|Table of Contents|

Evaluation of the effect of automatic detection model for lymphovascular infiltration inmultiple tumors

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2023 19
Page:
3572-3577
Research Field:
Publishing date:

Info

Title:
Evaluation of the effect of automatic detection model for lymphovascular infiltration inmultiple tumors
Author(s):
WANG Chunbao1; DING Caixia2; LUO Ali3; LI Hansheng4; YANG Zhe1; LIAN Jie1; CUI Lei4; ZHANG Guanjun1
1.Department of Pathology,the First Affiliated Hospital of Xi'an Jiaotong University,Shaanxi Xi'an 710061,China;2.Department of Pathology,Shaanxi Provincial Tumor Hospital,Shaanxi Xi'an 710061,China；3.Department of Pathology,Xi'an Chest Hospital,Shaanxi Xi'an 710100,China;4.School of Information Science and Technology,Northwest University,Shaanxi Xi'an 710100,China.
Keywords:
pathology; cancer; lymphovascular infiltration; Algorithm; artificia lintelligence
PACS:
R733.4
DOI:
10.3969/j.issn.1672-4992.2023.19.007
Abstract:
Objective:To test and analyze the detection effect and generalization ability of the global library(GLB) target detection model of lymphovascular infiltration(LVI).Methods:131 cases of LVI positive and negative from the Department of Pathology of the First Affiliated Hospital of Xi'an Jiaotong University were randomly selected.All slides were stained with HE and D2-40 immunohistochemistry.The experimental group includes three groups:pathologists' manual reading group,algorithm group and algorithm assisted pathologists.The LVI results and detection time of the three groups were counted respectively.Results:The comparison of the consistency among pathologists,pure algorithm and algorithm assisted pathologists showed that in 131 cases,the consistency Kappa values under the three modes were good(0.709,0.786,0.796),slight(0.208) and moderate(0.412),respectively.The most common reason for pathologists' errors is missed diagnosis(n=8),and the second is due to IHC staining problems(including 6 cases of insufficient staining,while 3 cases of significant non staining).The rest included 2 tissue fissures,1 small vein(D2-40 not stained),and 3 unknown causes.On the one hand,the reason for the error of pure algorithm judgment is due to pathological section or staining technology,such as free small tissues(15/63),non-specific or insufficient staining(14/63),bubbles(8/63),etc.On the other hand,the similarity between the tissue morphology of some LVIs and the detection targets leads to algorithm misjudgment,such as glands(14/63),blood vessels(13/63),and peripheral small nerves(5/63).The time spent in the three modes is 59.28 s,82.40 s and 10.43 s respectively.Conclusion:Although our results confirm the ability of algorithm assisted pathological diagnosis to improve diagnostic efficiency,the implementation of algorithm assisted diagnosis should fully consider the quality control of pathological slides and the necessity of developing multi-level design,and try to accumulate large data to cover multiple target analogues.

References:

[1]NARIMATSU T,KAMBARA T,ABE H,et al.5-fluorouracil-based adjuvant chemotherapy improves the clinical outcomes of patients with lymphovascular invasion of upper urinary tract cancer and low expression of dihydropyrimidine dehydrogenase［J］.Oncology Letters,2019,17(5):4429-4436.
[2]PETERS EEM,BARTOSCHA C,MCCLUGGAGE WG,et al.Reproducibility of lymphovascular space invasion(LVSI) assessment in endometrial cancer［J］.Histopathology,2019,75(1):128-136.
[3]KAHN HJ,MARKS A.A new monoclonal antibody,D2-40,for detection of lymphatic invasion in primary tumors［J］.Laboratory Investigation,2002,82(9):1255-1257.
[4]FAN L,MAC MT,FRISHBERG DP,et al.Interobserver and intraobserver variability in evaluating vascular invasion in hepatocellular carcinoma［J］.Journal of Gastroenterology and Hepatology,2010,25(9):1556-1561.
[5]HARRIS EI,LEWIN DN,WANG HL,et al.Lymphovascular invasion in colorectal cancer［J］.The American Journal of Surgical Pathology,2008,32(12):1816-1821.
[6]GAVRIELIDES MA,GALLAS BD,LENZ P,et al.Observer variability in the interpretation of HER2/neu immunohistochemical expression with unaided and computer-aided digital microscopy［J］.Archives of Pathology & Laboratory Medicine,2011,135(2):233-242.
[7]KOELZER VH,KOELZER VH,SIRINUKUNWATTANA K,et al.Precision immunoprofiling by image analysis and artificial intelligence［J］.Virchows Archiv,2019,474(4):511-522.
[8]STEINER DF,MACDONALD R,LIU Y,et al.Impact of deep learning assistance on the histopathologic review of lymph nodes for metastatic breast cancer［J］.The American Journal of Surgical Pathology,2018,42(12):1636-1646.
[9]LI H,FENG J,KANG B,et al.Global bank:A guided pathway of encoding and decoding for pathological image analysis［C］.2019 IEEE international conference on bioinformatics and biomedicine(BIBM),San Diego,California,USA:IEEE,2019.
[10]GHOSH A,SIRINUKUNWATTANA K,KHALID AN,et al.The potential of artificial intelligence to detect lymphovascular invasion in testicular cancer［J］.Cancers(Basel),2021,13(6):1325.
[11]BAXI V,EDWARDS R,MONTALTO M,et al.Digital pathology and artificial intelligence in translational medicine and clinical practice［J］.Mod Pathol,2022,35(1):23-32.
[12]DU M,CHEN L,CHENG Y,et al.Tumor budding and other risk factors of lymph node metastasis in submucosal early gastric carcinoma［J］.The American Journal of Surgical Pathology,2019,43(8):1074-1082.
[13]GOTO A,NISHIKAWA J,HIDEURA E,et al.Lymph node metastasis can be determined by just tumor depth and lymphovascular invasion in early gastric cancer patients after endoscopic submucosal dissection［J］.European Journal of Gastroenterology & Hepatology,2017,29(12):1346-1350.
[14]PARK JW,AHN S,LEE H,et al.Predictive factors for lymph node metastasis in early gastric cancer with lymphatic invasion after endoscopic resection［J］.Surgical Endoscopy,2017,31(11):4419-4424.
[15]ARIGAMI T,NATSUGOE S,UENOSONO Y,et al.Lymphatic invasion using D2-40 monoclonal antibody and its relationship to lymph node micrometastasis in pN0 gastric cancer［J］.British Journal of Cancer,2005,93(6):688-693.
[16]RONNOW C,ARTHURSSON V,TOTH E,et al.Lymphovascular infiltration,not depth of invasion,is the critical risk factor of metastases in early colorectal cancer［J］.Annals of Surgery,2022,75(1):e148-e154.
[17]WADA H,SHIOZAWA M,SUGANO N,et al.Lymphatic invasion identified with D2-40 immunostaining as a risk factor of nodal metastasis in T1 colorectal cancer［J］.International Journal of Clinical Oncology,2013,18(6):1025-1031.
[18]AKAGI Y,ADACHI Y,OHCHI T,et al.Prognostic impact of lymphatic invasion of colorectal cancer:a single-center analysis of 1,616 patients over 24 years［J］.Anticancer Res,2013,33(7):2965-2970.
[19]MOON Y,PARK JK,LEE KY,et al.Lymphatic invasion is a more significant prognostic factor than visceral pleural invasion in non-small cell lung cancer with tumours of 3 cm or less［J］.Respirology,2017,22(6):1179-1184.
[20]林志强.非小细胞肺癌纵隔淋巴结转移风险模型的构建及预测效能的初步验证［J］.现代肿瘤医学，2021,29(18):1328-1331. LIN ZQ.The establishment of a risk model for mediastinal lymph node metastasis in non-small cell lung cancer and preliminary validation of its predictive efficacy［J］.Modern Oncology,2021,29(18):1328-1331.
[21]NIEMIEC JA,ADAMCZYK A,AMBICKA A,et al.Prognostic role of lymphatic vessel density and lymphovascular invasion in chemotherapy-naive and chemotherapy-treated patients with invasive breast cancer［J］.American Journal of Translational Research,2017,9(3):1435-1447.
[22]MOHAMMED RAA,MENON S,MARTIN SG,et al.Prognostic significance of lymphatic invasion in lymph node-positive breast carcinoma:findings from a large case series with long-term follow-up using immunohistochemical endothelial marker［J］.Modern Pathology,2014,27(12):1568-1577.
[23]LITJENS G,SANCHEZ CI,TIMOFEEVA N,et al.Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis［J］.Scientific Reports,2016,6:26286.

Memo

Memo:
陕西省肿瘤医院2022年院内国家自然科学基金孵育项目(编号：SC222710)
Last Update: 2023-08-31