Dataset Information

Automated acquisition of explainable knowledge from unannotated histopathology images.

ABSTRACT: Deep learning algorithms have been successfully used in medical image classification. In the next stage, the technology of acquiring explainable knowledge from medical images is highly desired. Here we show that deep learning algorithm enables automated acquisition of explainable features from diagnostic annotation-free histopathology images. We compare the prediction accuracy of prostate cancer recurrence using our algorithm-generated features with that of diagnosis by expert pathologists using established criteria on 13,188 whole-mount pathology images consisting of over 86 billion image patches. Our method not only reveals findings established by humans but also features that have not been recognized, showing higher accuracy than human in prognostic prediction. Combining both our algorithm-generated features and human-established criteria predicts the recurrence more accurately than using either method alone. We confirm robustness of our method using external validation datasets including 2276 pathology images. This study opens up fields of machine learning analysis for discovering uncharted knowledge.

SUBMITTER: Yamamoto Y

PROVIDER: S-EPMC6920352 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated acquisition of explainable knowledge from unannotated histopathology images.

Yamamoto Yoichiro Y Tsuzuki Toyonori T Akatsuka Jun J Ueki Masao M Morikawa Hiromu H Numata Yasushi Y Takahara Taishi T Tsuyuki Takuji T Tsutsumi Kotaro K Nakazawa Ryuto R Shimizu Akira A Maeda Ichiro I Tsuchiya Shinichi S Kanno Hiroyuki H Kondo Yukihiro Y Fukumoto Manabu M Tamiya Gen G Ueda Naonori N Kimura Go G

Nature communications 20191218 1

Deep learning algorithms have been successfully used in medical image classification. In the next stage, the technology of acquiring explainable knowledge from medical images is highly desired. Here we show that deep learning algorithm enables automated acquisition of explainable features from diagnostic annotation-free histopathology images. We compare the prediction accuracy of prostate cancer recurrence using our algorithm-generated features with that of diagnosis by expert pathologists using ...[more]

PMID: 31852890

Similar Datasets

Project description:ImportanceA retinopathy of prematurity (ROP) diagnosis currently relies on indirect ophthalmoscopy assessed by experienced ophthalmologists. A deep learning algorithm based on retinal images may facilitate early detection and timely treatment of ROP to improve visual outcomes.ObjectiveTo develop a retinal image-based, multidimensional, automated, deep learning platform for ROP screening and validate its performance accuracy.Design, setting, and participantsA total of 14 108 eyes of 8652 preterm infants who received ROP screening from 4 centers from November 4, 2010, to November 14, 2019, were included, and a total of 52 249 retinal images were randomly split into training, validation, and test sets. Four main dimensional independent classifiers were developed, including image quality, any stage of ROP, intraocular hemorrhage, and preplus/plus disease. Referral-warranted ROP was automatically generated by integrating the results of 4 classifiers at the image, eye, and patient levels. DeepSHAP, a method based on DeepLIFT and Shapley values (solution concepts in cooperative game theory), was adopted as the heat map technology to explain the predictions. The performance of the platform was further validated as compared with that of the experienced ROP experts. Data were analyzed from February 12, 2020, to June 24, 2020.ExposureA deep learning algorithm.Main outcomes and measuresThe performance of each classifier included true negative, false positive, false negative, true positive, F1 score, sensitivity, specificity, receiver operating characteristic, area under curve (AUC), and Cohen unweighted κ.ResultsA total of 14 108 eyes of 8652 preterm infants (mean [SD] gestational age, 32.9 [3.1] weeks; 4818 boys [60.4%] of 7973 with known sex) received ROP screening. The performance of all classifiers achieved an F1 score of 0.718 to 0.981, a sensitivity of 0.918 to 0.982, a specificity of 0.949 to 0.992, and an AUC of 0.983 to 0.998, whereas that of the referral system achieved an F1 score of 0.898 to 0.956, a sensitivity of 0.981 to 0.986, a specificity of 0.939 to 0.974, and an AUC of 0.9901 to 0.9956. Fine-grained and class-discriminative heat maps were generated by DeepSHAP in real time. The platform achieved a Cohen unweighted κ of 0.86 to 0.98 compared with a Cohen κ of 0.93 to 0.98 by the ROP experts.Conclusions and relevanceIn this diagnostic study, an automated ROP screening platform was able to identify and classify multidimensional pathologic lesions in the retinal images. This platform may be able to assist routine ROP screening in general and children hospitals.

