Cargando…
Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment
The Gleason grading system, currently the most powerful prognostic predictor of prostate cancer, is based solely on the tumor’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 co...
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6966453/ https://www.ncbi.nlm.nih.gov/pubmed/31769420 http://dx.doi.org/10.3390/cancers11121860 |
_version_ | 1783488736276774912 |
---|---|
author | Ryu, Han Suk Jin, Min-Sun Park, Jeong Hwan Lee, Sanghun Cho, Joonyoung Oh, Sangjun Kwak, Tae-Yeong Woo, Junwoo Isaac Mun, Yechan Kim, Sun Woo Hwang, Soohyun Shin, Su-Jin Chang, Hyeyoon |
author_facet | Ryu, Han Suk Jin, Min-Sun Park, Jeong Hwan Lee, Sanghun Cho, Joonyoung Oh, Sangjun Kwak, Tae-Yeong Woo, Junwoo Isaac Mun, Yechan Kim, Sun Woo Hwang, Soohyun Shin, Su-Jin Chang, Hyeyoon |
author_sort | Ryu, Han Suk |
collection | PubMed |
description | The Gleason grading system, currently the most powerful prognostic predictor of prostate cancer, is based solely on the tumor’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’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’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. |
format | Online Article Text |
id | pubmed-6966453 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-69664532020-01-27 Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment Ryu, Han Suk Jin, Min-Sun Park, Jeong Hwan Lee, Sanghun Cho, Joonyoung Oh, Sangjun Kwak, Tae-Yeong Woo, Junwoo Isaac Mun, Yechan Kim, Sun Woo Hwang, Soohyun Shin, Su-Jin Chang, Hyeyoon Cancers (Basel) Article The Gleason grading system, currently the most powerful prognostic predictor of prostate cancer, is based solely on the tumor’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’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’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. MDPI 2019-11-25 /pmc/articles/PMC6966453/ /pubmed/31769420 http://dx.doi.org/10.3390/cancers11121860 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Ryu, Han Suk Jin, Min-Sun Park, Jeong Hwan Lee, Sanghun Cho, Joonyoung Oh, Sangjun Kwak, Tae-Yeong Woo, Junwoo Isaac Mun, Yechan Kim, Sun Woo Hwang, Soohyun Shin, Su-Jin Chang, Hyeyoon Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment |
title | Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment |
title_full | Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment |
title_fullStr | Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment |
title_full_unstemmed | Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment |
title_short | Automated Gleason Scoring and Tumor Quantification in Prostate Core Needle Biopsy Images Using Deep Neural Networks and Its Comparison with Pathologist-Based Assessment |
title_sort | automated gleason scoring and tumor quantification in prostate core needle biopsy images using deep neural networks and its comparison with pathologist-based assessment |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6966453/ https://www.ncbi.nlm.nih.gov/pubmed/31769420 http://dx.doi.org/10.3390/cancers11121860 |
work_keys_str_mv | AT ryuhansuk automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT jinminsun automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT parkjeonghwan automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT leesanghun automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT chojoonyoung automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT ohsangjun automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT kwaktaeyeong automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT woojunwooisaac automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT munyechan automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT kimsunwoo automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT hwangsoohyun automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT shinsujin automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment AT changhyeyoon automatedgleasonscoringandtumorquantificationinprostatecoreneedlebiopsyimagesusingdeepneuralnetworksanditscomparisonwithpathologistbasedassessment |