2021
DOI: 10.1038/s41598-021-86912-w
|View full text |Cite
|
Sign up to set email alerts
|

PathoNet introduced as a deep neural network backend for evaluation of Ki-67 and tumor-infiltrating lymphocytes in breast cancer

Abstract: The nuclear protein Ki-67 and Tumor infiltrating lymphocytes (TILs) have been introduced as prognostic factors in predicting both tumor progression and probable response to chemotherapy. The value of Ki-67 index and TILs in approach to heterogeneous tumors such as Breast cancer (BC) that is the most common cancer in women worldwide, has been highlighted in literature. Considering that estimation of both factors are dependent on professional pathologists’ observation and inter-individual variations may also exi… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
24
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
4

Relationship

0
9

Authors

Journals

citations
Cited by 43 publications
(28 citation statements)
references
References 40 publications
0
24
0
1
Order By: Relevance
“…(17,35,36). Numerous applications such as quantification of receptor status (37), estimation of Ki-67 index (38), or implementation into Ziehl-Neelsen staining (39) As a data-driven model, an unbiased and comprehensive training dataset is always preferred in an ideal condition. Our current model can be improved from the following aspects.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…(17,35,36). Numerous applications such as quantification of receptor status (37), estimation of Ki-67 index (38), or implementation into Ziehl-Neelsen staining (39) As a data-driven model, an unbiased and comprehensive training dataset is always preferred in an ideal condition. Our current model can be improved from the following aspects.…”
Section: Discussionmentioning
confidence: 99%
“…( 17 , 35 , 36 ). Numerous applications such as quantification of receptor status ( 37 ), estimation of Ki-67 index ( 38 ), or implementation into Ziehl-Neelsen staining ( 39 ) and Masson's Trichrome ( 40 ) are potentially feasible in cardiovascular studies as well. Besides generic image classification and segmentation, DNN has demonstrated its viability to synthesize pseudo H&E images from Raman spectroscopy and other multi-modality non-linear imaging techniques, augmenting non-invasive and in vivo diagnosis ( 41 ).…”
Section: Discussionmentioning
confidence: 99%
“…More recently, although alternative approaches are actively pursued [51][52][53][54], well consolidated methodologies derived by CNNs are still being used [55]. In particular, two families of algorithms deserve a mention for the rather large popularity gained in the last few years, both stemming from the original R-CNN model [56].…”
Section: Lymphocyte Detection and Density Mapsmentioning
confidence: 99%
“…Garcia et al (20) proposed a deep learning model to count TILs in IHC images of gastric cancer tissue samples by using a model trained with 70x70 square pixel patches extracted from biopsy micrographs scanned at 40x magnification and labeled by pathologists. PathoNet, developed by Negahbani et al (21), implements a deep learning model based on the U-Net architecture (22) for detection and classification of Ki-67 and TILs in breast cancer cases.…”
Section: Introductionmentioning
confidence: 99%