Abstract
PURPOSEDeep learning (DL), a class of approaches involving self-learned discriminative features, is increasingly being applied to digital pathology (DP) images for tasks such as disease identification and segmentation of tissue primitives (eg, nuclei, glands, lymphocytes). One application of DP is in telepathology, which involves digitally transmitting DP slides over the Internet for secondary diagnosis by an expert at a remote location. Unfortunately, the places benefiting most from telepathology often have poor Internet quality, resulting in prohibitive transmission times of DP images. Image compression may help, but the degree to which image compression affects performance of DL algorithms has been largely unexplored.METHODSWe investigated the effects of image compression on the performance of DL strategies in the context of 3 representative use cases involving segmentation of nuclei (n = 137), segmentation of lymph node metastasis (n = 380), and lymphocyte detection (n = 100). For each use case, test images at various levels of compression (JPEG compression quality score ranging from 1-100 and JPEG2000 compression peak signal-to-noise ratio ranging from 18-100 dB) were evaluated by a DL classifier. Performance metrics including F1 score and area under the receiver operating characteristic curve were computed at the various compression levels.RESULTSOur results suggest that DP images can be compressed by 85% while still maintaining the performance of the DL algorithms at 95% of what is achievable without any compression. Interestingly, the maximum compression level sustainable by DL algorithms is similar to where pathologists also reported difficulties in providing accurate interpretations.CONCLUSIONOur findings seem to suggest that in low-resource settings, DP images can be significantly compressed before transmission for DL-based telepathology applications.
Highlights
The advent of whole-slide scanners has enabled highthroughput digitization of routine glass pathology tissue slides
We investigated the effects of image compression on the performance of deep learning (DL) strategies in the context of 3 representative use cases involving segmentation of nuclei (n = 137), segmentation of lymph node metastasis (n = 380), and lymphocyte detection (n = 100)
Our results suggest that digital pathology (DP) images can be compressed by 85% while still maintaining the performance of the DL algorithms at 95% of what is achievable without any compression
Summary
The advent of whole-slide scanners has enabled highthroughput digitization of routine glass pathology tissue slides. One of the most popular DL network types is the convolutional neural network (CNN).[5,6] Through an iterative examination of a labeled data set, CNNs attempt to learn increasingly higher levels of data abstractions from the original data. This process, which involves minimizing the error between the model prediction and ground truth data labels, allows for learning the most discriminating representations between categories of interest. CNNs have been proposed to increase the efficiency of tasks such as segmentation of histologic primitives (eg, nuclei segmentation[5] and epithelium segmentation7), detection (eg, mitotic events8), disease
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
