Application of artificial intelligence in medical image data processing for digestive tract tumors

doi:10.16150/j.1671-2870.2025.06.005

Abstract

Abstract:

In recent years, with the rapid development of artificial intelligence (AI) algorithm models, a variety of approaches have emerged, such as convolutional neural networks (CNN) algorithms mainly for image classification, decision trees and support vector machine models for decision classification, attention mechanism models for impro-ving identification accuracy, object detection models for lesion identification and localization in images, and semantic segmentation and instance segmentation models for precise lesion segmentation in images. The deep integration of AI-based CNN with medical imaging has significantly improved the efficiency and accuracy of disease diagnosis. With the improvement of digital medicine, the integration points of image data with AI in disease diagnosis and treatment pathways have further expanded. Besides traditional images, (radiology, ultrasonography, endoscopy, pathology), non-classical images, such as surgical resection specimen images and organoid images, are gradually incorporated into the scope of AI research. The deep involvement of AI helps decode hidden information in multi-dimensional data, conti-nuously transforming disease diagnosis and treatment patterns. In the foreseeable future, the integration of AI algorithms with various disease diagnosis and treatment devices will become powerful tools for disease diagnosis, treatment, and even prediction of development trends.

Key words: Traditional medical images, Surgical specimens, Organoids, Artificial intelligence

CLC Number:

R445
R735

YANG Ruixin, YU Yingyan. Application of artificial intelligence in medical image data processing for digestive tract tumors[J]. Journal of Diagnostics Concepts & Practice, 2025, 24(06): 605-612.

Figures/Tables 2

Table1

Table 2

References 32

[1]	PESAPANE F, CODARI M, SARDANELLI F. Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine[J]. Eur Radiol Exp, 2018, 2(1):35. doi: 10.1186/s41747-018-0061-6
[2]	HIRASAWA T, AOYAMA K, TANIMOTO T, et al. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images[J]. Gastric Cancer, 2018, 21(4):653-660. doi: 10.1007/s10120-018-0793-2 pmid: 29335825
[3]	YANG R, YU Y. Artificial convolutional neural network in object detection and semantic segmentation for medical imaging analysis[J]. Front Oncol, 2021, 11:638182. doi: 10.3389/fonc.2021.638182 URL
[4]	SHUKLA P, VERMA A, ABHISHEK, et al. Interpreting SVM for medical images using Quadtree[J]. Multimed Tools Appl, 2020, 79(39-40):29353-29373. doi: 10.1007/s11042-020-09431-2
[5]	NGUYEN THI CAM H, SARLAN A, ARSHAD N I. A hybrid model integrating recurrent neural networks and the semi-supervised support vector machine for identification of early student dropout risk[J]. Peer J Comput Sci, 2024, 10:e2572.
[6]	SCHLEMPER J, OKTAY O, SCHAAP M, et al. Attention gated networks: Learning to leverage salient regions in medical images[J]. Med Image Anal, 2019, 53:197-207. doi: S1361-8415(18)30613-3 pmid: 30802813
[7]	ZHOU Q, ZHOU Y, HOU N, et al. DFA-UNet: dual-stream feature-fusion attention U-Net for lymph node segmentation in lung cancer diagnosis[J]. Front Neurosci, 2024, 18:1448294. doi: 10.3389/fnins.2024.1448294 URL
[8]	LI H, NAN Y, DEL SER J, et al. Large-kernel attention for 3D medical image segmentation[J]. Cognit Comput, 2024, 16(4):2063-2077. doi: 10.1007/s12559-023-10126-7
[9]	VENHUIZEN F G, VAN GINNEKEN B, LIEFERS B, et al. Deep learning approach for the detection and quantification of intraretinal cystoid fluid in multivendor optical coherence tomography[J]. Biomed Opt Express, 2018, 9(4):1545-1569. doi: 10.1364/BOE.9.001545 pmid: 29675301
[10]	HE W, LI C, NIE X, et al. Recognition and detection of aero-engine blade damage based on Improved Cascade Mask R-CNN[J]. Appl Opt, 2021, 60(17):5124-5133. doi: 10.1364/AO.423333 pmid: 34143079
[11]	TIAN Z, ZHANG B, CHEN H, et al. Instance and panoptic segmentation using conditional convolutions[J]. IEEE Trans Pattern Anal Mach Intell, 2023, 45(1):669-680. doi: 10.1109/TPAMI.2022.3145407 URL
[12]	MA X B, XU Q L, LI N, et al. A decision tree model to distinguish between benign and malignant pulmonary nodules on CT scans[J]. Eur Rev Med Pharmacol Sci, 2023, 27(12):5692-5699.
[13]	LUO H, XU G, LI C, et al. Real-time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: a multicentre, case-control, diagnostic study[J]. Lancet Oncol, 2019, 20(12):1645-1654. doi: S1470-2045(19)30637-0 pmid: 31591062
[14]	AN P, YANG D, WANG J, et al. A deep learning method for delineating early gastric cancer resection margin under chromoendoscopy and white light endoscopy[J]. Gastric Cancer, 2020, 23(5):884-892. doi: 10.1007/s10120-020-01071-7 pmid: 32356118
[15]	WICKSTRØM K, KAMPFFMEYER M, JENSSEN R. Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps[J]. Med Image Anal, 2020, 60:101619. doi: 10.1016/j.media.2019.101619 URL
[16]	YANG R, ZHANG J, ZHAN F, et al. Artificial intelligence efficiently predicts gastric lesions, Helicobacter pylori infection and lymph node metastasis upon endoscopic images[J]. Chin J Cancer Res, 2024, 36(5):489-502. doi: 10.21147/j.issn.1000-9604.2024.05.03 URL
[17]	中华医学会肿瘤学分会早诊早治学组, 苗智峰, 徐忠法, 等. 胃癌早诊早治中国专家共识(2023版)[J]. 中华消化外科杂志, 2024, 23(1):23-36.
	Early Diagnosis and Treatment Group, Chinese Society of Oncology, Chinese Medical Association, Miao ZF, Xu ZF, et al. Chinese expert consensus on early diagnosis and treatment of gastric cancer (2023 edition)[J]. Chin J Dig Surg, 2024, 23(1): 23-36.
[18]	杨鋆, 辛城霖, 张忠涛. 中低位直肠癌的精准诊断与规范治疗[J]. 中华消化外科杂志, 2024, 23(1):85-90.
	YANG Y, XIN C L, ZHANG Z T. Precision diagnosis and standardized treatment of midlow rectal cancer[J]. Chin J Dig Surg, 2024, 23(1): 85-90.
[19]	FENG Q X, LIU C, QI L, et al. An intelligent clinical decision support system for preoperative prediction of lymph node metastasis in gastric cancer[J]. J Am Coll Radiol, 2019, 16(7):952-960. doi: 10.1016/j.jacr.2018.12.017 URL
[20]	GAO Y, ZHANG Z D, LI S, et al. Deep neural network-assisted computed tomography diagnosis of metastatic lymph nodes from gastric cancer[J]. Chin Med J (Engl), 2019, 132(23):2804-2811.
[21]	LIU Y, CHEN L, FAN M, et al. Application of AI-assisted MRI for the identification of surgical target areas in pediatric hip and periarticular infections[J]. BMC Musculoskelet Disord, 2024, 25(1):428. doi: 10.1186/s12891-024-07548-1
[22]	YANG R, YAN C, LU S, et al. Tracking cancer lesions on surgical samples of gastric cancer by artificial intelligent algorithms[J]. J Cancer, 2021, 12(21):6473-6483. doi: 10.7150/jca.63879 pmid: 34659538
[23]	MA B, GUO Y, HU W, et al. Artificial intelligence-based multiclass classification of benign or malignant mucosal lesions of the stomach[J]. Front Pharmacol, 2020, 11:572372. doi: 10.3389/fphar.2020.572372 URL
[24]	TUNG C L, CHANG H C, YANG B Z, et al. Identifying pathological slices of gastric cancer via deep learning[J]. J Formos Med Assoc, 2022, 121(12):2457-2464. doi: 10.1016/j.jfma.2022.05.004 URL
[25]	ZHU M, GUO M, LIU C Q, et al. Deep-learning model AIBISI predicts bacterial infection across cancer types based on pathological images[J]. Heliyon, 2023, 9(4):e15400.
[26]	姚金玉, 卢庆苗, 鲁一兵. 甲状腺类器官研究进展[J]. 中华内分泌代谢杂志, 2024, 40(1):73-76.
	YAO J Y, LU Q M, LU Y B. Advances in the research of thyroid organoid[J]. Chin J Endocrinol Metab, 2024, 40(1):73-76.
[27]	黄立颖, 张欢, 李裕明, 等. 胃肠内分泌细胞分化和功能研究进展[J]. 中华内分泌代谢杂志, 2024, 40(6):538-544.
	HUANG L Y, ZHANG H, LI Y M. Enteroendocrine cell differentiation and function: An update[J]. Chin J Endocrinol Metab, 2024, 40(6):538-544.
[28]	BIAN X, LI G, WANG C, et al. A deep learning model for detection and tracking in high-throughput images of organoid[J]. Comput Biol Med, 2021, 134:104490. doi: 10.1016/j.compbiomed.2021.104490 URL
[29]	KASSIS T, HERNANDEZ-GORDILLO V, LANGER R, et al. OrgaQuant: Human intestinal organoid localization and quantification using deep convolutional neural networks[J]. Sci Rep, 2019, 9(1):12479. doi: 10.1038/s41598-019-48874-y pmid: 31462669
[30]	YANG R, DU Y, KWAN W, et al. A quick and reliable image-based AI algorithm for evaluating cellular senescence of gastric organoids[J]. Cancer Biol Med, 2023, 20(7):519-536.
[31]	OKAMOTO T, NATSUME Y, DOI M, et al. Integration of human inspection and artificial intelligence-based morphological typing of patient-derived organoids reveals interpatient heterogeneity of colorectal cancer[J]. Cancer Sci, 2022, 113(8):2693-2703. doi: 10.1111/cas.v113.8 URL
[32]	田捷, 王坤, 董迪, 等. 基于人工智能和医疗大数据的肿瘤荧光手术导航与量化评估策略[J]. 中华消化外科杂志, 2024, 23(4):536-542.
	TIAN J, WANG K, DONG D, et al. Navigation and quantitative evaluation strategies for tumor fluorescent surgery based on artificial intelligence and medical big data[J]. Chin J Dig Surg, 2024, 23(4): 536-542.

AI 模型	算法	功能	参数
CNN	VGG、Inception、ResNet、InceptionResNetV2、DenseNet、EfficientNet、Xception、MobileNet	图像分类	精确度、准确率、召回率、特异性、阳性预测值、阴性预测值、受试者操作特征曲线和曲线下面积
SVM	SVM、S3VM	图像聚类	精确度、准确率、召回率、特异度、阳性预测值、阴性预测值、受试者操作特征曲线和曲线下面积
注意力机制	软注意力、硬注意力	注意力	提高AI模型的训练效果
目标检测	YOLO、SSD、CenterNet、EfficientNet	病变检测	mAP
语义分割	FCN、SegNet、U-Net、V-Net、DeepLab、PSPNet	病变分割	mIoU
实例分割	掩码 R-CNN、级联掩码 R-CNN、YOLACT、CondInst、SOLO	单一病变分割	mIoU

应用	AI 模型	图像类型	功能	评估参数
内镜图像	SSD	彩色内镜图像	早期胃癌检测	mAP
	DeepLab v3+	白光内镜图像	上消化道肿瘤评估	mIoU
	UNet++	彩色内镜图像或白光内镜图像	早期胃癌边缘勾画	mIoU
	FCN-8	白光内镜图像	结直肠息肉分割	mIoU
	EfficientNetB7	白光内镜图像	胃癌与非胃癌、幽门螺旋杆菌感染与非幽门螺旋杆菌感染的分类，淋巴结转移的预测	精确度、准确率、召回率、AUC
放射影像	SVM	CT	淋巴结转移的预测	mIoU
	Faster R-CNN	CT	淋巴结转移的预测	mAP
	R-CNN	MRI	手术目标勾画	mIoU
手术切除标本图像	RFB-SSD ResNet50-PSPNet	胃切除标本图像	病变检测与分割，淋巴结转移的预测	mAP、mIoU
病理图像	InceptionV3	全切片数字图像	正常、慢性胃炎和肠型胃癌的分类	精确度、准确率、召回率、AUC
	YOLOv4	全切片数字图像	胃癌诊断	mAP
	ResNet18	全切片数字图像	幽门螺旋杆菌的预测	精确度、准确率、召回率、AUC
类器官图像	SSD	白光类器官图像	类器官的检测与追踪	mAP
	Faster R-CNN	白光类器官图像	人体肠道类器官的定位与量化	mAP
	CBAM-YOLOv3	白光类器官图像	类器官活力评估	mAP
	U-Net、SVM	白光类器官图像	结直肠癌类器官亚型分类	mAP、mIoU