A Portable System for On-Site Medical Spectral Imaging: Pre-Clinical Development and Early Evaluation

Bartczak, Piotr; Iso-Mustajärvi, Matti; Vrzáková, Hana; Bednarik, Roman; Fraunberg, Mikael von und zu; Elomaa, Antti-Pekka

doi:10.1109/cbms.2018.00052

Cited by 1 publication

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When FN is investigated, the most feasible wavelengths were focused on longer VIS wavelengths, namely, above 644 nm. We did not compare these samples to any other tissues in this study; however, the medium-to-high spectral region has been found most relevant earlier in ex vivo temporal bone and soft tissue studies ( Bartczak et al, 2018 ; Wisotzky et al, 2018 ).…”

Section: Discussionmentioning

confidence: 99%

“…In addition, a light-absorbing cloth was used to cover the cart to prevent the surrounding light pollution from distorting the measurement. The experimental setup, including image calibration and schematics, has been thoroughly described by Bartczak et al (2018) .…”

Section: Methodsmentioning

confidence: 99%

“…In this study, the spectral properties of ex vivo bone, dura mater, muscle, fat, and carotid artery all exhibit a unique spectral signature. The authors considered intraoperative requirements and highlighted that short capture times are required for operation room conditions ( Bartczak et al, 2018 ). In particular, liquid crystal tunable filter (LCTF)-based systems appear clinically feasible since they do not require mechanical filter adjustment and enable band selection ( Gebhart et al, 2005 ; Nouri et al, 2014 ).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spectrally Tunable Neural Network-Assisted Segmentation of Microneurosurgical Anatomy

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background Distinct tissue types are differentiated based on the surgeon’s knowledge and subjective visible information, typically assisted with white-light intraoperative imaging systems. Narrow-band imaging (NBI) assists in tissue identification and enables automated classifiers, but many anatomical details moderate computational predictions and cause bias. In particular, tissues’ light-source-dependent optical characteristics, anatomical location, and potentially hazardous microstructural changes such as peeling have been overlooked in previous literature. Methods Narrow-band images of five ( n = 5) facial nerves (FNs) and internal carotid arteries (ICAs) were captured from freshly frozen temporal bones. The FNs were split into intracranial and intratemporal samples, and ICAs’ adventitia was peeled from the distal end. Three-dimensional (3D) spectral data were captured by a custom-built liquid crystal tunable filter (LCTF) spectral imaging (SI) system. We investigated the normal variance between the samples and utilized descriptive and machine learning analysis on the image stack hypercubes. Results Reflectance between intact and peeled arteries in lower-wavelength domains between 400 and 576 nm was significantly different ( p < 0.05). Proximal FN could be differentiated from distal FN in a higher range, 490–720 nm ( p < 0.001). ICA with intact tunica differed from proximal FN nearly thorough the VIS range, 412–592 nm ( p < 0.001) and 664–720 nm ( p < 0.05) as did its distal counterpart, 422–720 nm ( p < 0.001). The availed U-Net algorithm classified 90.93% of the pixels correctly in comparison to tissue margins delineated by a specialist. Conclusion Selective NBI represents a promising method for assisting tissue identification and computational segmentation of surgical microanatomy. Further multidisciplinary research is required for its clinical applications and intraoperative integration.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%