Whole Slide Image Based Prognosis Prediction in Rectal Cancer Using Unsupervised Artificial Intelligence

Overview

Journal BMC Cancer

Publisher Biomed Central

Specialty Oncology

Date 2024 Dec 19

PMID 39696090

Authors

Xuezhi Zhou

Jing Dai

Yizhan Lu

Qingqing Zhao

Yong Liu

Chang Wang

Zongya Zhao

Chong Wang

Zhixian Gao

Yi Yu

Yandong Zhao

Wuteng Cao

Affiliations

Soon will be listed here.

Abstract

Background: Rectal cancer is a common cancer worldwide and lacks effective prognostic markers. The development of prognostic markers by computational pathology methods has attracted increasing attention. This paper aims to construct a prognostic signature from whole slide images for predicting progression-free survival (PFS) of rectal cancer through an unsupervised artificial intelligence algorithm.

Methods: A total of 238 patients with rectal cancer from two datasets were collected for the development and validation of the prognostic signature. A tumor detection model was built by transfer learning. Then, on the basis of the tumor patches recognized by the tumor detection model, a convolutional autoencoder model was built for decoding the tumor patches into deep latent features. Next, on the basis of the deep latent features, the tumor patches were divided into different clusters. The cluster number and other hyperparameters were optimized by a nested cross-validation method. The percentage of each cluster from the patient's tumor patches, which is hereafter called PCF, was calculated for prognostic signature construction. The prognostic signature was constructed by Cox proportional hazard regression with L2 regularization. Finally, bioinformatic analysis was performed to explore the underlying biological mechanisms of the PCFs.

Results: The accuracy of the tumor detection model in distinguishing tumor patches from non-tumor patches achieved 99.3%. The optimal cluster number was determined to be 9. Therfore, 9 PCFs were calculated to construct the prognostic signature. The prognostic signature achieved a concordance index of 0.701 in the validation cohort. The Kaplan-Meier survival curves showed the prognostic signature had good risk stratification ability. Through the bioinformatic analysis, several PCF-associated genes were identified. These genes were enriched in various gene ontology terms.

Conclusion: The developed prognostic signature can effectively predict PFS in patients with rectal cancer and exploration of the underlying biological mechanisms may help to promote its clinical translation.

Citing Articles

Auxiliary meta-learning strategy for cancer recognition: leveraging external data and optimized feature mapping.

Wang K, Fei X, Su L, Fang T, Shen H BMC Cancer. 2025; 25(1):367.

PMID: 40016648 PMC: 11869438. DOI: 10.1186/s12885-025-13740-w.

References

Courtiol P, Maussion C, Moarii M, Pronier E, Pilcer S, Sefta M . Deep learning-based classification of mesothelioma improves prediction of patient outcome. Nat Med. 2019; 25(10):1519-1525. DOI: 10.1038/s41591-019-0583-3. View

Staal F, van der Reijd D, Taghavi M, Lambregts D, Beets-Tan R, Maas M . Radiomics for the Prediction of Treatment Outcome and Survival in Patients With Colorectal Cancer: A Systematic Review. Clin Colorectal Cancer. 2020; 20(1):52-71. DOI: 10.1016/j.clcc.2020.11.001. View

Skrede O, de Raedt S, Kleppe A, Hveem T, Liestol K, Maddison J . Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet. 2020; 395(10221):350-360. DOI: 10.1016/S0140-6736(19)32998-8. View

Benson A, Venook A, Al-Hawary M, Azad N, Chen Y, Ciombor K . Rectal Cancer, Version 2.2022, NCCN Clinical Practice Guidelines in Oncology. J Natl Compr Canc Netw. 2022; 20(10):1139-1167. DOI: 10.6004/jnccn.2022.0051. View

Wysocka M, Wysocki O, Zufferey M, Landers D, Freitas A . A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data. BMC Bioinformatics. 2023; 24(1):198. PMC: 10186658. DOI: 10.1186/s12859-023-05262-8. View

Zhou X, Lu Y, Wu Y, Yu Y, Liu Y, Wang C . Construction and validation of a deep learning prognostic model based on digital pathology images of stage III colorectal cancer. Eur J Surg Oncol. 2024; 50(7):108369. DOI: 10.1016/j.ejso.2024.108369. View

Camp R, Dolled-Filhart M, Rimm D . X-tile: a new bio-informatics tool for biomarker assessment and outcome-based cut-point optimization. Clin Cancer Res. 2004; 10(21):7252-9. DOI: 10.1158/1078-0432.CCR-04-0713. View

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. 2020; 65:101789. DOI: 10.1016/j.media.2020.101789. View

Kather J, Krisam J, Charoentong P, Luedde T, Herpel E, Weis C . Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study. PLoS Med. 2019; 16(1):e1002730. PMC: 6345440. DOI: 10.1371/journal.pmed.1002730. View

10.

Takashina Y, Kudo S, Kouyama Y, Ichimasa K, Miyachi H, Mori Y . Whole slide image-based prediction of lymph node metastasis in T1 colorectal cancer using unsupervised artificial intelligence. Dig Endosc. 2023; 35(7):902-908. DOI: 10.1111/den.14547. View

11.

Molinari C, Marisi G, Passardi A, Matteucci L, de Maio G, Ulivi P . Heterogeneity in Colorectal Cancer: A Challenge for Personalized Medicine?. Int J Mol Sci. 2018; 19(12). PMC: 6321493. DOI: 10.3390/ijms19123733. View

12.

Wang W, Zhao Y, Teng L, Yan J, Guo Y, Qiu Y . Neuropathologist-level integrated classification of adult-type diffuse gliomas using deep learning from whole-slide pathological images. Nat Commun. 2023; 14(1):6359. PMC: 10567721. DOI: 10.1038/s41467-023-41195-9. View

13.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

14.

Dimitriou N, Arandjelovic O, Caie P . Deep Learning for Whole Slide Image Analysis: An Overview. Front Med (Lausanne). 2019; 6:264. PMC: 6882930. DOI: 10.3389/fmed.2019.00264. View

15.

Li X, Jonnagaddala J, Cen M, Zhang H, Xu S . Colorectal Cancer Survival Prediction Using Deep Distribution Based Multiple-Instance Learning. Entropy (Basel). 2022; 24(11). PMC: 9689861. DOI: 10.3390/e24111669. View

16.

Jiang X, Hoffmeister M, Brenner H, Muti H, Yuan T, Foersch S . End-to-end prognostication in colorectal cancer by deep learning: a retrospective, multicentre study. Lancet Digit Health. 2023; 6(1):e33-e43. DOI: 10.1016/S2589-7500(23)00208-X. View

17.

Wang S, Liu Z, Rong Y, Zhou B, Bai Y, Wei W . Deep learning provides a new computed tomography-based prognostic biomarker for recurrence prediction in high-grade serous ovarian cancer. Radiother Oncol. 2018; 132:171-177. DOI: 10.1016/j.radonc.2018.10.019. View

18.

Sung H, Ferlay J, Siegel R, Laversanne M, Soerjomataram I, Jemal A . Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021; 71(3):209-249. DOI: 10.3322/caac.21660. View

19.

van der Laak J, Litjens G, Ciompi F . Deep learning in histopathology: the path to the clinic. Nat Med. 2021; 27(5):775-784. DOI: 10.1038/s41591-021-01343-4. View

20.

Mobadersany P, Yousefi S, Amgad M, Gutman D, Barnholtz-Sloan J, Velazquez Vega J . Predicting cancer outcomes from histology and genomics using convolutional networks. Proc Natl Acad Sci U S A. 2018; 115(13):E2970-E2979. PMC: 5879673. DOI: 10.1073/pnas.1717139115. View