1
|
Wu R, Qin K, Fang Y, Xu Y, Zhang H, Li W, Luo X, Han Z, Liu S, Li Q. Application of the convolution neural network in determining the depth of invasion of gastrointestinal cancer: a systematic review and meta-analysis. J Gastrointest Surg 2024; 28:538-547. [PMID: 38583908 DOI: 10.1016/j.gassur.2023.12.029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/22/2023] [Revised: 12/16/2023] [Accepted: 12/30/2023] [Indexed: 04/09/2024]
Abstract
BACKGROUND With the development of endoscopic technology, endoscopic submucosal dissection (ESD) has been widely used in the treatment of gastrointestinal tumors. It is necessary to evaluate the depth of tumor invasion before the application of ESD. The convolution neural network (CNN) is a type of artificial intelligence that has the potential to assist in the classification of the depth of invasion in endoscopic images. This meta-analysis aimed to evaluate the performance of CNN in determining the depth of invasion of gastrointestinal tumors. METHODS A search on PubMed, Web of Science, and SinoMed was performed to collect the original publications about the use of CNN in determining the depth of invasion of gastrointestinal neoplasms. Pooled sensitivity and specificity were calculated using an exact binominal rendition of the bivariate mixed-effects regression model. I2 was used for the evaluation of heterogeneity. RESULTS A total of 17 articles were included; the pooled sensitivity was 84% (95% CI, 0.81-0.88), specificity was 91% (95% CI, 0.85-0.94), and the area under the curve (AUC) was 0.93 (95% CI, 0.90-0.95). The performance of CNN was significantly better than that of endoscopists (AUC: 0.93 vs 0.83, respectively; P = .0005). CONCLUSION Our review revealed that CNN is one of the most effective methods of endoscopy to evaluate the depth of invasion of early gastrointestinal tumors, which has the potential to work as a remarkable tool for clinical endoscopists to make decisions on whether the lesion is feasible for endoscopic treatment.
Collapse
Affiliation(s)
- Ruo Wu
- Nanfang Hospital (The First School of Clinical Medicine), Southern Medical University, Guangzhou, Guangdong, China
| | - Kaiwen Qin
- Department of Gastroenterology, Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China
| | - Yuxin Fang
- Department of Gastroenterology, Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China
| | - Yuyuan Xu
- Department of Hepatology Unit and Infectious Diseases, State Key Laboratory of Organ Failure Research, Guangdong Provincial Key Laboratory of Viral Hepatitis Research, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China
| | - Haonan Zhang
- Department of Gastroenterology, Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China
| | - Wenhua Li
- Nanfang Hospital (The First School of Clinical Medicine), Southern Medical University, Guangzhou, Guangdong, China
| | - Xiaobei Luo
- Department of Gastroenterology, Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China
| | - Zelong Han
- Department of Gastroenterology, Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China
| | - Side Liu
- Department of Gastroenterology, Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China; Pazhou Lab, Guangzhou, Guangdong, China
| | - Qingyuan Li
- Department of Gastroenterology, Guangdong Provincial Key Laboratory of Gastroenterology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong, China.
| |
Collapse
|
2
|
Grillo F, Paudice M, Gambella A, Bozzano S, Sciallero S, Puccini A, Lastraioli S, Dono M, Parente P, Vanoli A, Angerilli V, Fassan M, Mastracci L. Evaluating mismatch repair deficiency in colorectal cancer biopsy specimens. Histochem Cell Biol 2023:10.1007/s00418-023-02202-8. [PMID: 37284845 PMCID: PMC10386921 DOI: 10.1007/s00418-023-02202-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/25/2023] [Indexed: 06/08/2023]
Abstract
Mismatch repair (MMR) testing on all new cases of colorectal cancer (CRC) has customarily been preferably performed on surgical specimens, as more tissue is available; however, new clinical trials for the use of immune checkpoint inhibitors in the neoadjuvant setting require MMR testing on biopsy samples. This study aims at identifying advantages, disadvantages and any potential pitfalls in MMR evaluation on biopsy tissue and how to cope with them. The study is prospective-retrospective, recruiting 141 biopsies (86 proficient (p)MMR and 55 deficient (d)MMR) and 97 paired surgical specimens (48 pMMR; 49 dMMR). In biopsy specimens, a high number of indeterminate stains was observed, in particular for MLH1 (31 cases, 56.4%). The main reasons were a punctate nuclear expression of MLH1, relatively weak MLH1 nuclear expression compared to internal controls, or both (making MLH1 loss difficult to interpret), which was solved by reducing primary incubation times for MLH1. A mean of ≥ 5 biopsies had adequate immunostains, compared to ≤ 3 biopsies in inadequate cases. Conversely, surgical specimens rarely suffered from indeterminate reactions, while weaker staining intensity (p < 0.007) for MLH1 and PMS2 and increased patchiness grade (p < 0.0001) were seen. Central artefacts were almost exclusive to surgical specimens. MMR status classification was possible in 92/97 matched biopsy/resection specimen cases, and all of these were concordant (47 pMMR and 45 dMMR). Evaluation of MMR status on CRC biopsy samples is feasible, if pitfalls in interpretation are known, making laboratory-specific appropriate staining protocols fundamental for high-quality diagnoses.
