Journal Home > Volume 1 , Issue 1
Medicine Advances 2023, 1(1): 30-43 https://doi.org/10.1002/med4.9
Original Article | Open Access | Issue | Published: 21 March 2023

Automated assessment of necrosis tumor ratio in colorectal cancer using an artificial intelligence-based digital pathology analysis

Show Author's Information Huifen Ye1,2,3,,  Yunrui Ye1,2,3,,  Yiting Wang4,,  Tong Tong5,6,,  Su Yao7,  Yao Xu3,  Qingru Hu1,  Yulin Liu1,  Changhong Liang1,2,3,  Guangyi Wang1,  Ke Zhao1,3,8( ),  Xinjuan Fan4( ),  Yanfen Cui9( ),  Zaiyi Liu1,2,3 ( )
Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
The Second School of Clinical Medicine, Southern Medical University, Guangzhou, China
Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
Department of Pathology, The Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China
Department of Oncology, Shanghai Medical College, Shanghai, China
Department of Pathology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
Department of Radiology, Shanxi Cancer Hospital, Shanxi Medical University, Taiyuan, China

Huifen Ye, Yunrui Ye, Yiting Wang and Tong Tong contributed equally to this work.

Keywords:
artificial intelligence, colorectal cancer, digital pathology, necrosis, whole-slide images
Cite this article:
Ye H, Ye Y, Wang Y, et al. Automated assessment of necrosis tumor ratio in colorectal cancer using an artificial intelligence-based digital pathology analysis. Medicine Advances, 2023, 1(1): 30-43. https://doi.org/10.1002/med4.9
Download citation
EndNote(RIS)
BibTeX

292

Views

10

Downloads

Citations

0

Crossref

N/A

WoS

N/A

Scopus

N/A

CSCD

Abstract Full text About this article
Background

With the advance in digital pathology and artificial intelligence (AI)-powered approaches, necrosis is proposed as a marker of poor prognosis in colorectal cancer (CRC). However, most previous studies quantified necrosis merely as a tissue type and patch-level segmentation. Thus, it was worth exploring and validating the prognostic and predictive value of necrosis proportion with a pixel-level segmentation in large multicenter cohorts.

Methods

A semantic segmentation model was trained with 12 tissue types labeled by pathologists. Segmentation was performed using the U-net model with a subsequently derived necrosis tumor ratio (NTR). We proposed the NTR score (NTR-low or NTR-high) to evaluate the prognostic and predictive value of necrosis for disease-free survival (DFS) and overall survival (OS) in the development (N = 443) and validation cohorts (N = 333) using 75% as a threshold.

Results

The 2-category NTR was an independent prognostic factor and NTR-low was associated with significant prolonged DFS (unadjusted HR for high vs. low 1.72 [95% CI 1.19–2.49] and 1.98 [1.22–3.23] in the development and validation cohorts). Similar trends were observed for OS. The prognostic value of NTR was maintained in the multivariate analysis for both cohorts. Furthermore, a stratified analysis showed that NTR-high was a high risk with adjuvant chemotherapy for OS in stage Ⅱ CRC (p = 0.047).

Conclusion

AI-based pixel-level quantified NTR has a stable prognostic value in CRC associated with unfavorable survival. Additionally, adjuvant chemotherapy provided survival benefits for patients with a high NTR score in stage Ⅱ CRC.


menu
Abstract
Full text
Outline
About this article

Automated assessment of necrosis tumor ratio in colorectal cancer using an artificial intelligence-based digital pathology analysis

Show Author's information Huifen Ye1,2,3,, Yunrui Ye1,2,3,, Yiting Wang4,, Tong Tong5,6,, Su Yao7, Yao Xu3, Qingru Hu1, Yulin Liu1, Changhong Liang1,2,3, Guangyi Wang1, Ke Zhao1,3,8( ), Xinjuan Fan4( ), Yanfen Cui9( ), Zaiyi Liu1,2,3 ( )
Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
The Second School of Clinical Medicine, Southern Medical University, Guangzhou, China
Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangzhou, China
Department of Pathology, The Sixth Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, China
Department of Oncology, Shanghai Medical College, Shanghai, China
Department of Pathology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China
Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
Department of Radiology, Shanxi Cancer Hospital, Shanxi Medical University, Taiyuan, China

Huifen Ye, Yunrui Ye, Yiting Wang and Tong Tong contributed equally to this work.

Abstract

Background

With the advance in digital pathology and artificial intelligence (AI)-powered approaches, necrosis is proposed as a marker of poor prognosis in colorectal cancer (CRC). However, most previous studies quantified necrosis merely as a tissue type and patch-level segmentation. Thus, it was worth exploring and validating the prognostic and predictive value of necrosis proportion with a pixel-level segmentation in large multicenter cohorts.

