Siegel, R. L., Miller, Ok. D., Fuchs, H. E. & Jemal, A. Most cancers Statistics, 2021. CA Most cancers J. Clin. 71, 7–33 (2021).
Mottet, N. et al. EAU-EANM-ESTRO-ESUR-SIOG pointers on prostate most cancers—2020 replace. Half 1: screening, prognosis, and native therapy with healing intent. Eur. Urol. 79, 243–262 (2021).
Gleason, D. F. In Urologic Pathology. the Prostate Vol. 171 (1977).
Gleason, D. F. & Mellinger, G. T. Prediction of prognosis for prostatic adenocarcinoma by mixed histological grading and medical staging. J. Urol. 111, 58–64 (1974).
Epstein, J. I., Allsbrook, W. C. Jr., Amin, M. B., Egevad, L. L. & Committee, I. G. The 2005 Worldwide Society of Urological Pathology (ISUP) consensus convention on Gleason grading of prostatic carcinoma. Am. J. Surg. Pathol. 29, 1228–1242 (2005).
Epstein, J. I., Srigley, J., Grignon, D., Humphrey, P. & Otis, C. Suggestions for the reporting of prostate carcinoma. Virchows Arch. 451, 751–756 (2007).
Epstein, J. I. et al. A up to date prostate most cancers grading system: a validated different to the Gleason rating. Eur. Urol. 69, 428–435 (2016).
Varma, M., Shah, R. B., Williamson, S. R. & Berney, D. M. 2019 Gleason grading suggestions from ISUP and GUPS: broadly concordant however with vital variations. Virchows Archiv. 478, 813–815 (2021).
Allsbrook, W. C. Jr et al. Interobserver reproducibility of Gleason grading of prostatic carcinoma: common pathologist. Hum. Pathol. 32, 81–88 (2001).
Ozkan, T. A. et al. Interobserver variability in Gleason histological grading of prostate most cancers. Scand J. Urol. 50, 420–424 (2016).
Bulten, W. et al. Automated deep-learning system for Gleason grading of prostate most cancers utilizing biopsies: a diagnostic examine. Lancet Oncol. 21, 233–241 (2020).
Nagpal, Ok. et al. Growth and validation of a deep studying algorithm for Gleason grading of prostate most cancers from biopsy specimens. JAMA Oncol. 6, 1372–1380 (2020).
Pantanowitz, L. et al. A synthetic intelligence algorithm for prostate most cancers prognosis in entire slide photographs of core needle biopsies: a blinded medical validation and deployment examine. Lancet Digit Well being 2, e407–e416 (2020).
Burchardt, M. et al. Interobserver reproducibility of Gleason grading: analysis utilizing prostate most cancers tissue microarrays. J. Most cancers Res. Clin. Oncol. 134, 1071–1078 (2008).
Ouellet, V. et al. The Terry Fox Analysis Institute Canadian Prostate Most cancers Biomarker Community: an evaluation of a pan-Canadian multi-center cohort for biomarker validation. BMC Urol. 18, 78 (2018).
Bello, I. et al. Revisiting resnets: improved coaching and scaling methods. Adv. Neural Inf. Course of. Syst. 34, 22614–22627 (2021).
Simonyan, Ok. & Zisserman, A. Very deep convolutional networks for large-scale picture recognition. Preprint at https://arxiv.org/abs/1409.1556 (2014).
Tan, M. & Le, Q. Efficientnet: rethinking mannequin scaling for convolutional neural networks. In Worldwide Convention on Machine Studying 6105–6114 (PMLR, 2019).
Sanda, M. G. et al. Clinically localized prostate most cancers: AUA/ASTRO/SUO guideline. Half I: threat stratification, shared choice making, and care choices. J. Urol. 199, 683–690 (2018).
Roobol, M. J. & Carlsson, S. V. Danger stratification in prostate most cancers screening. Nat. Rev. Urol. 10, 38–48 (2013).
Huang, Y., Li, W., Macheret, F., Gabriel, R. A. & Ohno-Machado, L. A tutorial on calibration measurements and calibration fashions for medical prediction fashions. J. Am. Med. Inform. Assoc. 27, 621–633 (2020).
Vaicenavicius, J. et al. Evaluating mannequin calibration in classification. In The twenty second Worldwide Convention on Synthetic Intelligence and Statistics 3459–3467 (PMLR, 2019).
Strom, P. et al. Synthetic intelligence for prognosis and grading of prostate most cancers in biopsies: a population-based, diagnostic examine. Lancet Oncol. 21, 222–232 (2020).
