A Diagnostics & Imaging Week

iCAD (Nashua, New Hampshire), a provider of computer-aided detection (CAD) solutions that are designed to enable healthcare professionals to identify cancer and other life-threatening conditions earlier, said that its Second Look CAD system was used in a study published in the Sept. 1 edition of Cancer, a journal of the American Cancer Society (ACS; Atlanta).

The study was titled “Evaluation of Breast Cancer with a Computer-Aided Detection System by Mammographic Appearance and Histopathology.”

Study findings revealed that CAD technology effectively identified 98% of the microcalcifications, 95% of the invasive lobular carcinomas, 89% of the mixed mass/ microcalcification lesions and 84% of the masses in 273 women with confirmed breast cancer. The study, which was based out of the department of radiology at the George Washington University Medical Center (Washington), concluded that CAD – with an overall sensitivity of 89% – “represents a useful tool for the detection of breast cancer,” the company said.

According to the study, “On the basis of lesion histopathology, CAD showed a higher detection rate for DCIS and invasive lobular carcinomas. This indicates that CAD has an important role in reducing the occurrence of missed cancers, even with difficult to detect lesions, such as invasive lobular carcinoma.”

Dr. Rachel Brem, director of breast imaging at George Washington University Medical Center and study principal investigator, said, “This study further demonstrates the potential of CAD for the improved diagnosis of breast cancer. It is particularly exciting, as it demonstrates the effectiveness of CAD in cancers that are often difficult to detect mammographically such as invasive lobular carcinomas.”

The study was conducted over a four-year span from three institutions collecting 1,000 consecutive screen-detected, biopsy-proven breast carcinomas. Every third tumor was selected until 275 consecutive carcinoma tumors were identified at random for system testing. Due to incomplete tumor data from two patients, the study was conducted on 273 carcinomas.

From a consecutive series of 494 women with normal screenings, 155 mammograms were randomly selected for this study. For the 265 patients with cancer who had age data available, the mean age was 60.6 years and for the 154 women with normal mammograms with age data available, the mean age was 58.9.

W. Scott Parr, president and CEO of iCAD, said the company “was privileged to take part in a study that further established the benefits of CAD for the early identification of breast cancer.”

According to the ACS, an estimated 211,240 new cases of breast cancer will be diagnosed in 2005.