2020
DOI: 10.1038/s41746-020-0272-0
|View full text |Cite
|
Sign up to set email alerts
|

Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning

Abstract: Histopathological diagnosis of lymphomas represents a challenge requiring either expertise or centralised review, and greatly depends on the technical process of tissue sections. Hence, we developed an innovative deep-learning framework, empowered with a certainty estimation level, designed for haematoxylin and eosin-stained slides analysis, with special focus on follicular lymphoma (FL) diagnosis. Whole-slide images of lymph nodes affected by FL or follicular hyperplasia were used for training, validating, an… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
54
0
2

Year Published

2021
2021
2024
2024

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 74 publications
(77 citation statements)
references
References 22 publications
0
54
0
2
Order By: Relevance
“…In this study, the CNN model trained by images directly was capable of differentiating these two types of PITLs (AUC = 0.82); however, the classification performance was significantly inferior to the tree-based models (p < 0.01) using quantitative nuclear morphometric features as input. Previous studies have shown that CNNs can achieve over 95% AUC in the classification of lymphomas, for instance, the diffuse large B-cell lymphoma [29] and the follicular lymphoma (FL) [30]. In these studies, the researchers utilized architectural patterns rather than cellular details for analysis.…”
Section: Discussionmentioning
confidence: 99%
“…In this study, the CNN model trained by images directly was capable of differentiating these two types of PITLs (AUC = 0.82); however, the classification performance was significantly inferior to the tree-based models (p < 0.01) using quantitative nuclear morphometric features as input. Previous studies have shown that CNNs can achieve over 95% AUC in the classification of lymphomas, for instance, the diffuse large B-cell lymphoma [29] and the follicular lymphoma (FL) [30]. In these studies, the researchers utilized architectural patterns rather than cellular details for analysis.…”
Section: Discussionmentioning
confidence: 99%
“…17,18 Furthermore, a large histopathology-based study to recognize FL versus reactive hyperplasia showed that machine learning techniques were reliable in screening for FL, even those that were BCL2 À . 19 These tools were promising but used pathology criteria alone as the gold standard for comparison.…”
Section: Chronic Lymphocytic Leukemiamentioning
confidence: 99%
“…Prowadzonych jest coraz więcej badań, których celem jest porównanie trafności rozpoznań dokonywanych przez sztuczną inteligencję z rozpoznaniami stawianymi przez doświadczonych patomorfologów. Wyniki dowodzą, że w dużej części przypadków sztuczna inteligencja radzi sobie podobnie do specjalistów, a dodatkowo może im pomagać w stawianiu rozpoznań, zmniejszając tym samym ryzyko błędu ludzkiego [43][44][45][46][47][48].…”
Section: Zastosowania Ai W Patomorfologiiunclassified
“…Innym przykładem wykorzystania AI w patomorfologii jest konwolucyjna sieć neuronowa, która uzyskała ponad 90% dokładności w stosunku do danych walidacyjnych w rozpoznawaniu glejaka mózgu, dokładność wynoszącą 96% przy klasyfikacji GBM lub LGG oraz 71% w identyfikacji stopnia LGG II lub III [45]. Z kolei w innym badaniu zaprojektowano sieć neuronową, do której walidacji i wyszkolenia użyto 378 preparatów mikroskopowych z biopsji węzłów chłonnych w przebiegu chłoniaka grudkowego (197) lub hiperplazji pęcherzykowej (181), a które uzyskała AUC mieszczący się w granicach 0,92-0,99 [47].…”
Section: Zastosowania Ai W Patomorfologiiunclassified