• Something wrong with this record ?

A novel assessment of whole-mount Gleason grading in prostate cancer to identify candidates for radical prostatectomy: a machine learning-based multiomics study

J. Ning, CP. Spielvogel, D. Haberl, K. Trachtova, S. Stoiber, S. Rasul, V. Bystry, G. Wasinger, P. Baltzer, E. Gurnhofer, G. Timelthaler, M. Schlederer, L. Papp, H. Schachner, T. Helbich, M. Hartenbach, B. Grubmüller, SF. Shariat, M. Hacker, A....

. 2024 ; 14 (12) : 4570-4581. [pub] 20240801

Language English Country Australia

Document type Journal Article

Persistent link   https://www.medvik.cz/link/bmc24019418

Purpose: This study aims to assess whole-mount Gleason grading (GG) in prostate cancer (PCa) accurately using a multiomics machine learning (ML) model and to compare its performance with biopsy-proven GG (bxGG) assessment. Materials and Methods: A total of 146 patients with PCa recruited in a pilot study of a prospective clinical trial (NCT02659527) were retrospectively included in the side study, all of whom underwent 68Ga-PSMA-11 integrated positron emission tomography (PET) / magnetic resonance (MR) before radical prostatectomy (RP) between May 2014 and April 2020. To establish a multiomics ML model, we quantified PET radiomics features, pathway-level genomics features from whole exome sequencing, and pathomics features derived from immunohistochemical staining of 11 biomarkers. Based on the multiomics dataset, five ML models were established and validated using 100-fold Monte Carlo cross-validation. Results: Among five ML models, the random forest (RF) model performed best in terms of the area under the curve (AUC). Compared to bxGG assessment alone, the RF model was superior in terms of AUC (0.87 vs 0.75), specificity (0.72 vs 0.61), positive predictive value (0.79 vs 0.75), and accuracy (0.78 vs 0.77) and showed slightly decreased sensitivity (0.83 vs 0.89) and negative predictive value (0.80 vs 0.81). Among the feature categories, bxGG was identified as the most important feature, followed by pathomics, clinical, radiomics and genomics features. The three important individual features were bxGG, PSA staining and one intensity-related radiomics feature. Conclusion: The findings demonstrate a superior assessment of the developed multiomics-based ML model in whole-mount GG compared to the current clinical baseline of bxGG. This enables personalized patient management by identifying high-risk PCa patients for RP.

Center for Biomarker Research in Medicine Graz Styria Austria

Center for Cancer Research Medical University of Vienna 1090 Vienna Austria

Center for Medical Physics and Biomedical Engineering Vienna Austria

Central European Institute of Technology Masaryk University Brno 62500 Czech Republic

Christian Doppler Laboratory for Applied Metabolomics 1090 Vienna Austria

Clinical Institute of Pathology Department for Experimental and Laboratory Animal Pathology Medical University of Vienna Vienna Austria

Comprehensive Cancer Center Medical University Vienna Vienna Austria

Department of Biomedical Imaging and Image guided Therapy Division of Molecular and Gender Imaging Medical University of Vienna 1090 Vienna Austria

Department of Urology 2nd Faculty of Medicine Charles University Prague Czech Republic

Department of Urology Medical University of Vienna Vienna Austria

Department of Urology University of Texas Southwestern Dallas Texas

Division of Medical Oncology Department of Urology Weill Medical College of Cornell University New York New York

Division of Nuclear Medicine Department of Biomedical Imaging and Image Guided Therapy Medical University of Vienna 1090 Vienna Austria

Institute for Urology and Reproductive Health 1 M Sechenov 1st Moscow State Medical University Moscow Russia

Karl Landsteiner Institute of Urology and Andrology Vienna Austria

Unit of Laboratory Animal Pathology University of Veterinary Medicine Vienna 1210 Vienna Austria

Working Group of Diagnostic Imaging in Urology Austrian Society of Urology Vienna Austria

