies to develop a suite of software applications to quantify, volumetrically observe, and follow lesions over time.
"Our goals are to provide clinical added value and productivity to the end user," said Michael Auffret, vice president of product management at Median.
Those goals are already being achieved by practitioners in Europe. Median has introduced lesion management systems (LMS) for the lung, colon, and liver. They have been installed in clinical settings in Europe but have not yet been approved for use in the U.S. by the FDA. That is expected later this year.
Much of the work leading up to these products' release has come from 10 years of European collaborations, including a continuing relationship with the École Polytechnique Fédérale de Lausanne and eight years of working with Focus Imaging Europe, a PACS-on-demand and CAD company, and HealthCenter Europe.
"We are not starting from technology that has been used for other applications, such as the military industry," Auffret said. "We have been working in the medical industry for more than 10 years. The people in the company have a lot of experience in medical imaging and work very closely with radiologists."
All three lesion management systems are developed from a Web-based medical image analysis system that can be integrated into existing information management infrastructure, including PACS workstations. LMS-Lung highlights solid as well as nonsolid or mixed lesions associated with a high prevalence of malignancy. The software identifies regions of interest (ROIs) that can harbor small metastases. The segmentation option measures key characteristics of lung lesions, such as volume, length, width, diameter, and density.
LMS-Colon presents ROIs in the lumen of the colon that are similar in shape and density to polyps. It provides 3D reconstruction and volume and density measurements of lesions. It displays CT colonography studies in prone-supine visualization, as well as interactive multiplanar and 2D/3D. It also offers a large set of window settings and measurement tools.
LMS-Liver tabulates findings based on Response Evaluation Criteria in Solid Tumor measures. It also quantifies hepatic lesions according to volume and the largest diameter.
All three products also automatically register past and present examinations to compare lesion changes over time.
"We can evaluate solid lesions and the patient's response to treatment, and we can provide these kinds of tabulated results on the liver, lungs, and other lesions," Auffret said.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.