Automatic detection of cotton balls during brain surgery: Where deep learning meets ultrasound imaging to tackle foreign objects.
Author
Mahapatra, SmrutiBalamurugan, Manish
Chung, Kathryn
Kuppoor, Venkat
Curry, Eli
Aghabaglau, Fariba
Kaovasia, Tarana Parvez
Acord, Molly
Ainechi, Ana
Kim, Jeong Hun
Tshey, Yohannes
Ghinda, Christina Diana
Son, Jennifer K
Pustavoitau, Aliaksei
Tyler, Betty
Robinson, Shenandoah D
Theodore, Nicholas
Brem, Henry
Huang, Judy
Manbachi, Amir
Date
2021-02-26Journal
Proceedings of SPIE--the International Society for Optical EngineeringPublisher
SPIE, The International Society for Optical EngineeringType
Article
Metadata
Show full item recordAbstract
Cotton balls are a versatile and efficient tool commonly used in neurosurgical procedures to absorb fluids and manipulate delicate tissues. However, the use of cotton balls is accompanied by the risk of accidental retention in the brain after surgery. Retained cotton balls can lead to dangerous immune responses and potential complications, such as adhesions and textilomas. In a previous study, we showed that ultrasound can be safely used to detect cotton balls in the operating area due to the distinct acoustic properties of cotton compared with the acoustic properties of surrounding tissue. In this study, we enhance the experimental setup using a 3D-printed custom depth box and a Butterfly IQ handheld ultrasound probe. Cotton balls were placed in variety of positions to evaluate size and depth detectability limits. Recorded images were then analyzed using a novel algorithm that implements recently released YOLOv4, a state-of-the-art, real-time object recognition system. As per the radiologists' opinion, the algorithm was able to detect the cotton ball correctly 61% of the time, at approximately 32 FPS. The algorithm could accurately detect cotton balls up to 5mm in diameter, which corresponds to the size of surgical balls used by neurosurgeons, making the algorithm a promising candidate for regular intraoperative use.Keyword
Deep learningneuroimaging
object detection
recognition system
retained foreign object
ultrasound
Identifier to cite or link to this item
http://hdl.handle.net/10713/18154ae974a485f413a2113503eed53cd6c53
10.1117/12.2580887
Scopus Count
Collections
Related articles
- Automatic detection of foreign body objects in neurosurgery using a deep learning approach on intraoperative ultrasound images: From animal models to first in-human testing.
- Authors: Abramson HG, Curry EJ, Mess G, Thombre R, Kempski-Leadingham KM, Mistry S, Somanathan S, Roy L, Abu-Bonsrah N, Coles G, Doloff JC, Brem H, Theodore N, Huang J, Manbachi A
- Issue date: 2022
- Minimizing cotton ball retention in neurological procedures.
- Authors: Bechtold R, Garlow B, Liu R, Tandon A, Szewc A, Zhu W, Musmanno O, Gorelick N, Suk I, Huang J, Brem H, Manbachi A, Coles G
- Issue date: 2020 Apr
- Minimizing cotton retention in neurosurgical procedures: which imaging modality can help?
- Authors: Bechtold R, Tselepidakis N, Garlow B, Glaister S, Zhu W, Liu R, Szewc A, Tandon A, Buono Z, Pitingolo J, Madalo C, Ferrara I, Shale C, Benassi T, Belzberg M, Gorelick N, Hwang B, Molina CA, Coles G, Tyler B, Suk I, Huang J, Brem H, Manbachi A
- Issue date: 2020 Feb
- Assessing individual performance and maintaining breath sample integrity in biomedical detection dogs.
- Authors: Reeve C, Wentzell P, Wielens B, Jones C, Stehouwer K, Gadbois S
- Issue date: 2018 Oct
- The use of cotton balls to collect infant urine samples for 2H/1H and 18O/16O isotope ratio measurements.
- Authors: Wong WW, Clarke LL, Llaurador M, Ferlic L, Klein PD
- Issue date: 1993 Aug