Project description:IntroductionCerebral microbleeds (CMBs) are associated with white matter damage, and various neurodegenerative and cerebrovascular diseases. CMBs occur as small, circular hypointense lesions on T2*-weighted gradient recalled echo (GRE) and susceptibility-weighted imaging (SWI) images, and hyperintense on quantitative susceptibility mapping (QSM) images due to their paramagnetic nature. Accurate automated detection of CMBs would help to determine quantitative imaging biomarkers (e.g., CMB count) on large datasets. In this work, we propose a fully automated, deep learning-based, 3-step algorithm, using structural and anatomical properties of CMBs from any single input image modality (e.g., GRE/SWI/QSM) for their accurate detections.MethodsIn our method, the first step consists of an initial candidate detection step that detects CMBs with high sensitivity. In the second step, candidate discrimination step is performed using a knowledge distillation framework, with a multi-tasking teacher network that guides the student network to classify CMB and non-CMB instances in an offline manner. Finally, a morphological clean-up step further reduces false positives using anatomical constraints. We used four datasets consisting of different modalities specified above, acquired using various protocols and with a variety of pathological and demographic characteristics.ResultsOn cross-validation within datasets, our method achieved a cluster-wise true positive rate (TPR) of over 90% with an average of <2 false positives per subject. The knowledge distillation framework improves the cluster-wise TPR of the student model by 15%. Our method is flexible in terms of the input modality and provides comparable cluster-wise TPR and better cluster-wise precision compared to existing state-of-the-art methods. When evaluating across different datasets, our method showed good generalizability with a cluster-wise TPR >80 % with different modalities. The python implementation of the proposed method is openly available.

Project description:BackgroundHistological assessment of skeletal muscle sections is important for the research of muscle physiology and diseases. Quantifiable measures of skeletal muscle often include mean fiber diameter, fiber size distribution, and centrally nucleated muscle fibers. These parameters offer insights into the dynamic adaptation of skeletal muscle cells during repeated cycles of degeneration and regeneration associated with many muscle diseases and injuries. Computational programs designed to obtain these parameters would greatly facilitate such efforts and offer significant advantage over manual image analysis, which is very labor-intensive and often subjective. Here, we describe a customized pipeline termed MuscleAnalyzer for muscle histology analysis based upon CellProfiler, a free, open-source software for measuring and analyzing cell images.ResultsThe MuscleAnalyzer pipeline consists of loading, adjusting, and running a series of image-processing modules provided by CellProfiler. This pipeline was evaluated using wild-type and mdx muscle sections co-stained with laminin (to demarcate the muscle fiber boundaries) and 4',6-diamidino-2-phenylindole (DAPI, to label the nuclei). The immunofluorescence images analyzed using the MuscleAnalyzer pipeline or manually yielded similar results in the number of muscle fibers per image (p = 0.42) and central nucleated fiber (CNF) percentage (p = 0.29) in mdx mice. However, for a total of 67 images, CellProfiler completed the analysis in ~ 10 min on a regular PC while it took an investigator ~ 3 h using the manual approach in order to quantify the number of muscle fibers and CNF. Moreover, the MuscleAnalyzer pipeline also provided the measurement of the cross-sectional area (CSA) and minimal Feret's diameter (MFD) of muscle fibers, and thus fiber size distribution can be plotted.ConclusionsOur data indicate that the MuscleAnalyzer pipeline can efficiently and accurately analyze laminin and DAPI co-stained muscle images in a batch format and provide quantitative measurements for muscle histological properties such as muscle fiber diameters, fiber size distribution, and CNF percentage.

Dataset Information

Automated acquisition of explainable knowledge from unannotated histopathology images.

Publications

Automated acquisition of explainable knowledge from unannotated histopathology images.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets