Table Info

Table 4.

Ten-fold cross-validation results of binary classification of RhoB expression in rectal-cancer biopsy

Methods	ACC (%)	SEN (%)	SPE (%)	PRE (%)	F₁
ResNet-18	59.09 ± 8.83	75.71 ± 15.13	30.00 ± 19.72	65.65 ± 5.86	0.70 ± 0.08
ResNet-18 & SVM	67.28 ± 10.36	68.57 ± 27.48	65.00 ± 28.50	81.43 ± 12.21	0.70 ± 0.16
SqueezeNet	61.82 ± 10.32	70.00 ± 22.79	47.50 ± 21.89	71.75 ± 11.12	0.68 ± 0.14
SqueezeNet & SVM	67.28 ± 4.98	77.14 ± 21.30	50.00 ± 46.77	80.72 ± 17.78	0.73 ± 0.12
DenseNet-201	60.00 ± 8.78	72.86 ± 10.54	37.50 ± 24.30	68.11 ± 8.91	0.70 ± 0.07
DenseNet-201 & SVM	69.09 ± 10.36	82.86 ± 18.63	45.00 ± 20.92	78.89 ± 7.40	0.77 ± 0.10
AlexNet	54.55 ± 17.14	74.29 ± 25.02	20.00 ± 19.72	60.34 ± 14.70	0.66 ± 0.18
AlexNet & SVM	72.74 ± 11.13	85.71 ± 0.00	50.00 ± 30.62	76.67 ± 13.69	0.80 ± 0.07
Xception	60.91 ± 9.63	80.00 ± 13.36	27.50 ± 34.26	68.48 ± 13.20	0.72 ± 0.06
Xception & SVM	74.55 ± 7.61	74.29 ± 18.63	75.00 ± 30.62	87.14 ± 13.01	0.78 ± 0.08
NASNet-Large	71.82 ± 15.72	77.14 ± 22.54	62.50 ± 21.25	78.28 ± 11.94	0.76 ± 0.15
NASNet-Large & SVM	84.55 ± 7.48	90.00 ± 11.76	75.00 ± 20.41	87.70 ± 9.55	0.88 ± 0.06

Declarations

Author contributions

TDP and XFS: Conceptualization. TDP: Methodology. TDP: Software. TDP, VR, BL, CF, and XFS: Formal analysis. BL and CF: Data curation. TDP: Writing—original draft. TDP, VR, BL, CF, and XFS: Writing—review & editing.

Conflicts of interest

The authors declare that there are no conflicts of interest.

Ethical approval

The ethical applications were approved by the Institutional Ethics Committee of Linköping University (Dnr 2012-107-31 and Dnr 2014-79-31).

Consent to participate

The informed consent to participate in the study was obtained from all participants.

Consent to publication

Not applicable.

Availability of data and materials

The IHC image data used in this study are available at the first author’s homepage: https://sites.google.com/view/tuan-d-pham/codes under the name “Rectal cancer biopsy”.

Funding

Not applicable.

Copyright

References

The precision medicine initiative [Internet]. [cited 2022 Feb 9]. Available from: https://obamawhitehouse.archives.gov/precision-medicine

Ghasemi M, Nabipour I, Omrani A, Alipour Z, Assadi M. Precision medicine and molecular imaging: new targeted approaches toward cancer therapeutic and diagnosis. Am J Nucl Med Mol Imaging. 2016;6:310–27. [PubMed] [PMC]

Meehan J, Gray M, Martínez-Pérez C, Kay C, Pang LY, Fraser JA, et al. Precision medicine and the role of biomarkers of radiotherapy response in breast cancer. Front Oncol. 2020;10:628. [DOI] [PubMed] [PMC]

Boniolo F, Dorigatti E, Ohnmacht AJ, Saur D, Schubert B, Menden MP. Artificial intelligence in early drug discovery enabling precision medicine. Expert Opin Drug Discov. 2021;16:991–1007. [DOI] [PubMed]

Wang Y, Wang D, Ye X, Wang Y, Yin Y, Jin Y. A tree ensemble-based two-stage model for advanced-stage colorectal cancer survival prediction. Inf Sci. 2019;474:106–24. [DOI]

Pham TD, Fan C, Zhang H, Sun XF. Artificial intelligence-based 5-year survival prediction and prognosis of DNp73 expression in rectal cancer patients. Clin Transl Med. 2020;10:e159. [DOI] [PubMed] [PMC]

Lorenzovici N, Dulf EH, Mocan T, Mocan L. Artificial intelligence in colorectal cancer diagnosis using clinical data: non-invasive approach. Diagnostics (Basel). 2021;11:514. [DOI] [PubMed] [PMC]

Skrede OJ, De Raedt S, Kleppe A, Hveem TS, Liestøl K, Maddison J, et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet. 2020;395:350–60. [DOI] [PubMed]

Yu G, Sun K, Xu C, Shi XH, Wu C, Xie T, et al. Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images. Nat Commun. 2021;12:6311. [DOI] [PubMed] [PMC]

10.