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc24019418
003      
CZ-PrNML
005      
20241024110744.0
007      
ta
008      
241015s2024 at f 000 0|eng||
009      
AR
024    7_
$a 10.7150/thno.96921 $2 doi
035    __
$a (PubMed)39239512
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a at
100    1_
$a Ning, Jing $u Christian Doppler Laboratory for Applied Metabolomics, 1090 Vienna, Austria $u Clinical Institute of Pathology, Department for Experimental and Laboratory Animal Pathology, Medical University of Vienna, Vienna, Austria $u Division of Nuclear Medicine, Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, 1090 Vienna, Austria
245    12
$a A novel assessment of whole-mount Gleason grading in prostate cancer to identify candidates for radical prostatectomy: a machine learning-based multiomics study / $c J. Ning, CP. Spielvogel, D. Haberl, K. Trachtova, S. Stoiber, S. Rasul, V. Bystry, G. Wasinger, P. Baltzer, E. Gurnhofer, G. Timelthaler, M. Schlederer, L. Papp, H. Schachner, T. Helbich, M. Hartenbach, B. Grubmüller, SF. Shariat, M. Hacker, A. Haug, L. Kenner
520    9_
$a Purpose: This study aims to assess whole-mount Gleason grading (GG) in prostate cancer (PCa) accurately using a multiomics machine learning (ML) model and to compare its performance with biopsy-proven GG (bxGG) assessment. Materials and Methods: A total of 146 patients with PCa recruited in a pilot study of a prospective clinical trial (NCT02659527) were retrospectively included in the side study, all of whom underwent 68Ga-PSMA-11 integrated positron emission tomography (PET) / magnetic resonance (MR) before radical prostatectomy (RP) between May 2014 and April 2020. To establish a multiomics ML model, we quantified PET radiomics features, pathway-level genomics features from whole exome sequencing, and pathomics features derived from immunohistochemical staining of 11 biomarkers. Based on the multiomics dataset, five ML models were established and validated using 100-fold Monte Carlo cross-validation. Results: Among five ML models, the random forest (RF) model performed best in terms of the area under the curve (AUC). Compared to bxGG assessment alone, the RF model was superior in terms of AUC (0.87 vs 0.75), specificity (0.72 vs 0.61), positive predictive value (0.79 vs 0.75), and accuracy (0.78 vs 0.77) and showed slightly decreased sensitivity (0.83 vs 0.89) and negative predictive value (0.80 vs 0.81). Among the feature categories, bxGG was identified as the most important feature, followed by pathomics, clinical, radiomics and genomics features. The three important individual features were bxGG, PSA staining and one intensity-related radiomics feature. Conclusion: The findings demonstrate a superior assessment of the developed multiomics-based ML model in whole-mount GG compared to the current clinical baseline of bxGG. This enables personalized patient management by identifying high-risk PCa patients for RP.
650    _2
$a lidé $7 D006801
650    _2
$a mužské pohlaví $7 D008297
650    12
$a nádory prostaty $x chirurgie $x patologie $x genetika $x diagnostické zobrazování $7 D011471
650    12
$a strojové učení $7 D000069550
650    12
$a prostatektomie $x metody $7 D011468
650    12
$a stupeň nádoru $7 D060787
650    _2
$a senioři $7 D000368
650    _2
$a lidé středního věku $7 D008875
650    _2
$a retrospektivní studie $7 D012189
650    _2
$a prospektivní studie $7 D011446
650    _2
$a pilotní projekty $7 D010865
650    _2
$a pozitronová emisní tomografie $x metody $7 D049268
650    _2
$a magnetická rezonanční tomografie $x metody $7 D008279
650    _2
$a genomika $x metody $7 D023281
650    _2
$a multiomika $7 D000095028
655    _2
$a časopisecké články $7 D016428
700    1_
$a Spielvogel, Clemens P $u Christian Doppler Laboratory for Applied Metabolomics, 1090 Vienna, Austria $u Division of Nuclear Medicine, Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Haberl, David $u Christian Doppler Laboratory for Applied Metabolomics, 1090 Vienna, Austria $u Division of Nuclear Medicine, Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Trachtova, Karolina $u Christian Doppler Laboratory for Applied Metabolomics, 1090 Vienna, Austria $u Central European Institute of Technology, Masaryk University, Brno 62500, Czech Republic
