Automated identification of malignancy in whole-slide pathological images: identification of eyelid malignant melanoma in gigapixel pathological slides using deep learning.

Automated identification of malignancy in whole-slide pathological images: identification of eyelid malignant melanoma in gigapixel pathological slides using deep learning.

Publication date: Jul 13, 2019

To develop a deep learning system (DLS) that can automatically detect malignant melanoma (MM) in the eyelid from histopathological sections with colossal information density.

Setting: Double institutional study.

We retrospectively reviewed 225 230 pathological patches (small section cut from pathologist-labelled area from an H&E image), cut from 155 H&E-stained whole-slide images (WSI).

Labelled gigapixel pathological WSIs were used to train and test a model designed to assign patch-level classification. Using malignant probability from a convolutional neural network, the patches were embedded back into each WSI to generate a visualisation heatmap and leveraged a random forest model to establish a WSI-level diagnosis.

For classification, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity were used to evaluate the efficacy of the DLS in detecting MM.

For patch diagnosis, the model achieved an AUC of 0.989 (95% CI 0.989 to 0.991), with an accuracy, sensitivity and specificity of 94.9%, 94.7% and 95.3%, respectively. We displayed the lesion area on the WSIs as graded by malignant potential. For WSI, the obtained sensitivity, specificity and accuracy were 100%, 96.5% and 98.2%, respectively, with an AUC of 0.998 (95% CI 0.994 to 1.000).

Our DLS, which uses artificial intelligence, can automatically detect MM in histopathological slides and highlight the lesion area on WSIs using a probabilistic heatmap. In addition, our approach has the potential to be applied to the histopathological sections of other tumour types.

Wang, L., Ding, L., Liu, Z., Sun, L., Chen, L., Jia, R., Dai, X., Cao, J., and Ye, J. Automated identification of malignancy in whole-slide pathological images: identification of eyelid malignant melanoma in gigapixel pathological slides using deep learning. 23402. 2019 Br J Ophthalmol.

Concepts Keywords
Artificial Intelligence Cancer
AUC Melanoma
Convolutional Neural Network RTT
Deep Learning Pathology
DLS Eyelid
Eyelid Biology
Heatmap Articles
Histopathological Medicine
Lesion Neural network
Malignancy Artificial intelligence
Malignant Telemedicine
Malignant Melanoma
Pathologist
Probabilistic
Probability
Random Forest
Receiver Operating Characteristic
Tumour
WSIs

Semantics

Type Source Name
disease MESH diagnosis
disease DOID malignant melanoma
disease MESH malignant melanoma
disease MESH malignancy

Similar

Original Article

Leave a Comment

Your email address will not be published. Required fields are marked *