Surgical endoscopy · 2026
AI-powered hierarchical classification of ampullary neoplasms: a deep learning approach using white-light and narrow-band imaging.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Yoon Dan, Chang Sung Hoon, Paik Woo Hyun, Kim Chang Hyun, Kim Byeong Soo, Kim Young Gyun, Chung Hyunsoo, Ryu Ji Kon, Lee Sang Hyub, Cho In Rae, Choi Seong Ji, Kim Joo Seong, Kim Sungwan, Choi Jin Ho
Аннотация
BACKGROUND: Endoscopic diagnosis of Ampulla of Vater (AoV) lesions remains challenging owing to complex morphology and limited representative images, particularly for high-risk dysplastic lesions. This study aimed to develop a hierarchical deep learning framework for the stepwise classification of ampullary lesions using white-light (WL) and narrow-band endoscopic images (NBI).
METHODS: The framework employs three sequential binary classifications: (1) normal vs. abnormal, (2) adenoma vs. cancer, and (3) high-grade dysplasia (HGD) vs. low-grade dysplasia (LGD) within adenomas. Each stage uses EfficientNet-B4 classifiers trained independently on WL and NBI. Predictions are integrated using confidence-based voting. To overcome data scarcity and class imbalance, for HGD and cancer, we used StyleGAN2-ADA to generate synthetic images. The hierarchical model was developed using 4244 endoscopic images from 464 patients collected at Seoul National University Hospital (2693/833/718 for train/validation/test).
RESULTS: The hierarchical model achieved stage-specific accuracies of 95.6% (normal vs. abnormal), 94.4% (adenoma vs. cancer), and 92.7% (LGD vs. HGD), resulting in overall diagnostic accuracy of 92.2%. The model demonstrated excellent sensitivity of 83.3% for HGD and 87.5% for cancer, with specificities exceeding 98%. The confidence-based dual-modality approach (AUROC: 0.921) significantly outperformed single-modality approaches using WL alone (AUROC: 0.866) or NBI alone (AUROC: 0.895), by integrating their complementary diagnostic strengths. Generative adversarial network-based augmentation substantially improved sensitivity for cancer (from 87.5% to 91.7%) and HGD (from 83.3% to 86.5%), while overall accuracy increased from 94.5% to 95.1%.
CONCLUSIONS: A hierarchical deep learning approach integrating dual-modality imaging and synthetic data augmentation significantly improves diagnostic performance for ampullary lesions.
METHODS: The framework employs three sequential binary classifications: (1) normal vs. abnormal, (2) adenoma vs. cancer, and (3) high-grade dysplasia (HGD) vs. low-grade dysplasia (LGD) within adenomas. Each stage uses EfficientNet-B4 classifiers trained independently on WL and NBI. Predictions are integrated using confidence-based voting. To overcome data scarcity and class imbalance, for HGD and cancer, we used StyleGAN2-ADA to generate synthetic images. The hierarchical model was developed using 4244 endoscopic images from 464 patients collected at Seoul National University Hospital (2693/833/718 for train/validation/test).
RESULTS: The hierarchical model achieved stage-specific accuracies of 95.6% (normal vs. abnormal), 94.4% (adenoma vs. cancer), and 92.7% (LGD vs. HGD), resulting in overall diagnostic accuracy of 92.2%. The model demonstrated excellent sensitivity of 83.3% for HGD and 87.5% for cancer, with specificities exceeding 98%. The confidence-based dual-modality approach (AUROC: 0.921) significantly outperformed single-modality approaches using WL alone (AUROC: 0.866) or NBI alone (AUROC: 0.895), by integrating their complementary diagnostic strengths. Generative adversarial network-based augmentation substantially improved sensitivity for cancer (from 87.5% to 91.7%) and HGD (from 83.3% to 86.5%), while overall accuracy increased from 94.5% to 95.1%.
CONCLUSIONS: A hierarchical deep learning approach integrating dual-modality imaging and synthetic data augmentation significantly improves diagnostic performance for ampullary lesions.