UCD Centre for Precision Surgery, School of Medicine, University College Dublin, Dublin, Ireland.
IBM Research Europe, Dublin, Ireland.
Surg Endosc. 2023 Aug;37(8):6361-6370. doi: 10.1007/s00464-023-09963-2. Epub 2023 Mar 9.
Indocyanine green (ICG) quantification and assessment by machine learning (ML) could discriminate tissue types through perfusion characterisation, including delineation of malignancy. Here, we detail the important challenges overcome before effective clinical validation of such capability in a prospective patient series of quantitative fluorescence angiograms regarding primary and secondary colorectal neoplasia.
ICG perfusion videos from 50 patients (37 with benign (13) and malignant (24) rectal tumours and 13 with colorectal liver metastases) of between 2- and 15-min duration following intravenously administered ICG were formally studied (clinicaltrials.gov: NCT04220242). Video quality with respect to interpretative ML reliability was studied observing practical, technical and technological aspects of fluorescence signal acquisition. Investigated parameters included ICG dosing and administration, distance-intensity fluorescent signal variation, tissue and camera movement (including real-time camera tracking) as well as sampling issues with user-selected digital tissue biopsy. Attenuating strategies for the identified problems were developed, applied and evaluated. ML methods to classify extracted data, including datasets with interrupted time-series lengths with inference simulated data were also evaluated.
Definable, remediable challenges arose across both rectal and liver cohorts. Varying ICG dose by tissue type was identified as an important feature of real-time fluorescence quantification. Multi-region sampling within a lesion mitigated representation issues whilst distance-intensity relationships, as well as movement-instability issues, were demonstrated and ameliorated with post-processing techniques including normalisation and smoothing of extracted time-fluorescence curves. ML methods (automated feature extraction and classification) enabled ML algorithms glean excellent pathological categorisation results (AUC-ROC > 0.9, 37 rectal lesions) with imputation proving a robust method of compensation for interrupted time-series data with duration discrepancies.
Purposeful clinical and data-processing protocols enable powerful pathological characterisation with existing clinical systems. Video analysis as shown can inform iterative and definitive clinical validation studies on how to close the translation gap between research applications and real-world, real-time clinical utility.
通过机器学习（ML）对吲哚菁绿（ICG）进行定量和评估，可以通过灌注特征来区分组织类型，包括恶性肿瘤的描绘。在这里，我们详细介绍了在对原发性和继发性结直肠肿瘤的定量荧光血管造影术的前瞻性患者系列中，对这种能力进行有效临床验证之前克服的重要挑战。
对 50 名患者（37 名直肠肿瘤患者中有良性（13 名）和恶性（24 名），13 名结直肠肝转移患者）静脉注射 ICG 后 2-15 分钟的 ICG 灌注视频进行了正式研究（clinicaltrials.gov：NCT04220242）。观察荧光信号采集的实际、技术和技术方面，研究了视频质量与解释性 ML 可靠性之间的关系。研究的参数包括 ICG 剂量和给药、强度荧光信号变化、组织和相机运动（包括实时相机跟踪）以及用户选择的数字组织活检的采样问题。针对所确定的问题开发、应用和评估了衰减策略。还评估了用于分类提取数据的 ML 方法，包括具有推断模拟数据的中断时间序列长度的数据集。
在直肠和肝脏队列中都出现了可定义的、可纠正的挑战。根据组织类型改变 ICG 剂量被确定为实时荧光定量的一个重要特征。在病变内进行多区域采样减轻了代表性问题，而距离-强度关系以及运动不稳定性问题通过后处理技术（包括提取时间荧光曲线的归一化和平滑处理）得到了证明和改善。ML 方法（自动特征提取和分类）使 ML 算法能够获得出色的病理分类结果（AUC-ROC>0.9，37 个直肠病变），插补证明是补偿具有持续时间差异的中断时间序列数据的稳健方法。
有针对性的临床和数据处理方案使现有的临床系统能够实现强大的病理特征描述。如所示的视频分析可以为如何缩小研究应用与现实世界实时临床实用性之间的转化差距提供信息，从而为迭代和最终的临床验证研究提供信息。