Silva-Rodriguez, J., Colomer, A., Dolz, J. & Naranjo, V. Self-learning for weakly supervised Gleason grading of native patterns. IEEE J. Biomed. Well being Inform. 25, 3094–3104 (2021).
Huang, W. et al. Growth and validation of a synthetic intelligence–powered platform for prostate most cancers grading and quantification. JAMA Netw. Open 4, e2132554–e2132554 (2021).
He, T. et al. Bag of tips for picture classification with convolutional neural networks. In Proceedings of the IEEE/CVF Convention on Laptop Imaginative and prescient and Sample Recognition 558–567 (2019).
Pinckaers, H. et al. Predicting biochemical recurrence of prostate most cancers with synthetic intelligence. Commun. Med. 2, 64 (2022).
Wulczyn, E. et al. Predicting prostate most cancers specific-mortality with synthetic intelligence-based Gleason grading. Commun. Med. 1, 1–8 (2021).
Kramer, M. A. Nonlinear principal part evaluation utilizing autoassociative neural networks. AIChE J. 37, 233–243 (1991).
Vapnik, V. The Nature of Statistical Studying Idea (Springer Science & Enterprise Media, 1999).
Yamamoto, Y. et al. Automated acquisition of explainable data from unannotated histopathology photographs. Nat. Commun. 10, 5642 (2019).
Chen, R. J. et al. Pan-cancer integrative histology-genomic evaluation through multimodal deep studying. Most cancers Cell 40, 865–878.e866 (2022).
Mobadersany, P. et al. Predicting most cancers outcomes from histology and genomics utilizing convolutional networks. Proc. Natl Acad. Sci. 115, E2970–E2979 (2018).
Rudin, C. Cease explaining black field machine studying fashions for prime stakes selections and use interpretable fashions as a substitute. Nat. Mach. Intell. 1, 206–215 (2019).
Saporta, A. et al. Benchmarking saliency strategies for chest X-ray interpretation. Nat. Mach. Intell. 4, 867–878 (2022).
Arun, N. et al. Assessing the trustworthiness of saliency maps for localizing abnormalities in medical imaging. Radiol. Artif. Intell. 3, e200267 (2021).
Saad, F., Bögemann, M., Suzuki, Ok. & Shore, N. Remedy of nonmetastatic castration-resistant prostate most cancers: concentrate on second-generation androgen receptor inhibitors. Prostate Most cancers Prostatic. Dis. 24, 323–334 (2021).
Saad, F. et al. 2022 Canadian Urological Affiliation (CUA)-Canadian Uro Oncology Group (CUOG) guideline: Administration of castration-resistant prostate most cancers (CRPC). Can. Urol. Assoc. J. 16, E506–E515 (2022).
Kim, H. E. et al. Switch studying for medical picture classification: a literature evaluation. BMC Med. Imaging 22, 69 (2022).
Morid, M. A., Borjali, A. & Del Fiol, G. A scoping evaluation of switch studying analysis on medical picture evaluation utilizing ImageNet. Comput. Biol. Med. 128, 104115 (2021).
Bulten, W. et al. Synthetic intelligence for prognosis and Gleason grading of prostate most cancers: the PANDA problem. Nat. Med. 28, 154–163 (2022).
Harrell, F. E. Regression Modeling Methods: with Functions to Linear Fashions, Logistic Regression, and Survival Evaluation (Springer, 2001).
Leyh-Bannurah, S. R. et al. A multi-institutional validation of gleason rating derived from tissue microarray cores. Pathol. Oncol. Res. 25, 979–986 (2019).
Ghassemi, M., Oakden-Rayner, L. & Beam, A. L. The false hope of present approaches to explainable synthetic intelligence in well being care. Lancet Digit. Well being 3, e745–e750 (2021).
Mingard, C., Valle-Pérez, G., Skalse, J. & Louis, A. A. Is SGD a Bayesian sampler? Properly, virtually. J. Mach. Be taught. Res. 22, 3579–3642 (2021).
Valle-Perez, G., Camargo, C. Q. & Louis, A. A. Deep studying generalizes as a result of the parameter-function map is biased in the direction of easy capabilities. Preprint at https://arxiv.org/abs/1805.08522 (2018).
Mingard, C. et al. Neural networks are a priori biased in the direction of boolean capabilities with low entropy. Preprint at https://arxiv.org/abs/1909.11522 (2019).
Wenzel, F. et al. How good is the Bayes posterior in deep neural networks actually? Preprint at https://arxiv.org/abs/2002.02405 (2020).
Matzke, E. A. et al. Certification for biobanks: this system developed by the Canadian Tumour Repository Community (CTRNet). Biopreserv. Biobank 10, 426–432 (2012).
Wissing, M. et al. Optimization of the 2014 Gleason grade grouping in a Canadian cohort of sufferers with localized prostate most cancers. BJU Int. 123, 624–631 (2019).
Brimo, F. et al. Methods for biochemical and pathologic high quality assurance in a big multi-institutional biorepository; The expertise of the PROCURE Quebec Prostate Most cancers Biobank. Biopreserv. Biobank 11, 285–290 (2013).
Workforce, P. P., Gohagan, J. Ok., Prorok, P. C., Hayes, R. B. & Kramer, B.-S. The prostate, lung, colorectal and ovarian (PLCO) most cancers screening trial of the Nationwide Most cancers Institute: historical past, group, and standing. Controll. Clin. Trials 21, 251S–272S (2000).
Andriole, G. L. et al. Mortality outcomes from a randomized prostate-cancer screening trial. N. Engl. J. Med. 360, 1310–1319 (2009).
Greene, F. L. et al. AJCC Most cancers Staging Handbook: TNM Classification of Malignant Tumors (Springer Science & Enterprise Media, 2002).
Egevad, L., Delahunt, B., Srigley, J. R. & Samaratunga, H. Worldwide Society of Urological Pathology (ISUP) grading of prostate most cancers—an ISUP consensus on up to date grading. APMIS 124, 433–435 (2016).
Eminaga, O. et al. PlexusNet: a neural community architectural idea for medical picture classification. Comp. Biol. Med. 154, 106594 (2023).
Kingma, D. P. & Ba, J. Adam: a way for stochastic optimization. Preprint at https://arxiv.org/abs/1412.6980 (2014).
Heller, G. & Mo, Q. Estimating the concordance chance in a survival evaluation with a discrete variety of threat teams. Lifetime Knowledge Anal. 22, 263–279 (2016).
Uno, H., Cai, T., Pencina, M. J., D’Agostino, R. B. & Wei, L. J. On the C-statistics for evaluating total adequacy of threat prediction procedures with censored survival information. Stat Med. 30, 1105–1117 (2011).
Heagerty, P. J. & Zheng, Y. Survival mannequin predictive accuracy and ROC curves. Biometrics 61, 92–105 (2005).
He, Ok., Zhang, X., Ren, S. & Solar, J. Deep residual studying for picture recognition. In Proceedings of the IEEE Convention on Laptop Imaginative and prescient and Sample Recognition 770–778 (2016).
Katzman, J. L. et al. DeepSurv: customized therapy recommender system utilizing a Cox proportional hazards deep neural community. BMC Med. Res. Methodol. 18, 24 (2018).
Touvron, H. et al. Augmenting Convolutional networks with attention-based aggregation. Preprint at https://arxiv.org/abs/2112.13692 (2021).
Kass, G. V. An exploratory approach for investigating giant portions of categorical information. J. R. Stat. Soc. Ser. C Appl. Stat. 29, 119–127 (1980).
Sakamoto, Y., Ishiguro, M. & Kitagawa, G. Akaike Info Criterion Statistics. Vol. 81, 26853 (D. Reidel, 1986).
Vrieze, S. I. Mannequin choice and psychological concept: a dialogue of the variations between the Akaike data criterion (AIC) and the Bayesian data criterion (BIC). Psychol. Strategies 17, 228 (2012).
Neath, A. A. & Cavanaugh, J. E. The Bayesian data criterion: background, derivation, and functions. Wiley Interdiscip. Rev. Comput. Stat. 4, 199–203 (2012).
Harrell, F. E. Regression modeling methods. Bios 330, 14 (2017).
Harrell Jr, F. E., Harrell Jr, M. F. E. & Hmisc, D. Bundle ‘rms’. Vanderbilt College 229, Q8 (2017).
Schemper, M., Wakounig, S. & Heinze, G. The estimation of common hazard ratios by weighted Cox regression. Stat. Med. 28, 2473–2489 (2009).
Cox, D. R. Partial chance. Biometrika 62, 269–276 (1975).
Qiu, W. et al. Bundle ‘powerSurvEpi’ (2009).
Buslaev, A. et al. Albumentations: quick and versatile picture augmentations. Info 11, 125 (2020).
Gulli, A. & Pal, S. Deep studying with Keras (Packt Publishing Ltd, 2017).
Abadi, M. et al. Tensorflow: a system for large-scale machine studying. In twelfth {USENIX} Symposium on Working Methods Design and Implementation ({OSDI} 16) 265–283 (2016).
