Predicting MYC translocation in HE specimens of diffuse large B-cell lymphoma through deep learning

2020 ◽  
Author(s):  
Zaneta Swiderska-Chadaj ◽  
Konnie Hebeda ◽  
Michiel van den Brand ◽  
Geert Litjens
Keyword(s):  
Deep Learning ◽  
B Cell ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Large B Cell Lymphoma ◽  
Large B Cell

scholarly journals A deep learning diagnostic platform for diffuse large B-cell lymphoma with high accuracy across multiple hospitals

2020 ◽  
Vol 11 (1) ◽  
Author(s):  
Dongguang Li ◽  
Jacob R. Bledsoe ◽  
Yu Zeng ◽  
Wei Liu ◽  
Yiguo Hu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Diagnostic Accuracy ◽  
B Cell ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Hematopoietic Malignancies ◽  
Learning Platform ◽  
Large B Cell Lymphoma ◽  
Image Collection ◽  
Large B Cell

AbstractDiagnostic histopathology is a gold standard for diagnosing hematopoietic malignancies. Pathologic diagnosis requires labor-intensive reading of a large number of tissue slides with high diagnostic accuracy equal or close to 100 percent to guide treatment options, but this requirement is difficult to meet. Although artificial intelligence (AI) helps to reduce the labor of reading pathologic slides, diagnostic accuracy has not reached a clinically usable level. Establishment of an AI model often demands big datasets and an ability to handle large variations in sample preparation and image collection. Here, we establish a highly accurate deep learning platform, consisting of multiple convolutional neural networks, to classify pathologic images by using smaller datasets. We analyze human diffuse large B-cell lymphoma (DLBCL) and non-DLBCL pathologic images from three hospitals separately using AI models, and obtain a diagnostic rate of close to 100 percent (100% for hospital A, 99.71% for hospital B and 100% for hospital C). The technical variability introduced by slide preparation and image collection reduces AI model performance in cross-hospital tests, but the 100% diagnostic accuracy is maintained after its elimination. It is now clinically practical to utilize deep learning models for diagnosis of DLBCL and ultimately other human hematopoietic malignancies.

scholarly journals Deep-Learning 18F-FDG Uptake Classification Enables Total Metabolic Tumor Volume Estimation in Diffuse Large B-Cell Lymphoma

2020 ◽  
Vol 62 (1) ◽  
pp. 30-36 ◽  
Author(s):  
Nicolò Capobianco ◽  
Michel Meignan ◽  
Anne-Ségolène Cottereau ◽  
Laetitia Vercellino ◽  
Ludovic Sibille ◽  
...  
Keyword(s):  
Deep Learning ◽  
B Cell ◽  
Tumor Volume ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Metabolic Tumor Volume ◽  
Volume Estimation ◽  
Large B Cell Lymphoma ◽  
18F Fdg ◽  
Large B Cell

Lymphome

Praxis ◽  
2016 ◽  
Vol 105 (1) ◽  
pp. 47-52 ◽  
Author(s):  
Andreas Lohri
Keyword(s):  
B Cell ◽  
Cell Lymphoma ◽  
B Cell Lymphoma ◽  
Staging System ◽  
Maligne Lymphome ◽  
Interim Pet ◽  
Large B Cell Lymphoma ◽  
Ann Arbor ◽  
Large B Cell

Zusammenfassung. Maligne Lymphome unterteilen sich zwar in über 60 Entitäten, das grosszellige B-Zell-Lymphom, das follikuläre Lymphom, der Hodgkin und das Mantelzell-Lymphom machen aber mehr als die Hälfte aller Lymphome aus. Im revidierten Ann Arbor staging system gelten die Suffixe «A» und «B» nur noch für den Hodgkin. «E» erscheint nur noch bei Stadien I und II. Eine Knochenmarksuntersuchung wird beim Hodgkin nicht mehr verlangt, beim DLBCL (Diffuse large B cell lymphoma) nur, falls das PET keinen Knochenmark-Befall zeigt. Der PET-Untersuchung, speziell dem Interim-PET, kommt eine entscheidende Bedeutung zu. PET-gesteuerte Therapien führen zu weniger Toxizität. Gezielt wirkende Medikamente mit eindrücklicher Wirksamkeit wurden neu zugelassen. Deren Kosten sind hoch. Eine strahlen- und chemotherapiefreie Behandlung maligner Lymphome wird in Zukunft möglich sein.

Sign in / Sign up

Export Citation Format

Share Document