Artificial intelligence diagnostic system predicts multiple Lugol-voiding lesions in the esophagus and patients at high risk for esophageal squamous cell carcinoma

Artificial intelligence in gastrointestinal cancer research: Image learning advances and applications

With the rapid advancement of artificial intelligence (AI) technologies, including deep learning, large language models, and neural networks, these methodologies are increasingly being developed and integrated into cancer research. Gastrointestinal tumors are characterized by complexity and heterogeneity, posing significant challenges for early detection, diagnostic accuracy, and the development of personalized treatment strategies. The application of AI in digestive oncology has demonstrated its transformative potential. AI not only alleviates the diagnostic burden on clinicians, but it improves tumor screening sensitivity, specificity, and accuracy. Additionally, AI aids the detection of biomarkers such as microsatellite instability and mismatch repair, supports intraoperative assessments of tumor invasion depth, predicts treatment responses, and facilitates the design of personalized treatment plans to potentially significantly enhance patient outcomes. Moreover, the integration of AI with multiomics analyses and imaging technologies has led to substantial advancements in foundational research on the tumor microenvironment. This review highlights the progress of AI in gastrointestinal oncology over the past 5 years with focus on early tumor screening, diagnosis, molecular marker identification, treatment planning, and prognosis predictions. We also explored the potential of AI to enhance medical imaging analyses to aid tumor detection and characterization as well as its role in automating and refining histopathological assessments.

Role of Artificial Intelligence in the Detection and Management of Premalignant and Malignant Lesions of the Esophagus and Stomach

The advent of artificial intelligence (AI) and deep learning algorithms, particularly convolutional neural networks, promises to address pitfalls, bridging the care for patients at high risk with improved detection (computer-aided detection [CADe]) and characterization (computer-aided diagnosis [CADx]) of lesions. This review describes the available artificial intelligence (AI) technology and the current data on AI tools for screening esophageal squamous cell cancer, Barret's esophagus-related neoplasia, and gastric cancer. These tools outperformed endoscopists in many situations. Recent randomized controlled trials have demonstrated the successful application of AI tools in clinical practice with improved outcomes.

Randomized controlled trial of an artificial intelligence diagnostic system for the detection of esophageal squamous cell carcinoma in clinical practice

BACKGROUND

Artificial intelligence (AI) has made remarkable progress in image recognition using deep learning systems. It has been used to detect esophageal squamous cell carcinoma (ESCC); however, none of the previous reports were investigations in a clinical setting, being retrospective in design. We therefore conducted this trial to determine how AI can help endoscopists detect ESCC in a clinical setting.

METHODS

This was a prospective, single-center, exploratory, and randomized controlled trial. High risk patients with ESCC undergoing screening or surveillance esophagogastroduodenoscopy were enrolled and randomly assigned to either the AI or control groups. In the AI group, the endoscopists watched both the AI monitor that detected ESCC with annotation and the normal monitor simultaneously; in the control group, the endoscopists watched only the normal monitor. In both groups, the endoscopists observed the esophagus using white-light imaging (WLI), followed by narrow-band imaging (NBI), then iodine staining. The primary end point was the enhanced detection rate of ESCC by nonexperts using AI. The detection rate was defined as the ratio of WLI/NBI-detected ESCCs to all ESCCs detected by iodine staining.

RESULTS

320 patients were included in the analysis. The detection rate of ESCC among nonexperts was 47% in the AI group and 45% in the control group (P = 0.93), with no significant difference, which was similarly found for experts (87% vs. 57%; P = 0.20) and all endoscopists (57% vs. 50%; P = 0.70).

CONCLUSIONS

This study could not demonstrate an improvement in the esophageal cancer detection rate using the AI diagnostic support system for ESCC.

Artificial intelligence in endoscopic diagnosis of esophageal squamous cell carcinoma and precancerous lesions

ABSTRACT

Esophageal squamous cell carcinoma (ESCC) poses a significant global health challenge, necessitating early detection, timely diagnosis, and prompt treatment to improve patient outcomes. Endoscopic examination plays a pivotal role in this regard. However, despite the availability of various endoscopic techniques, certain limitations can result in missed or misdiagnosed ESCCs. Currently, artificial intelligence (AI)-assisted endoscopic diagnosis has made significant strides in addressing these limitations and improving the diagnosis of ESCC and precancerous lesions. In this review, we provide an overview of the current state of AI applications for endoscopic diagnosis of ESCC and precancerous lesions in aspects including lesion characterization, margin delineation, invasion depth estimation, and microvascular subtype classification. Furthermore, we offer insights into the future direction of this field, highlighting potential advancements that can lead to more accurate diagnoses and ultimately better prognoses for patients.

Optimizing AI models to predict esophageal squamous cell carcinoma risk by incorporating small datasets of soft palate images

There is a currently an unmet need for non-invasive methods to predict the risk of esophageal squamous cell carcinoma (ESCC). Previously, we found that specific soft palate morphologies are strongly associated with increased ESCC risk. However, there is currently no artificial intelligence (AI) system that utilizes oral images for ESCC risk assessment. Here, we evaluated three AI models and three fine-tuning approaches with regard to their ESCC predictive power. Our dataset contained 539 cases, which were subdivided into 221 high-risk cases (2491 images) and 318 non-high-risk cases (2524 images). We used 480 cases (4295 images) for the training dataset, and the rest for validation. The Bilinear convolutional neural network (CNN) model (especially when pre-trained on fractal images) demonstrated diagnostic precision that was comparable to or better than other models for distinguishing between high-risk and non-high-risk groups. In addition, when tested with a small number of images containing soft palate data, the model showed high precision: the best AUC model had 0.91 (sensitivity 0.86, specificity 0.79). This study presents a significant advance in the development of an AI-based non-invasive screening tool for the identification of high-risk ESCC patients. The approach may be particularly suitable for institutes with limited medical imaging resources.

Artificial intelligence enhances the management of esophageal squamous cell carcinoma in the precision oncology era

Esophageal squamous cell carcinoma (ESCC) is the most common histological type of esophageal cancer with a poor prognosis. Early diagnosis and prognosis assessment are crucial for improving the survival rate of ESCC patients. With the advancement of artificial intelligence (AI) technology and the proliferation of medical digital information, AI has demonstrated promising sensitivity and accuracy in assisting precise detection, treatment decision-making, and prognosis assessment of ESCC. It has become a unique opportunity to enhance comprehensive clinical management of ESCC in the era of precision oncology. This review examines how AI is applied to the diagnosis, treatment, and prognosis assessment of ESCC in the era of precision oncology, and analyzes the challenges and potential opportunities that AI faces in clinical translation. Through insights into future prospects, it is hoped that this review will contribute to the real-world application of AI in future clinical settings, ultimately alleviating the disease burden caused by ESCC.

Efficiency of endoscopic artificial intelligence in the diagnosis of early esophageal cancer

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.

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

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.

The current state of artificial intelligence in endoscopic diagnosis of early esophageal squamous cell carcinoma

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.

Impact of linked color imaging and blue laser imaging on the diagnosis of esophageal squamous cell carcinoma in iodine unstained areas

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.

Comprehensive risk evaluation for metachronous carcinogenesis after endoscopic submucosal dissection of superficial pharyngeal squamous cell carcinoma

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.

An artificial intelligence system for distinguishing between gastrointestinal stromal tumors and leiomyomas using endoscopic ultrasonography

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.