2020
DOI: 10.1038/s41591-019-0715-9
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Intraoperative diagnosis is essential for providing safe and effective care during cancer surgery 1. The existing workflow for intraoperative diagnosis based on hematoxylin and eosin-staining of processed tissue is time-, resource-, and labor-intensive 2,3. Moreover, interpretation of intraoperative histologic images is dependent on a contracting, unevenly distributed pathology workforce 4. Here, we report a parallel workflow that combines stimulated Raman histology (SRH) 5-7 , a label-free optical imaging met… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

3
233
0
2

Year Published

2020
2020
2023
2023

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 427 publications
(238 citation statements)
references
References 31 publications
3
233
0
2
Order By: Relevance
“…Over the past year, technology companies have made headlines claiming that their artificially intelligent (AI) products can outperform clinicians at diagnosing breast cancer,1 brain tumours,2 and diabetic retinopathy 3. Claims such as these have influenced policy makers, and AI now forms a key component of the national health strategies in England, the United States, and China.…”
mentioning
confidence: 99%
“…Over the past year, technology companies have made headlines claiming that their artificially intelligent (AI) products can outperform clinicians at diagnosing breast cancer,1 brain tumours,2 and diabetic retinopathy 3. Claims such as these have influenced policy makers, and AI now forms a key component of the national health strategies in England, the United States, and China.…”
mentioning
confidence: 99%
“…Two series of LRS studies on brain cancer are particularly encouraging. Hollon et al [74] have recently reported on the utility of an NN trained on over 2.5 million simulated Raman histology images to predict brain tumor diagnosis in an operating room under 150 s. They report an accuracy of 94.6% compared to pathologist interpretation which had an accuracy of 93.9% [74]. The work is an excellent example of the computational challenges amenable to current NN algorithms.…”
Section: Discussionmentioning
confidence: 99%
“…Since there is no universal instrumentation or standard operating procedure in the clinic, structured training data in which a sample's true class juxtaposes its Raman spectrum cannot be translated from the bench. Deep learning (DL) uses artificial neural networks (ANNs) to circumvent this issue, and several designs such as convolutional neural networks (CNNs) in image analysis and data mining have been successfully applied to other spectroscopic techniques such as fluorescence lifetime imaging microscopy (FLIM), and multiphoton light-sheet microscopy (Hollon et al, 2020;Krauß et al, 2018;Suzuki et al, 2019). Taylor et al (2019) reported a work on high-resolution Raman microscopic detection of follicular thyroid cancer cells with unsupervised ML obtained a more accurate (89.8%) distinction of FTC-133 and Nthy-ori 3-1, in comparison to single-cell spectra (77.6%).…”
Section: Modality Of Raman Imaging On Tissuesmentioning
confidence: 99%
“…The semantic boundaries can be digitally stained and clearly separated. These may refer to tumors, traumatic brain injury (TBI), or any morphological and metabolic difference that can result in spectral differences (Hollon et al, 2020).…”
Section: Modality Of Raman Imaging On Tissuesmentioning
confidence: 99%
See 1 more Smart Citation