Impact of color augmentation and tissue type in deep learning for hematoxylin and eosin image super resolution

Manuel, Cyrus; Zehnder, Philip; Kaya, Sertan; Sullivan, Ruth; Hu, Fangyao

doi:10.1016/j.jpi.2022.100148

Cited by 6 publications

(5 citation statements)

References 31 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acquiring high-resolution WSI is essential for accurate diagnosis in digital pathology and AI applications (34).…”

Section: Device-dependent Challengesmentioning

confidence: 99%

“…Apart from the color changes and distortions in the glass slides, the colors obtained in the final image WSI may differ biggest challenge (33). The real time inference and training phase get slower with the increase of the per slide and overall size of the data (33,34). When it is not possible to use WSI due to memory hardware limitations, the images divide into patches and output patches tile.…”

Section: Color Standardization and Normalizationmentioning

confidence: 99%

“…Acquiring high-resolution WSI is essential for accurate diagnosis in digital pathology and AI applications ( 33 ). During the acquisition of WSI, there may be problems with the device due to the optical and hardware parts and software that digitize the information from the optical source and sensor.…”

Section: Challengesmentioning

confidence: 99%

“…Color normalization is essential during the preparation of input and output data in AI applications to get the high-performing models ( 39 ). However, AI stain normalization applications ( 38 ) face challenges especially for real-time applications: the memory and run-time bottlenecks associated with the processing of images in high resolution, e.g., 40x ( 33 ). Moreover, stain normalization can be sensitive to the quality of the input images, e.g., when they contain stain spots or dirt.…”

Section: Challengesmentioning

confidence: 99%

See 3 more Smart Citations

Whole slide images in artificial intelligence applications in digital pathology: challenges and pitfalls

Kayhan¹,

Ozyoruk²,

Demır³

2023

TJPATH

View full text Add to dashboard Cite

The use of digitized data in pathology research is rapidly increasing. The whole slide image (WSI) is an indispensable part of the visual examination of slides in digital pathology and artificial intelligence applications; therefore, the acquisition of WSI with the highest quality is essential. Unlike the conventional routine of pathology, the digital conversion of tissue slides and the differences in its use pose difficulties for pathologists. We categorized these challenges into three groups: before, during, and after the WSI acquisition. The problems before WSI acquisition are usually related to the quality of the glass slide and reflect all existing problems in the analytical process in pathology laboratories. WSI acquisition problems are dependent on the device used to produce the final image file. They may be related to the parts of the device that create an optical image or the hardware and software that enable digitization. Post-WSI acquisition issues are related to the final image file itself, which is the final form of this data, or the software and hardware that will use this file. Because of the digital nature of the data, most of the difficulties are related to the capabilities of the hardware or software. Being aware of the challenges and pitfalls of using digital pathology and AI will make pathologists' integration to the new technologies easier in their daily practice or research.

show abstract

“…Acquiring high-resolution WSI is essential for accurate diagnosis in digital pathology and AI applications (34).…”

Section: Device-dependent Challengesmentioning

confidence: 99%

Section: Color Standardization and Normalizationmentioning

confidence: 99%

Section: Challengesmentioning

confidence: 99%

Section: Challengesmentioning

confidence: 99%

See 2 more Smart Citations

Whole slide images in artificial intelligence applications in digital pathology: challenges and pitfalls

Kayhan¹,

Ozyoruk²,

Demır³

2023

TJPATH

View full text Add to dashboard Cite

show abstract

“…To our knowledge, we have introduced a multiscale model (MSR) for the first time that demonstrates no significant difference in diagnostic consistency between 100 paired SR and HR regions of interest (ROIs) from some typical diseases [31,32]. Subsequent studies have further confirmed that SR generation can generate high-quality pathological images [33][34][35]. However, there is not yet sufficient evidence to demonstrate the overall diagnose performance of SR WSIs on a large scale, in particular, whether SR images can establish accurate AIPs.…”

Section: Introduction：mentioning

confidence: 99%

Accurate diagnosis achieved via super-resolution whole slide images by pathologists and artificial intelligence

Wang,

Liu,

Chen

et al. 2024

Preprint

View full text Add to dashboard Cite

BackgroundDigital pathology significantly improves diagnostic efficiency and accuracy; however, pathological tissue sections are scanned at high resolutions (HR), magnified by 40 times (40X) incurring high data volume, leading to storage bottlenecks for processing large numbers of whole slide images (WSIs) for later diagnosis in clinic and hospitals.MethodWe propose to scan at a magnification of 5 times (5X). We developed a novel multi-scale deep learning super-resolution (SR) model that can be used to accurately computes 40X SR WSIs from the 5X WSIs.ResultsThe required storage size for the resultant data volume of 5X WSIs is only one sixty-fourth (less than 2%) of that of 40X WSIs. For comparison, three pathologists used 40X scanned HR and 40X computed SR WSIs from the same 480 histology glass slides spanning 47 diseases (such tumors, inflammation, hyperplasia, abscess, tumor-like lesions) across 12 organ systems. The results are nearly perfectly consistent with each other, with Kappa values (HR and SR WSIs) of 0.988±0.018, 0.924±0.059, and 0.966±0.037, respectively, for the three pathologists. There were no significant differences in diagnoses of three pathologists between the HR and corresponding SR WSIs, with Area under the Curve (AUC): 0.920±0.164 vs. 0.921±0.158 (p-value=0.653), 0.931±0.128 vs. 0.943±0.121 (p-value=0.736), and 0.946±0.088 vs. 0.941±0.098 (p-value=0.198). A previously developed highly accurate colorectal cancer artificial intelligence system (AI) diagnosed 1,821 HR and 1,821 SR WSIs, with AUC values of 0.984±0.016 vs. 0.984±0.013 (p-value=0.810), again with nearly perfect matching results.ConclusionsThe pixel numbers of 5X WSIs is only less than 2% of that of 40X WSIs. The 40X computed SR WSIs can achieve accurate diagnosis comparable to 40X scanned HR WSIs, both by pathologists and AI. This study provides a promising solution to overcome a common storage bottleneck in digital pathology.

show abstract

Generative Adversarial Networks in Digital Histopathology: Current Applications, Limitations, Ethical Considerations, and Future Directions

Alajaji,

Khoury,

Elgharib

et al. 2024

Modern Pathology

View full text Add to dashboard Cite

Impact of color augmentation and tissue type in deep learning for hematoxylin and eosin image super resolution

Cited by 6 publications

References 31 publications

Whole slide images in artificial intelligence applications in digital pathology: challenges and pitfalls

Whole slide images in artificial intelligence applications in digital pathology: challenges and pitfalls

Accurate diagnosis achieved via super-resolution whole slide images by pathologists and artificial intelligence

Generative Adversarial Networks in Digital Histopathology: Current Applications, Limitations, Ethical Considerations, and Future Directions

Contact Info

Product

Resources

About