Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model
The pathologists follow a systematic and partially manual process to obtain histological tissue sections from the biological tissue extracted from patients. This process is far from being perfect and can introduce some errors in the quality of the tissue sections (distortions, deformations, folds an...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2018-12-01
|
| Series: | Bulletin of the Polish Academy of Sciences: Technical Sciences |
| Subjects: | |
| Online Access: | https://journals.pan.pl/Content/109874/PDF/10_849-856_00807_Bpast.No.66-6_31.12.18_K2.pdf |
| _version_ | 1811314206834688000 |
|---|---|
| author | Z. Swiderska-Chadaj T. Markiewicz J. Gallego G. Bueno B. Grala M. Lorent |
| author_facet | Z. Swiderska-Chadaj T. Markiewicz J. Gallego G. Bueno B. Grala M. Lorent |
| author_sort | Z. Swiderska-Chadaj |
| collection | DOAJ |
| description | The pathologists follow a systematic and partially manual process to obtain histological tissue sections from the biological tissue extracted from patients. This process is far from being perfect and can introduce some errors in the quality of the tissue sections (distortions, deformations, folds and tissue breaks). In this paper, we propose a deep learning (DL) method for the detection and segmentation of these damaged regions in whole slide images (WSIs). The proposed technique is based on convolutional neural networks (CNNs) and uses the U-net model to achieve the pixel-wise segmentation of these unwanted regions. The results obtained show that this technique yields satisfactory results and can be applied as a pre-processing step for automatic WSI analysis in order to prevent the use of the damaged areas in the evaluation processes. |
| first_indexed | 2024-04-13T11:07:51Z |
| format | Article |
| id | doaj.art-8c1dccd3ae8f44daa1ec7f2ec4f5c715 |
| institution | Directory Open Access Journal |
| issn | 2300-1917 |
| language | English |
| last_indexed | 2024-04-13T11:07:51Z |
| publishDate | 2018-12-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Bulletin of the Polish Academy of Sciences: Technical Sciences |
| spelling | doaj.art-8c1dccd3ae8f44daa1ec7f2ec4f5c7152022-12-22T02:49:13ZengPolish Academy of SciencesBulletin of the Polish Academy of Sciences: Technical Sciences2300-19172018-12-0166No 6 (Special Section on Deep Learning: Theory and Practice)849856https://doi.org/10.24425/bpas.2018.125932Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net modelZ. Swiderska-ChadajT. MarkiewiczJ. GallegoG. BuenoB. GralaM. LorentThe pathologists follow a systematic and partially manual process to obtain histological tissue sections from the biological tissue extracted from patients. This process is far from being perfect and can introduce some errors in the quality of the tissue sections (distortions, deformations, folds and tissue breaks). In this paper, we propose a deep learning (DL) method for the detection and segmentation of these damaged regions in whole slide images (WSIs). The proposed technique is based on convolutional neural networks (CNNs) and uses the U-net model to achieve the pixel-wise segmentation of these unwanted regions. The results obtained show that this technique yields satisfactory results and can be applied as a pre-processing step for automatic WSI analysis in order to prevent the use of the damaged areas in the evaluation processes.https://journals.pan.pl/Content/109874/PDF/10_849-856_00807_Bpast.No.66-6_31.12.18_K2.pdfdamaged tissue regions detectionartifacts detectiondeep learningki-67 staining specimens |
| spellingShingle | Z. Swiderska-Chadaj T. Markiewicz J. Gallego G. Bueno B. Grala M. Lorent Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model Bulletin of the Polish Academy of Sciences: Technical Sciences damaged tissue regions detection artifacts detection deep learning ki-67 staining specimens |
| title | Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model |
| title_full | Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model |
| title_fullStr | Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model |
| title_full_unstemmed | Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model |
| title_short | Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model |
| title_sort | deep learning for damaged tissue detection and segmentation in ki 67 brain tumor specimens based on the u net model |
| topic | damaged tissue regions detection artifacts detection deep learning ki-67 staining specimens |
| url | https://journals.pan.pl/Content/109874/PDF/10_849-856_00807_Bpast.No.66-6_31.12.18_K2.pdf |
| work_keys_str_mv | AT zswiderskachadaj deeplearningfordamagedtissuedetectionandsegmentationinki67braintumorspecimensbasedontheunetmodel AT tmarkiewicz deeplearningfordamagedtissuedetectionandsegmentationinki67braintumorspecimensbasedontheunetmodel AT jgallego deeplearningfordamagedtissuedetectionandsegmentationinki67braintumorspecimensbasedontheunetmodel AT gbueno deeplearningfordamagedtissuedetectionandsegmentationinki67braintumorspecimensbasedontheunetmodel AT bgrala deeplearningfordamagedtissuedetectionandsegmentationinki67braintumorspecimensbasedontheunetmodel AT mlorent deeplearningfordamagedtissuedetectionandsegmentationinki67braintumorspecimensbasedontheunetmodel |