1
|
Tao Y, Fang L, Qin G, Xu Y, Zhang S, Zhang X, Du S. Efficiency of endoscopic artificial intelligence in the diagnosis of early esophageal cancer. Thorac Cancer 2024; 15:1296-1304. [PMID: 38685604 PMCID: PMC11147664 DOI: 10.1111/1759-7714.15261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2023] [Revised: 02/03/2024] [Accepted: 02/06/2024] [Indexed: 05/02/2024] Open
Abstract
BACKGROUND The accuracy of artificial intelligence (AI) and experts in diagnosing early esophageal cancer (EC) and its infiltration depth was summarized and analyzed, thus identifying the advantages of AI over traditional manual diagnosis, with a view to more accurately assisting doctors in evaluating the patients' conditions and improving their cure and survival rates. METHODS The PubMed, EMBASE, Cochrane, Google, and CNKI databases were searched for relevant literature related to AI diagnosis of early EC and its invasion depth published before August 2023. Summary analysis of pooled sensitivity, specificity, summary receiver operating characteristics (SROC) and area under the curve (AUC) of AI in diagnosing early EC were performed, and Review Manager and Stata were adopted for data analysis. RESULTS A total of 19 studies were enrolled with a low to moderate total risk of bias. The pooled sensitivity of AI for diagnosing early EC was markedly higher than that of novices and comparable to that of endoscopists. Moreover, AI predicted early EC with markedly higher AUCs than novices and experts (0.93 vs. 0.74 vs. 0.89). In addition, pooled sensitivity and specificity in the diagnosis of invasion depth in early EC were higher than that of experts, with AUCs of 0.97 and 0.92, respectively. CONCLUSION AI-assistance can diagnose early EC and its infiltration depth more accurately, which can help in its early intervention and the customization of personalized treatment plans. Therefore, AI systems have great potential in the early diagnosis of EC.
Collapse
Affiliation(s)
- Yongkang Tao
- Department of GastroenterologyChina‐Japan Friendship HospitalBeijingChina
| | - Long Fang
- Department of GastroenterologyChina‐Japan Friendship HospitalBeijingChina
| | - Geng Qin
- Department of GastroenterologyChina‐Japan Friendship HospitalBeijingChina
| | - Yingying Xu
- Department of GastroenterologyChina‐Japan Friendship HospitalBeijingChina
| | - Shuang Zhang
- Beijing University of Chinese MedicineBeijingChina
| | | | - Shiyu Du
- Department of GastroenterologyChina‐Japan Friendship HospitalBeijingChina
| |
Collapse
|
2
|
Murakami D, Yamato M, Nishino T, Arai M. Comprehensive screening for superficial oesophageal squamous cell carcinoma and precancerous lesions. Lancet Gastroenterol Hepatol 2024; 9:291-292. [PMID: 38460535 DOI: 10.1016/s2468-1253(24)00002-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/03/2024] [Accepted: 01/04/2024] [Indexed: 03/11/2024]
Affiliation(s)
- Daisuke Murakami
- Department of Gastroenterology, Yachiyo Medical Center, Tokyo Women's Medical University, Chiba 276-8524, Japan; Institute of Advanced Biomedical Engineering and Science, Tokyo Women's Medical University, Chiba 276-8524, Japan.
| | - Masayuki Yamato
- Institute of Advanced Biomedical Engineering and Science, Tokyo Women's Medical University, Chiba 276-8524, Japan
| | - Takayoshi Nishino
- Department of Gastroenterology, Yachiyo Medical Center, Tokyo Women's Medical University, Chiba 276-8524, Japan
| | - Makoto Arai
- Department of Gastroenterology, Yachiyo Medical Center, Tokyo Women's Medical University, Chiba 276-8524, Japan
| |
Collapse
|
3
|
Ma H, Ma X, Yang C, Niu Q, Gao T, Liu C, Chen Y. Development and evaluation of a program based on a generative pre-trained transformer model from a public natural language processing platform for efficiency enhancement in post-procedural quality control of esophageal endoscopic submucosal dissection. Surg Endosc 2024; 38:1264-1272. [PMID: 38097750 DOI: 10.1007/s00464-023-10620-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2023] [Accepted: 11/28/2023] [Indexed: 02/23/2024]
Abstract
BACKGROUND Post-procedural quality control of endoscopic submucosal dissection (ESD) is emphasized in guidelines. However, this process can be tedious and time-consuming. Recently, a pre-training model called generative pre-trained transformer (GPT) on a public natural language processing platform has emerged and garnered significant attention, whose capabilities align well with the post-procedural quality control process and have the potential to streamline it. Therefore, we developed a simple program utilizing this platform and evaluated its performance. METHODS Esophageal ESDs were retrospectively included. The manual quality control process was performed and act as reference standard. GPT's prompt was optimized through multiple iterations. A Python program was developed to automatically submit prompt with pathological report of each ESD procedure and collect quality control information provided by GPT. Its performance on quality control was evaluated with accuracy, precision, recall, and F-1 score. RESULTS 165 cases were involved into the dataset, of which 5 were utilized as the prompt optimization dataset and 160 as the validation dataset. Definitive prompt was achieved through seven iterations. Time spent on the validation dataset by GPT was 13.47 ± 2.43 min. Accuracies of pathological diagnosis, invasion depth, horizontal margin, vertical margin, vascular invasion, and lymphatic invasion of the quality control program were (0.940, 0.952) (95% CI), (0.925, 0.945) (95% CI), 0.931, 1.0, and 1.0, respectively. Precisions were (0.965, 0.969) (95% CI), (0.934, 0.954) (95% CI), and 0.957 for pathological diagnosis, invasion depth, and horizontal margin, respectively. Recalls were (0.940, 0.952) (95% CI), (0.925, 0.945) (95% CI), and 0.931 for factors as mentioned, respectively. F1-score were (0.945, 0.957) (95% CI), (0.928, 0.948) (95% CI), and 0.941 for factors as mentioned, respectively. CONCLUSIONS This quality control program was qualified of post-procedural quality control of esophageal ESDs. GPT can be easily applied to this quality control process and reduce workload of the endoscopists.
