Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology
Abstract Background Prostate cancer is a major health concern in aging men. Paralleling an aging society, prostate cancer prevalence increases emphasizing the need for efficient diagnostic algorithms. Methods Retrospectively, 106 prostate tissue samples from 48 patients (mean age, $$66\pm 6.6$$ 66 ±...
Main Authors: | , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-01-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12859-022-05124-9 |
_version_ | 1797958476086902784 |
---|---|
author | Yauheniya Zhdanovich Jörg Ackermann Peter J. Wild Jens Köllermann Katrin Bankov Claudia Döring Nadine Flinner Henning Reis Mike Wenzel Benedikt Höh Philipp Mandel Thomas J. Vogl Patrick Harter Katharina Filipski Ina Koch Simon Bernatz |
author_facet | Yauheniya Zhdanovich Jörg Ackermann Peter J. Wild Jens Köllermann Katrin Bankov Claudia Döring Nadine Flinner Henning Reis Mike Wenzel Benedikt Höh Philipp Mandel Thomas J. Vogl Patrick Harter Katharina Filipski Ina Koch Simon Bernatz |
author_sort | Yauheniya Zhdanovich |
collection | DOAJ |
description | Abstract Background Prostate cancer is a major health concern in aging men. Paralleling an aging society, prostate cancer prevalence increases emphasizing the need for efficient diagnostic algorithms. Methods Retrospectively, 106 prostate tissue samples from 48 patients (mean age, $$66\pm 6.6$$ 66 ± 6.6 years) were included in the study. Patients suffered from prostate cancer (n = 38) or benign prostatic hyperplasia (n = 10) and were treated with radical prostatectomy or Holmium laser enucleation of the prostate, respectively. We constructed tissue microarrays (TMAs) comprising representative malignant (n = 38) and benign (n = 68) tissue cores. TMAs were processed to histological slides, stained, digitized and assessed for the applicability of machine learning strategies and open–source tools in diagnosis of prostate cancer. We applied the software QuPath to extract features for shape, stain intensity, and texture of TMA cores for three stainings, H&E, ERG, and PIN-4. Three machine learning algorithms, neural network (NN), support vector machines (SVM), and random forest (RF), were trained and cross-validated with 100 Monte Carlo random splits into 70% training set and 30% test set. We determined AUC values for single color channels, with and without optimization of hyperparameters by exhaustive grid search. We applied recursive feature elimination to feature sets of multiple color transforms. Results Mean AUC was above 0.80. PIN-4 stainings yielded higher AUC than H&E and ERG. For PIN-4 with the color transform saturation, NN, RF, and SVM revealed AUC of $$0.93\pm 0.04$$ 0.93 ± 0.04 , $$0.91\pm 0.06$$ 0.91 ± 0.06 , and $$0.92\pm 0.05$$ 0.92 ± 0.05 , respectively. Optimization of hyperparameters improved the AUC only slightly by 0.01. For H&E, feature selection resulted in no increase of AUC but to an increase of 0.02–0.06 for ERG and PIN-4. Conclusions Automated pipelines may be able to discriminate with high accuracy between malignant and benign tissue. We found PIN-4 staining best suited for classification. Further bioinformatic analysis of larger data sets would be crucial to evaluate the reliability of automated classification methods for clinical practice and to evaluate potential discrimination of aggressiveness of cancer to pave the way to automatic precision medicine. |
first_indexed | 2024-04-11T00:19:36Z |
format | Article |
id | doaj.art-532f11674417410a85d48b26aa59cb1d |
institution | Directory Open Access Journal |
issn | 1471-2105 |
language | English |
last_indexed | 2024-04-11T00:19:36Z |
publishDate | 2023-01-01 |
publisher | BMC |
record_format | Article |
series | BMC Bioinformatics |
spelling | doaj.art-532f11674417410a85d48b26aa59cb1d2023-01-08T12:22:17ZengBMCBMC Bioinformatics1471-21052023-01-0124111410.1186/s12859-022-05124-9Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathologyYauheniya Zhdanovich0Jörg Ackermann1Peter J. Wild2Jens Köllermann3Katrin Bankov4Claudia Döring5Nadine Flinner6Henning Reis7Mike Wenzel8Benedikt Höh9Philipp Mandel10Thomas J. Vogl11Patrick Harter12Katharina Filipski13Ina Koch14Simon Bernatz15Institute of Pathology, Ludwig-Maximilians University MunichMolecular Bioinformatics Group, Institute of Computer Science, Faculty of Computer Science and MathematicsDr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital FrankfurtDr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital FrankfurtDr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital FrankfurtDr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital FrankfurtDr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital FrankfurtDr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital FrankfurtDepartment of Urology, Goethe University Frankfurt am Main, University Hospital FrankfurtDepartment of Urology, Goethe University Frankfurt am Main, University Hospital FrankfurtDepartment of Urology, Goethe University Frankfurt am Main, University Hospital FrankfurtDepartment of Diagnostic and Interventional