Collapse
Affiliation(s)
- F Grillo
- IRCCS Ospedale Policlinico San Martino, Largo Benzi 10, 16132, Genoa, Italy.
- Pathology Unit, Department of Surgical Sciences and Integrated Diagnostics (DISC), University of Genoa, Genoa, Italy.
| | - M Paudice
- IRCCS Ospedale Policlinico San Martino, Largo Benzi 10, 16132, Genoa, Italy
- Pathology Unit, Department of Surgical Sciences and Integrated Diagnostics (DISC), University of Genoa, Genoa, Italy
| | - A Gambella
- Department of Medical Sciences, University of Turin, Turin, Italy
| | - S Bozzano
- Pathology Unit, Department of Surgical Sciences and Integrated Diagnostics (DISC), University of Genoa, Genoa, Italy
| | - S Sciallero
- Medical Oncology Unit 1, IRCCS Ospedale Policlinico San Martino, 16132, Genoa, Italy
| | - A Puccini
- Medical Oncology and Hematology Unit, IRCCS Humanitas Research Hospital, Humanitas Cancer Center, Rozzano, Milan, Italy
| | - S Lastraioli
- Molecular Diagnostic Unit, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - M Dono
- Molecular Diagnostic Unit, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - P Parente
- Pathology Unit, Fondazione IRCCS Casa Sollievo della Sofferenza, San Giovanni Rotondo, FG, Italy
| | - A Vanoli
- Department of Molecular Medicine, Unit of Anatomic Pathology, University of Pavia, Pavia, Italy
- Anatomic Pathology Unit, Fondazione IRCCS San Matteo Hospital, Pavia, Italy
| | - V Angerilli
- Department of Medicine (DIMED), Surgical Pathology Unit, University Hospital of Padua, Padua, Italy
| | - M Fassan
- Department of Medicine (DIMED), Surgical Pathology Unit, University Hospital of Padua, Padua, Italy
- Veneto Institute of Oncology IOV - IRCCS, Padua, Italy
| | - L Mastracci
- IRCCS Ospedale Policlinico San Martino, Largo Benzi 10, 16132, Genoa, Italy
- Pathology Unit, Department of Surgical Sciences and Integrated Diagnostics (DISC), University of Genoa, Genoa, Italy
| |
Collapse
|
3
|
Swift SL, Duffy S, Lang SH. Impact of tumor heterogeneity and tissue sampling for genetic mutation testing: a systematic review and post hoc analysis. J Clin Epidemiol 2020; 126:45-55. [PMID: 32540382 DOI: 10.1016/j.jclinepi.2020.06.010] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2020] [Accepted: 06/10/2020] [Indexed: 02/07/2023]
Abstract
OBJECTIVE The objective of the study was to identify guidelines to assist systematic reviewers or clinical researchers in identifying sampling bias due to tumor heterogeneity (TH) in solid cancers assayed for somatic mutations. We also assessed current reporting standards to determine the impact of TH on sample bias. STUDY DESIGN AND SETTING We conducted a systematic review searching 13 databases (to January 2019) to identify guidelines. A post hoc analysis was performed using 12 prostate tumor somatic mutation data sets from a previous systematic review to assess reporting on TH. RESULTS Searches identified 2,085 records. No formal guidelines were identified. Forty publications contained incidental recommendations across five major themes: using multiple tumor samples (n = 29), sample purity thresholds (n = 14), using specific sequencing methods (n = 8), using liquid biopsies (n = 4), and microdissection (n = 4). In post hoc analyses, 50% (6 of 12) clearly reported pathology methods. Forty-two percent (5 of 12) did not report pathology results. Forty-two percent (5 of 12) confirmed the pathology of the sample by direct diagnosis rather than inference. Forty-two percent (5 of 12) used multiple samples per patient. Fifty-eight percent (7 of 12) reported on tumor purity (reported ranges 10% to 100%). CONCLUSIONS As precision medicine progresses to the clinic, guidelines are required to help evidence-based decision makers understand how TH may impact sample bias. Authors need to clearly report pathology methods and results and tumor purity methods and results.
Collapse
Affiliation(s)
| | - Steve Duffy
- Kleijnen Systematic Reviews Ltd, Escrick, York YO19 6FD, UK
| | - Shona H Lang
- Kleijnen Systematic Reviews Ltd, Escrick, York YO19 6FD, UK.
