Real-time administration of indocyanine green in combination with computer vision and artificial intelligence for the identification and delineation of colorectal liver metastases

Hardy, Niall; Epperlein, Jonathan P.; Dalli, Jeffrey; Robertson, William; Liddy, Richard M.; Aird, John; Mulligan, Niall; Neary, Peter; McEntee, G.; Conneely, John B.; Cahill, Ronan

doi:10.1016/j.sopen.2023.03.004

Cited by 8 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also serves as a discriminating target for tissue characterisation by characterising and analysing these findings in real time [26]. ICG outflow (represented graphically here by the downslope after peak) has been identified as an important predictor of malignancy along with curve centre of mass (COM), a function of both inflow and outflow, and both are used here to graphically represent the differences, not only to the surrounding healthy tissue, but also within different locations of a malignant lesion [11,14]. Such intra-lesional heterogeneity is not seen when the same methods are applied to benign pathologies, a finding that has been utilized to characterise rectal tumours in real time with high accuracy [20].…”

Section: Discussionmentioning

confidence: 99%

“…One sequential sample per patient was stained with haematoxylin and eosin (H&E) to maximise contrast under white light examination and for comparison with the obtained fluorescence images. Samples for fluorescence examination were unstained as H&E has previously been shown to significantly reduce fluorescence intensity [14].…”

Section: Fluorescence Microscopy: Tissue Preparation and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Geotemporal Fluorophore Biodistribution Mapping of Colorectal Cancer: Micro and Macroscopic Insights

Hardy,

Mulligan,

Dalli

et al. 2024

Current Oncology

Self Cite

View full text Add to dashboard Cite

Fluorescence-guided oncology promises to improve both the detection and treatment of malignancy. We sought to investigate the temporal distribution of indocyanine green (ICG), an exogenous fluorophore in human colorectal cancer. This analysis aims to enhance our understanding of ICG’s effectiveness in current tumour detection and inform potential future diagnostic and therapeutic enhancements. Methods: Fifty consenting patients undergoing treatment for suspected/confirmed colorectal neoplasia provided near infrared (NIR) video and imagery of transanally recorded and ex vivo resected rectal lesions following intravenous ICG administration (0.25 mg/kg), with a subgroup providing tissue samples for microscopic (including near infrared) analysis. Computer vision techniques detailed macroscopic ‘early’ (<15 min post ICG administration) and ‘late’ (>2 h) tissue fluorescence appearances from surgical imagery with digital NIR scanning (Licor, Lincoln, NE, USA) and from microscopic analysis (Nikon, Tokyo, Japan) undertaken by a consultant pathologist detailing tissue-level fluorescence distribution over the same time. Results: Significant intra-tumoural fluorescence heterogeneity was seen ‘early’ in malignant versus benign lesions. In all ‘early’ samples, fluorescence was predominantly within the tissue stroma, with uptake within plasma cells, blood vessels and lymphatics, but not within malignant or healthy glands. At ‘late’ stage observation, fluorescence was visualised non-uniformly within the intracellular cytoplasm of malignant tissue but not retained in benign glands. Fluorescence also accumulated within any present peritumoural inflammatory tissue. Conclusion: This study demonstrates the time course diffusion patterns of ICG through both benign and malignant tumours in vivo in human patients at both macroscopic and microscopic levels, demonstrating important cellular drivers and features of geolocalisation and how they differ longitudinally after exposure to ICG.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Fluorescence Microscopy: Tissue Preparation and Analysismentioning

confidence: 99%

Geotemporal Fluorophore Biodistribution Mapping of Colorectal Cancer: Micro and Macroscopic Insights

Hardy,

Mulligan,

Dalli

et al. 2024

Current Oncology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another challenge in ICG-FI is the quantification of fluorescence intensity, which further complicates result interpretation and comparison. This issue is not limited to BC tumor detection but is also relevant for assessing tissue viability through vascular assessment [54][55][56]. In the reviewed studies, fluorescence signal quantification and TBR calculations were performed using three different programs across six out of the seven clinical studies that included quantification [4,10,15,16,31,33].…”

Section: Imaging Systems and Fi Quantificationmentioning

confidence: 99%

Fluorescence imaging for real-time detection of breast cancer tumors using IV injection of indocyanine green with non-conventional imaging: a systematic review of preclinical and clinical studies of perioperative imaging technologies