Radiology, Goethe University Frankfurt am Main, University Hospital FrankfurtNeurological Institute (Edinger Institute), University Hospital FrankfurtNeurological Institute (Edinger Institute), University Hospital FrankfurtMolecular Bioinformatics Group, Institute of Computer Science, Faculty of Computer Science and MathematicsDr. Senckenberg Institute for Pathology, Goethe University Frankfurt am Main, University Hospital FrankfurtAbstract Background Prostate cancer is a major health concern in aging men. Paralleling an aging society, prostate cancer prevalence increases emphasizing the need for efficient diagnostic algorithms. Methods Retrospectively, 106 prostate tissue samples from 48 patients (mean age, $$66\pm 6.6$$ 66 ± 6.6 years) were included in the study. Patients suffered from prostate cancer (n = 38) or benign prostatic hyperplasia (n = 10) and were treated with radical prostatectomy or Holmium laser enucleation of the prostate, respectively. We constructed tissue microarrays (TMAs) comprising representative malignant (n = 38) and benign (n = 68) tissue cores. TMAs were processed to histological slides, stained, digitized and assessed for the applicability of machine learning strategies and open–source tools in diagnosis of prostate cancer. We applied the software QuPath to extract features for shape, stain intensity, and texture of TMA cores for three stainings, H&E, ERG, and PIN-4. Three machine learning algorithms, neural network (NN), support vector machines (SVM), and random forest (RF), were trained and cross-validated with 100 Monte Carlo random splits into 70% training set and 30% test set. We determined AUC values for single color channels, with and without optimization of hyperparameters by exhaustive grid search. We applied recursive feature elimination to feature sets of multiple color transforms. Results Mean AUC was above 0.80. PIN-4 stainings yielded higher AUC than H&E and ERG. For PIN-4 with the color transform saturation, NN, RF, and SVM revealed AUC of $$0.93\pm 0.04$$ 0.93 ± 0.04 , $$0.91\pm 0.06$$ 0.91 ± 0.06 , and $$0.92\pm 0.05$$ 0.92 ± 0.05 , respectively. Optimization of hyperparameters improved the AUC only slightly by 0.01. For H&E, feature selection resulted in no increase of AUC but to an increase of 0.02–0.06 for ERG and PIN-4. Conclusions Automated pipelines may be able to discriminate with high accuracy between malignant and benign tissue. We found PIN-4 staining best suited for classification. Further bioinformatic analysis of larger data sets would be crucial to evaluate the reliability of automated classification methods for clinical practice and to evaluate potential discrimination of aggressiveness of cancer to pave the way to automatic precision medicine.https://doi.org/10.1186/s12859-022-05124-9Prostate cancerPredictionQuantitative featuresStatistical analysisMachine learning |
spellingShingle | Yauheniya Zhdanovich Jörg Ackermann Peter J. Wild Jens Köllermann Katrin Bankov Claudia Döring Nadine Flinner Henning Reis Mike Wenzel Benedikt Höh Philipp Mandel Thomas J. Vogl Patrick Harter Katharina Filipski Ina Koch Simon Bernatz Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology BMC Bioinformatics Prostate cancer Prediction Quantitative features Statistical analysis Machine learning |
title | Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology |
title_full | Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology |
title_fullStr | Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology |
title_full_unstemmed | Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology |
title_short | Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology |
title_sort | evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology |
topic | Prostate cancer Prediction Quantitative features Statistical analysis Machine learning |
url | https://doi.org/10.1186/s12859-022-05124-9 |
work_keys_str_mv | AT yauheniyazhdanovich evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT jorgackermann evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT peterjwild evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT jenskollermann evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT katrinbankov evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT claudiadoring evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT nadineflinner evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT henningreis evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT mikewenzel evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT benedikthoh evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT philippmandel evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT thomasjvogl evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT patrickharter evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT katharinafilipski evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT inakoch evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology AT simonbernatz evaluationofautomaticdiscriminationbetweenbenignandmalignantprostatetissueintheeraofhighprecisiondigitalpathology |