700    1_
$a Stoiber, Stefan $u Christian Doppler Laboratory for Applied Metabolomics, 1090 Vienna, Austria $u Clinical Institute of Pathology, Department for Experimental and Laboratory Animal Pathology, Medical University of Vienna, Vienna, Austria
700    1_
$a Rasul, Sazan $u Division of Nuclear Medicine, Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Bystry, Vojtech $u Central European Institute of Technology, Masaryk University, Brno 62500, Czech Republic
700    1_
$a Wasinger, Gabriel $u Clinical Institute of Pathology, Department for Experimental and Laboratory Animal Pathology, Medical University of Vienna, Vienna, Austria
700    1_
$a Baltzer, Pascal $u Department of Biomedical Imaging and Image-guided Therapy, Division of Molecular and Gender Imaging, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Gurnhofer, Elisabeth $u Clinical Institute of Pathology, Department for Experimental and Laboratory Animal Pathology, Medical University of Vienna, Vienna, Austria
700    1_
$a Timelthaler, Gerald $u Center for Cancer Research, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Schlederer, Michaela $u Clinical Institute of Pathology, Department for Experimental and Laboratory Animal Pathology, Medical University of Vienna, Vienna, Austria
700    1_
$a Papp, Laszlo $u Center for Medical Physics and Biomedical Engineering, Vienna, Austria
700    1_
$a Schachner, Helga $u Clinical Institute of Pathology, Department for Experimental and Laboratory Animal Pathology, Medical University of Vienna, Vienna, Austria
700    1_
$a Helbich, Thomas $u Department of Biomedical Imaging and Image-guided Therapy, Division of Molecular and Gender Imaging, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Hartenbach, Markus $u Division of Nuclear Medicine, Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Grubmüller, Bernhard $u Department of Urology, Medical University of Vienna, Vienna, Austria $u Working Group of Diagnostic Imaging in Urology, Austrian Society of Urology, Vienna, Austria
700    1_
$a Shariat, Shahrokh F $u Department of Urology, Medical University of Vienna, Vienna, Austria $u Karl Landsteiner Institute of Urology and Andrology, Vienna, Austria $u Department of Urology, University of Texas Southwestern, Dallas, Texas $u Division of Medical Oncology, Department of Urology, Weill Medical College of Cornell University, New York, New York $u Department of Urology, Second Faculty of Medicine, Charles University, Prague, Czech Republic $u Institute for Urology and Reproductive Health, I.M. Sechenov First Moscow State Medical University, Moscow, Russia
700    1_
$a Hacker, Marcus $u Division of Nuclear Medicine, Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Haug, Alexander $u Christian Doppler Laboratory for Applied Metabolomics, 1090 Vienna, Austria $u Division of Nuclear Medicine, Department of Biomedical Imaging and Image-Guided Therapy, Medical University of Vienna, 1090 Vienna, Austria
700    1_
$a Kenner, Lukas $u Christian Doppler Laboratory for Applied Metabolomics, 1090 Vienna, Austria $u Clinical Institute of Pathology, Department for Experimental and Laboratory Animal Pathology, Medical University of Vienna, Vienna, Austria $u Unit of Laboratory Animal Pathology, University of Veterinary Medicine Vienna, 1210 Vienna, Austria $u Comprehensive Cancer Center, Medical University Vienna, Vienna, Austria $u Center for Biomarker Research in Medicine (CBmed), Graz, Styria, Austria
773    0_
$w MED00177173 $t Theranostics $x 1838-7640 $g Roč. 14, č. 12 (2024), s. 4570-4581
856    41
$u https://pubmed.ncbi.nlm.nih.gov/39239512 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20241015 $b ABA008
991    __
$a 20241024110738 $b ABA008
999    __
$a ok $b bmc $g 2201948 $s 1231391
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2024 $b 14 $c 12 $d 4570-4581 $e 20240801 $i 1838-7640 $m Theranostics $n Theranostics $x MED00177173
LZP    __
$a Pubmed-20241015
Back

Find record

Citation metrics

Archiving options