Quantitative analysis of intestinal perfusion with indocyanine green (ICG) and methylene blue (MB) using a single clinically approved fluorescence imaging system: a demonstration in a porcine model.

BACKGROUND: Near-infrared fluorescence (NIRF) angiography with intraoperative administration of indocyanine green (ICG) has rapidly disseminated in clinical practice. Another clinically approved, and widely available dye, methylene blue (MB), has up to now not been used for this purpose. Recently, we demonstrated promising results for the real-time evaluation of intestinal perfusion using this dye. The primary aim of this study was to perform a quantitative analysis of bowel perfusion assessment for both ICG and MB. METHODS: Four mature female Landrace pigs underwent laparotomy under general anesthesia. An ischemic bowel loop with five regions of interest (ROIs) with varying levels of perfusion was created in each animal. An intravenous (IV) injection of 0.25 mg/kg-0.50 mg/kg MB was administered after 10 min, followed by NIRF imaging in MB mode and measurement of local lactate levels in all corresponding ROIs. This procedure was repeated in ICG mode (IV dose of 0.2 mg/kg) after 60 min. The quest spectrum fluorescence camera (Quest Medical Imaging, Middenmeer, The Netherlands) was used for NIRF imaging of both MB and ICG. RESULTS: Intraoperative NIRF imaging of bowel perfusion assessment with MB and ICG was successful in all studied animals. Ingress (i/s) levels were calculated and correlated with local lactate levels. Both MB and ICG ingress values showed a significant negative correlation (r = - 0.7709; p = < 0.001; r = - 0.5367, p = 0.015, respectively) with local lactate levels. This correlation was stronger for MB compared to ICG, although ICG analysis showed higher absolute ingress values. CONCLUSION: Our fluorescence quantification analysis validates the potential to use MB for bowel perfusion assessment besides the well-known and widely used ICG. Further human studies are necessary to translate our findings to clinical applications.

Surgical optomics: hyperspectral imaging and deep learning towards precision intraoperative automatic tissue recognition-results from the EX-MACHYNA trial.

BACKGROUND: Hyperspectral imaging (HSI), combined with machine learning, can help to identify characteristic tissue signatures enabling automatic tissue recognition during surgery. This study aims to develop the first HSI-based automatic abdominal tissue recognition with human data in a prospective bi-center setting. METHODS: Data were collected from patients undergoing elective open abdominal surgery at two international tertiary referral hospitals from September 2020 to June 2021. HS images were captured at various time points throughout the surgical procedure. Resulting RGB images were annotated with 13 distinct organ labels. Convolutional Neural Networks (CNNs) were employed for the analysis, with both external and internal validation settings utilized. RESULTS: A total of 169 patients were included, 73 (43.2%) from Strasbourg and 96 (56.8%) from Verona. The internal validation within centers combined patients from both centers into a single cohort, randomly allocated to the training (127 patients, 75.1%, 585 images) and test sets (42 patients, 24.9%, 181 images). This validation setting showed the best performance. The highest true positive rate was achieved for the skin (100%) and the liver (97%). Misclassifications included tissues with a similar embryological origin (omentum and mesentery: 32%) or with overlaying boundaries (liver and hepatic ligament: 22%). The median DICE score for ten tissue classes exceeded 80%. CONCLUSION: To improve automatic surgical scene segmentation and to drive clinical translation, multicenter accurate HSI datasets are essential, but further work is needed to quantify the clinical value of HSI. HSI might be included in a new omics science, namely surgical optomics, which uses light to extract quantifiable tissue features during surgery.

Advancing laser ablation assessment in hyperspectral imaging through machine learning.

Hyperspectral imaging (HSI) is gaining increasing relevance in medicine, with an innovative application being the intraoperative assessment of the outcome of laser ablation treatment used for minimally invasive tumor removal. However, the high dimensionality and complexity of HSI data create a need for end-to-end image processing workflows specifically tailored to handle these data. This study addresses this challenge by proposing a multi-stage workflow for the analysis of hyperspectral data and allows investigating the performance of different components and modalities for ablation detection and segmentation. To address dimensionality reduction, we integrated principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) to capture dominant variations and reveal intricate structures, respectively. Additionally, we employed the Faster Region-based Convolutional Neural Network (Faster R-CNN) to accurately localize ablation areas. The two-stage detection process of Faster R-CNN, along with the choice of dimensionality reduction technique and data modality, significantly influenced the performance in detecting ablation areas. The evaluation of the ablation detection on an independent test set demonstrated a mean average precision of approximately 0.74, which validates the generalization ability of the models. In the segmentation component, the Mean Shift algorithm showed high quality segmentation without manual cluster definition. Our results prove that the integration of PCA, t-SNE, and Faster R-CNN enables improved interpretation of hyperspectral data, leading to the development of reliable ablation detection and segmentation systems.

