Construction of a combined prognostic model for pancreatic ductal adenocarcinoma based on deep learning and digital pathology images.
Combined model
Deep learning
Pancreatic ductal adenocarcinoma
Survival prognosis
Journal
BMC gastroenterology
ISSN: 1471-230X
Titre abrégé: BMC Gastroenterol
Pays: England
ID NLM: 100968547
Informations de publication
Date de publication:
31 Oct 2024
31 Oct 2024
Historique:
received:
28
06
2024
accepted:
16
10
2024
medline:
1
11
2024
pubmed:
1
11
2024
entrez:
1
11
2024
Statut:
epublish
Résumé
Deep learning has made significant advancements in the field of digital pathology, and the integration of multiple models has further improved accuracy. In this study, we aimed to construct a combined prognostic model using deep learning-extracted features from digital pathology images of pancreatic ductal adenocarcinoma (PDAC) alongside clinical predictive indicators and to explore its prognostic value. A retrospective analysis was conducted on 142 postoperative pathologically confirmed PDAC cases. These cases were divided into training (n = 114) and testing sets (n = 28) at an 8:2 ratio. Tumor whole-slide imaging features were extracted and screened to construct a pathological risk model based on a pre-trained deep learning model. Clinical and pathological data from the training set were used to select independent predictive factors for PDAC and establish a clinical risk model using LASSO, univariate, and multivariate Cox regression analyses. Based on the pathological and clinical risk models, a combined model was developed. The Harrell concordance index (C-index) was computed to assess the predictive performance of each model for PDAC survival prognosis. For the training and testing sets, the C-index values for the clinical risk model were 0.76 and 0.75, respectively; for the pathological risk model, they were 0.82 and 0.73, respectively; and for the combined model, they were 0.86 and 0.77, respectively. The combined model exhibited appropriate calibration at 1-, 3-, and 5-year time points, as well as a superior area under the curve of the receiver operating characteristic curve and clinical net benefit compared to the single models. Integrating the pathological and clinical risk models may provide a higher predictive value for survival prognosis.
Sections du résumé
BACKGROUND
BACKGROUND
Deep learning has made significant advancements in the field of digital pathology, and the integration of multiple models has further improved accuracy. In this study, we aimed to construct a combined prognostic model using deep learning-extracted features from digital pathology images of pancreatic ductal adenocarcinoma (PDAC) alongside clinical predictive indicators and to explore its prognostic value.
METHODS
METHODS
A retrospective analysis was conducted on 142 postoperative pathologically confirmed PDAC cases. These cases were divided into training (n = 114) and testing sets (n = 28) at an 8:2 ratio. Tumor whole-slide imaging features were extracted and screened to construct a pathological risk model based on a pre-trained deep learning model. Clinical and pathological data from the training set were used to select independent predictive factors for PDAC and establish a clinical risk model using LASSO, univariate, and multivariate Cox regression analyses. Based on the pathological and clinical risk models, a combined model was developed. The Harrell concordance index (C-index) was computed to assess the predictive performance of each model for PDAC survival prognosis.
RESULTS
RESULTS
For the training and testing sets, the C-index values for the clinical risk model were 0.76 and 0.75, respectively; for the pathological risk model, they were 0.82 and 0.73, respectively; and for the combined model, they were 0.86 and 0.77, respectively. The combined model exhibited appropriate calibration at 1-, 3-, and 5-year time points, as well as a superior area under the curve of the receiver operating characteristic curve and clinical net benefit compared to the single models.
CONCLUSIONS
CONCLUSIONS
Integrating the pathological and clinical risk models may provide a higher predictive value for survival prognosis.
Identifiants
pubmed: 39482576
doi: 10.1186/s12876-024-03469-4
pii: 10.1186/s12876-024-03469-4
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
387Informations de copyright
© 2024. The Author(s).
