HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images

Chan, Lyndon; Hosseini, Mahdi S.; Rowsell, Corwyn; Plataniotis, Konstantinos N.; Damaskinos, Savvas

doi:10.1109/iccv.2019.01076

Cited by 90 publications

(73 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To lower the need for manual training annotations, Mahmood et al [25] proposed a method to synthesize H&E patches from segmentation masks using adversarial methods followed by training networks on them for nuclei segmentation. Chan et al [26] proposed a weakly supervised method for semantic segmentation of histological tissue subtype.…”

Section: Introductionmentioning

confidence: 99%

Domain Adaptation-Based Deep Learning for Automated Tumor Cell (TC) Scoring and Survival Analysis on PD-L1 Stained Tissue Images

Kapil

Meier

Steele

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

We report the ability of two deep learningbased decision systems to stratify non-small cell lung cancer (NSCLC) patients treated with checkpoint inhibitor therapy into two distinct survival groups. Both systems analyze functional and morphological properties of epithelial regions in digital histopathology whole slide images stained with the SP263 PD-L1 antibody. The first system learns to replicate the pathologist assessment of the Tumor Cell (TC) score with a cut-point for positivity at 25% for patient stratification. The second system is free from assumptions related to TC scoring and directly learns patient stratification from the overall survival time and event information. Both systems are built on a novel unpaired domain adaptation deep learning solution for epithelial region segmentation. This approach significantly reduces the need for large pixel-precise manually annotated datasets while superseding serial sectioning or re-staining of slides to obtain ground truth by cytokeratin staining. The capacity of the first system to replicate the TC scoring by pathologists is evaluated on 703 unseen cases, with an addition of 97 cases from an independent cohort. Our results show Lin's concordance values of 0.93 and 0.96 against pathologist scoring, respectively. The ability of the first and second system to stratify anti-PD-L1 treated patients is evaluated on 151 clinical samples. Both systems show similar stratification powers (first system: HR =0.539, p=0.004 and second system: HR=0.525, p=0.003) compared to TC scoring by pathologists (HR=0.574, p=0.01).

show abstract

Section: Introductionmentioning

confidence: 99%

Domain Adaptation-Based Deep Learning for Automated Tumor Cell (TC) Scoring and Survival Analysis on PD-L1 Stained Tissue Images

Kapil

Meier

Steele

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…While Label Augmentation did not give encouraging results here, the idea of of incorporating contour uncertainty into learning should not be abandoned, and may lead to ways to deal more specifically with the type of imperfection exemplified in our "deformed" datasets. Finally, it would be interesting to study the impact of SNOW annotations in the case of multi-class segmentations 32 .…”

Section: Discussionmentioning

confidence: 99%

Snow Supervision in Digital Pathology: Managing Imperfect Annotations for Segmentation in Deep Learning

Foucart

Debeir

Decaestecker

2020

Preprint

View full text Add to dashboard Cite

In digital pathology, image segmentation algorithms are usually ranked on clean, benchmark datasets. However, annotations in digital pathology are hard, time-consuming and by nature imperfect. We expand on the SNOW (Semi-, Noisy and/or Weak) supervision concept introduced in an earlier work to characterize such data supervision imperfections. We analyse the effects of SNOW supervision on typical DCNNs, and explore learning strategies to counteract those effects. We apply those lessons to the real-world task of artefact detection in whole-slide imaging. Our results show that SNOW supervision has an important impact on the performances of DCNNs and that relying on benchmarks and challenge datasets may not always be relevant for assessing algorithm performance. We show that a learning strategy adapted to SNOW supervision, such as “Generative Annotations", can greatly improve the results of DCNNs on real-world datasets.

show abstract

“…An example from top to lowest level would be Epithelium - Simple Epithelium - Simple Squamous Epithelium. Using this Atlas of Digital Pathology, Chan et al [ 82 ] then trained a model that can segment out 31 of the tissue types in the database across over more than 10 organ types. The generalizability of the model may be attributed to the non-organ-specific nature of the tissue types in the Atlas of Digital Pathology.…”

Section: Challenges Moving Forwardmentioning

confidence: 99%

State of machine and deep learning in histopathological applications in digestive diseases

Kobayashi¹,

Saltz²,

Yang³

2021

WJG

View full text Add to dashboard Cite

Machine learning (ML)- and deep learning (DL)-based imaging modalities have exhibited the capacity to handle extremely high dimensional data for a number of computer vision tasks. While these approaches have been applied to numerous data types, this capacity can be especially leveraged by application on histopathological images, which capture cellular and structural features with their high-resolution, microscopic perspectives. Already, these methodologies have demonstrated promising performance in a variety of applications like disease classification, cancer grading, structure and cellular localizations, and prognostic predictions. A wide range of pathologies requiring histopathological evaluation exist in gastroenterology and hepatology, indicating these as disciplines highly targetable for integration of these technologies. Gastroenterologists have also already been primed to consider the impact of these algorithms, as development of real-time endoscopic video analysis software has been an active and popular field of research. This heightened clinical awareness will likely be important for future integration of these methods and to drive interdisciplinary collaborations on emerging studies. To provide an overview on the application of these methodologies for gastrointestinal and hepatological histopathological slides, this review will discuss general ML and DL concepts, introduce recent and emerging literature using these methods, and cover challenges moving forward to further advance the field.

show abstract

HistoSegNet: Semantic Segmentation of Histological Tissue Type in Whole Slide Images

Cited by 90 publications

References 35 publications

Domain Adaptation-Based Deep Learning for Automated Tumor Cell (TC) Scoring and Survival Analysis on PD-L1 Stained Tissue Images

Domain Adaptation-Based Deep Learning for Automated Tumor Cell (TC) Scoring and Survival Analysis on PD-L1 Stained Tissue Images

Snow Supervision in Digital Pathology: Managing Imperfect Annotations for Segmentation in Deep Learning

State of machine and deep learning in histopathological applications in digestive diseases

Contact Info

Product

Resources

About