Hardy Niall P, Epperlein Jonathan P, Dalli Jeffrey, Robertson William, Liddy Richard, Aird John J, Mulligan Niall, Neary Peter M, McEntee Gerard P, Conneely John B, Cahill Ronan A
UCD Centre for Precision Surgery, School of Medicine, UCD, Dublin, Ireland.
IBM Research Europe, Dublin, Ireland.
Surg Open Sci. 2023 Mar 2;12:48-54. doi: 10.1016/j.sopen.2023.03.004. eCollection 2023 Mar.
Fluorescence guided surgery for the identification of colorectal liver metastases (CRLM) can be better with low specificity and antecedent dosing impracticalities limiting indocyanine green (ICG) usefulness currently. We investigated the application of artificial intelligence methods (AIM) to demonstrate and characterise CLRMs based on dynamic signalling immediately following intraoperative ICG administration.
Twenty-five patients with liver surface lesions (24 CRLM and 1 benign cyst) undergoing open/laparoscopic/robotic procedures were studied. ICG (0.05 mg/kg) was administered with near-infrared recording of fluorescence perfusion. User-selected region-of-interest (ROI) perfusion profiles were generated, milestones relating to ICG inflow/outflow extracted and used to train a machine learning (ML) classifier. 2D heatmaps were constructed in a subset using AIM to depict whole screen imaging based on dynamic tissue-ICG interaction. Fluorescence appearances were also assessed microscopically (using H&E and fresh-frozen preparations) to provide tissue-level explainability of such methods.
The ML algorithm correctly classified 97.2 % of CRLM ROIs (n = 132) and all benign lesion ROIs (n = 6) within 90-s of ICG administration following initial mathematical curve analysis identifying ICG inflow/outflow differentials between healthy liver and CRLMs. Time-fluorescence plots extracted for each pixel in 10 lesions enabled creation of 2D characterising heatmaps using flow parameters and through unsupervised ML. Microscopy confirmed statistically less CLRM fluorescence vs adjacent liver (mean ± std deviation signal/area 2.46 ± 9.56 vs 507.43 ± 160.82 respectively p < 0.001) with H&E diminishing ICG signal (n = 4).
ML accurately identifies CRLMs from surrounding liver tissue enabling representative 2D mapping of such lesions from their fluorescence perfusion patterns using AIM. This may assist in reducing positive margin rates at metastatectomy and in identifying unexpected/occult malignancies.
目前，用于识别结直肠癌肝转移（CRLM）的荧光引导手术特异性较低，且前期给药存在不便，限制了吲哚菁绿（ICG）的应用。我们研究了人工智能方法（AIM）在术中给予ICG后基于动态信号来显示和表征CRLM的应用。
对25例接受开放/腹腔镜/机器人手术的肝表面病变患者（24例CRLM和1例良性囊肿）进行研究。给予ICG（0.05mg/kg），并进行荧光灌注的近红外记录。生成用户选择的感兴趣区域（ROI）灌注曲线，提取与ICG流入/流出相关的关键节点并用于训练机器学习（ML）分类器。在一个子集中使用AIM构建二维热图，以基于动态组织-ICG相互作用描绘全屏幕成像。还通过显微镜（使用苏木精和伊红染色以及新鲜冷冻制剂）评估荧光外观，以提供此类方法在组织水平上的可解释性。
在通过初始数学曲线分析确定健康肝脏和CRLM之间的ICG流入/流出差异后，ML算法在ICG给药后90秒内正确分类了97.2%的CRLM ROI（n = 132）和所有良性病变ROI（n = 6）。从10个病变的每个像素提取的时间-荧光图能够使用流动参数并通过无监督ML创建二维特征热图。显微镜检查证实，与相邻肝脏相比，CRLM的荧光在统计学上更少（平均±标准差信号/面积分别为2.46±9.56和507.43±160.82，p < 0.001），苏木精和伊红染色使ICG信号减弱（n = 4）。
ML能够准确地从周围肝组织中识别出CRLM，从而使用AIM根据其荧光灌注模式对这些病变进行代表性的二维映射。这可能有助于降低肝转移瘤切除术的切缘阳性率，并识别意外/隐匿性恶性肿瘤。
