PDF(Pubmed)
Abstract：
Patients with gastric atrophy and intestinal metaplasia (IM) were at risk for gastric cancer, necessitating an accurate risk assessment. We aimed to establish and validate a diagnostic approach for gastric biopsy specimens using deep learning and OLGA/OLGIM for individual gastric cancer risk classification.
In this study, we prospectively enrolled 545 patients suspected of atrophic gastritis during endoscopy from 13 tertiary hospitals between December 22, 2017, to September 25, 2020, with a total of 2725 whole-slide images (WSIs). Patients were randomly divided into a training set (n = 349), an internal validation set (n = 87), and an external validation set (n = 109). Sixty patients from the external validation set were randomly selected and divided into two groups for an observer study, one with the assistance of algorithm results and the other without. We proposed a semi-supervised deep learning algorithm to diagnose and grade IM and atrophy, and we compared it with the assessments of 10 pathologists. The model\'s performance was evaluated based on the area under the curve (AUC), sensitivity, specificity, and weighted kappa value.
The algorithm, named GasMIL, was established and demonstrated encouraging performance in diagnosing IM (AUC 0.884, 95% CI 0.862-0.902) and atrophy (AUC 0.877, 95% CI 0.855-0.897) in the external test set. In the observer study, GasMIL achieved an 80% sensitivity, 85% specificity, a weighted kappa value of 0.61, and an AUC of 0.953, surpassing the performance of all ten pathologists in diagnosing atrophy. Among the 10 pathologists, GasMIL\'s AUC ranked second in OLGA (0.729, 95% CI 0.625-0.833) and fifth in OLGIM (0.792, 95% CI 0.688-0.896). With the assistance of GasMIL, pathologists demonstrated improved AUC (p = 0.013), sensitivity (p = 0.014), and weighted kappa (p = 0.016) in diagnosing IM, and improved specificity (p = 0.007) in diagnosing atrophy compared to pathologists working alone.
GasMIL shows the best overall performance in diagnosing IM and atrophy when compared to pathologists, significantly enhancing their diagnostic capabilities.
In this study, we prospectively enrolled 545 patients suspected of atrophic gastritis during endoscopy from 13 tertiary hospitals between December 22, 2017, to September 25, 2020, with a total of 2725 whole-slide images (WSIs). Patients were randomly divided into a training set (n = 349), an internal validation set (n = 87), and an external validation set (n = 109). Sixty patients from the external validation set were randomly selected and divided into two groups for an observer study, one with the assistance of algorithm results and the other without. We proposed a semi-supervised deep learning algorithm to diagnose and grade IM and atrophy, and we compared it with the assessments of 10 pathologists. The model\'s performance was evaluated based on the area under the curve (AUC), sensitivity, specificity, and weighted kappa value.
The algorithm, named GasMIL, was established and demonstrated encouraging performance in diagnosing IM (AUC 0.884, 95% CI 0.862-0.902) and atrophy (AUC 0.877, 95% CI 0.855-0.897) in the external test set. In the observer study, GasMIL achieved an 80% sensitivity, 85% specificity, a weighted kappa value of 0.61, and an AUC of 0.953, surpassing the performance of all ten pathologists in diagnosing atrophy. Among the 10 pathologists, GasMIL\'s AUC ranked second in OLGA (0.729, 95% CI 0.625-0.833) and fifth in OLGIM (0.792, 95% CI 0.688-0.896). With the assistance of GasMIL, pathologists demonstrated improved AUC (p = 0.013), sensitivity (p = 0.014), and weighted kappa (p = 0.016) in diagnosing IM, and improved specificity (p = 0.007) in diagnosing atrophy compared to pathologists working alone.
GasMIL shows the best overall performance in diagnosing IM and atrophy when compared to pathologists, significantly enhancing their diagnostic capabilities.
摘要：
目的：胃萎缩和肠上皮化生（IM）患者有胃癌的风险，需要准确的风险评估。我们旨在使用深度学习和OLGA/OLGIM为个体胃癌风险分类建立和验证胃活检标本的诊断方法。
方法：在本研究中，我们前瞻性纳入了2017年12月22日至2020年9月25日期间13家三级医院内镜检查中疑似萎缩性胃炎的545例患者,共2725张全张图像(WSI).患者被随机分为一组训练组(n=349)，内部验证集(n=87)，和外部验证集（n=109）。从外部验证集中随机选择60名患者，并将其分为两组进行观察研究，一个有算法结果的辅助，另一个没有。我们提出了一种半监督深度学习算法来诊断和分级IM和萎缩，我们将其与10位病理学家的评估进行了比较。根据曲线下面积（AUC）评估模型的性能，灵敏度,特异性，和加权kappa值。
结果：算法，名叫Gasmil,在外部测试集中，在诊断IM(AUC0.884，95%CI0.862-0.902)和萎缩(AUC0.877，95%CI0.855-0.897)方面建立并证明了令人鼓舞的表现。在观察者研究中，GasMIL实现了80%的灵敏度,85%特异性,加权kappa值为0.61，AUC为0.953，超过了所有10位病理学家诊断萎缩的能力。在10位病理学家中，GasMIL的AUC在OLGA中排名第二（0.729，95%CI0.625-0.833），在OLGIM中排名第五（0.792，95%CI0.688-0.896）。在Gasmil的协助下,病理学家表现出改善的AUC（p=0.013），灵敏度（p=0.014），和加权κ(p=0.016)诊断IM，与单独工作的病理学家相比，诊断萎缩的特异性提高（p=0.007）。
结论：与病理学家相比，GasMIL在诊断IM和萎缩方面表现最佳。显著提高其诊断能力。
方法：在本研究中，我们前瞻性纳入了2017年12月22日至2020年9月25日期间13家三级医院内镜检查中疑似萎缩性胃炎的545例患者,共2725张全张图像(WSI).患者被随机分为一组训练组(n=349)，内部验证集(n=87)，和外部验证集（n=109）。从外部验证集中随机选择60名患者，并将其分为两组进行观察研究，一个有算法结果的辅助，另一个没有。我们提出了一种半监督深度学习算法来诊断和分级IM和萎缩，我们将其与10位病理学家的评估进行了比较。根据曲线下面积（AUC）评估模型的性能，灵敏度,特异性，和加权kappa值。
结果：算法，名叫Gasmil,在外部测试集中，在诊断IM(AUC0.884，95%CI0.862-0.902)和萎缩(AUC0.877，95%CI0.855-0.897)方面建立并证明了令人鼓舞的表现。在观察者研究中，GasMIL实现了80%的灵敏度,85%特异性,加权kappa值为0.61，AUC为0.953，超过了所有10位病理学家诊断萎缩的能力。在10位病理学家中，GasMIL的AUC在OLGA中排名第二（0.729，95%CI0.625-0.833），在OLGIM中排名第五（0.792，95%CI0.688-0.896）。在Gasmil的协助下,病理学家表现出改善的AUC（p=0.013），灵敏度（p=0.014），和加权κ(p=0.016)诊断IM，与单独工作的病理学家相比，诊断萎缩的特异性提高（p=0.007）。
结论：与病理学家相比，GasMIL在诊断IM和萎缩方面表现最佳。显著提高其诊断能力。
