Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment
Autor: | Yechan Mun, Sun Woo Kim, Jeong Hwan Park, Tae-Yeong Kwak, Hyeyoon Chang, Han Suk Ryu, Sangjun Oh, Min Sun Jin, Cho Joon Young, Junwoo Isaac Woo, Soohyun Hwang, Sanghun Lee, Su Jin Shin |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2019 |
Předmět: |
Cancer Research
Pathology medicine.medical_specialty Prostate biopsy 030232 urology & nephrology urologic and male genital diseases Article 03 medical and health sciences Prostate cancer 0302 clinical medicine Cohen's kappa Prostate Biopsy medicine Medical diagnosis neoplasms prostate core needle biopsy Gleason grading system medicine.diagnostic_test business.industry deep neural network Cancer medicine.disease prostate cancer medicine.anatomical_structure Oncology 030220 oncology & carcinogenesis gleason scoring system business |
Zdroj: | Cancers Volume 11 Issue 12 |
ISSN: | 2072-6694 |
DOI: | 10.3390/cancers11121860 |
Popis: | The Gleason grading system, currently the most powerful prognostic predictor of prostate cancer, is based solely on the tumor&rsquo s histological architecture and has high inter-observer variability. We propose an automated Gleason scoring system based on deep neural networks for diagnosis of prostate core needle biopsy samples. To verify its efficacy, the system was trained using 1133 cases of prostate core needle biopsy samples and validated on 700 cases. Further, system-based diagnosis results were compared with reference standards derived from three certified pathologists. In addition, the system&rsquo s ability to quantify cancer in terms of tumor length was also evaluated via comparison with pathologist-based measurements. The results showed a substantial diagnostic concordance between the system-grade group classification and the reference standard (0.907 quadratic-weighted Cohen&rsquo s kappa coefficient). The system tumor length measurements were also notably closer to the reference standard (correlation coefficient, R = 0.97) than the original hospital diagnoses (R = 0.90). We expect this system to assist pathologists to reduce the probability of over- or under-diagnosis by providing pathologist-level second opinions on the Gleason score when diagnosing prostate biopsy, and to support research on prostate cancer treatment and prognosis by providing reproducible diagnosis based on the consistent standards. |
Databáze: | OpenAIRE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |