12 juni 2024: Bron: LUMC Leiden

In een persbericht melden onderzoekers van het Leids Universitair Medisch Centrum (LUMC) dat zij met HECTOR, een AI-model hebben ontwikkeld dat het risico op een recidief van eerder behandelde baarmoederhalskanker nauwkeurig kan voorspellen. HECTOR (Histopathology-based Endometrial Cancer Tailored Outcome Risk) is ontwikkeld met hulp van AI = Kunstmatige Intelligentie en werkt beter en goedkoper en is minder belastend voor de patiënt dan de huidige gebruikte methoden. Volgens de onderzoekers zou HECTOR de standaard screening methode moeten worden. Ook voor andere vormen van kanker zou AI = Kunstmatige Intelligentie een meerwaarde kunnen betekenen in screening.

HECTOR is ontwikkeld door gebruik te maken van microscopische beelden van tumoren en data uit eerdere klinische studies (PORTEC-1/2/3) van meer dan duizend patiënten. Vervolgens werd HECTOR getest op beelden van patiënten die niet waren gebruikt tijdens de trainingsfase. En daaruit bleken de resultaten zeer nauwkeurig in het voorspellen van wel of geen recidief in dit geval. Ook kan uit de resultaten gelezen worden hoe groot het risico is op een recidief.

Een van de grootste voordelen van HECTOR is dat het slechts een microscopisch beeld en het tumorstadium nodig heeft, waardoor de methode goedkoper is dan de huidige standaard screeningsmethoden. HECTOR blijkt ook patiënten in te kunnen delen in laag, gemiddeld en hoog risico op een recidief. Daardoor kan patiënten ook een meer gepersonaliseerde behandeling wroden geboden.
Patiënten met een hoog risico, zoals voorspeld door HECTOR, bleken het meeste baat te hebben bij de toevoeging van chemotherapie aan de bestraling na de operatie. "En misschien nog wel belangrijker: patiënten met een laag risico kan aanvullende chemotherapie gespaard blijven", aldus hoofdonderzoeker en patholoog Tjalling Bosse.

In dit artikel staat een video van You Tube waarop te zien is hoe HECTOR werkt. 

Het persbericht is afgeleid van de studie zoals die is gepubliceerd in Nature:

. 2024 May 24.
 doi: 10.1038/s41591-024-02993-w. Online ahead of print.

Prediction of recurrence risk in endometrial cancer with multimodal deep learning

Sarah Volinsky-Fremond 1, Nanda Horeweg 2, Sonali Andani 3 4 5, Jurriaan Barkey Wolf 1, Maxime W Lafarge 4, Cor D de Kroon 6, Gitte Ørtoft 7, Estrid Høgdall 8, Jouke Dijkstra 9, Jan J Jobsen 10, Ludy C H W Lutgens 11, Melanie E Powell 12, Linda R Mileshkin 13, Helen Mackay 14, Alexandra Leary 15, Dionyssios Katsaros 16, Hans W Nijman 17, Stephanie M de Boer 2, Remi A Nout 18, Marco de Bruyn 17, David Church 19 20, Vincent T H B M Smit 1, Carien L Creutzberg 2, Viktor H Koelzer 4 21, Tjalling Bosse 22
Affiliations 

Abstract

Predicting distant recurrence of endometrial cancer (EC) is crucial for personalized adjuvant treatment. The current gold standard of combined pathological and molecular profiling is costly, hampering implementation. Here we developed HECTOR (histopathology-based endometrial cancer tailored outcome risk), a multimodal deep learning prognostic model using hematoxylin and eosin-stained, whole-slide images and tumor stage as input, on 2,072 patients from eight EC cohorts including the PORTEC-1/-2/-3 randomized trials. HECTOR demonstrated C-indices in internal (n = 353) and two external (n = 160 and n = 151) test sets of 0.789, 0.828 and 0.815, respectively, outperforming the current gold standard, and identified patients with markedly different outcomes (10-year distant recurrence-free probabilities of 97.0%, 77.7% and 58.1% for HECTOR low-, intermediate- and high-risk groups, respectively, by Kaplan-Meier analysis). HECTOR also predicted adjuvant chemotherapy benefit better than current methods. Morphological and genomic feature extraction identified correlates of HECTOR risk groups, some with therapeutic potential. HECTOR improves on the current gold standard and may help delivery of personalized treatment in EC.

PubMed Disclaimer

References

    1. Crosbie, E. J. et al. Endometrial cancer. Lancet 399, 1412–1428 (2022). - PubMed - DOI
    1. Ørtoft, G., Lausten-Thomsen, L., Høgdall, C., Hansen, E. S. & Dueholm, M. Lymph-vascular space invasion (LVSI) as a strong and independent predictor for non-locoregional recurrences in endometrial cancer: a Danish Gynecological Cancer Group Study. J. Gynecol. Oncol. 30, e84 (2019). - PubMed - PMC - DOI
    1. de Boer, S. M. et al. Adjuvant chemoradiotherapy versus radiotherapy alone in women with high-risk endometrial cancer (PORTEC-3): patterns of recurrence and post-hoc survival analysis of a randomised phase 3 trial. Lancet Oncol. 20, 1273–1285 (2019). - PubMed - PMC - DOI
    1. Hogberg, T. et al. Sequential adjuvant chemotherapy and radiotherapy in endometrial cancer—results from two randomised studies. Eur. J. Cancer 46, 2422–2431 (2010). - PubMed - PMC - DOI
    1. Concin, N. et al. ESGO/ESTRO/ESP guidelines for the management of patients with endometrial carcinoma. Int. J. Gynecol. Cancer 31, 12–39 (2021). - PubMed - DOI
    1. Abu-Rustum, N. et al. Uterine neoplasms, version 1.2023, NCCN Clinical Practice Guidelines in Oncology. J. Natl Compr. Cancer Netw. 21, 181–209 (2023). - DOI
    1. Oaknin, A. et al. Endometrial cancer: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up. Ann. Oncol. 33, 860–877 (2022). - PubMed - DOI
    1. Harkenrider, M. M. et al. Radiation therapy for endometrial cancer: an American Society for Radiation Oncology clinical practice guideline. Pract. Radiat. Oncol. 13, 41–65 (2023). - PubMed - DOI
    1. Berek, J. S. et al. FIGO staging of endometrial cancer: 2023. Int. J. Gynecol. Obstet. 162, 383–394 (2023). - DOI
    1. Horeweg, N. et al. Prognostic integrated image-based immune and molecular profiling in early-stage endometrial cancer. Cancer Immunol. Res. 8, 1508–1519 (2020). - PubMed - DOI
    1. Fremond, S. et al. Interpretable deep learning model to predict the molecular classification of endometrial cancer from haematoxylin and eosin-stained whole-slide images: a combined analysis of the PORTEC randomised trials and clinical cohorts. Lancet Digit. Health 5, e71–e82 (2023). - PubMed - DOI
    1. Lafarge, M. W. & Koelzer, V. H. Towards computationally efficient prediction of molecular signatures from routine histology images. Lancet Digit. Health 3, e752–e753 (2021). - PubMed - DOI
    1. Sirinukunwattana, K. et al. Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning. Gut 70, 544–554 (2021). - PubMed - DOI
    1. Graham, S. et al. Hover-Net: simultaneous segmentation and classification of nuclei in multi-tissue histology images. Med. Image Anal. 58, 101563 (2019). - PubMed - DOI
    1. Lee, Y. et al. Derivation of prognostic contextual histopathological features from whole-slide images of tumours via graph deep learning. Nat. Biomed. Eng. https://doi.org/10.1038/s41551-022-00923-0 (2022). - DOI - PubMed - PMC
    1. Chen, R. J. et al. Pan-cancer integrative histology-genomic analysis via multimodal deep learning. Cancer Cell 40, 865–878.e6 (2022). - PubMed - PMC - DOI
    1. Wulczyn, E. et al. Interpretable survival prediction for colorectal cancer using deep learning. NPJ Digit. Med. 4, 71 (2021). - PubMed - PMC - DOI
    1. Yao, J., Zhu, X., Jonnagaddala, J., Hawkins, N. & Huang, J. Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks. Med. Image Anal. 65, 101789 (2020). - PubMed - DOI
    1. Chen, R. J. et al. Whole slide images are 2D point clouds: context-aware survival prediction using patch-based graph convolutional networks. In International Conference on Medical Image Computing and Computer-Assisted Intervention Vol. 12908 (eds de Bruijne, M. et al.) 339–349 (Springer Cham, 2021).
    1. Courtiol, P. et al. Deep learning-based classification of mesothelioma improves prediction of patient outcome. Nat. Med. 25, 1519–1525 (2019). - PubMed - DOI
    1. Chen, R. J. et al. Multimodal co-attention transformer for survival prediction in gigapixel whole slide images. In 2021 IEEE/CVF International Conference on Computer Vision (ICCV) 3995–4005 (IEEE, 2021); https://ieeexplore.ieee.org/document/9710773
    1. Ilse, M., Tomczak, J. & Welling, M. Attention-based deep multiple instance learning. In Proc. of the 35th International Conference on Machine Learning Vol. 80 (eds Dy, J. & Krause, A.) 2127–2136 (PMLR, 2018).
    1. Wagner, S. J. et al. Transformer-based biomarker prediction from colorectal cancer histology: a large-scale multicentric study. Cancer Cell 41, 1650–1661.e4 (2023). - PubMed - PMC - DOI
    1. Using AI to improve the molecular classification of brain tumors. Nat. Med. 29, 793–794 (2023).
    1. Jiménez-Sánchez, D. et al. Weakly supervised deep learning to predict recurrence in low-grade endometrial cancer from multiplexed immunofluorescence images. NPJ Digit. Med. 6, 48 (2023). - PubMed - PMC - DOI
    1. Creutzberg, C. L. et al. Surgery and postoperative radiotherapy versus surgery alone for patients with stage-1 endometrial carcinoma: multicentre randomised trial. PORTEC study group. post operative radiation therapy in endometrial carcinoma. Lancet 355, 1404–1411 (2000). - PubMed - DOI
    1. Nout, R. A. et al. Vaginal brachytherapy versus pelvic external beam radiotherapy for patients with endometrial cancer of high-intermediate risk (PORTEC-2): an open-label, non-inferiority, randomised trial. Lancet 375, 816–823 (2010). - PubMed - DOI
    1. Stelloo, E. et al. Refining prognosis and identifying targetable pathways for high-risk endometrial cancer; a TransPORTEC initiative. Mod. Pathol. 28, 836–844 (2015). - PubMed - DOI
    1. Jobsen, J. J. et al. Outcome of endometrial cancer stage IIIA with adnexa or serosal involvement only. Obstet. Gynecol. Int. 2011, 962518 (2011). - PubMed - PMC - DOI
    1. Ørtoft, G. et al. Location of recurrences in high-risk stage I endometrial cancer patients not given postoperative radiotherapy: a Danish gynecological cancer group study. Int. J. Gynecol. Cancer 29, 497–504 (2019). - PubMed - DOI
    1. Workel, H. H. et al. CD103 defines intraepithelial CD8+ PD1+ tumour-infiltrating lymphocytes of prognostic significance in endometrial adenocarcinoma. Eur. J. Cancer 60, 1–11 (2016). - PubMed - DOI
    1. Kandoth, C. et al. Integrated genomic characterization of endometrial carcinoma. Nature 497, 67–73 (2013). - PubMed - DOI
    1. Uno, H., Cai, T., Pencina, M. J., D’Agostino, R. B. & Wei, L. J. On the C-statistics for evaluating overall adequacy of risk prediction procedures with censored survival data. Stat. Med. 30, 1105–1117 (2011). - PubMed - PMC - DOI
    1. Pecorelli, S. Revised FIGO staging for carcinoma of the vulva, cervix, and endometrium. Int. J. Gynaecol. Obstet. 105, 103–104 (2009). - PubMed - DOI
    1. Zadeh, A., Chen, M., Poria, S., Cambria, E. & Morency, L.-P. Tensor fusion network for multimodal sentiment analysis. In Proc. 2017 Conference on Empirical Methods in Natural Language Processing 1103–1114 (Association for Computational Linguistics, 2017).
    1. Mormont, R., Geurts, P. & Maree, R. Multi-task pre-training of deep neural networks for digital pathology. IEEE J. Biomed. Health Inform. 25, 412–421 (2021). - PubMed - DOI