Abraham JP, Magee D, Cremolini C, Antoniotti C, Halbert DD, Xiu J, et al. Clinical validation of a machine-learning-derived signature predictive of outcomes from first-line oxaliplatin-based chemotherapy in advanced colorectal cancer. Clin Cancer Res. 2021;27:1174–83. [DOI] [PubMed]

11.

Wulczyn E, Steiner DF, Moran M, Plass M, Reihs R, Tan F, et al. Interpretable survival prediction for colorectal cancer using deep learning. NPJ Digit Med. 2021;4:71. [DOI] [PubMed] [PMC]

12.

Yu C, Helwig EJ. The role of AI technology in prediction, diagnosis and treatment of colorectal cancer. Artif Intell Rev. 2022;55:323–43. [DOI] [PubMed] [PMC]

13.

Lebowitz PF, Casey PJ, Prendergast GC, Thissen JA. Farnesyltransferase inhibitors alter the prenylation and growth-stimulating function of RhoB. J Biol Chem. 1997;272:15591–4. [DOI] [PubMed]

14.

Huang M, Prendergast GC. RhoB in cancer suppression. Histol Histopathol. 2006;21:213–8. [DOI] [PubMed]

15.

Chen W, Niu S, Ma X, Zhang P, Gao Y, Fan Y, et al. RhoB acts as a tumor suppressor that inhibits malignancy of clear cell renal cell carcinoma. PLoS One. 2016;11:e0157599. [DOI] [PubMed] [PMC]

16.

Liu N, Cui W, Jiang X, Zhang Z, Gnosa S, Ali Z, et al. The critical role of dysregulated RhoB signaling pathway in radioresistance of colorectal cancer. Int J Radiat Oncol Biol Phys. 2019;104:1153–64. [DOI] [PubMed]

17.

Pham T, Ravi V, Liu N, Luo B, Fan CW, Sun XF. Tensor decomposition of largest convolutional eigenvalues reveals pathological predictive power of RhoB in rectal cancer biopsy. Res Sq [Preprint]. 2021 [cited 2022 Sep 18]. Available from: https://www.researchsquare.com/article/rs-957359/v1

18.

Swedish Rectal Cancer Trial; Cedermark B, Dahlberg M, Glimelius B, Påhlman L, Rutqvist LE, Wilking N. Improved survival with preoperative radiotherapy in resectable rectal cancer. N Engl J Med. 1997;336:980–7. Erratum in: N Engl J Med. 1997;336:1539. [DOI] [PubMed]

19.

Lin M, Chen Q, Yan S. Network in network. Version: 3. ArXiv [Preprint]. [posted 2013 Dec 16; revised 2013 Dec 18; revised 2014 Mar 4; cited 2022 Sep 18]. Available from: https://doi.org/10.48550/arXiv.1312.4400

20.

ImageNet [Internet]. Stanford Vision Lab, Stanford University, Princeton University; c2020 [cited 2022 Jan 21]. Available from: http://www.image-net.org

21.

He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2016:770–8. [DOI]

22.

Deep learning reading group: SqueezeNet [Internet]. KDnuggets; c2022 [cited 2021 Sep 10]. Available from: https://www.kdnuggets.com/2016/09/deep-learning-reading-group-squeezenet.html

23.

Iandola F. SqueezeNet [Internet]. GitHub, Inc.; c2022 [cited 2021 Sep 10]. Available from: https://github.com/forresti/SqueezeNet

24.

Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2017:2261–9. [DOI]

25.

Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017;60:84–90. [DOI]

26.

Chollet F. Xception: deep learning with depthwise separable convolutions. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2017:1800–7. [DOI]

27.

Zoph B, Vasudevan V, Shlens J, Le QV. Learning transferable architectures for scalable image recognition. Version: 4. ArXiv [Preprint]. [posted 2017 Jul 21; revised 2017 Oct 25; revised 2017 Dec 1; revised 2018 Apr 11; cited 2022 Sep 18]. Available from: http://arxiv.org/abs/1707.07012

28.

NASNet - a brief overview [Internet]. OpenGenus IQ; c2022 [cited 2022 Feb 12]. Available from: https://iq.opengenus.org/nasnet/

29.

Pham TD, Fan C, Zhang H, Sun XF. Deep learning of P73 biomarker expression in rectal cancer patients. Proc Int Jt Conf Neural Netw. 2019:1–8. [DOI]

30.

