Machine Learning Based Prediction of Squamous Cell Carcinoma in Ex Vivo Confocal Laser Scanning Microscopy

Image classification with convolutional neural networks (CNN) offers an unprecedented opportunity to medical imaging. Regulatory agencies in the USA and Europe have already cleared numerous deep learning/machine learning based medical devices and algorithms. While the field of radiology is on the fo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Cancers Jg. 13; H. 21; S. 5522
Hauptverfasser: Ruini, Cristel, Schlingmann, Sophia, Jonke, Žan, Avci, Pinar, Padrón-Laso, Víctor, Neumeier, Florian, Koveshazi, Istvan, Ikeliani, Ikenna U, Patzer, Kathrin, Kunrad, Elena, Kendziora, Benjamin, Sattler, Elke, French, Lars E, Hartmann, Daniela
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 03.11.2021
MDPI
Schlagworte:
Algorithms
Artificial intelligence
Big Data
Cancer
Confocal microscopy
convolutional networks; digital pathology; digital staining; ex vivo confocal laser scanning microscopy; fluorescence confocal microscopy; machine learning; mohs surgery; neural networks; reflectance confocal microscopy; squamous cell carcinoma
Decision making
Deep learning
Dermatology
Histopathology
Lasers
Learning algorithms
Machine learning
Medical equipment
Micrography
Microscopy
Neural networks
Paraffin
Pathology
Segmentation
Skin cancer
Squamous cell carcinoma
squamous cell carcinoma; ex vivo confocal laser scanning microscopy; reflectance confocal microscopy; fluorescence confocal microscopy; digital pathology; digital staining; neural networks; convolutional networks; machine learning; Mohs surgery
Tumors
United States > US
Germany
ISSN:2072-6694, 2072-6694
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Image classification with convolutional neural networks (CNN) offers an unprecedented opportunity to medical imaging. Regulatory agencies in the USA and Europe have already cleared numerous deep learning/machine learning based medical devices and algorithms. While the field of radiology is on the forefront of artificial intelligence (AI) revolution, conventional pathology, which commonly relies on examination of tissue samples on a glass slide, is falling behind in leveraging this technology. On the other hand, ex vivo confocal laser scanning microscopy (ex vivo CLSM), owing to its digital workflow features, has a high potential to benefit from integrating AI tools into the assessment and decision-making process. Aim of this work was to explore a preliminary application of CNN in digitally stained ex vivo CLSM images of cutaneous squamous cell carcinoma (cSCC) for automated detection of tumor tissue. Thirty-four freshly excised tissue samples were prospectively collected and examined immediately after resection. After the histologically confirmed ex vivo CLSM diagnosis, the tumor tissue was annotated for segmentation by experts, in order to train the MobileNet CNN. The model was then trained and evaluated using cross validation. The overall sensitivity and specificity of the deep neural network for detecting cSCC and tumor free areas on ex vivo CLSM slides compared to expert evaluation were 0.76 and 0.91, respectively. The area under the ROC curve was equal to 0.90 and the area under the precision-recall curve was 0.85. The results demonstrate a high potential of deep learning models to detect cSCC regions on digitally stained ex vivo CLSM slides and to distinguish them from tumor-free skin.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
The two first authors contributed equally to the work and share the first authorship.
ISSN:2072-6694
2072-6694
DOI:10.3390/cancers13215522