    1. Lambert, J. & Chevret, S. Summary measure of discrimination in survival models based on cumulative/dynamic time-dependent ROC curves. Stat. Methods Med. Res. 25, 2088–2102 (2016). - PubMed - DOI
    1. Graf, E., Schmoor, C., Sauerbrei, W. & Schumacher, M. Assessment and comparison of prognostic classification schemes for survival data. Stat. Med. 18, 2529–2545 (1999). - PubMed - DOI
    1. Pai, R. K. et al. Quantitative pathologic analysis of digitized images of colorectal carcinoma improves prediction of recurrence-free survival. Gastroenterology 163, 1531–1546.e8 (2022). - PubMed - DOI
    1. Esteva, A. et al. Prostate cancer therapy personalization via multi-modal deep learning on randomized phase III clinical trials. NPJ Digit. Med. 5, 71 (2022). - PubMed - PMC - DOI
    1. Pece, S. et al. Comparison of StemPrintER with Oncotype DX recurrence score for predicting risk of breast cancer distant recurrence after endocrine therapy. Eur. J. Cancer 164, 52–61 (2022). - PubMed - DOI
    1. Jaume, G. et al. Modeling dense multimodal interactions between biological pathways and histology for survival prediction. In Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024).
    1. Kojima, M. et al. Aberrant claudin-6-adhesion signaling promotes endometrial cancer progression via estrogen receptor α. Mol. Cancer Res. 19, 1208–1220 (2021). - PubMed - DOI
    1. Mackensen, A. et al. CLDN6-specific CAR-T cells plus amplifying RNA vaccine in relapsed or refractory solid tumors: the phase 1 BNT211-01 trial. Nat. Med. https://doi.org/10.1038/s41591-023-02612-0 (2023). - DOI - PubMed - PMC
    1. Ueno, H. et al. Prognostic value of desmoplastic reaction characterisation in stage II colon cancer: prospective validation in a phase 3 study (SACURA trial). Br. J. Cancer 124, 1088–1097 (2021). - PubMed - PMC - DOI
    1. Corrado, G. et al. Endometrial cancer prognosis correlates with the expression of L1CAM and miR34a biomarkers. J. Exp. Clin. Cancer Res. 37, 139 (2018). - PubMed - PMC - DOI
    1. Mirza, M. R. et al. Dostarlimab for primary advanced or recurrent endometrial cancer. N. Engl. J. Med. 388, 2145–2158 (2023). - PubMed - DOI
    1. Makker, V. et al. Lenvatinib plus pembrolizumab for advanced endometrial cancer. N. Engl. J. Med. 386, 437–448 (2022). - PubMed - DOI
    1. Eskander, R. N. et al. Pembrolizumab plus chemotherapy in advanced endometrial cancer. N. Engl. J. Med. 388, 2159–2170 (2023). - PubMed - PMC - DOI
    1. Kiemen, A. L. et al. Tissue clearing and 3D reconstruction of digitized, serially sectioned slides provide novel insights into pancreatic cancer. Med 4, 75–91 (2023). - PubMed - DOI
    1. Foersch, S. et al. Multistain deep learning for prediction of prognosis and therapy response in colorectal cancer. Nat. Med. 29, 430–439 (2023). - PubMed - DOI
    1. Braman, N. et al. Deep orthogonal fusion: multimodal prognostic biomarker discovery integrating radiology, pathology, genomic, and clinical data. In Medical Image Computing and Computer Assisted Intervention—MICCAI 2021 (eds de Bruijne, M. et al.) 667–677 (Springer, 2021).
    1. Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172–180 (2023). - PubMed - PMC - DOI
    1. Jaume, G., Song, A. H. & Mahmood, F. Integrating context for superior cancer prognosis. Nat. Biomed. Eng. 6, 1323–1325 (2022). - PubMed - DOI
    1. Song, A. H. et al. Analysis of 3D pathology samples using weakly supervised AI. Cell 187, 2502–2520.e17 (2024). - PubMed - DOI
    1. León-Castillo, A. et al. Molecular classification of the PORTEC-3 trial for high-risk endometrial cancer: impact on prognosis and benefit from adjuvant therapy. J. Clin. Oncol. 38, 3388–3397 (2020). - PubMed - PMC - DOI