Collapse
Affiliation(s)
- Huaiyuan Ma
- Department of Gastroenterology and Hepatology, Binzhou Medical University Hospital, Binzhou, 256603, Shandong, China
- Digestive Disease Research Institute of Binzhou Medical University Hospital, Binzhou, Shandong, China
| | - Xingbin Ma
- Department of Gastroenterology and Hepatology, Binzhou Medical University Hospital, Binzhou, 256603, Shandong, China
- Digestive Disease Research Institute of Binzhou Medical University Hospital, Binzhou, Shandong, China
| | - Chunxiao Yang
- Department of Gastroenterology and Hepatology, Binzhou Medical University Hospital, Binzhou, 256603, Shandong, China
- Digestive Disease Research Institute of Binzhou Medical University Hospital, Binzhou, Shandong, China
| | - Qiong Niu
- Department of Gastroenterology and Hepatology, Binzhou Medical University Hospital, Binzhou, 256603, Shandong, China
- Digestive Disease Research Institute of Binzhou Medical University Hospital, Binzhou, Shandong, China
| | - Tao Gao
- Endoscopy Center of Binzhou Medical University Hospital, Binzhou, Shandong, China
| | - Chengxia Liu
- Department of Gastroenterology and Hepatology, Binzhou Medical University Hospital, Binzhou, 256603, Shandong, China.
- Digestive Disease Research Institute of Binzhou Medical University Hospital, Binzhou, Shandong, China.
- Endoscopy Center of Binzhou Medical University Hospital, Binzhou, Shandong, China.
| | - Yan Chen
- Department of Gastroenterology and Hepatology, Binzhou Medical University Hospital, Binzhou, 256603, Shandong, China.
- Digestive Disease Research Institute of Binzhou Medical University Hospital, Binzhou, Shandong, China.
- Endoscopy Center of Binzhou Medical University Hospital, Binzhou, Shandong, China.
| |
Collapse
|
4
|
Pan Y, He L, Chen W, Yang Y. The current state of artificial intelligence in endoscopic diagnosis of early esophageal squamous cell carcinoma. Front Oncol 2023; 13:1198941. [PMID: 37293591 PMCID: PMC10247226 DOI: 10.3389/fonc.2023.1198941] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/02/2023] [Accepted: 05/16/2023] [Indexed: 06/10/2023] Open
Abstract
Esophageal squamous cell carcinoma (ESCC) is a common malignant tumor of the digestive tract. The most effective method of reducing the disease burden in areas with a high incidence of esophageal cancer is to prevent the disease from developing into invasive cancer through screening. Endoscopic screening is key for the early diagnosis and treatment of ESCC. However, due to the uneven professional level of endoscopists, there are still many missed cases because of failure to recognize lesions. In recent years, along with remarkable progress in medical imaging and video evaluation technology based on deep machine learning, the development of artificial intelligence (AI) is expected to provide new auxiliary methods of endoscopic diagnosis and the treatment of early ESCC. The convolution neural network (CNN) in the deep learning model extracts the key features of the input image data using continuous convolution layers and then classifies images through full-layer connections. The CNN is widely used in medical image classification, and greatly improves the accuracy of endoscopic image classification. This review focuses on the AI-assisted diagnosis of early ESCC and prediction of early ESCC invasion depth under multiple imaging modalities. The excellent image recognition ability of AI is suitable for the detection and diagnosis of ESCC and can reduce missed diagnoses and help endoscopists better complete endoscopic examinations. However, the selective bias used in the training dataset of the AI system affects its general utility.
