Software vendor puts twist on CAD software

Article

London-based newcomer Medicsight is challenging current second-read computer-aided detection manufacturers with a new kind of technology: software designed to "read" data jointly with radiologists.After more than three years developing semiautomatic

London-based newcomer Medicsight is challenging current second-read computer-aided detection manufacturers with a new kind of technology: software designed to "read" data jointly with radiologists.

After more than three years developing semiautomatic software for detecting nodules in the lung, cancerous or precancerous polyps in the colon, and calcifications in the heart, the company is poised for rapid deployment of its innovative portfolio, said CEO Paul Samuel.

Lung CAR (computer-assisted reader) software already bears the CE mark, clearing the way for its sale in Europe. On Aug. 16, the image analysis software for evaluating lung lesions or nodules on CT scans passed FDA review. And the company is just getting started. As many as five other CAR-based technologies could be submitted to the FDA for review before year's end. In the next six months, executives at Medicsight expect to close distribution deals with OEMs of imaging hardware, software, and PACS.

Medicsight expects to capitalize on the joint-read capability of its software, which Samuel believes will be a growth area. This type of software allows radiologists to view unfiltered images alongside software-enhanced regions of interest. Presenting data this way speeds up image analysis, Samuel said. With second-read products currently on the market, radiologists view images twice, employing CAD as a spot check for suspicious findings they may have inadvertently overlooked in their initial reviews of unfiltered images.

In addition to the joint-read feature, Lung CAR has tools for comparing scans taken at different times that permit simultaneous viewing of multiple scans, 3D object manipulation and object orientation, simultaneous zoom and rotation of two 3D images of nodules, and customizable display sorting by slice number or nodule size.

Other features built into Lung CAR include maximum intensity projection, orthogonal visualization, and 3D reconstructions of nodules with scales presenting anterior, posterior, superior, inferior, left, and right views, as well as full 3D rotation.

A nodule comparison option allows radiologists to review and compare nodules in follow-up studies, while tracking the degree of change in volume. The software can also calculate tumor volume doubling time and rate of volume growth, which are essential in assessing small, indeterminate lesions and diagnosing malignancies.

"Accurate measurement is critical, because it potentially allows the radiologist to shorten the time between follow-up scans and perhaps reduce morbidity for patients," Samuel said. "It also may allow radiologists to catch tumors earlier and potentially improve life expectancy."

Lung CAR has a series of filters for highlighting portions of lung scans that may contain nodules, including filters for enhancing the edges of structures and removing background noise. Its automatic extraction and calculation properties locate and determine the distance of nodules from the edge of the lung and the chest wall. Shape descriptors compute the maximum diameter of nodules in 3D space as well as the longest axial dimension, mean volume, and density.

The key advantage of Lung CAR is its ability to accurately identify the boundaries of suspicious nodules, which is fundamental to the measurement and detection of early-stage cancers. Samuel explained that lung nodules may arise along the wall of the lung or next to blood vessels. If software picks up bits of lung wall or blood vessels along with a nodule, it will not be able to perform precise volume assessments.

"If software cannot distinguish correctly between a lung nodule and a blood vessel or between a colon polyp and stool or folds of tissue, it will never be able to reliably measure what you are trying to detect," he said.

Recent Videos
Study: MRI-Based AI Enhances Detection of Seminal Vesicle Invasion in Prostate Cancer
What New Research Reveals About the Impact of AI and DBT Screening: An Interview with Manisha Bahl, MD
Can AI Assessment of Longitudinal MRI Scans Improve Prediction for Pediatric Glioma Recurrence?
A Closer Look at MRI-Guided Adaptive Radiotherapy for Monitoring and Treating Glioblastomas
Incorporating CT Colonography into Radiology Practice
What New Research Reveals About Computed Tomography and Radiation-Induced Cancer Risk
What New Interventional Radiology Research Reveals About Treatment for Breast Cancer Liver Metastases
New Mammography Studies Assess Image-Based AI Risk Models and Breast Arterial Calcification Detection
Can Deep Learning Provide a CT-Less Alternative for Attenuation Compensation with SPECT MPI?
Employing AI in Detecting Subdural Hematomas on Head CTs: An Interview with Jeremy Heit, MD, PhD
Related Content
© 2025 MJH Life Sciences

All rights reserved.