    1. van den Heerik, A. S. V. M. et al. PORTEC-4a: international randomized trial of molecular profile-based adjuvant treatment for women with high–intermediate risk endometrial cancer. Int. J. Gynecol. Cancer 30, 2002–2007 (2020). - PubMed - PMC - DOI
    1. Kuoppala, T. et al. Surgically staged high-risk endometrial cancer: randomized study of adjuvant radiotherapy alone vs. sequential chemo-radiotherapy. Gynecol. Oncol. 110, 190–195 (2008). - PubMed - DOI
    1. RAINBO Research Consortium. Refining adjuvant treatment in endometrial cancer based on molecular features: the RAINBO clinical trial program. Int. J. Gynecol. Cancer 33, 109–117 (2022). - PMC - DOI
    1. Li, C. et al. Efficient self-supervised vision transformers for representation learning. In International Conference on Learning Representations (ICLR, 2022); https://openreview.net/forum?id=fVu3o-YUGQK
    1. Zadeh, S. G. & Schmid, M. Bias in cross-entropy-based training of deep survival networks. IEEE Trans. Pattern Anal. Mach. Intell. 43, 3126–3137 (2021). - PubMed - DOI
    1. Höhn, A. K. et al. 2020 WHO classification of female genital tumors. Geburtshilfe Frauenheilkd. 81, 1145–1153 (2021). - PubMed - PMC - DOI
    1. Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. In Proc. of the 34th International Conference on Machine Learning Vol. 70 (eds Precup, D. & Teh, Y. W.) 3319–3328 (PMLR, 2017).
    1. Lafarge, M. W. & Koelzer, V. H. in Mitosis Domain Generalization and Diabetic Retinopathy Analysis (eds.Sheng, B. & Aubreville, M.) 226–233 (Springer Nature Switzerland, 2023).
    1. Cerami, E. et al. The cBio cancer genomics portal: an open platform for exploring multidimensional cancer genomics data. Cancer Discov. 2, 401–404 (2012). - PubMed - DOI
    1. Gao, J. et al. Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal. Sci. Signal. 6, pl1 (2013). - PubMed - PMC - DOI
    1. Wang, X. et al. Transformer-based unsupervised contrastive learning for histopathological image classification. Med. Image Anal. 81, 102559 (2022). - PubMed - DOI
    1. Liu, Z. et al. Swin transformer: hierarchical vision transformer using shifted windows. In Proc. of the IEEE/CVF International Conference on Computer Vision (ICCV) 9992–10002 (IEEE, 2021); https://ieeexplore.ieee.org/document/9710580
    1. Aubreville, M. et al. MItosis DOmain Generalization Challenge 2022. Zenodo https://doi.org/10.5281/zenodo.6362337 (2022).
    1. Thorsson, V. et al. The immune landscape of cancer. Immunity 48, 812–830.e14 (2018). - PubMed - PMC - DOI
    1. Chakravarty, D. et al. OncoKB: a precision oncology knowledge base. JCO Precis. Oncol. https://doi.org/10.1200/PO.17.00011 (2017).
    1. Love, M. I., Huber, W. & Anders, S. Moderated estimation of fold change and dispersion for RNA-seq data with DESeq2. Genome Biol. 15, 550 (2014). - PubMed - PMC - DOI




 

baarmoederhalskanker, recidief, AI-model, Hector, LUMC Leiden


Plaats een reactie ...

Reageer op "AI-model Hector voorspelt nauwkeurig of behandelde baarmoederhalskanker terug zal keren met een recidief of dat het risico daarop klein zal zijn"


Gerelateerde artikelen
 

Gerelateerde artikelen

AI-model Hector voorspelt >> Bestraling - radiotherapie >> Gezondheidsraad adviseert >> Amerikaanse Vereniging van >> Risico's en oorzaken van baarmoederhalskanker >> Pilgebruik en baarmoederhalskanker: >> Diagnose van baarmoederhalskanker: >> Diagnose van baarmoederhalskanker: >> Diagnose baarmoederhalskanker: >> Diagnose baarmoederhalskanker: >>