Methods

A semantic segmentation model was trained with 12 tissue types labeled by pathologists. Segmentation was performed using the U-net model with a subsequently derived necrosis tumor ratio (NTR). We proposed the NTR score (NTR-low or NTR-high) to evaluate the prognostic and predictive value of necrosis for disease-free survival (DFS) and overall survival (OS) in the development (N = 443) and validation cohorts (N = 333) using 75% as a threshold.

Results

The 2-category NTR was an independent prognostic factor and NTR-low was associated with significant prolonged DFS (unadjusted HR for high vs. low 1.72 [95% CI 1.19–2.49] and 1.98 [1.22–3.23] in the development and validation cohorts). Similar trends were observed for OS. The prognostic value of NTR was maintained in the multivariate analysis for both cohorts. Furthermore, a stratified analysis showed that NTR-high was a high risk with adjuvant chemotherapy for OS in stage Ⅱ CRC (p = 0.047).

Conclusion

AI-based pixel-level quantified NTR has a stable prognostic value in CRC associated with unfavorable survival. Additionally, adjuvant chemotherapy provided survival benefits for patients with a high NTR score in stage Ⅱ CRC.

Keywords: artificial intelligence, colorectal cancer, digital pathology, necrosis, whole-slide images

References(39)

[1]

Khan K, Rata M, Cunningham D, Koh DM, Tunariu N, Hahne JC, et al. Functional imaging and circulating biomarkers of response to regorafenib in treatment-refractory metastatic colorectal cancer patients in a prospective phase Ⅱ study. Gut. 2018;67(8):1484–92. https://doi.org/10.1136/gutjnl-2017-314178
DOI Google Scholar
[2]

Nagtegaal ID, Quirke P, Schmoll HJ. Has the new TNM classification for colorectal cancer improved care? Nat Rev Clin Oncol. 2011;9(2):119–23. https://doi.org/10.1038/nrclinonc.2011.157
DOI Google Scholar
[3]

Dekker E, Tanis PJ, Vleugels JLA, Kasi PM, Wallace MB. Colorectal cancer. Lancet. 2019;394(10207):1467–80. https://doi.org/10.1016/s0140-6736(19)32319-0
DOI Google Scholar
[4]

Hacking S, Nasim R, Lee L, Vitkovski T, Thomas R, Shaffer E, et al. Whole slide imaging and colorectal carcinoma: a validation study for tumor budding and stromal differentiation. Pathol Res Pract. 2020;216(11):153233. https://doi.org/10.1016/j.prp.2020.153233
DOI Google Scholar
[5]

Zhao K, Wu L, Huang Y, Yao S, Xu Z, Lin H, et al. Deep learning quantified mucus-tumor ratio predicting survival of patients with colorectal cancer using whole-slide images. Precis Clin Med. 2021;4(1):17–24. https://doi.org/10.1093/pcmedi/pbab002
DOI Google Scholar
[6]

Yang J, Ye H, Fan X, Li Y, Wu X, Zhao M, et al. Artificial intelligence for quantifying immune infiltrates interacting with stroma in colorectal cancer. J Transl Med. 2022;20(1):451. https://doi.org/10.1186/s12967-022-03666-3
DOI Google Scholar
[7]

Pollheimer MJ, Kornprat P, Lindtner RA, Harbaum L, Schlemmer A, Rehak P, et al. Tumor necrosis is a new promising prognostic factor in colorectal cancer. Hum Pathol. 2010;41(12):1749–57. https://doi.org/10.1016/j.humpath.2010.04.018
DOI Google Scholar
[8]

Yee PP, Li W. Tumor necrosis: a synergistic consequence of metabolic stress and inflammation. Bioessays. 2021;43(7):e2100029. https://doi.org/10.1002/bies.202100029
DOI Google Scholar
[9]

Zhang X, Chen L. The recent progress of the mechanism and regulation of tumor necrosis in colorectal cancer. J Cancer Res Clin Oncol. 2016;142(2):453–63. https://doi.org/10.1007/s00432-015-1997-z
DOI Google Scholar
[10]

Jin S, DiPaola RS, Mathew R, White E. Metabolic catastrophe as a means to cancer cell death. J Cell Sci. 2007;120(Pt 3):379–83. https://doi.org/10.1242/jcs.03349
DOI Google Scholar
[11]

Tomes L, Emberley E, Niu Y, Troup S, Pastorek J, Strange K, et al. Necrosis and hypoxia in invasive breast carcinoma. Breast Cancer Res Treat. 2003;81(1):61–9. https://doi.org/10.1023/a:1025476722493
DOI Google Scholar
[12]

Zong WX, Thompson CB. Necrotic death as a cell fate. Gene Dev. 2006;20(1):1–15. https://doi.org/10.1101/gad.1376506
DOI Google Scholar
[13]