Preoperative detection of hepatocellular carcinoma's microvascular invasion on CT-scan by machine learning and radiomics: A preliminary analysis.

INTRODUCTION: Microvascular invasion (MVI) is the main risk factor for overall mortality and recurrence after surgery for hepatocellular carcinoma (HCC).The aim was to train machine-learning models to predict MVI on preoperative CT scan. METHODS: 3-phases CT scans were retrospectively collected among 4 Italian centers. DICOM files were manually segmented to detect the liver and the tumor(s). Radiomics features were extracted from the tumoral, peritumoral and healthy liver areas in each phase. Principal component analysis (PCA) was performed to reduce the dimensions of the dataset. Data were divided between training (70%) and test (30%) sets. Random-Forest (RF), fully connected MLP Artificial neural network (neuralnet) and extreme gradient boosting (XGB) models were fitted to predict MVI. Prediction accuracy was estimated in the test set. RESULTS: Between 2008 and 2022, 218 preoperative CT scans were collected. At the histological specimen, 72(33.02%) patients had MVI. First and second order radiomics features were extracted, obtaining 672 variables. PCA selected 58 dimensions explaining >95% of the variance.In the test set, the XGB model obtained Accuracy = 68.7% (Sens: 38.1%, Spec: 83.7%, PPV: 53.3% and NPV: 73.4%). The neuralnet showed an Accuracy = 50% (Sens: 52.3%, Spec: 48.8%, PPV: 33.3%, NPV: 67.7%). RF was the best performer (Acc = 96.8%, 95%CI: 0.91-0.99, Sens: 95.2%, Spec: 97.6%, PPV: 95.2% and NPV: 97.6%). CONCLUSION: Our model allowed a high prediction accuracy of the presence of MVI at the time of HCC diagnosis. This could lead to change the treatment allocation, the surgical extension and the follow-up strategy for those patients.

Ventilaçäo näo-ivasiva com pressäo positiva em pacientes com insuficiência respiratória aguda / Non-ivasive positive pressure ventilation in patients with acute respiratory failure

Estudos recentes qugerem que ventilaçäo näo-ivasiva com pressäo positiva(VNIPP) na insuficiência respiratória aguda é capaz de produzir melhora clínica e gasométrica, além de diminuir a necessidade de intubaçäo traqueal. Neste estudo prospectivo, aberto, realizado na Unidade de Terapia Intensiva do Hospital Universitário da Universidade Federal de Juiz de Fora, os autores objetivaram avaliar a eficácia e segurança da utilizaçäo da VNIPP em pacientes com insuficiência respiratória aguda. Vinte e cinco pacientes com diagnóstico clínico ou gasométrico de insuficiência respiratória (após suplementaçäo de oxigênio, persistência de freqüência respiratória maior que 24rpm, ou utilizaçäo de musculatura acessória da respiraçäo, ou PaO2 < 60mmHg, ou PaCO2 > 50mmHg) foram tratados com VNIPP. Quinze pacientes (60 por cento) obtiveram sucesso no tratamento, sem necessidade de intubaçäo traqueal. Após duas horas de VNIPP houve reduçäo da freqüência respiratória (de36 ñ 2rpm para 26 ñ 1rpm, p < 0,01) e melhora da PaO2 (de 76 ñ 6mmHg para 100 ñ 12mmHg, p < 0,05). Entre os pacientes que estavam com hipercapnia, após 2 horas houve reduçäo da PaCO2 (de 60 ñ 2mmHg para 49 ñ 3mmHg, p < 0,05). Quatro pacientes (16 por cento) apresentaram complicaçöes (lesäo da pele em contato com a máscara), porém em apenas um houve necessidade de suspensäo da ventilaçäo. Entre os dez pacientes que näo obtiveram sucesso, três näo se adaptaram ao método, impossibilitando sua aplicaçäo, enquanto em sete o suporte ventilatório teve que ser interrompido. os autores concluem que a VNIPP é uma opçäo segura e que pode ser utilizada no tratamento da insuficiência respiratória aguda em pacientes selecionados, com o objetivo de tentar evitar a intubaçäo traqueal