Chen Yijiang, Janowczyk Andrew, Madabhushi Anant
Case Western Reserve University, Cleveland, OH.
Precision Oncology Center, Lausanne University Hospital, Lausanne, Switzerland.
JCO Clin Cancer Inform. 2020 Mar;4:221-233. doi: 10.1200/CCI.19.00068.
Deep 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.
We 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.
Our 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.
Our findings seem to suggest that in low-resource settings, DP images can be significantly compressed before transmission for DL-based telepathology applications.
深度学习（DL）是一类涉及自学习判别特征的方法，越来越多地应用于数字病理学（DP）图像，用于疾病识别和组织原语（如细胞核、腺体、淋巴细胞）分割等任务。DP的一个应用是远程病理学，它涉及通过互联网数字传输DP载玻片，以供远程专家进行二次诊断。不幸的是，最能从远程病理学中受益的地方往往网络质量较差，导致DP图像的传输时间过长。图像压缩可能会有所帮助，但图像压缩对DL算法性能的影响程度在很大程度上尚未得到探索。
我们在3个代表性用例的背景下研究了图像压缩对DL策略性能的影响，这些用例包括细胞核分割（n = 137）、淋巴结转移分割（n = 380）和淋巴细胞检测（n = 100）。对于每个用例，由DL分类器评估不同压缩级别（JPEG压缩质量分数范围为1 - 100，JPEG2000压缩峰值信噪比范围为18 - 100 dB）的测试图像。在不同压缩级别计算包括F1分数和接收器操作特征曲线下面积在内的性能指标。
我们的结果表明，DP图像可以压缩85%，同时仍能保持DL算法的性能，达到无压缩时可实现性能的95%。有趣的是，DL算法能够承受的最大压缩级别与病理学家报告在提供准确解释时也存在困难的级别相似。
我们的研究结果似乎表明，在资源匮乏的环境中，对于基于DL的远程病理学应用，DP图像在传输前可以进行显著压缩。
