Effective and efficient active learning for deep learning-based tissue image analysis.

MOTIVATION: Deep learning attained excellent results in digital pathology recently. A challenge with its use is that high quality, representative training datasets are required to build robust models. Data annotation in the domain is labor intensive and demands substantial time commitment from expert pathologists. Active learning (AL) is a strategy to minimize annotation. The goal is to select samples from the pool of unlabeled data for annotation that improves model accuracy. However, AL is a very compute demanding approach. The benefits for model learning may vary according to the strategy used, and it may be hard for a domain specialist to fine tune the solution without an integrated interface. RESULTS: We developed a framework that includes a friendly user interface along with run-time optimizations to reduce annotation and execution time in AL in digital pathology. Our solution implements several AL strategies along with our diversity-aware data acquisition (DADA) acquisition function, which enforces data diversity to improve the prediction performance of a model. In this work, we employed a model simplification strategy [Network Auto-Reduction (NAR)] that significantly improves AL execution time when coupled with DADA. NAR produces less compute demanding models, which replace the target models during the AL process to reduce processing demands. An evaluation with a tumor-infiltrating lymphocytes classification application shows that: (i) DADA attains superior performance compared to state-of-the-art AL strategies for different convolutional neural networks (CNNs), (ii) NAR improves the AL execution time by up to 4.3×, and (iii) target models trained with patches/data selected by the NAR reduced versions achieve similar or superior classification quality to using target CNNs for data selection. AVAILABILITY AND IMPLEMENTATION: Source code: https://github.com/alsmeirelles/DADA.

Self-supervised semantic segmentation of retinal pigment epithelium cells in flatmount fluorescent microscopy images.

MOTIVATION: Morphological analyses with flatmount fluorescent images are essential to retinal pigment epithelial (RPE) aging studies and thus require accurate RPE cell segmentation. Although rapid technology advances in deep learning semantic segmentation have achieved great success in many biomedical research, the performance of these supervised learning methods for RPE cell segmentation is still limited by inadequate training data with high-quality annotations. RESULTS: To address this problem, we develop a Self-Supervised Semantic Segmentation (S4) method that utilizes a self-supervised learning strategy to train a semantic segmentation network with an encoder-decoder architecture. We employ a reconstruction and a pairwise representation loss to make the encoder extract structural information, while we create a morphology loss to produce the segmentation map. In addition, we develop a novel image augmentation algorithm (AugCut) to produce multiple views for self-supervised learning and enhance the network training performance. To validate the efficacy of our method, we applied our developed S4 method for RPE cell segmentation to a large set of flatmount fluorescent microscopy images, we compare our developed method for RPE cell segmentation with other state-of-the-art deep learning approaches. Compared with other state-of-the-art deep learning approaches, our method demonstrates better performance in both qualitative and quantitative evaluations, suggesting its promising potential to support large-scale cell morphological analyses in RPE aging investigations. AVAILABILITY AND IMPLEMENTATION: The codes and the documentation are available at: https://github.com/jkonglab/S4_RPE.

A spatial attention guided deep learning system for prediction of pathological complete response using breast cancer histopathology images.

MOTIVATION: Predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC) patients accurately is direly needed for clinical decision making. pCR is also regarded as a strong predictor of overall survival. In this work, we propose a deep learning system to predict pCR to NAC based on serial pathology images stained with hematoxylin and eosin and two immunohistochemical biomarkers (Ki67 and PHH3). To support human prior domain knowledge-based guidance and enhance interpretability of the deep learning system, we introduce a human knowledge-derived spatial attention mechanism to inform deep learning models of informative tissue areas of interest. For each patient, three serial breast tumor tissue sections from biopsy blocks were sectioned, stained in three different stains and integrated. The resulting comprehensive attention information from the image triplets is used to guide our prediction system for prognostic tissue regions. RESULTS: The experimental dataset consists of 26 419 pathology image patches of 1000×1000 pixels from 73 TNBC patients treated with NAC. Image patches from randomly selected 43 patients are used as a training dataset and images patches from the rest 30 are used as a testing dataset. By the maximum voting from patch-level results, our proposed model achieves a 93% patient-level accuracy, outperforming baselines and other state-of-the-art systems, suggesting its high potential for clinical decision making. AVAILABILITY AND IMPLEMENTATION: The codes, the documentation and example data are available on an open source at: https://github.com/jkonglab/PCR_Prediction_Serial_WSIs_biomarkers. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Foveal blur-boosted segmentation of nuclei in histopathology images with shape prior knowledge and probability map constraints.

