Application of deep learning image reconstruction algorithm in dual-energy CT scanning for preoperative T sta-ging of gastric cancer

doi:10.16150/j.1671-2870.2023.02.008

Abstract

Abstract:

Objective: To investigate the value of deep learning image reconstruction (DLIR) algorithm in dual-energy CT scanning for preoperative T staging of gastric cancer. Methods: Data from preoperative dual-energy CT of 45 patients with pathology-confirmed gastric cancer during January 2022 to February 2022 were retrospectively analyzed. The raw data of dual-energy scanning in venous phase were reconstructed by filtered back projection (FBP), adaptive statistical iterative reconstruction-V with a weight of 50% (AV-50) and of 100% (AV-100), and deep learning image reconstruction-mid-range (DLIR-M) algorithms. Then these images were used to reconstruct a 50 keV level virtual mono-energy image with a 1.25mm layer thickness. Images were reviewed by two radiologists with 5 and 10 years of experience in T staging of gastrointestinal tumors. It revealed that 22 cases were diagnosed pathologically as having early gastric cancer (T_1a-T_1b) and 23 cases as having advanced gastric cancer (T₂-T₃). Diagnostic accuracy of different reconstruction algorithms for T staging of gastric cancer were calculated using area under the receiver operating curve (AUC) ，with pathology results as the golden standard. Results: The AUC of the reconstructed dual-energy CT images based on FBP, AV-50, AV-100 and DLIR-M algorithms were 0.638, 0.667, 0.577 and 0.867, respectively. The AUC of DLIR-M images was significantly higher than those of FBP (P=0.0498), AV-50 (P=0.0477) and AV-100 (P=0.0123) images. Conclusions: Compared with traditional reconstruction algorithms of FBP and Asir-V，DLIR algorithm may further improve the accuracy of dual-energy CT scanning in preoperative T staging of gastric cancer. DLIR-M is significant for treatment decision-making.

Key words: Gastric cancer, Deep learning, Image reconstruction, Staging diagnosis

CLC Number:

R735.2

YAN Ling, WANG Lingyun, CHEN Yong, DU Lianjun. Application of deep learning image reconstruction algorithm in dual-energy CT scanning for preoperative T sta-ging of gastric cancer[J]. Journal of Diagnostics Concepts & Practice, 2023, 22(02): 154-159.

