Abstract
Currently, there are 3.1 million American men affected by prostate cancer. Early detection represents the only way to safe lives. To evaluate a prostate cancer, the most widespread rank is the so-called Gleason score, based on the microscopic cancer appearance. Once assigned to the diagnosed prostate cancer its relative Gleason score, the correct therapy to be adopted must be promptly defined. To support pathologists and radiologists in timely diagnosis, in this paper we propose a method aimed to infer the Gleason score and the prostate cancer therapy exploiting formal methods. We consider a set of radiomic features directly obtained from magnetic resonance images. For this reason the proposed method is non invasive, since it does not require a biopsy. We model magnetic resonance images of patients as timed automata networks and we assign the Gleason score and the relative treatment, exploiting a set of temporal logic properties. In the experimental analysis, the properties are verified on 36 different patients, confirming the effectiveness of the proposed method with a sensitivity and a specificity equal to 1 for all the evaluated cases in Gleason score inference, and a sensitivity equal to 0.94 and a specificity equal to 1 in treatment prediction.
Highlights
Prostate cancer is the development of cancer in the prostate, a gland in the male reproductive system
In this paper we define the representation of magnetic resonances in terms of timed automata networks and, using the model checking technique and the radiomic features, we infer the prostate cancer Gleason score and the treatment suggested by radiologists and pathologists
The paper proceeds as follows: Section II describes the proposed method to infer prostate Gleason score and treatment, in Section III an experiment with real-world patients is performed to demonstrate the effectiveness of the proposed method, Section IV proposes an overview related to the current state-of-the-art in prostate cancer inference and, in Section V conclusion and future works area drawn
Summary
Prostate cancer is the development of cancer in the prostate, a gland in the male reproductive system. In recent years radiomics is emerging as a field of medical study focused on the extraction of a large amount of quantitative features from medical images [11]. In this paper we define the representation of magnetic resonances in terms of timed automata networks and, using the model checking technique and the radiomic features, we infer the prostate cancer Gleason score and the treatment suggested by radiologists and pathologists. The paper proceeds as follows: Section II describes the proposed method to infer prostate Gleason score and treatment, in Section III an experiment with real-world patients is performed to demonstrate the effectiveness of the proposed method, Section IV proposes an overview related to the current state-of-the-art in prostate cancer inference and, in Section V conclusion and future works area drawn
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
