CAD Generated MRI Series Improves Detection of Clinically Significant Prostate Cancer

Prostate cancer is the second most common cause of cancer death in men, after lung cancer. Because of the aging population, its incidence is expected to approximately double by 2030. Though prostate cancer is one of the leading causes of cancer death in men, most men diagnosed with prostate cancer do not die from it. This disparity exists because smaller cancers are unlikely to progress far enough during the patients’ lifetimes to prove fatal. These cancers are considered clinically insignificant. However, clinically significant cancers are associated with a high probability of death within 10 years after diagnosis. Whether a cancer is considered clinically significant or insignificant is based on its Gleason score, the sum of a primary and a secondary grade assigned to the cancer by a pathologist.

Studies have shown men with clinically insignificant prostate cancers do not benefit from treatment. Still, many of these men end up receiving treatment as many clinicians, not wanting to miss any cancers, will err on the side of caution. This overtreatment has grown even more acute with increasing use of prostate-specific antigen (PSA) screening. Tests for the biomarker PSA are widely used for screening and diagnosis of prostate cancer, but there is still considerable debate about the extent to which these tests should inform decisions about performing biopsies in men with elevated levels of PSA, or even be used at all. As a result, more men undergo biopsy, leading to anxiety and possible detrimental effects of further interventions. Other patients are placed in active surveillance programs after detection of clinically insignificant cancers with regular assessments over time, which involve risks for the patients and additional costs for the health care system. Clinicians now face the challenge of figuring out how to detach the likelihood of overtreatment from the higher rates of diagnosis that accompany PSA screening.

Now, a new study by researchers at Massachusetts General Hospital (Boston, MA, USA) has found that the addition of a computer-aided diagnostic (CAD) generated MRI series improves detection of clinically significant prostate cancer. In the study, nine radiologists retrospectively interpreted 150 prostate MRI examinations without and then with an additional random forest-based CAD model-generated MRI series. Characteristics of biopsy negative versus positive (Gleason ≥ 7 adenocarcinoma) groups were compared using the Wilcoxon test for continuous and Pearson's chi-squared test for categorical variables. The diagnostic performance of readers was compared without versus with CAD using MRMC methods to estimate the area under the receiver operator characteristic curve (AUC). Inter-reader agreement was assessed using weighted inter-rater agreement statistics. Analyses were repeated in peripheral and transition zone subgroups.

The study revealed that among 150 men with median age 67 ± 7.4 years, those with clinically significant prostate cancer were older (68 ± 7.6 years vs. 66 ± 7.0 years; p < .02), had smaller prostate volume (43.9 mL vs. 60.6 mL; p < .001), and no difference in prostate specific antigen (PSA) levels (7.8 ng/mL vs. 6.9 ng/mL; p = .08), but higher PSA density (0.17 ng/mL/cc vs. 0.10 ng/mL/cc; p < .001). Inter-rater agreement (IRA) for PI-RADS scores was moderate without CAD and significantly improved to substantial with CAD (IRA = 0.47 vs. 0.65; p < .001). CAD also significantly improved average reader AUC (AUC = 0.72, vs. AUC = 0.67; p = .02). Based on these findings, the researchers concluded that the addition of a random forest method-based, CAD-generated MRI image series improved inter-reader agreement and diagnostic performance for the detection of clinically significant prostate cancer, particularly in the transition zone.

Related Links:
Massachusetts General Hospital