Fan J, Lee J, Lee Y. A transfer learning architecture based on a support vector machine for histopathology image classification. Appl Sci. 2021;11:6380. [DOI]

31.

Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods. Cambridge: Cambridge University Press; 2000. [DOI]

32.

Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. 2nd ed. New York: Springer; 2009. [DOI]

33.

Sanli I, Osong B, Dekker A, TerHaag K, van Kuijk SMJ, van Soest J, et al. Radiomics biopsy signature for predicting survival in patients with spinal bone metastases (SBMs). Clin Transl Radiat Oncol. 2022;33:57–65. [DOI] [PubMed] [PMC]

34.

Ziv E, Durack JC, Solomon SB. The importance of biopsy in the era of molecular medicine. Cancer J. 2016;22:418–22. [DOI] [PubMed] [PMC]

35.

Bradley E. Incorporating biomarkers into clinical trial designs: points to consider. Nat Biotechnol. 2012;30:596–9. [DOI] [PubMed]

36.

Louie AD, Huntington K, Carlsen L, Zhou L, El-Deiry WS. Integrating molecular biomarker inputs into development and use of clinical cancer therapeutics. Front Pharmacol. 2021;12:747194. [DOI] [PubMed] [PMC]

37.

Pham TD. A comprehensive study on classification of COVID-19 on computed tomography with pretrained convolutional neural networks. Sci Rep. 2020;10:16942. [DOI] [PubMed] [PMC]

38.

Pham TD. Classification of COVID-19 chest X-rays with deep learning: new models or fine tuning? Health Inf Sci Syst. 2020;9:2. [DOI] [PubMed] [PMC]

39.

Mean plus standard deviation is greater than the maximum in IBM SPSS Statistics [Internet]. IBM Corporation; c2022 [cited 2022 Mar 28]. Available from: https://www.ibm.com/support/pages/mean-plus-standard-deviation-greater-maximum-ibm-spss-statistics

40.

Altman DG, Bland JM. Standard deviations and standard errors. BMJ. 2005;331:903. [DOI] [PubMed] [PMC]

41.

Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48:441–6. [DOI] [PubMed] [PMC]

42.

Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016;278:563–77. [DOI] [PubMed] [PMC]

43.

Nardone V, Reginelli A, Grassi R, Boldrini L, Vacca G, D’Ippolito E, et al. Delta radiomics: a systematic review. Radiol Med. 2021;126:1571–83. [DOI] [PubMed]

44.

Nardone V, Boldrini L, Grassi R, Franceschini D, Morelli I, Becherini C, et al. Radiomics in the setting of neoadjuvant radiotherapy: a new approach for tailored treatment. Cancers (Basel). 2021;13:3590. [DOI] [PubMed] [PMC]

45.

Nardone V, Reginelli A, Grassi R, Vacca G, Giacobbe G, Angrisani A, et al. Ability of delta radiomics to predict a complete pathological response in patients with loco-regional rectal cancer addressed to neoadjuvant chemo-radiation and surgery. Cancers (Basel). 2022;14:3004. [DOI] [PubMed] [PMC]

46.

Boldrini L, Lenkowicz J, Orlandini LC, Yin G, Cusumano D, Chiloiro G, et al. Applicability of a pathological complete response magnetic resonance-based radiomics model for locally advanced rectal cancer in intercontinental cohort. Radiat Oncol. 2022;17:78. [DOI] [PubMed] [PMC]

47.

Bayanati H, E Thornhill R, Souza CA, Sethi-Virmani V, Gupta A, Maziak D, et al. Quantitative CT texture and shape analysis: can it differentiate benign and malignant mediastinal lymph nodes in patients with primary lung cancer? Eur Radiol. 2015;25:480–7. [DOI] [PubMed]

48.

Pham TD, Watanabe Y, Higuchi M, Suzuki H. Texture analysis and synthesis of malignant and benign mediastinal lymph nodes in patients with lung cancer on computed tomography. Sci Rep. 2017;7:43209. [DOI] [PubMed] [PMC]

49.

Rödel C, Martus P, Papadoupolos T, Füzesi L, Klimpfinger M, Fietkau R, et al. Prognostic significance of tumor regression after preoperative chemoradiotherapy for rectal cancer. J Clin Oncol. 2005;23:8688–96. [DOI] [PubMed]

50.

Ramspek CL, Jager KJ, Dekker FW, Zoccali C, van Diepen M. External validation of prognostic models: what, why, how, when and where? Clin Kidney J. 2021;14:49–58. [DOI] [PubMed] [PMC]

51.

Alves Martins BA, de Bulhões GF, Cavalcanti IN, Martins MM, de Oliveira PG, Martins AMA. Biomarkers in colorectal cancer: the role of translational proteomics research. Front Oncol. 2019;9:1284. [DOI] [PubMed] [PMC]