Pop,

Veys,

Bormans

et al. 2024

Breast Cancer Res Treat

View full text Add to dashboard Cite

Background This review summarizes the available data on the effectiveness of indocyanine green fluorescence imaging (ICG-FI) for real-time detection of breast cancer (BC) tumors with perioperative imaging technologies. Methods PubMed and Scopus databases were exhaustively searched for publications on the use of the real-time ICG-FI evaluation of BC tumors with non-conventional breast imaging technologies. Results Twenty-three studies were included in this review. ICG-FI has been used for BC tumor identification in 12 orthotopic animal tumor experiences, 4 studies on animal assessment, and for 7 human clinical applications. The BC tumor-to-background ratio (TBR) was 1.1–8.5 in orthotopic tumor models and 1.4–3.9 in animal experiences. The detection of primary human BC tumors varied from 40% to 100%. The mean TBR reported for human BC varied from 2.1 to 3.7. In two studies evaluating BC surgical margins, good sensitivity (93.3% and 100%) and specificity (60% and 96%) have been reported, with a negative predictive value of ICG-FI to predict margin involvement intraoperatively of 100% in one study. Conclusions The use of ICG-FI as a guiding tool for the real-time identification of BC tumors and for the assessment of tumor boundaries is promising. There is great variability between the studies with regard to timing and dose. Further evidence is needed to assess whether ICG-guided BC surgery may be implemented as a standard of care.

show abstract

“…In a study by Hardy et al, the application of Artificial Intelligence/Machine Learning techniques demonstrated the ability to identify CRLM and map their fluorescence perfusion patterns using 2D mapping [58]. This approach may have implications for reducing positive margin rates during metastasectomy and detecting additional metastases.…”

Section: Use Of Ai With Icgmentioning

confidence: 99%

Use of Near-Infrared Fluorescence Techniques in Minimally Invasive Surgery for Colorectal Liver Metastases

Patel,

Rehman,

McKay

et al. 2023

JCM

View full text Add to dashboard Cite

Colorectal liver metastases (CRLM) afflict a significant proportion of patients with colorectal cancer (CRC), ranging from 25% to 30% of patients throughout the course of the disease. In recent years, there has been a surge of interest in the application of near-infrared fluorescence (NIRF) imaging as an intraoperative imaging technique for liver surgery. The utilisation of NIRF-guided liver surgery, facilitated by the administration of fluorescent dye indocyanine green (ICG), has gained traction in numerous medical institutions worldwide. This innovative approach aims to enhance lesion differentiation and provide valuable guidance for surgical margins. The use of ICG, particularly in minimally invasive surgery, has the potential to improve lesion detection rates, increase the likelihood of achieving R0 resection, and enable anatomically guided resections. However, it is important to acknowledge the limitations of ICG, such as its low specificity. Consequently, there has been a growing demand for the development of tumour-specific fluorescent probes and the advancement of camera systems, which are expected to address these concerns and further refine the accuracy and reliability of intraoperative fluorescence imaging in liver surgery. While NIRF imaging has been extensively studied in patients with CRLM, it is worth noting that a significant proportion of published research has predominantly focused on the detection of hepatocellular carcinoma (HCC). In this study, we present a comprehensive literature review of the existing literature pertaining to intraoperative fluorescence imaging in minimally invasive surgery for CRLM. Moreover, our analysis places specific emphasis on the techniques employed in liver resection using ICG, with a focus on tumour detection in minimal invasive surgery (MIS). Additionally, we delve into recent developments in this field and offer insights into future perspectives for further advancements.

show abstract

Real-time administration of indocyanine green in combination with computer vision and artificial intelligence for the identification and delineation of colorectal liver metastases

Cited by 8 publications

References 27 publications

Geotemporal Fluorophore Biodistribution Mapping of Colorectal Cancer: Micro and Macroscopic Insights

Geotemporal Fluorophore Biodistribution Mapping of Colorectal Cancer: Micro and Macroscopic Insights

Fluorescence imaging for real-time detection of breast cancer tumors using IV injection of indocyanine green with non-conventional imaging: a systematic review of preclinical and clinical studies of perioperative imaging technologies

Use of Near-Infrared Fluorescence Techniques in Minimally Invasive Surgery for Colorectal Liver Metastases

Contact Info

Product

Resources

About