Collapse
Affiliation(s)
- Yuwei Pan
- Department of Gastroenterology, Chongqing University Cancer Hospital, Chongqing, China
| | - Lanying He
- Department of Gastroenterology, Chongqing University Cancer Hospital, Chongqing, China
| | - Weiqing Chen
- Department of Gastroenterology, Chongqing University Cancer Hospital, Chongqing, China
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, China
| | - Yongtao Yang
- Department of Gastroenterology, Chongqing University Cancer Hospital, Chongqing, China
- Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment, Chongqing University Cancer Hospital, Chongqing, China
| |
Collapse
|
5
|
Tsunoda M, Miura Y, Osawa H, Nagayama M, Kagaya Y, Funayama Y, Kobayashi T, Togashi M, Hayashi H, Hiraoka Y, Nomoto Y, Iwashita C, Ino Y, Takahashi H, Fukuda H, Lefor AK, Yamamoto H. Impact of linked color imaging and blue laser imaging on the diagnosis of esophageal squamous cell carcinoma in iodine unstained areas. Kaohsiung J Med Sci 2023; 39:533-543. [PMID: 36810969 DOI: 10.1002/kjm2.12660] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2022] [Revised: 01/09/2023] [Accepted: 01/18/2023] [Indexed: 02/24/2023] Open
Abstract
The pink color sign in iodine unstained areas is useful to differentiate esophageal squamous cell carcinoma (ESCC) from other lesions. However, some ESCCs have obscure color findings which affect the ability of endoscopists to differentiate these lesions and determine the resection line. Using white light imaging (WLI), linked color imaging (LCI) and blue laser imaging (BLI), 40 early ESCCs were retrospectively evaluated using images before and after iodine staining. Visibility scores for ESCC by expert and non-expert endoscopists were compared using these three modalities and color differences measured for malignant lesions and surrounding mucosa. BLI had the highest score and color difference without iodine staining. Each determination with iodine was much higher than without iodine regardless of the modality. With iodine, ESCC mainly appeared pink, purple and green using WLI, LCI and BLI, respectively and visibility scores determined by non-experts and experts were significantly higher for LCI (both p < 0.001) and BLI (p = 0.018 and p < 0.001) than for WLI. The score with LCI was significantly higher than with BLI among non-experts (p = 0.035). With iodine, the color difference using LCI was twice that with WLI and one with BLI was significantly larger than with WLI (p < 0.001). These greater tendencies were found regardless of location, depth of cancer or intensity of pink color using WLI. In conclusion, areas of ESCC unstained by iodine were easily recognized using LCI and BLI. Visibility of these lesions is excellent even by non-expert endoscopists, suggesting that this method is useful to diagnose ESCC and determine the resection line.
Collapse
Affiliation(s)
- Masato Tsunoda
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Yoshimasa Miura
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Hiroyuki Osawa
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Manabu Nagayama
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Yuka Kagaya
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Yohei Funayama
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Takuma Kobayashi
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Mami Togashi
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Hiroki Hayashi
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Yuji Hiraoka
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Yoshie Nomoto
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Chihiro Iwashita
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Yuji Ino
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Haruo Takahashi
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | - Hisashi Fukuda
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| | | | - Hironori Yamamoto
- Division of Gastroenterology, Department of Medicine, Jichi Medical University, Shimotsuke, Japan
| |
Collapse
|
6
|
Ogasawara N, Kikuchi D, Tanaka M, Ochiai Y, Okamura T, Hayasaka J, Suzuki Y, Mitsunaga Y, Nomura K, Odagiri H, Yamashita S, Matsui A, Hoteya S. Comprehensive risk evaluation for metachronous carcinogenesis after endoscopic submucosal dissection of superficial pharyngeal squamous cell carcinoma. Esophagus 2022; 19:460-468. [PMID: 35099639 DOI: 10.1007/s10388-022-00907-8] [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: 09/15/2021] [Accepted: 01/23/2022] [Indexed: 02/03/2023]
Abstract
BACKGROUND Pharyngeal squamous cell carcinoma (PSCC) is associated with a high likelihood of metachronous carcinogenesis, which is known to have a poor prognosis. This study aimed to identify comprehensive risk evaluation indicators for metachronous carcinogenesis after endoscopic submucosal dissection (ESD) of superficial PSCC. METHODS The risk of metachronous carcinogenesis was evaluated in 144 patients with superficial PSCC (with no history of PSCC or esophageal squamous cell carcinoma) who underwent initial ESD from 2008 to 2020. Multiple lugol-voiding lesions (LVLs) in the background pharyngeal and esophageal epithelium were evaluated as endoscopic indicators. The hemoglobin, albumin, lymphocyte, and platelet (HALP) score was analyzed as a serum marker. RESULTS The median follow-up period was 4.3 years. The coincidence rate for pharyngeal and esophageal LVL grade was 55%. The cumulative 3-year metachronous PSCC rate was 18.9%. The cumulative 3-year second metachronous PSCC rate was 43.9%. Forward stepwise multivariate Cox proportional hazards regression analysis identified pharyngeal LVL grade and a lower HALP score as significant independent predictors. Pharyngeal LVL grade was superior to esophageal LVL grade as a predictor of metachronous PSCC. A lower HALP score was significantly associated with younger age in forward stepwise multivariate logistic regression analysis. CONCLUSIONS Patients with a history of superficial PSCC remain at risk for metachronous carcinogenesis over time, and long-term follow-up is imperative. Comprehensive evaluation of endoscopic features with a novel serum marker, namely, the HALP score, can help predict metachronous carcinogenesis.
