Contrast-enhanced intra-operative ultrasound as a clinical decision making tool during surgery for colorectal liver metastases: The ULIIS study

An artificial intelligence-based recognition model of colorectal liver metastases in intraoperative ultrasonography with improved accuracy through algorithm integration

BACKGROUND/PURPOSE

Contrast-enhanced intraoperative ultrasonography (CE-IOUS) is crucial for detecting colorectal liver metastases (CLM) during surgery. Although artificial intelligence shows potential in diagnostic systems, its application in CE-IOUS is limited.

METHODS

This study aimed to develop an automatic tumor detection model using Mask region-based convolutional neural network (Mask R-CNN) for CE-IOUS images. CE-IOUS videos of the CLM from 121 patients were collected, generating ground truth data. A total of 2659 images were obtained. Two models were developed: the basic recognition model (BRM), which was trained on CE-mode images, and the subtraction model (SM), which used images created by a subtraction algorithm that highlighted the differences in pixel values between the basic-mode and CE-mode images. The subtraction algorithm focuses on echogenicity differences. These two models were combined into a combination model (CM), which assessed outcomes using the prediction probabilities from both models.

RESULTS

The optimal epochs were determined by the maximum area under the curve (AUC), and the thresholds were calculated accordingly. BRM, SM, and CM achieved 89.4%, 86.6%, and 96.5% accuracy, respectively. CM outperformed the individual models, achieving an AUC of 0.99.

CONCLUSIONS

A novel automated recognition model was developed for accurate CLM detection in CE-IOUS by integrating image- and algorithm-based models.

Ultrasonography - a novel auxiliary interpretive approach for tuberculin-purified pure protein derivative skin test: a comparative study

BACKGROUND

The tuberculin-purified protein derivative (PPD) test is commonly used as a screening tool for tuberculosis (TB). However, the traditional judgment standard of the PPD test is influenced by subjective factors, which can lead to less accurate and intuitive test results.

OBJECTIVES

To evaluate the accuracy of ultrasonography as a novel auxiliary judgment method for the tuberculin-PPD test and its clinical application.

DESIGN

This study was designed as a comparative study following the STROBE guidance.

METHODS

From February to May 2022, 208 patients with active tuberculosis infection were enrolled. Manual judgment and ultrasonography were employed in a double-blind-utilized manner, and the PPD examination results were recorded. Kappa statistic was performed to measure the concordance between the two diagnostic methods. Fisher's exact test was used for the analyses of the PPD test results of all 208 active tuberculosis infection patients' PPD results.

RESULTS

There was a significant difference between the two methods in the PPD result judgment (p < 0.001), particularly in the positive ratio of the PPD test results, (p < 0.05). Overall, 50 patients were determined as PPD positive based on manual judgment. However, only 24 patients' PPD test results were determined as positive via ultrasonography. The remaining 26 patients should have been classified as strong positive but were misclassified as positive. The misdiagnosis ratio was 52% (26/50).

CONCLUSION

Ultrasonography has superior accuracy to traditional manual judgment. Moreover, it does not rely on sophisticated clinical experience or training and can reveal subtle changes of the skin corresponding to each PPD test result providing intuitive results. In conclusion, ultrasonography can be used as an auxiliary interpretive approach for PPD test and has a promising future for clinical application.

Efficacy of Near-Infrared Fluorescence-Guided Hepatectomy for the Detection of Colorectal Liver Metastases: A Randomized Controlled Trial

BACKGROUND

The application of indocyanine green fluorescence-guided hepatectomy for liver metastases from colorectal cancer is in the preliminary stage of clinical practice; thus, its efficacy needs to be determined. This study compared the number of intrahepatic colorectal liver metastases detected intraoperatively and postoperative recovery data between patients who underwent traditional hepatectomy (nonindocyanine green group) and traditional hepatectomy plus intraoperative indocyanine green fluorescence imaging (indocyanine green group).

STUDY DESIGN

Between January 2018 and March 2020, patients with potentially resectable colorectal liver metastases were randomly assigned to the nonindocyanine green or indocyanine green group. The number of intrahepatic colorectal liver metastases identified intraoperatively and based on postoperative recovery data were compared between both groups.

