[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4676":3,"related-4676":71},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":18,"tags":20,"primary_topic":9,"secondary_topics":21,"classification":22,"search_phrases":39,"slug":40,"view_count":15,"doi":41,"paper":42,"created_at":70},4676,"Multi-class Identification and Quantification of Breast Implant-related Complications in Ultrasonography Using a Pathology-informed Lesion Graph: A Deep Learning Development and Validation Study","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fasj\u002Fsjag221","BACKGROUND: Breast ultrasonography (US) is cost-effective for detecting breast implant-related complications, but its reliability remains highly operator-dependent. OBJECTIVES: This study developed and validated a deep learning model for the automated multi-class identification and quantitative evaluation of breast implant complications (rupture, capsular contracture, and hematoma). METHODS: We retrospectively analyzed 14,679 breast US images across 1,022 breast implant sequences from 908 patients. The proposed architecture integrates multiscale visual encoding, automated probe position mapping, and a pathology-informed mask graph layer with a Gradient Reversal Layer for lumen adversarial debiasing. Four convolutional backbones were benchmarked using an independent patient-level test dataset (N=197 implants). RESULTS: The optimized DenseNet-based framework achieved 96.97% balanced accuracy with expert-guided spatial priors and 88.67% under autonomous baseline conditions. The model yielded 100% sensitivity for normal, rupture, and hematoma cohorts, and 87.88% sensitivity for capsular contracture; minor false-negatives were traced to morphological heterogeneity and coexisting pathologies. Furthermore, the system extracted quantitative morphometric profiles, yielding a mean relative capsule thickness of 2.4±0.4% for capsular contractures and a mean relative fluid area of 13.9±6.4% for hematomas. CONCLUSIONS: The proposed multiscale model delivers a comprehensive, clinical-grade output, comprising accurate complication classification, five-zone spatial localization, and objective morphometric metrics, while mitigating operator dependency. This system holds strong potential as an accessible, high-performance decision support tool for long-term safety screening of patients with breast implants.","背景：乳腺超声（US）在检测乳房植入物相关并发症方面具有成本效益，但其可靠性在很大程度上仍依赖于操作者。目的：本研究开发并验证了一种深度学习模型，用于自动多分类识别和定量评估乳房植入物并发症（破裂、包膜挛缩和血肿）。方法：我们回顾性分析了来自908名患者的1,022个乳房植入物序列中的14,679张乳腺超声图像。所提出的架构整合了多尺度视觉编码、自动探头位置映射，以及带有梯度反转层的病理信息掩膜图图层，用于管腔对抗去偏。使用独立的患者级测试数据集（N=197个植入物）对四种卷积骨干网络进行了基准测试。结果：优化的基于DenseNet的框架在专家引导的空间先验下达到了96.97%的平衡准确率，在自主基线条件下为88.67%。该模型对正常、破裂和血肿队列的灵敏度为100%，对包膜挛缩的灵敏度为87.88%；少量假阴性可归因于形态异质性和共存病变。此外，该系统提取了定量形态学特征，包膜挛缩的平均相对包膜厚度为2.4±0.4%，血肿的平均相对液体面积为13.9±6.4%。结论：所提出的多尺度模型提供了全面的临床级输出，包括准确的并发症分类、五区空间定位和客观的形态学指标，同时减轻了操作者依赖性。该系统作为乳房植入物患者长期安全筛查的可及、高性能决策支持工具具有强大潜力。",null,"Aesthetic Surgery Journal","2026-10-09T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该资讯为乳腺超声人工智能论文，与三农、农业信息化、智慧农业、数字乡村等主题无关，不予入选。",[19],{"name":10,"url":6},[12],[],{"status":23,"locked":14,"version":24,"method":25,"evidence":26},"needs_review","2026-10-22.2","rules",{"candidates":27,"agricultural_evidence":14,"reason":38},[28],{"code":29,"score":30,"supported":31,"title":32,"abstract":34,"tags":37},"I2",17,true,[33],"deep learning",[35,33,36],"深度学习","decision support",[],"农业相关性需要复核",[],"Multi-classIdentificationandQuantificati-4676","10.1093\u002Fasj\u002Fsjag221",{"doi":41,"openalex_id":43,"authors":44,"venue":10,"cited_by_count":15,"oa_url":61,"card":62,"direction":68,"ingested_from":69},"W7221329072",[45,48,50,53,56,58],{"name":46,"orcid":47},"Hyokyung Yoo","https:\u002F\u002Forcid.org\u002F0000-0002-9171-0379",{"name":49,"orcid":9},"Byeong Soo Kim",{"name":51,"orcid":52},"Jae Jin Ock","https:\u002F\u002Forcid.org\u002F0000-0003-0677-7390",{"name":54,"orcid":55},"Ki Yong Hong","https:\u002F\u002Forcid.org\u002F0000-0002-8579-0237",{"name":57,"orcid":9},"Chang Hak",{"name":59,"orcid":60},"Sungwan Kim","https:\u002F\u002Forcid.org\u002F0000-0002-9318-849X","https:\u002F\u002Facademic.oup.com\u002Fasj\u002Fadvance-article-pdf\u002Fdoi\u002F10.1093\u002Fasj\u002Fsjag221\u002F71820494\u002Fsjag221.pdf",{"tldr":63,"method":64,"finding":65,"direction":66,"opportunity":67},"开发深度学习模型自动识别和量化乳腺植入物并发症（破裂、包膜挛缩、血肿）。","基于14,679张超声图像，结合多尺度编码、探针定位和病理信息掩膜图。","DenseNet框架平衡准确率达96.97%，实现并发症分类、空间定位和形态学量化。","农业人工智能与决策模型","该病理信息图与对抗去偏方法可迁移至农业图像中多类病害识别与量化，解决标注偏差问题。","农业遥感与作物表型","openalex","2026-10-11T23:30:27.542679Z",{"total":15,"page":72,"page_size":72,"items":73},1,[]]