| |
Collapse
|
4
|
Nishitani M, Yoshida N, Tsuji S, Masunaga T, Hirai H, Miyajima S, Dejima A, Nakashima T, Wakita S, Takemura K, Minato H, Kaneko S, Doyama H. Optimal number of endoscopic biopsies for diagnosis of early gastric cancer. Endosc Int Open 2019; 7:E1683-E1690. [PMID: 31803818 PMCID: PMC6887641 DOI: 10.1055/a-1007-1730] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/30/2019] [Accepted: 08/05/2019] [Indexed: 02/06/2023] Open
Abstract
Background and study aims No recommendations are available for optimal number of endoscopic biopsies for early gastric cancer (GC), and whether detection of early GC is improved by increasing the number of biopsy is unclear. We therefore evaluated the relationship between number of biopsies and diagnostic accuracy. Materials and methods We retrospectively evaluated 858 early GCs (623 from endoscopic submucosal dissection and 235 surgical specimens), which we classified as obtained after one, two, or three or more biopsies. We assessed diagnostic accuracy by number of biopsies, and in subgroups by tumor diameter, gross type, and surface color. Results Almost half the lesions were obtained after one biopsy each, 30 % after two biopsies, and 20 % after three or more biopsies. Although diagnostic accuracy increased with biopsy number, it was significantly greater for the two-biopsy group than the one-biopsy group, (92.5 % vs. 83.9 %, P = 0.0009), but did not significantly differ between the two- and three or more-biopsy groups. This finding was seen when tumors were evaluated by size, but not by elevated type and surface color, for which more biopsies did not improve diagnostic accuracy. Multivariate analysis demonstrated that two or more biopsies was the independent significant factors for diagnostic accuracy. Conclusions Two biopsies are the optimal number required to diagnose early GC.
Collapse
Affiliation(s)
- Masaki Nishitani
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan,Department of Gastroenterology, Kanazawa University Hospital, Kanazawa, Japan
| | - Naohiro Yoshida
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan,Corresponding author Naohiro Yoshida Department of GastroenterologyIshikawa Prefectural Central Hospital2-1 Kuratsukihigashi, KanazawaIshikawa 920-8530Japan+81-76-238-2337
| | - Shigetsugu Tsuji
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Teppei Masunaga
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Hirokazu Hirai
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Saori Miyajima
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Akihiro Dejima
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Takashi Nakashima
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Shigenori Wakita
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Kenichi Takemura
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Hiroshi Minato
- Department of Diagnostic Pathology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Shuichi Kaneko
- Department of Gastroenterology, Kanazawa University Hospital, Kanazawa, Japan
| | - Hisashi Doyama
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| |
Collapse
|
5
|
Gotoda T, Uedo N, Yoshinaga S, Tanuma T, Morita Y, Doyama H, Aso A, Hirasawa T, Yano T, Uchita K, Ho SH, Hsieh PH. Basic principles and practice of gastric cancer screening using high-definition white-light gastroscopy: Eyes can only see what the brain knows. Dig Endosc 2016; 28 Suppl 1:2-15. [PMID: 26836611 DOI: 10.1111/den.12623] [Citation(s) in RCA: 28] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/12/2016] [Accepted: 01/26/2016] [Indexed: 12/17/2022]
Abstract
Endoscopic diagnosis of gastrointestinal tumors consists of the following processes: (i) detection; (ii) differential diagnosis; and (iii) quantitative diagnosis (size and depth) of a lesion. Although detection is the first step to make a diagnosis of the tumor, the lesion can be overlooked if an endoscopist has no knowledge of what an early-stage 'superficial lesion' looks like. In recent years, image-enhanced endoscopy has become common, but white-light endoscopy (WLI) is still the first step for detection and characterization of lesions in general clinical practice. Settings and practice of routine esophagogastroduodenoscopy (EGD) such as use of antispasmodics, number of endoscopic images taken, and observational procedure are customarily decided in each facility in each country and are not well standardized. Therefore, in the present article, we attempted to outline currently available evidence and actual Japanese practice on gastric cancer screening using WLI, and provide tips for detecting EGC during routine EGD which could become the basis of future research.
Collapse
Affiliation(s)
- Takuji Gotoda
- Division of Gastroenterology and Hepatology, Department of Medicine, Nihon University School of Medicine, Tokyo, Japan
| | - Noriya Uedo
- Department of Gastrointestinal Oncology, Osaka Medical Center for Cancer and Cardiovascular Disease, Osaka, Japan
| | | | - Tokuma Tanuma
- Center for Gastroenterology, Teine Keijinkai Hospital, Kobe Hospital, Sapporo, Japan
| | - Yoshinori Morita
- Department of Gastroenterology, Kobe University School of Medicine, Kobe, Japan
| | - Hisashi Doyama
- Department of Gastroenterology, Ishikawa Prefectural Central Hospital, Kanazawa, Japan
| | - Akira Aso
- Depatment of Medicine and Bioregulatory Science, Graduate School of Science, Kyushu University, Fukuoka, Japan
| | - Toshiaki Hirasawa
- Cancer Institute Hospital of the Japanese Foundation of Cancer Research, National Cancer Center Hospital East, Kashiwa, Japan
| | - Tomonori Yano
- Endoscopy division, Department of Gastroterology, National Cancer Center Hospital East, Chiba, Japan
| | - Kunihisa Uchita
- Department of Gastroenterology, Kochi Red Cross Hospital, Kochi, Japan
| | - Shiaw-Hooi Ho
- Division of Gastroenterology and Hepatology, Department of Medicine, University of Malaya, Kuala Lumpur, Malaysia
| | - Ping-Hsin Hsieh
- Department of Gastroenterology and Hepatology, Chi-Mei Medical Center, Tainan, Taiwan
| |
Collapse
|