MOTIVATION: In most tissue-based biomedical research, the lack of sufficient pathology training images with well-annotated ground truth inevitably limits the performance of deep learning systems. In this study, we propose a convolutional neural network with foveal blur enriching datasets with multiple local nuclei regions of interest derived from original pathology images. We further propose a human-knowledge boosted deep learning system by inclusion to the convolutional neural network new loss function terms capturing shape prior knowledge and imposing smoothness constraints on the predicted probability maps. RESULTS: Our proposed system outperforms all state-of-the-art deep learning and non-deep learning methods by Jaccard coefficient, Dice coefficient, Accuracy and Panoptic Quality in three independent datasets. The high segmentation accuracy and execution speed suggest its promising potential for automating histopathology nuclei segmentation in biomedical research and clinical settings. AVAILABILITY AND IMPLEMENTATION: The codes, the documentation and example data are available on an open source at: https://github.com/HongyiDuanmu26/FovealBoosted. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Deep-learning-based accurate hepatic steatosis quantification for histological assessment of liver biopsies.

Hepatic steatosis droplet quantification with histology biopsies has high clinical significance for risk stratification and management of patients with fatty liver diseases and in the decision to use donor livers for transplantation. However, pathology reviewing processes, when conducted manually, are subject to a high inter- and intra-reader variability, due to the overwhelmingly large number and significantly varying appearance of steatosis instances. This process is challenging as there is a large number of overlapped steatosis droplets with either missing or weak boundaries. In this study, we propose a deep-learning-based region-boundary integrated network for precise steatosis quantification with whole slide liver histopathology images. The proposed model consists of two sequential steps: a region extraction and a boundary prediction module for foreground regions and steatosis boundary prediction, followed by an integrated prediction map generation. Missing steatosis boundaries are next recovered from the predicted map and assembled from adjacent image patches to generate results for the whole slide histopathology image. The resulting steatosis measures both at the pixel level and steatosis object-level present strong correlation with pathologist annotations, radiology readouts and clinical data. In addition, the segregated steatosis object count is shown as a promising alternative measure to the traditional metrics at the pixel level. These results suggest a high potential of artificial intelligence-assisted technology to enhance liver disease decision support using whole slide images.

Multi-objective Parameter Auto-tuning for Tissue Image Segmentation Workflows.

We propose a software platform that integrates methods and tools for multi-objective parameter auto-tuning in tissue image segmentation workflows. The goal of our work is to provide an approach for improving the accuracy of nucleus/cell segmentation pipelines by tuning their input parameters. The shape, size, and texture features of nuclei in tissue are important biomarkers for disease prognosis, and accurate computation of these features depends on accurate delineation of boundaries of nuclei. Input parameters in many nucleus segmentation workflows affect segmentation accuracy and have to be tuned for optimal performance. This is a time-consuming and computationally expensive process; automating this step facilitates more robust image segmentation workflows and enables more efficient application of image analysis in large image datasets. Our software platform adjusts the parameters of a nuclear segmentation algorithm to maximize the quality of image segmentation results while minimizing the execution time. It implements several optimization methods to search the parameter space efficiently. In addition, the methodology is developed to execute on high-performance computing systems to reduce the execution time of the parameter tuning phase. These capabilities are packaged in a Docker container for easy deployment and can be used through a friendly interface extension in 3D Slicer. Our results using three real-world image segmentation workflows demonstrate that the proposed solution is able to (1) search a small fraction (about 100 points) of the parameter space, which contains billions to trillions of points, and improve the quality of segmentation output by × 1.20, × 1.29, and × 1.29, on average; (2) decrease the execution time of a segmentation workflow by up to 11.79× while improving output quality; and (3) effectively use parallel systems to accelerate parameter tuning and segmentation phases.

MaReIA: A Cloud MapReduce Based High Performance Whole Slide Image Analysis Framework.

Recent advancements in systematic analysis of high resolution whole slide images have increase efficiency of diagnosis, prognosis and prediction of cancer and important diseases. Due to the enormous sizes and dimensions of whole slide images, the analysis requires extensive computing resources which are not commonly available. Images have to be tiled for processing due to computer memory limitations, which lead to inaccurate results due to the ignorance of boundary crossing objects. Thus, we propose a generic and highly scalable cloud-based image analysis framework for whole slide images. The framework enables parallelized integration of image analysis steps, such as segmentation and aggregation of micro-structures in a single pipeline, and generation of final objects manageable by databases. The core concept relies on the abstraction of objects in whole slide images as different classes of spatial geometries, which in turn can be handled as text based records in MapReduce. The framework applies an overlapping partitioning scheme on images, and provides parallelization of tiling and image segmentation based on MapReduce architecture. It further provides robust object normalization, graceful handling of boundary objects with an efficient spatial indexing based matching method to generate accurate results. Our experiments on Amazon EMR show that MaReIA is highly scalable, generic and extremely cost effective by benchmark tests.

Algorithm sensitivity analysis and parameter tuning for tissue image segmentation pipelines.

Motivation: Sensitivity analysis and parameter tuning are important processes in large-scale image analysis. They are very costly because the image analysis workflows are required to be executed several times to systematically correlate output variations with parameter changes or to tune parameters. An integrated solution with minimum user interaction that uses effective methodologies and high performance computing is required to scale these studies to large imaging datasets and expensive analysis workflows. Results: The experiments with two segmentation workflows show that the proposed approach can (i) quickly identify and prune parameters that are non-influential; (ii) search a small fraction (about 100 points) of the parameter search space with billions to trillions of points and improve the quality of segmentation results (Dice and Jaccard metrics) by as much as 1.42× compared to the results from the default parameters; (iii) attain good scalability on a high performance cluster with several effective optimizations. Conclusions: Our work demonstrates the feasibility of performing sensitivity analyses, parameter studies and auto-tuning with large datasets. The proposed framework can enable the quantification of error estimations and output variations in image segmentation pipelines. Availability and Implementation: Source code: https://github.com/SBU-BMI/region-templates/ . Contact: teodoro@unb.br. Supplementary information: Supplementary data are available at Bioinformatics online.

Application Performance Analysis and Efficient Execution on Systems with multi-core CPUs, GPUs and MICs: A Case Study with Microscopy Image Analysis.

We carry out a comparative performance study of multi-core CPUs, GPUs and Intel Xeon Phi (Many Integrated Core-MIC) with a microscopy image analysis application. We experimentally evaluate the performance of computing devices on core operations of the application. We correlate the observed performance with the characteristics of computing devices and data access patterns, computation complexities, and parallelization forms of the operations. The results show a significant variability in the performance of operations with respect to the device used. The performances of operations with regular data access are comparable or sometimes better on a MIC than that on a GPU. GPUs are more efficient than MICs for operations that access data irregularly, because of the lower bandwidth of the MIC for random data accesses. We propose new performance-aware scheduling strategies that consider variabilities in operation speedups. Our scheduling strategies significantly improve application performance compared to classic strategies in hybrid configurations.

Scalable analysis of Big pathology image data cohorts using efficient methods and high-performance computing strategies.

BACKGROUND: We describe a suite of tools and methods that form a core set of capabilities for researchers and clinical investigators to evaluate multiple analytical pipelines and quantify sensitivity and variability of the results while conducting large-scale studies in investigative pathology and oncology. The overarching objective of the current investigation is to address the challenges of large data sizes and high computational demands. RESULTS: The proposed tools and methods take advantage of state-of-the-art parallel machines and efficient content-based image searching strategies. The content based image retrieval (CBIR) algorithms can quickly detect and retrieve image patches similar to a query patch using a hierarchical analysis approach. The analysis component based on high performance computing can carry out consensus clustering on 500,000 data points using a large shared memory system. CONCLUSIONS: Our work demonstrates efficient CBIR algorithms and high performance computing can be leveraged for efficient analysis of large microscopy images to meet the challenges of clinically salient applications in pathology. These technologies enable researchers and clinical investigators to make more effective use of the rich informational content contained within digitized microscopy specimens.

Comparative Performance Analysis of Intel Xeon Phi, GPU, and CPU: A Case Study from Microscopy Image Analysis.

