Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Dec;407(8):3553-3560.
doi: 10.1007/s00423-022-02674-7. Epub 2022 Sep 7.

Artificial intelligence for identification of focal lesions in intraoperative liver ultrasonography

Yiftach Barash  1 , Eyal Klang  1 , Adar Lux  1 , Eli Konen  1 , Nir Horesh  2 , Ron Pery  2 , Nadav Zilka  2 , Rony Eshkenazy  2 , Ido Nachmany #  2 , Niv Pencovich #  3
Affiliations

Artificial intelligence for identification of focal lesions in intraoperative liver ultrasonography

Yiftach Barash et al. Langenbecks Arch Surg. 2022 Dec.

Abstract

Purpose: Intraoperative ultrasonography (IOUS) of the liver is a crucial adjunct in every liver resection and may significantly impact intraoperative surgical decisions. However, IOUS is highly operator dependent and has a steep learning curve. We describe the design and assessment of an artificial intelligence (AI) system to identify focal liver lesions in IOUS.

Methods: IOUS images were collected during liver resections performed between November 2020 and November 2021. The images were labeled by radiologists and surgeons as normal liver tissue versus images that contain liver lesions. A convolutional neural network (CNN) was trained and tested to classify images based on the labeling. Algorithm performance was tested in terms of area under the curves (AUCs), accuracy, sensitivity, specificity, F1 score, positive predictive value, and negative predictive value.

Results: Overall, the dataset included 5043 IOUS images from 16 patients. Of these, 2576 were labeled as normal liver tissue and 2467 as containing focal liver lesions. Training and testing image sets were taken from different patients. Network performance area under the curve (AUC) was 80.2 ± 2.9%, and the overall classification accuracy was 74.6% ± 3.1%. For maximal sensitivity of 99%, the classification specificity is 36.4 ± 9.4%.

Conclusions: This study provides for the first time a proof of concept for the use of AI in IOUS and show that high accuracy can be achieved. Further studies using high volume data are warranted to increase accuracy and differentiate between lesion types.

Keywords: Deep learning; Hepatectomy; Machine learning; Neural networks; Ultrasonic diagnosis.

PubMed Disclaimer

References

    1. Lubner MG, Mankowski Gettle L, Kim DH, Ziemlewicz TJ, Dahiya N, Pickhardt P (2021) Diagnostic and procedural intraoperative ultrasound: technique, tips and tricks for optimizing results. Br J Radiol 94(1121):20201406. https://doi.org/10.1259/bjr.20201406 - DOI
    1. Kamiyama T, Kakisaka T, Orimo T (2021) Current role of intraoperative ultrasonography in hepatectomy. Surg Today 51(12):1887–1896. https://doi.org/10.1007/s00595-020-02219-9 - DOI
    1. Hagopian EJ (2020) Liver ultrasound: a key procedure in the surgeon’s toolbox. J Surg Oncol 122(1):61–69. https://doi.org/10.1002/jso.25908 - DOI
    1. Ellebaek SB, Fristrup CW, Mortensen MB (2017) Intraoperative ultrasound as a screening modality for the detection of liver metastases during resection of primary colorectal cancer -a systematic review. Ultrasound Int Open 3(2):E60–E68. https://doi.org/10.1055/s-0043-100503 - DOI
    1. Arita J, Ono Y, Takahashi M, Inoue Y, Takahashi Y, Matsueda K, Saiura A (2015) Routine preoperative liver-specific magnetic resonance imaging does not exclude the necessity of contrast-enhanced intraoperative ultrasound in hepatic resection for colorectal liver metastasis. Ann surg 262(6):1086–1091. https://doi.org/10.1097/SLA.0000000000001085 - DOI

LinkOut - more resources