RESULTS

Overall, we recruited 80 patients, among whom 72 eligible patients were randomly assigned. After allocation, 64 patients, comprising 32 in each group, underwent the allocated intervention and follow-up. Compared with the nonindocyanine green group, the mean number of intrahepatic colorectal liver metastases identified intraoperatively in the indocyanine green group was significantly greater (mean [standard deviation], 3.03 [1.58] vs 2.28 [1.35]; p = 0.045), the postoperative hospital stay was shorter (p = 0.012) and the 1-year recurrence rate was also lower (p = 0.017). Postoperative complications and 90-day mortality were comparable, with no statistical differences.

CONCLUSIONS

Indocyanine green fluorescence imaging significantly increases the number of intrahepatic colorectal liver metastases identified and reduces postoperative hospital stay and 1-year recurrence rate without increasing hepatectomy-related complications and mortality rates.

Improved sensitivity and positive predictive value of contrast-enhanced intraoperative ultrasound in colorectal cancer liver metastasis: a systematic review and meta-analysis

BACKGROUND

Surgery is an effective treatment for improving the survival rate of patients with colorectal cancer liver metastases (CRLM). However, accurately determining the resection margin of liver lesions during surgery remains challenging. Therefore, this study aimed to evaluate the sensitivity and predictive value of intraoperative contrast-enhanced ultrasound (CE-IOUS) in CRLM patients undergoing surgery.

METHODS

We performed a literature search of the PubMed, Cochrane Central Register of Controlled Trials, Embase, Web of Science, China National Knowledge Infrastructure (CNKI), Wanfang, and Weipu databases using the following search terms: metastatic liver cancer, colorectal cancer, sensitivity, contrast-enhanced intraoperative ultrasound, CE-IOUS, colorectal liver metastases, and CRLM. The search period was set from the date of establishment of the database to September 2021. Quality assessment of diagnostic accuracy studies 2 (QUADAS-2) recommended by the Cochrane Collaboration was used to assess the methodological quality of the included studies, and network meta-analysis was performed using Stata 15.0 software.

RESULTS

A total of 10 articles met the inclusion criteria. The meta-analysis results showed that the overall sensitivity and specificity of CE-IOUS were 0.96 [95% confidence interval (CI), 0.95-0.97] and 0.75 (95% CI, 0.70-0.80), respectively. The overall sensitivity and specificity of IOUS were 0.84 (95% CI, 0.82-0.86) and 0.82 (95% CI, 0.77-0.87), respectively. The area under the summary receiving operating characteristic (SROC) curves (AUCs) of CE-IOUS and IOUS were 0.9753 and 0.8590, respectively. The odds ratio (OR) and 95% CI of CE-IOUS changed the surgical margin were 0.205 and 0.071-0.465, P=0.000, the difference was statistically significant.

DISCUSSION

Based on the results of this meta-analysis, CE-IOUS improved the sensitivity and predictive value of CRLM detection compared with IOUS, and is more suitable for intraoperative planning of surgical margins. At present, it is the most sensitive imaging method available, and is recommended for use during liver resection to provide doctors with more reliable information during surgery.

Intraoperative (Contrast-Enhanced) Ultrasound Has the Highest Diagnostic Accuracy of Any Imaging Modality in Resection of Colorectal Liver Metastases

AIM

Defining sensitivity, specificity, diagnostic accuracy for detection of colorectal liver metastases in imaging compared to intraoperative assessment. Defining a cutoff, where accuracy of detection is impaired.

METHODS

Prospective single-institution clinical trial (clinicaltrials.gov: NCT01522209). Patients underwent CEUS, MDCT, and 3 Tesla EOB-MRI within 2 weeks preoperatively. Intraoperative palpation, IOUS, and CEIOUS were performed. A patient and lesion-based database was analyzed for accuracy of detection of CEUS, CT, MRI, and Palp/IOUS/CEIOUS combined read. Histology was standard of reference.

RESULTS

Forty-seven high tumor load (mean 5, 4 lesions) patients were analyzed. Histopathology confirmed 264 lesions (245 malignant: 19 benign). Accuracy for detection of all lesions: CEUS 63%, CT 71%, MRI 92%, and PALP/IOUS/CEIOUS 98%. ROC analysis for lesion size showed severe impairment of accuracy in lesion detection smaller than 5mm. Intraoperative imaging was not impaired by lesion size. Patient-based analysis revealed a change of resection plan after IOUS/CEIOUS in 35% of patients.