Figures/Tables 6

Table 1

Figure 1

Figure 2

Table 2

Figure 3

Table 3

References 20

[1]	SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3):209-249. doi: 10.3322/caac.v71.3 URL
[2]	中华医学会肿瘤学分会, 中华医学会杂志社. 中华医学会胃癌临床诊疗指南(2021版)[J]. 中华医学杂志, 2022, 102(16):1169-1189.
	China Medical Association of Oncology, Chinese Medical Journal. Guidelines for the clinical diagnosis and treatment of gastric cancer (2021 version)[J]. National Med J China, 2022, 102(16):1169-1189.
[3]	Seevaratnam R, Cardoso R, McGregor C, et al. How useful is preoperative imaging for tumor, node, metastasis (TNM) staging of gastric cancer? A meta-analysis[J]. Gastric Cancer, 2012, 15(Suppl 1):S3-S18.
[4]	ALLUM W H, BLAZEBY J M, GRIFFIN S M, et al. Guidelines for the management of oesophageal and gastric cancer[J]. Gut, 2011, 60(11):1449-1472. doi: 10.1136/gut.2010.228254 pmid: 21705456
[5]	CHEN C Y, HSU J S, WU D C, et al. Gastric cancer: preoperative local staging with 3D multi-detector row CT--correlation with surgical and histopathologic results[J]. Radiology, 2007, 242(2):472-482. doi: 10.1148/radiol.2422051557 URL
[6]	ZHENG Z, YU Y, LU M, et al. Double contrast-enhanced ultrasonography for the preoperative evaluation of gastric cancer: a comparison to endoscopic ultrasonography with respect to histopathology[J]. Am J Surg, 2011, 202(5):605-611. doi: 10.1016/j.amjsurg.2010.09.033 pmid: 21824594
[7]	WANG J Y, HSIEH J S, HUANG Y S, et al. Endoscopic ultrasonography for preoperative locoregional staging and assessment of resectability in gastric cancer[J]. Clin Ima-ging, 1998, 22(5):355-359.
[8]	AHN H S, LEE H J, YOO M W, et al. Diagnostic accuracy of T and N stages with endoscopy, stomach protocol CT, and endoscopic ultrasonography in early gastric cancer[J]. J Surg Oncol, 2009, 99(1):20-27. doi: 10.1002/jso.21170 pmid: 18937292
[9]	MCCOLLOUGH C H, LENG S, YU L, et al. Dual- and multi-energy CT: principles, technical approaches, and clinical applications[J]. Radiology, 2015, 276(3):637-653. doi: 10.1148/radiol.2015142631 pmid: 26302388
[10]	LI J, FANG M, WANG R, et al. Diagnostic accuracy of dual-energy CT-based nomograms to predict lymph node metastasis in gastric cancer[J]. Eur Radiol, 2018, 28(12):5241-5249. doi: 10.1007/s00330-018-5483-2 pmid: 29869176
[11]	GAO X, ZHANG Y, YUAN F, et al. Locally advanced gastric cancer: total iodine uptake to predict the response of primary lesion to neoadjuvant chemotherapy[J]. J Cancer Res Clin Oncol, 2018, 144(11):2207-2218. doi: 10.1007/s00432-018-2728-z pmid: 30094537
[12]	SHI C, ZHANG H, YAN J, et al. Decreased stage migration rate of early gastric cancer with a new reconstruction algorithm using dual-energy CT images: a preliminary study[J]. Eur Radiol, 2017, 27(2):671-680. doi: 10.1007/s00330-016-4442-z pmid: 27271924
[13]	LI C, SHI C, ZHANG H, et al. Multiple instance learning for computer aided detection and diagnosis of gastric cancer with dual-energy CT imaging[J]. J Biomed Inform, 2015, 57:358-368. doi: 10.1016/j.jbi.2015.08.017 pmid: 26319541
[14]	LENG S, YU L, FLETCHER J G, et al. Maximizing iodine contrast-to-noise ratios in abdominal CT imaging through use of energy domain noise reduction and virtual monoenergetic dual-energy CT[J]. Radiology, 2015, 276(2):562-570. doi: 10.1148/radiol.2015140857 pmid: 25860839
[15]	ALBRECHT M H, TROMMER J, WICHMANN J L, et al. Comprehensive comparison of virtual monoenergetic and linearly blended reconstruction techniques in third-gene-ration dual-source dual-energy computed tomography angiography of the thorax and abdomen[J]. Invest Radiol, 2016, 51(9):582-590. doi: 10.1097/RLI.0000000000000272 URL
[16]	GREFFIER J, FRANDON J, HAMARD A, et al. Impact of iterative reconstructions on image quality and detecta-bility of focal liver lesions in low-energy monochromatic images[J]. Phys Med, 2020, 77:36-42. doi: 10.1016/j.ejmp.2020.07.024 URL
[17]	NODA Y, KAWAI N, NAGATA S, et al. Deep learning image reconstruction algorithm for pancreatic protocol dual-energy computed tomography: image quality and quantification of iodine concentration[J]. Eur Radiol, 2022, 32(1):384-394. doi: 10.1007/s00330-021-08121-3
[18]	SATO M, ICHIKAWA Y, DOMAE K, et al. Deep learning image reconstruction for improving image quality of contrast-enhanced dual-energy CT in abdomen[J]. Eur Radiol, 2022, 32(8):5499-5507. doi: 10.1007/s00330-022-08647-0 pmid: 35238970
[19]	FAIR E, PROFIO M, KULKARNI N, et al. Image quality evaluation in dual-energy CT of the chest, abdomen, and pelvis in obese patients with deep learning image reconstruction[J]. J Comput Assist Tomogr, 2022, 46(4):604-611. doi: 10.1097/RCT.0000000000001316 URL
[20]	常睿敏, 杨阳, 刘宝瑞. 胃癌免疫治疗研究进展[J]. 中国临床研究, 2023, 36(2):161-165.
	CHANG R Y, YANG Y, LIU B R. Advances in immunotherapy for gastric cancer[J]. Chin J Clin Res, 2023, 36(2):161-165.

Characteristics	Advanced gastric cancer（n=23）	Early gastric cancer（n=22）	P value
Age （mean ± SD）	53.2±13.5	59.3±15.1	0.163 1
Sex
Male	12	16	0.155 2
Female	11	6
Location in the stomach
Cardia-Fundus	3	2	0.600 0
Body	5	6
Antrum	15	14
Lauren type
Intestinal	15	16	0.804 9
Diffuse	6	5
Mixed	2	1
Degree of differentiation
Low	12	10	0.458 3
Median	8	9
High	3	3

Methods	Sensitivity	Specificity	AUC (95%CI)	P ^*
FBP	0.913	0.636	0.638 (0.474-0.803)	0.049 8
AV-50	0.652	0.727	0.667 (0.506-0.828)	0.047 7
AV-100	0.609	0.545	0.577 (0.408-0.746)	0.012 3
DLIR-M	0.870	0.864	0.867 (0.751-0.983)	-