Gland context networks: A novel approach for improving prostate cancer identification

Author(s)

Mendes, Rodrigo de P. ^[1] ; Yuan, Xin ^[2] ; Genega, Elizabeth M. ^{[3, 4]} ; Xu, Xiaoyin ^[5] ; Costa, Luciano da F. ^[6] ; Comin, Cesar H. ^[1]

Affiliation

^[1] Univ Fed Sao Carlos, Dept Comp Sci, Sao Carlos, SP - Brazil

^[2] Harvard Med Sch, Beth Israel Deaconess Med Ctr, Dept Med, Boston, MA 02115 - USA

^[3] Harvard Med Sch, Beth Israel Deaconess Med Ctr, Dept Pathol, Boston, MA 02115 - USA

^[4] Tufts Med Ctr, Dept Pathol & Lab Med, Boston, MA 02111 - USA

^[5] Harvard Med Sch, Brigham & Womens Hosp, Dept Radiol, Boston, MA 02115 - USA

^[6] Univ Sao Paulo, Sao Carlos Inst Phys, Sao Carlos, SP - Brazil

• Document type: Journal article
• Source: Computerized Medical Imaging and Graphics; v. 94, DEC 2021.
• Web of Science Citations: 0

Abstract

Prostate cancer (PCa) is a pervasive condition that is manifested in a wide range of histologic patterns in biopsy samples. Given the importance of identifying abnormal prostate tissue to improve prognosis, many computerized methodologies aimed at assisting pathologists in diagnosis have been developed. It is often argued that improved diagnosis of a tissue region can be obtained by considering measurements that can take into account several properties of its surroundings, therefore providing a more robust context for the analysis. Here we propose a novel methodology that can be used for systematically defining contextual features regarding prostate glands. This is done by defining a Gland Context Network (GCN), a representation of the prostate sample containing information about the spatial relationship between glands as well as the similarity between their appearance. We show that such a network can be used for establishing contextual features at any spatial scale, therefore providing information that is not easily obtained from traditional shape and textural features. Furthermore, it is shown that even basic features derived from a GCN can lead to state-of-the-art classification performance regarding PCa. All in all, GCNs can assist in defining more effective approaches for PCa grading. (AU)

• FAPESP's process: 21/12354-8 - Analysis and refinement of machine learning methods for blood vessel morphometry
• Grantee: Cesar Henrique Comin
• Support Opportunities: Regular Research Grants
• FAPESP's process: 18/09125-4 - Representation, characterization and modeling of biological images using complex networks
• Grantee: Cesar Henrique Comin
• Support Opportunities: Regular Research Grants
• FAPESP's process: 15/22308-2 - Intermediate representations in Computational Science for knowledge discovery
• Grantee: Roberto Marcondes Cesar Junior
• Support Opportunities: Research Projects - Thematic Grants