Lee SY, Ju MK, Jeon HM, Jeong EK, Lee YJ, Kim CH, et al. Regulation of tumor progression by programmed necrosis. Oxid Med Cell Longev. 2018;2018:3537471. https://doi.org/10.1155/2018/3537471
DOI Google Scholar
[14]

Ling YH, Chen JW, Wen SH, Huang CY, Li P, Lu LH, et al. Tumor necrosis as a poor prognostic predictor on postoperative survival of patients with solitary small hepatocellular carcinoma. BMC Cancer. 2020;20(1):607. https://doi.org/10.1186/s12885-020-07097-5
DOI Google Scholar
[15]

van Pelt GW, Sandberg TP, Morreau H, Gelderblom H, van Krieken J, Tollenaar R, et al. The tumour-stroma ratio in colon cancer: the biological role and its prognostic impact. Histopathology. 2018;73(2):197–206. https://doi.org/10.1111/his.13489
DOI Google Scholar
[16]

Mercan E, Mehta S, Bartlett J, Shapiro LG, Weaver DL, Elmore JG. Assessment of machine learning of breast pathology structures for automated differentiation of breast cancer and high-risk proliferative lesions. JAMA Netw Open. 2019;2(8):e198777. https://doi.org/10.1001/jamanetworkopen.2019.8777
DOI Google Scholar
[17]

Richards CH, Roxburgh CS, Anderson JH, McKee RF, Foulis AK, Horgan PG, et al. Prognostic value of tumour necrosis and host inflammatory responses in colorectal cancer. Br J Surg. 2012;99(2):287–94. https://doi.org/10.1002/bjs.7755
DOI Google Scholar
[18]

Xu Q, Yuan JP, Chen YY, Zhang HY, Wang LW, Xiong B. Prognostic significance of the tumor-stromal ratio in invasive breast cancer and a proposal of a new Ts-TNM staging system. J Oncol. 2020;2020:9050631. https://doi.org/10.1155/2020/9050631
DOI Google Scholar
[19]

Zhao K, Li Z, Yao S, Wang Y, Wu X, Xu Z, et al. Artificial intelligence quantified tumour-stroma ratio is an independent predictor for overall survival in resectable colorectal cancer. EBioMedicine. 2020;61:103054. https://doi.org/10.1016/j.ebiom.2020.103054
DOI Google Scholar
[20]

Jakubowska K, Koda M, Grudzińska M, Kisielewski W, Lomperta K, Famulski W. Neutrophil infiltration combined with necrosis in the primary tumor is a useful prognostic indicator for three-year disease-free survival time in patients with colorectal cancer. Oncol Lett. 2022;23(6):199. https://doi.org/10.3892/ol.2022.13320
DOI Google Scholar
[21]

Richards CH, Mohammed Z, Qayyum T, Horgan PG, McMillan DC. The prognostic value of histological tumor necrosis in solid organ malignant disease: a systematic review. Future Oncol. 2011;7(10):1223–35. https://doi.org/10.2217/fon.11.99
DOI Google Scholar
[22]

de Araujo CB, Russo LC, Castro LM, Forti FL, do Monte ER, Rioli V, et al. A novel intracellular peptide derived from g1/s cyclin d2 induces cell death. J Biol Chem. 2014;289(24):16711–26. https://doi.org/10.1074/jbc.M113.537118
DOI Google Scholar
[23]

Rhee H, Chung T, Yoo JE, Nahm JH, Woo HY, Choi GH, et al. Gross type of hepatocellular carcinoma reflects the tumor hypoxia, fibrosis, and stemness-related marker expression. Hepatol Int. 2020;14(2):239–48. https://doi.org/10.1007/s12072-020-10012-6
DOI Google Scholar
[24]

Liu X, Liu L, Ji Y, Li C, Wei T, Yang X, et al. Enrichment of short mutant cell-free DNA fragments enhanced detection of pancreatic cancer. EBioMedicine. 2019;41:345–56. https://doi.org/10.1016/j.ebiom.2019.02.010
DOI Google Scholar
[25]

Swinson DE, Jones JL, Richardson D, Cox G, Edwards JG, O'Byrne KJ. Tumour necrosis is an independent prognostic marker in non-small cell lung cancer: correlation with biological variables. Lung Cancer. 2002;37(3):235–40. https://doi.org/10.1016/s0169-5002(02)00172-1
DOI Google Scholar
[26]

Leek RD, Landers RJ, Harris AL, Lewis CE. Necrosis correlates with high vascular density and focal macrophage infiltration in invasive carcinoma of the breast. Br J Cancer. 1999;79(5-6):991–5. https://doi.org/10.1038/sj.bjc.6690158
DOI Google Scholar
[27]

