Massimo Salvi1, Martino Bosco2, Luca Molinaro3, Alessandro Gambella3, Mauro Papotti4, U Rajendra Acharya5, Filippo Molinari6. 1. Politecnico di Torino, PoliTo(BIO)Med Lab, Biolab, Department of Electronics and Telecommunications, Corso Duca degli Abruzzi 24, Turin, 10129, Italy. Electronic address: massimo.salvi@polito.it. 2. San Lazzaro Hospital, Department of Pathology, Via Petrino Belli 26, Alba, 12051, Italy. 3. A.O.U. Città della Salute e della Scienza Hospital, Division of Pathology, Corso Bramante 88, Turin, 10126, Italy. 4. University of Turin, Division of Pathology, Department of Oncology, Via Santena 5, Turin, 10126, Italy. 5. Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore; Department of Biomedical Engineering, School of Science and Technology, SUSS University, Clementi, 599491, Singapore; Department of Bioinformatics and Medical Engineering, Asia University, Taiwan. 6. Politecnico di Torino, PoliTo(BIO)Med Lab, Biolab, Department of Electronics and Telecommunications, Corso Duca degli Abruzzi 24, Turin, 10129, Italy.
Abstract
BACKGROUND: In digital pathology, the morphology and architecture of prostate glands have been routinely adopted by pathologists to evaluate the presence of cancer tissue. The manual annotations are operator-dependent, error-prone and time-consuming. The automated segmentation of prostate glands can be very challenging too due to large appearance variation and serious degeneration of these histological structures. METHOD: A new image segmentation method, called RINGS (Rapid IdentificatioN of Glandural Structures), is presented to segment prostate glands in histopathological images. We designed a novel glands segmentation strategy using a multi-channel algorithm that exploits and fuses both traditional and deep learning techniques. Specifically, the proposed approach employs a hybrid segmentation strategy based on stroma detection to accurately detect and delineate the prostate glands contours. RESULTS: Automated results are compared with manual annotations and seven state-of-the-art techniques designed for glands segmentation. Being based on stroma segmentation, no performance degradation is observed when segmenting healthy or pathological structures. Our method is able to delineate the prostate gland of the unknown histopathological image with a dice score of 90.16 % and outperforms all the compared state-of-the-art methods. CONCLUSIONS: To the best of our knowledge, the RINGS algorithm is the first fully automated method capable of maintaining a high sensitivity even in the presence of severe glandular degeneration. The proposed method will help to detect the prostate glands accurately and assist the pathologists to make accurate diagnosis and treatment. The developed model can be used to support prostate cancer diagnosis in polyclinics and community care centres.
BACKGROUND: In digital pathology, the morphology and architecture of prostate glands have been routinely adopted by pathologists to evaluate the presence of cancer tissue. The manual annotations are operator-dependent, error-prone and time-consuming. The automated segmentation of prostate glands can be very challenging too due to large appearance variation and serious degeneration of these histological structures. METHOD: A new image segmentation method, called RINGS (Rapid IdentificatioN of Glandural Structures), is presented to segment prostate glands in histopathological images. We designed a novel glands segmentation strategy using a multi-channel algorithm that exploits and fuses both traditional and deep learning techniques. Specifically, the proposed approach employs a hybrid segmentation strategy based on stroma detection to accurately detect and delineate the prostate glands contours. RESULTS: Automated results are compared with manual annotations and seven state-of-the-art techniques designed for glands segmentation. Being based on stroma segmentation, no performance degradation is observed when segmenting healthy or pathological structures. Our method is able to delineate the prostate gland of the unknown histopathological image with a dice score of 90.16 % and outperforms all the compared state-of-the-art methods. CONCLUSIONS: To the best of our knowledge, the RINGS algorithm is the first fully automated method capable of maintaining a high sensitivity even in the presence of severe glandular degeneration. The proposed method will help to detect the prostate glands accurately and assist the pathologists to make accurate diagnosis and treatment. The developed model can be used to support prostate cancer diagnosis in polyclinics and community care centres.