We study and characterize the performance of operations in an important class of applications on GPUs and Many Integrated Core (MIC) architectures. Our work is motivated by applications that analyze low-dimensional spatial datasets captured by high resolution sensors, such as image datasets obtained from whole slide tissue specimens using microscopy scanners. Common operations in these applications involve the detection and extraction of objects (object segmentation), the computation of features of each extracted object (feature computation), and characterization of objects based on these features (object classification). In this work, we have identify the data access and computation patterns of operations in the object segmentation and feature computation categories. We systematically implement and evaluate the performance of these operations on modern CPUs, GPUs, and MIC systems for a microscopy image analysis application. Our results show that the performance on a MIC of operations that perform regular data access is comparable or sometimes better than that on a GPU. On the other hand, GPUs are significantly more efficient than MICs for operations that access data irregularly. This is a result of the low performance of MICs when it comes to random data access. We also have examined the coordinated use of MICs and CPUs. Our experiments show that using a performance aware task strategy for scheduling application operations improves performance about 1.29× over a first-come-first-served strategy. This allows applications to obtain high performance efficiency on CPU-MIC systems - the example application attained an efficiency of 84% on 192 nodes (3072 CPU cores and 192 MICs).

Region Templates: Data Representation and Management for High-Throughput Image Analysis.

We introduce a region template abstraction and framework for the efficient storage, management and processing of common data types in analysis of large datasets of high resolution images on clusters of hybrid computing nodes. The region template abstraction provides a generic container template for common data structures, such as points, arrays, regions, and object sets, within a spatial and temporal bounding box. It allows for different data management strategies and I/O implementations, while providing a homogeneous, unified interface to applications for data storage and retrieval. A region template application is represented as a hierarchical dataflow in which each computing stage may be represented as another dataflow of finer-grain tasks. The execution of the application is coordinated by a runtime system that implements optimizations for hybrid machines, including performance-aware scheduling for maximizing the utilization of computing devices and techniques to reduce the impact of data transfers between CPUs and GPUs. An experimental evaluation on a state-of-the-art hybrid cluster using a microscopy imaging application shows that the abstraction adds negligible overhead (about 3%) and achieves good scalability and high data transfer rates. Optimizations in a high speed disk based storage implementation of the abstraction to support asynchronous data transfers and computation result in an application performance gain of about 1.13×. Finally, a processing rate of 11,730 4K×4K tiles per minute was achieved for the microscopy imaging application on a cluster with 100 nodes (300 GPUs and 1,200 CPU cores). This computation rate enables studies with very large datasets.

Efficient Irregular Wavefront Propagation Algorithms on Hybrid CPU-GPU Machines.

We address the problem of efficient execution of a computation pattern, referred to here as the irregular wavefront propagation pattern (IWPP), on hybrid systems with multiple CPUs and GPUs. The IWPP is common in several image processing operations. In the IWPP, data elements in the wavefront propagate waves to their neighboring elements on a grid if a propagation condition is satisfied. Elements receiving the propagated waves become part of the wavefront. This pattern results in irregular data accesses and computations. We develop and evaluate strategies for efficient computation and propagation of wavefronts using a multi-level queue structure. This queue structure improves the utilization of fast memories in a GPU and reduces synchronization overheads. We also develop a tile-based parallelization strategy to support execution on multiple CPUs and GPUs. We evaluate our approaches on a state-of-the-art GPU accelerated machine (equipped with 3 GPUs and 2 multicore CPUs) using the IWPP implementations of two widely used image processing operations: morphological reconstruction and euclidean distance transform. Our results show significant performance improvements on GPUs. The use of multiple CPUs and GPUs cooperatively attains speedups of 50× and 85× with respect to single core CPU executions for morphological reconstruction and euclidean distance transform, respectively.

Feature-based Analysis of Large-scale Spatio-Temporal Sensor Data on Hybrid Architectures.

Analysis of large sensor datasets for structural and functional features has applications in many domains, including weather and climate modeling, characterization of subsurface reservoirs, and biomedicine. The vast amount of data obtained from state-of-the-art sensors and the computational cost of analysis operations create a barrier to such analyses. In this paper, we describe middleware system support to take advantage of large clusters of hybrid CPU-GPU nodes to address the data and compute-intensive requirements of feature-based analyses in large spatio-temporal datasets.

Deep learning based registration of serial whole-slide histopathology images in different stains.