Références
Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, Bray F. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71(3):209–49.
doi: 10.3322/caac.21660
pubmed: 33538338
Halbrook CJ, Lyssiotis CA, Pasca di Magliano M, Maitra A. Pancreatic cancer: advances and challenges. Cell. 2023;186(8):1729–54.
doi: 10.1016/j.cell.2023.02.014
pubmed: 37059070
pmcid: 10182830
Mizrahi JD, Surana R, Valle JW, Shroff RT. Pancreatic cancer. Lancet. 2020;395(10242):2008–20.
doi: 10.1016/S0140-6736(20)30974-0
pubmed: 32593337
Zheng R, Zhang S, Zeng H, Wang S, Sun K, Chen R, Li L, Wei W, He J. Cancer incidence and mortality in China, 2016. J Natl Cancer Cent. 2022;2(1):1–9.
doi: 10.1016/j.jncc.2022.02.002
pubmed: 39035212
pmcid: 11256658
Maomao C, He L, Dianqin S, Siyi H, Xinxin Y, Fan Y, Shaoli Z, Changfa X, Lin L, Ji P, et al. Current cancer burden in China: epidemiology, etiology, and prevention. Cancer Biology Med. 2022;19(8):1121–38.
doi: 10.20892/j.issn.2095-3941.2022.0231
Birnbaum DJ, Bertucci F, Finetti P, Birnbaum D, Mamessier E. Head and body/tail pancreatic carcinomas are not the same tumors. Cancers (Basel). 2019;11(4).
Wang S, Yang DM, Rong R, Zhan X, Fujimoto J, Liu H, et al. Artificial intelligence in lung cancer pathology image analysis. Cancers (Basel). 2019;11(11):1673.
Xie X, Wang X, Liang Y, Yang J, Wu Y, Li L, et al. Tian GJFiO: evaluating cancer-related biomarkers based on pathological images: a systematic review. Front Oncol. 2021;11:763527.
Kumar N, Gupta R, Gupta SJJ. Whole slide imaging (WSI) in pathology: current perspectives and future directions. J Digit Imaging. 2020;33(4):1034–40.
LeCun Y, Bengio Y, Hinton GJ. Deep learn. 2015;521(7553):436–44.
Yao J, Cao K, Hou Y, Zhou J, Xia Y, Nogues I, Song Q, Jiang H, Ye X, Lu J, et al. Deep learning for fully automated prediction of overall survival in patients undergoing resection for pancreatic cancer: a retrospective multicenter study. Ann Surg. 2023;278(1):e68–79.
doi: 10.1097/SLA.0000000000005465
pubmed: 35781511
Wang R, Dai W, Gong J, Huang M, Hu T, Li H, Lin K, Tan C, Hu H, Tong T, et al. Development of a novel combined nomogram model integrating deep learning-pathomics, radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients. J Hematol Oncol. 2022;15(1):11.
doi: 10.1186/s13045-022-01225-3
pubmed: 35073937
pmcid: 8785554
She Y, Jin Z, Wu J, Deng J, Zhang L, Su H, Jiang G, Liu H, Xie D, Cao N, et al. Development and validation of a deep learning model for non-small cell lung cancer survival. JAMA Netw Open. 2020;3(6):e205842.
doi: 10.1001/jamanetworkopen.2020.5842
pubmed: 32492161
pmcid: 7272121
Shi J-Y, Wang X, Ding G-Y, Dong Z, Han J, Guan Z, et al. Exploring prognostic indicators in the pathological images of hepatocellular carcinoma based on deep learning. Gut. 2021;70(5):951–61.
Huang B, Tian S, Zhan N, Ma J, Huang Z, Zhang C, Zhang H, Ming F, Liao F, Ji M, et al. Accurate diagnosis and prognosis prediction of gastric cancer using deep learning on digital pathological images: a retrospective multicentre study. EBioMedicine. 2021;73:103631.
doi: 10.1016/j.ebiom.2021.103631
pubmed: 34678610
pmcid: 8529077
Wang Y, Ali MA, Vallon-Christersson J, Humphreys K, Hartman J, Rantalainen M. Transcriptional intra-tumour heterogeneity predicted by deep learning in routine breast histopathology slides provides independent prognostic information. Eur J Cancer. 2023;191:112953.
doi: 10.1016/j.ejca.2023.112953
pubmed: 37494846
Cancer, AJCo. AJCC cancer staging manual. 9th ed. edn: Springer; 2021.