CONCLUSION

At 5-mm lesion size, preoperative imaging shows a drop in accuracy of detection. In patients with multiple lesions, addition of MRI to MDCT seems useful. Accuracy of intraoperative ultrasound is not impacted by lesion size and should be mandatory. CEIOUS can improve intraoperative decision-making.

TRIAL REGISTRATION

Study registered with clinicaltrials.gov : NCT01522209.

A meta-analysis evaluating contrast-enhanced intraoperative ultrasound (CE-IOUS) in the context of surgery for colorectal liver metastases

BACKGROUND

This study aimed to assess the outcomes of contrast-enhanced intraoperative ultrasound (CE-IOUS) for patients with colorectal liver metastases (CRLMs) undergoing surgery.

METHOD

A thorough literature search was performed in PubMed, Scopus, and Cochrane databases, in accordance with the PRISMA guidelines. The Odds Ratio, Weighted Mean Difference, and 95% Confidence Interval were evaluated, by means of Random-Effects model.

RESULTS

Eleven articles met the inclusion criteria and incorporated 497 patients. The present study shows that CE-IOUS is associated with higher sensitivity and accuracy compared with multidetector computed tomography (MDCT), magnetic resonance imaging (MRI), and intraoperative ultrasound (IOUS) in identifying CRLMs (p < 0.05). The positive predictive value was similar among the different modalities. Furthermore, new CRLMs were identified by CE-IOUS, thus affecting the surgical plan in 128 patients (51.8% of the patients with new CRLMs). Moreover, 91 patients (71%) underwent a more extensive hepatectomy and 15 patients (11.7%) were considered non-operable. Two alternative contrast agents, Sonazoid and Sonovue, were employed with similar sensitivity (p > 0.05).

CONCLUSION

These outcomes suggest the superiority of the CE-IOUS over MDCT, MRI, and IOUS for the staging of patients with CRLMs undergoing surgery. However, they should be treated with caution given the small number of the included studies.

Contrast-Enhanced Intraoperative Ultrasound Improved Sensitivity and Positive Predictive Value in Colorectal Liver Metastasis: a Systematic Review and Meta-Analysis

BACKGROUND

The diagnostic accuracy of imaging modalities in colorectal cancer liver metastases (CRLM) has improved in recent years, therefore the role of current imaging techniques needs to be defined.

OBJECTIVE

The aim of this study was to assess the diagnostic performance of magnetic resonance imaging, preoperative imaging (magnetic resonance imaging or computed tomography), intraoperative ultrasound, and contrast-enhanced intraoperative ultrasound in the detection of CRLM.

MATERIALS AND METHODS

Eligible trials published before 30 March 2020 were identified from the EMBASE, PubMed, Web of Science, and Cochrane Library databases, and descriptive and quantitative data were extracted. Study quality was evaluated for the identified studies and a random-effects model was used to determine the integrated diagnosis estimation. Meta-regression was implemented to explore the possible contributors to heterogeneity.

RESULTS

Overall, 13 studies were included for analysis, comprising 682 patients with a total of 2303 liver lesions. The pooled sensitivity, specificity, and diagnostic odds ratio of contrast-enhanced intraoperative ultrasound were 0.94 (95% confidence interval [CI] 0.89-0.97), 0.83 (95% CI 0.67-0.92), and 79 (95% CI 32-196), respectively. The overall weighted area under the curve was 0.96 (95% CI 0.94-0.97). In univariate meta-regression analysis, disappearing liver metastasis, contrast agent, and Kupffer phase were the potent sources of heterogeneity; however, in multivariate meta-regression, no definite variable was the source of the study heterogeneity.

CONCLUSION

Contrast-enhanced intraoperative ultrasound demonstrated a high sensitivity and specificity for screening CRLM.

Disappearing colorectal liver metastases: Strategies for the management of patients achieving a radiographic complete response after systemic chemotherapy

The mainstays of treatment for colorectal liver metastases (CRLMs) are surgery and chemotherapy. Chemotherapeutic benefits of tumor shrinkage and systemic control of micrometastases are in part counterbalanced by chemotoxicity that can modify the liver parenchyma, jeopardizing the detection of CRLM. This review addresses the clinical decision-making process in the context of radiographic and pathologic responses, the preoperative imaging workup, and the approaches to the liver for CRLM, which disappear after systemic chemotherapy.