Collapse
Affiliation(s)
- Nobuhiko Ogasawara
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Daisuke Kikuchi
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan.
| | - Masami Tanaka
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Yorinari Ochiai
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Takayuki Okamura
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Junnosuke Hayasaka
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Yugo Suzuki
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Yutaka Mitsunaga
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Kosuke Nomura
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Hiroyuki Odagiri
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Satoshi Yamashita
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Akira Matsui
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| | - Shu Hoteya
- Department of Gastroenterology, Toranomon Hospital, 2-2-2 Toranomon, Minato-ku, Tokyo, 105-0001, Japan
| |
Collapse
|
7
|
Yang X, Wang H, Dong Q, Xu Y, Liu H, Ma X, Yan J, Li Q, Yang C, Li X. An artificial intelligence system for distinguishing between gastrointestinal stromal tumors and leiomyomas using endoscopic ultrasonography. Endoscopy 2022; 54:251-261. [PMID: 33827140 DOI: 10.1055/a-1476-8931] [Citation(s) in RCA: 17] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 04/07/2021] [Indexed: 12/18/2022]
Abstract
BACKGROUND Gastrointestinal stromal tumors (GISTs) and gastrointestinal leiomyomas (GILs) are the most common subepithelial lesions (SELs). All GISTs have malignant potential; however, GILs are considered benign. Current imaging cannot effectively distinguish GISTs from GILs. We aimed to develop an artificial intelligence (AI) system to differentiate these tumors using endoscopic ultrasonography (EUS). METHODS The AI system was based on EUS images of patients with histologically confirmed GISTs or GILs. Participants from four centers were collected to develop and retrospectively evaluate the AI-based system. The system was used when endosonographers considered SELs to be GISTs or GILs. It was then used in a multicenter prospective diagnostic test to clinically explore whether joint diagnoses by endosonographers and the AI system can distinguish between GISTs and GILs to improve the total diagnostic accuracy for SELs. RESULTS The AI system was developed using 10 439 EUS images from 752 participants with GISTs or GILs. In the prospective test, 132 participants were histologically diagnosed (36 GISTs, 44 GILs, and 52 other types of SELs) among 508 consecutive subjects. Through joint diagnoses, the total accuracy of endosonographers in diagnosing the 132 histologically confirmed participants increased from 69.7 % (95 % confidence interval [CI] 61.4 %-76.9 %) to 78.8 % (95 %CI 71.0 %-84.9 %; P = 0.01). The accuracy of endosonographers in diagnosing the 80 participants with GISTs or GILs increased from 73.8 % (95 %CI 63.1 %-82.2 %) to 88.8 % (95 %CI 79.8 %-94.2 %; P = 0.01). CONCLUSIONS We developed an AI-based EUS diagnostic system that can effectively distinguish GISTs from GILs and improve the diagnostic accuracy of SELs.
Collapse
Affiliation(s)
- Xintian Yang
- Department of Pediatric Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China.,Shandong Key Laboratory of Digital Medicine and Computer Assisted Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Han Wang
- Department of Pathology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen, China
| | - Qian Dong
- Department of Pediatric Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China.,Shandong Key Laboratory of Digital Medicine and Computer Assisted Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Yonghong Xu
- Department of Gastroenterology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Hua Liu
- Department of Gastroenterology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Xiaoying Ma
- Department of Gastroenterology, Qingdao Municipal Hospital, Qingdao, China
| | - Jing Yan
- Department of Gastroenterology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Qian Li
- Department of Gastroenterology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Chenyu Yang
- Department of Pediatric Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China.,Shandong Key Laboratory of Digital Medicine and Computer Assisted Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Xiaoyu Li
- Department of Gastroenterology, The Affiliated Hospital of Qingdao University, Qingdao, China
| |
Collapse
|