Jiao Y, Li J, Qian C, Fei S. Deep learning-based tumor microenvironment analysis in colon adenocarcinoma histopathological whole-slide images. Comput Methods Progr Biomed. 2021;204:106047. https://doi.org/10.1016/j.cmpb.2021.106047
DOI Google Scholar
[28]

Kather JN, Krisam J, Charoentong P, Luedde T, Herpel E, Weis CA, et al. Predicting survival from colorectal cancer histology slides using deep learning: a retrospective multicenter study. PLoS Med. 2019;16(1):e1002730. https://doi.org/10.1371/journal.pmed.1002730
DOI Google Scholar
[29]

Kaushik N, Kim S, Suh Y, Lee SJ. Proinvasive extracellular matrix remodeling for tumor progression. Arch Pharm Res. 2019;42(1):40–7. https://doi.org/10.1007/s12272-018-1097-0
DOI Google Scholar
[30]

Eble JA, Niland S. The extracellular matrix in tumor progression and metastasis. Clin Exp Metastasis. 2019;36(3):171–98. https://doi.org/10.1007/s10585-019-09966-1
DOI Google Scholar
[31]

Tharmalingham H, Hoskin P. Clinical trials targeting hypoxia. Br J Radiol. 2019;92(1093):20170966. https://doi.org/10.1259/bjr.20170966
DOI Google Scholar
[32]

Fang L, He Y, Liu Y, Ding H, Tong Y, Hu L, et al. Adjustment of microvessel area by stromal area to improve survival prediction in non-small cell lung cancer. J Cancer. 2019;10(15):3397–406. https://doi.org/10.7150/jca.31231
DOI Google Scholar
[33]

Bu P, Wang L, Chen KY, Rakhilin N, Sun J, Closa A, et al. miR-1269 promotes metastasis and forms a positive feedback loop with TGF-β. Nat Commun. 2015;6(1):6879. https://doi.org/10.1038/ncomms7879
DOI Google Scholar
[34]

Yuan Z, Weng S, Ye C, Hu H, Zhang S, Yuan Y. CSCO guidelines for colorectal cancer version 2022: updates and discussions. Chin J Cancer Res. 2022;34(2):67–70. https://doi.org/10.21147/j.issn.1000-9604.2022.02.01
DOI Google Scholar
[35]

Labianca R, Nordlinger B, Beretta GD, Mosconi S, Mandalà M, Cervantes A, et al. Early colon cancer: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol. 2013;24(Suppl 6):vi64–72. https://doi.org/10.1093/annonc/mdt354
DOI Google Scholar
[36]

Wyatt MD, Wilson DM, 3rd. Participation of DNA repair in the response to 5-fluorouracil. Cell Mol Life Sci. 2009;66(5):788–99. https://doi.org/10.1007/s00018-008-8557-5
DOI Google Scholar
[37]

Blondy S, David V, Verdier M, Mathonnet M, Perraud A, Christou N. 5-Fluorouracil resistance mechanisms in colorectal cancer: from classical pathways to promising processes. Cancer Sci. 2020;111(9):3142–54. https://doi.org/10.1111/cas.14532
DOI Google Scholar
[38]

Konishi Y, Taki T, Nakai T, Kuroe T, Morisue R, Miyoshi T, et al. Clinicopathological features and prognostic impact of dirty necrosis in metastatic lung cancers from the colon and rectum. Cancer Sci. 2022. https://doi.org/10.1111/cas.15647
DOI Google Scholar
[39]

Li L, Jiang W, Yang Y, Chen Z, Feng C, Li H, et al. Identification of dirty necrosis in colorectal carcinoma based on multiphoton microscopy. J Biomed Opt. 2014;19(6):066008. https://doi.org/10.1117/1.Jbo.19.6.066008
DOI Google Scholar
Publication history
Copyright
Acknowledgements
Rights and permissions

Publication history

Received: 20 January 2023
Accepted: 23 February 2023
Published: 21 March 2023
Issue date: March 2023

Copyright

© 2023 The Authors. Tsinghua University Press.

Acknowledgements

ACKNOWLEDGMENTS

This work was supported by Key-Area Research and Development Program of Guangdong Province (2021B0101420006), the National Key R&D Program of China (2021YFF1201003), Regional Innovation and Development Joint Fund of National Natural Science Foundation of China (U22A20345), the National Science Fund for Distinguished Young Scholars (81925023), National Natural Science Foundation of China (82071892, 82271941, 82271946 and 81971687), the National Science Foundation for Young Scientists of China (82202267), Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application (2022B1212010011), Project Funded by China Postdoctoral Science Foundation (2021M700897), High-level Hospital Construction Project (DFJHBF202105), and the Natural Science Foundation of Guangdong Province (2022A1515011252).

Rights and permissions

This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

Return