Keel Benjamin, Quyn Aaron, Jayne David, Relton Samuel David
School of Computing, University of Leeds, Leeds, UK
Leeds Teaching Hospitals NHS Trust, Leeds, UK.
BMJ Open. 2024 Dec 2;14(12):e086896. doi: 10.1136/bmjopen-2024-086896.
To assess the current state-of-the-art in deep learning methods applied to pre-operative radiologic staging of colorectal cancer lymph node metastasis. Specifically, by evaluating the data, methodology and validation of existing work, as well as the current use of explainable AI in this fast-moving domain.
Scoping review.
Academic databases MEDLINE, Embase, Scopus, IEEE Xplore, Web of Science and Google Scholar were searched with a date range of 1 January 2018 to 1 February 2024.
Includes any English language research articles or conference papers published since 2018 which have applied deep learning methods for feature extraction and classification of colorectal cancer lymph nodes on pre-operative radiologic imaging.
Key results and characteristics for each included study were extracted using a shared template. A narrative synthesis was then conducted to qualitatively integrate and interpret these findings.
This scoping review covers 13 studies which met the inclusion criteria. The deep learning methods had an area under the curve score of 0.856 (0.796 to 0.916) for patient-level lymph node diagnosis and 0.904 (0.841 to 0.967) for individual lymph node assessment, given with a 95% confidence interval. Most studies have fundamental limitations including unrepresentative data, inadequate methodology, poor model validation and limited explainability techniques.
Deep learning methods have demonstrated the potential for accurately diagnosing colorectal cancer lymph nodes using pre-operative radiologic imaging. However, several methodological and validation flaws such as selection bias and lack of external validation make it difficult to trust the results. This review has uncovered a research gap for robust, representative and explainable deep learning methods that are end-to-end from automatic lymph node detection to the diagnosis of lymph node metastasis.
评估深度学习方法在结直肠癌淋巴结转移术前放射学分期中的当前技术水平。具体而言，通过评估现有研究的数据、方法和验证情况，以及可解释人工智能在这个快速发展领域的当前应用。
范围综述。
检索学术数据库MEDLINE、Embase、Scopus、IEEE Xplore、Web of Science和谷歌学术，日期范围为2018年1月1日至2024年2月1日。
包括自2018年以来发表的任何英文研究文章或会议论文，这些文章将深度学习方法应用于术前放射学成像中结直肠癌淋巴结的特征提取和分类。
使用共享模板提取每项纳入研究的关键结果和特征。然后进行叙述性综合，以定性地整合和解释这些发现。
本范围综述涵盖了13项符合纳入标准的研究。深度学习方法在患者水平的淋巴结诊断中曲线下面积得分为0.856（0.796至0.916），在单个淋巴结评估中为0.904（0.841至0.967），给出的是95%置信区间。大多数研究存在基本局限性，包括数据缺乏代表性、方法不充分、模型验证不佳和可解释性技术有限。
结论性技术有限。
深度学习方法已显示出利用术前放射学成像准确诊断结直肠癌淋巴结的潜力。然而，一些方法和验证缺陷，如选择偏倚和缺乏外部验证，使得难以信任这些结果。本综述发现了一个研究空白，即需要从自动淋巴结检测到淋巴结转移诊断的端到端的强大、有代表性且可解释的深度学习方法。