Yan J, Zhang S, Li KK-W, Wang W, Li K, Duan W, Yuan B, Wang L, Liu L, Zhan Y, et al. Incremental prognostic value and underlying biological pathways of radiomics patterns in medulloblastoma. EBioMedicine. 2020;61:103093.
doi: 10.1016/j.ebiom.2020.103093
pubmed: 33096488
pmcid: 7581926
Katz MHG, Hwang R, Fleming JB, Evans DB. Tumor-node-metastasis staging of pancreatic adenocarcinoma. CA Cancer J Clin. 2008;58(2):111–25.
doi: 10.3322/CA.2007.0012
pubmed: 18272835
Schouten TJ, Daamen LA, Dorland G, van Roessel SR, Groot VP, Besselink MG, Bonsing BA, Bosscha K, Brosens LAA, Busch OR, et al. Nationwide validation of the 8th American Joint Committee on Cancer TNM Staging System and five proposed modifications for resected pancreatic cancer. Ann Surg Oncol. 2022;29(9):5988–99.
doi: 10.1245/s10434-022-11664-4
pubmed: 35469113
pmcid: 9356941
Pointer DT, Roife D, Powers BD, Murimwa G, Elessawy S, Thompson ZJ, Schell MJ, Hodul PJ, Pimiento JM, Fleming JB, et al. Neutrophil to lymphocyte ratio, not platelet to lymphocyte or lymphocyte to monocyte ratio, is predictive of patient survival after resection of early-stage pancreatic ductal adenocarcinoma. BMC Cancer. 2020;20(1):750.
doi: 10.1186/s12885-020-07182-9
pubmed: 32782024
pmcid: 7422564
Zuo X, Kong W, Feng L, Zhang H, Meng X, Chen W. Elevated platelet distribution width predicts poor prognosis in hepatocellular carcinoma. Cancer Biomark. 2019;24(3):307–13.
doi: 10.3233/CBM-182076
pubmed: 30829614
Cui M-M, Li N, Liu X, Yun Z-Y, Niu Y, Zhang Y, Gao B, Liu T, Wang R-T. Platelet distribution width correlates with prognosis of non-small cell lung cancer. Sci Rep. 2017;7(1):3456.
doi: 10.1038/s41598-017-03772-z
pubmed: 28615714
pmcid: 5471191
Huang Y, Cui M-M, Huang Y-X, Fu S, Zhang X, Guo H, Wang R-T. Preoperative platelet distribution width predicts breast cancer survival. Cancer Biomark. 2018;23(2):205–11.
doi: 10.3233/CBM-181267
pubmed: 30198864
Hayashi M, Kobayashi D, Takami H, Inokawa Y, Tanaka N, Kurimoto K, Nakanishi K, Umeda S, Shimizu D, Hattori N, et al. Albumin-globulin ratio indicates the survival outcome of pancreatic cancer cases who underwent preoperative treatment and curative surgical resection. Nutr Cancer. 2023;75(5):1330–9.
doi: 10.1080/01635581.2023.2191384
pubmed: 36961102
Zhang Y, Zhu J-Y, Zhou L-N, Tang M, Chen M-B, Tao M. Predicting the prognosis of gastric cancer by albumin/globulin ratio and the prognostic nutritional index. Nutr Cancer. 2020;72(4):635–44.
doi: 10.1080/01635581.2019.1651347
pubmed: 31423840
Atsumi Y, Kawahara S, Kakuta S, Onodera A, Hara K, Kazama K, Numata M, Aoyama T, Tamagawa A, Tamagawa H, et al. Low preoperative albumin-to-globulin ratio is a marker of poor prognosis in patients with esophageal cancer. Vivo. 2021;35(6):3555–61.
doi: 10.21873/invivo.12658
Ni XG, Bai XF, Mao YL, Shao YF, Wu JX, Shan Y, Wang CF, Wang J, Tian YT, Liu Q, et al. The clinical value of serum CEA, CA19-9, and CA242 in the diagnosis and prognosis of pancreatic cancer. Eur J Surg Oncol. 2005;31(2):164–9.
doi: 10.1016/j.ejso.2004.09.007
pubmed: 15698733
Ermiah E, Eddfair M, Abdulrahman O, Elfagieh M, Jebriel A, Al-Sharif M, Assidi M, Buhmeida A. Prognostic value of serum CEA and CA19-9 levels in pancreatic ductal adenocarcinoma. Mol Clin Oncol. 2022;17(2):126.
doi: 10.3892/mco.2022.2559
pubmed: 35832472
pmcid: 9264325
Ahmadipour M, Bhattacharya A, Sarafbidabad M, Syuhada Sazali E, Krishna Ghoshal S, Satgunam M, Singh R, Rezaei Ardani M, Missaoui N, Kahri H, et al. CA19-9 and CEA biosensors in pancreatic cancer. Clin Chim Acta. 2024;554:117788.
