Abstract
In the last years, the widespread use of the prostate-specific antigen (PSA) blood examination to triage patients who will enter the diagnostic/therapeutic path for prostate cancer (PCa) has almost halved PCa-specific mortality. As a counterpart, millions of men with clinically insignificant cancer not destined to cause death are treated, with no beneficial impact on overall survival. Therefore, there is a compelling need to develop tools that can help in stratifying patients according to their risk, to support physicians in the selection of the most appropriate treatment option for each individual patient. The aim of this study was to develop and validate on multivendor data a fully automated computer-aided diagnosis (CAD) system to detect and characterize PCas according to their aggressiveness. We propose a CAD system based on artificial intelligence algorithms that a) registers all images coming from different MRI sequences, b) provides candidates suspicious to be tumor, and c) provides an aggressiveness score of each candidate based on the results of a support vector machine classifier fed with radiomics features. The dataset was composed of 131 patients (149 tumors) from two different institutions that were divided in a training set, a narrow validation set, and an external validation set. The algorithm reached an area under the receiver operating characteristic (ROC) curve in distinguishing between low and high aggressive tumors of 0.96 and 0.81 on the training and validation sets, respectively. Moreover, when the output of the classifier was divided into three classes of risk, i.e., indolent, indeterminate, and aggressive, our method did not classify any aggressive tumor as indolent, meaning that, according to our score, all aggressive tumors would undergo treatment or further investigations. Our CAD performance is superior to that of previous studies and overcomes some of their limitations, such as the need to perform manual segmentation of the tumor or the fact that analysis is limited to single-center datasets. The results of this study are promising and could pave the way to a prediction tool for personalized decision making in patients harboring PCa.
Highlights
Prostate cancer (PCa) is the most common malignancy in men in both Europe and the United States [1, 2]
Our system provides a radiomics score based on texture features extracted from the automatic segmentation of the tumor, reaching a considerable accuracy in discriminating between low and high aggressive PCa (AUC respectively of 0.96 and 0.81 in the training and validation datasets)
The fully automatic pipeline we developed represents an important improvement with respect to previous studies, which relied mainly on manual segmentations performed by expert radiologists
Summary
Prostate cancer (PCa) is the most common malignancy in men in both Europe and the United States [1, 2]. Improved treatment and earlier diagnosis have almost halved PCa-specific mortality since the 1990s [3]. The ProtecT trial showed that in men with clinically localized PCa, active monitoring, radiotherapy, and prostatectomy have no statistically significant differences in cancer-specific mortality after 10 years of follow-up [7]. The Gleason grade (GG) criteria, published in 2013, underline the importance of properly classifying PCa by correlating pathology to prognosis [9]. The most significant classification change is the separation of patients classified with Gleason score (GS) 7 in two different categories: GG 2, with a GS of 3 + 4, including patients with a more favorable prognosis than GG 3 patients, with a GS of 4 + 3 [10]. Notwithstanding, treatment decisions are still based on PSA, biopsy, and staging [11]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have