See the published version of this preprint at Scientific Reports.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
Research Article
Chulhong Kim
Pohang University of 18 Science and Technology (POSTECH)
Corresponding Author
License:
This work is licensed under a CC BY 4.0 License. Read Full License
Automatic pattern recognition using deep learning techniques has become increasingly important. Unfortunately, due to limited system memory, general preprocessing methods for high-resolution images in the spatial domain can lose important data information such as high-frequency information and the region of interest. To overcome these limitations, we propose an image segmentation approach in the compressed domain based on principal component analysis (PCA) and discrete wavelet transform (DWT). After inference for each tile using neural networks, a whole prediction image was reconstructed by wavelet weighted ensemble (WWE) based on inverse discrete wavelet transform (IDWT). The training and validation were performed using 351 colorectal biopsy specimens, which were pathologically confirmed by two pathologists. For 39 test datasets, the average Dice score was 0.852 ± 0.086 and the pixel accuracy was 0.962 ± 0.027. We can train the networks for the high-resolution image (magnification x20) compared to the result in the spatial domain (magnification x10) in same the region of interest (6.25 × 10^2 um^2). The average Dice score and pixel accuracy are significantly increased by 6.4 % and 1.6 %, respectively. We believe that our approach has great potential for accurate diagnosis in pathology.
Keywords
Deep Learning, Histopathological Segmentation, Colorectal Cancer, Compressed Domain
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
The full text of this article is available to read as a PDF.
No competing interests reported.
This is a list of supplementary files associated with this preprint. Click to download.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at Scientific Reports.
Version 1
Posted 02 Jun, 2021
No community comments so far
Editorial decision: Major revision
On 11 Aug, 2021
Reviews received
Received 22 Jul, 2021
Reviewers agreed
On 13 Jul, 2021
Reviewers agreed
On 26 Jun, 2021
Reviewers invited
Invitations sent on 26 Jun, 2021
Editor assigned
On 26 Jun, 2021
Editor invited
On 02 Jun, 2021
Submission checks complete
On 31 May, 2021
First submitted
On 17 May, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Learn more about our company.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
See the published version of this preprint at Scientific Reports.
This is a preprint, a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research Article
Chulhong Kim
Pohang University of 18 Science and Technology (POSTECH)
Corresponding Author
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Published
View the published article at Scientific Reports.
Version 1
Posted 02 Jun, 2021
No community comments so far
Editorial decision: Major revision
On 11 Aug, 2021
Reviews received
Received 22 Jul, 2021
Reviewers agreed
On 13 Jul, 2021
Reviewers agreed
On 26 Jun, 2021
Reviewers invited
Invitations sent on 26 Jun, 2021
Editor assigned
On 26 Jun, 2021
Editor invited
On 02 Jun, 2021
Submission checks complete
On 31 May, 2021
First submitted
On 17 May, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
License:
This work is licensed under a CC BY 4.0 License. Read Full License
View the published article at Scientific Reports.
Automatic pattern recognition using deep learning techniques has become increasingly important. Unfortunately, due to limited system memory, general preprocessing methods for high-resolution images in the spatial domain can lose important data information such as high-frequency information and the region of interest. To overcome these limitations, we propose an image segmentation approach in the compressed domain based on principal component analysis (PCA) and discrete wavelet transform (DWT). After inference for each tile using neural networks, a whole prediction image was reconstructed by wavelet weighted ensemble (WWE) based on inverse discrete wavelet transform (IDWT). The training and validation were performed using 351 colorectal biopsy specimens, which were pathologically confirmed by two pathologists. For 39 test datasets, the average Dice score was 0.852 ± 0.086 and the pixel accuracy was 0.962 ± 0.027. We can train the networks for the high-resolution image (magnification x20) compared to the result in the spatial domain (magnification x10) in same the region of interest (6.25 × 10^2 um^2). The average Dice score and pixel accuracy are significantly increased by 6.4 % and 1.6 %, respectively. We believe that our approach has great potential for accurate diagnosis in pathology.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
The full text of this article is available to read as a PDF.
No competing interests reported.
This is a list of supplementary files associated with this preprint. Click to download.
Loading...