doi: 10.1016/j.cca.2024.117788
pubmed: 38246211
O’Neill RS, Stoita A. Biomarkers in the diagnosis of pancreatic cancer: are we closer to finding the golden ticket? World J Gastroenterol. 2021;27(26):4045–87.
doi: 10.3748/wjg.v27.i26.4045
pubmed: 34326612
pmcid: 8311531
Kato H, Kishiwada M, Hayasaki A, Chipaila J, Maeda K, Noguchi D, Gyoten K, Fujii T, Iizawa Y, Tanemura A, et al. Role of serum Carcinoma Embryonic Antigen (CEA) level in localized pancreatic adenocarcinoma: CEA level before operation is a significant prognostic indicator in patients with locally advanced pancreatic cancer treated with neoadjuvant therapy followed by surgical resection: a retrospective analysis. Ann Surg. 2022;275(5):e698–707.
doi: 10.1097/SLA.0000000000004148
pubmed: 32744820
Zhou X, Lu Y, Wu Y, Yu Y, Liu Y, Wang C, Zhao Z, Wang C, Gao Z, Li Z, et al. 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
pubmed: 38703632
Huang B, Huang H, Zhang S, Zhang D, Shi Q, Liu J, Guo J. Artificial intelligence in pancreatic cancer. Theranostics. 2022;12(16):6931–54.
doi: 10.7150/thno.77949
pubmed: 36276650
pmcid: 9576619
Karar ME, El-Fishawy N, Radad M. Automated classification of urine biomarkers to diagnose pancreatic cancer using 1-D convolutional neural networks. J Biol Eng. 2023;17(1):28.
doi: 10.1186/s13036-023-00340-0
pubmed: 37069681
pmcid: 10111836
Fu N, Fu W, Chen H, Chai W, Qian X, Wang W, Jiang Y, Shen B. A deep-learning radiomics-based lymph node metastasis predictive model for pancreatic cancer: a diagnostic study. Int J Surg (London England). 2023;109(8):2196–203.
doi: 10.1097/JS9.0000000000000469
Fu H, Mi W, Pan B, Guo Y, Li J, Xu R, Zheng J, Zou C, Zhang T, Liang Z, et al. Automatic pancreatic ductal adenocarcinoma detection in whole slide images using deep convolutional neural networks. Front Oncol. 2021;11:665929.
doi: 10.3389/fonc.2021.665929
pubmed: 34249702
pmcid: 8267174
Lin J, Yin M, Liu L, Gao J, Yu C, Liu X, et al. The development of a prediction model based on random survival forest for the postoperative prognosis of pancreatic cancer: a SEER-based study. Cancers (Basel). 2022;14(19):4667.
Gheysarzadeh A, Ansari A, Emami MH, Razavi AE, Mofid MR. Over-expression of low-density lipoprotein receptor-related protein-1 is associated with poor prognosis and invasion in pancreatic ductal adenocarcinoma. Pancreatology. 2019;19(3):429–35.
doi: 10.1016/j.pan.2019.02.012
pubmed: 30902418
Chen S, Hu S, Zhou B, Cheng B, Tong H, Su D, Li X, Chen Y, Zhang G. Telomere-related prognostic biomarkers for survival assessments in pancreatic cancer. Sci Rep. 2023;13(1):10586.
doi: 10.1038/s41598-023-37836-0
pubmed: 37391503
pmcid: 10313686
Fiocchi C. Omics and multi-omics in IBD: no integration, no breakthroughs. Int J Mol Sci. 2023;24(19).
Yang Z, Wang C, Wang Y, Lafata KJ, Zhang H, Ackerson BG, Kelsey C, Tong B, Yin FF. Development of a multi-feature-combined model: proof-of-concept with application to local failure prediction of post-SBRT or surgery early-stage NSCLC patients. Front Oncol. 2023;13:1185771.
doi: 10.3389/fonc.2023.1185771
pubmed: 37781201
pmcid: 10534017
Song R, Wang H, Zhang M, Liu Y, Meng X, Zhai S, Wang CC, Gong T, Wu Y, Jiang X, et al. Near-infrared light-triggered chlorine radical ((.) Cl) stress for cancer therapy. Angewandte Chemie (International ed English). 2020;59(47):21032–40.
doi: 10.1002/anie.202007434