For routine pathology diagnosis and imaging-based biomedical research, Whole-slide image (WSI) analyses have been largely limited to a 2D tissue image space. For a more definitive tissue representation to support fine-resolution spatial and integrative analyses, it is critical to extend such tissue-based investigations to a 3D tissue space with spatially aligned serial tissue WSIs in different stains, such as Hematoxylin and Eosin (H&E) and Immunohistochemistry (IHC) biomarkers. However, such WSI registration is technically challenged by the overwhelming image scale, the complex histology structure change, and the significant difference in tissue appearances in different stains. The goal of this study is to register serial sections from multi-stain histopathology whole-slide image blocks. We propose a novel translation-based deep learning registration network CGNReg that spatially aligns serial WSIs stained in H&E and by IHC biomarkers without prior deformation information for the model training. First, synthetic IHC images are produced from H&E slides through a robust image synthesis algorithm. Next, the synthetic and the real IHC images are registered through a Fully Convolutional Network with multi-scaled deformable vector fields and a joint loss optimization. We perform the registration at the full image resolution, retaining the tissue details in the results. Evaluated with a dataset of 76 breast cancer patients with 1 H&E and 2 IHC serial WSIs for each patient, CGNReg presents promising performance as compared with multiple state-of-the-art systems in our evaluation. Our results suggest that CGNReg can produce promising registration results with serial WSIs in different stains, enabling integrative 3D tissue-based biomedical investigations.

Effective active learning in digital pathology: A case study in tumor infiltrating lymphocytes.

BACKGROUND AND OBJECTIVE: Deep learning methods have demonstrated remarkable performance in pathology image analysis, but they require a large amount of annotated training data from expert pathologists. The aim of this study is to minimize the data annotation need in these analyses. METHODS: Active learning (AL) is an iterative approach to training deep learning models. It was used in our context with a Tumor Infiltrating Lymphocytes (TIL) classification task to minimize annotation. State-of-the-art AL methods were evaluated with the TIL application and we have proposed and evaluated a more efficient and effective AL acquisition method. The proposed method uses data grouping based on imaging features and model prediction uncertainty to select meaningful training samples (image patches). RESULTS: An experimental evaluation with a collection of cancer tissue images shows that: (i) Our approach reduces the number of patches required to attain a given AUC as compared to other approaches, and (ii) our optimization (subpooling) leads to AL execution time improvement of about 2.12×. CONCLUSIONS: This strategy enabled TIL based deep learning analyses using smaller annotation demand. We expect this approach may be used to build other analyses in digital pathology with fewer training samples.

MultiHeadGAN: A deep learning method for low contrast retinal pigment epithelium cell segmentation with fluorescent flatmount microscopy images.

BACKGROUND: Retinal pigment epithelium (RPE) aging is an important cause of vision loss. As RPE aging is accompanied by changes in cell morphological features, an accurate segmentation of RPE cells is a prerequisite to such morphology analyses. Due the overwhelmingly large cell number, manual annotations of RPE cell borders are time-consuming. Computer based methods do not work well on cells with weak or missing borders in the impaired RPE sheet regions. METHOD: To address such a challenge, we develop a semi-supervised deep learning approach, namely MultiHeadGAN, to segment low contrast cells from impaired regions in RPE flatmount images. The developed deep learning model has a multi-head structure that allows model training with only a small scale of human annotated data. To strengthen model learning, we further train our model with RPE cells without ground truth cell borders by generative adversarial networks. Additionally, we develop a new shape loss to guide the network to produce closed cell borders in the segmentation results. RESULTS: In this study, 155 annotated and 1,640 unlabeled image patches are included for model training. The testing dataset consists of 200 image patches presenting large impaired RPE regions. The average RPE segmentation performance of the developed model MultiHeadGAN is 85.4 (correct rate), 88.8 (weighted correct rate), 87.3 (precision), and 80.1 (recall), respectively. Compared with other state-of-the-art deep learning approaches, our method demonstrates its superior qualitative and quantitative performance. CONCLUSIONS: Suggested by our extensive experimental results, our developed deep learning method can accurately segment cells in RPE flatmount microscopy images and is promising to support large scale cell morphological analyses for RPE aging investigations.

Building Efficient CNN Architectures for Histopathology Images Analysis: A Case-Study in Tumor-Infiltrating Lymphocytes Classification.

Background: Deep learning methods have demonstrated remarkable performance in pathology image analysis, but they are computationally very demanding. The aim of our study is to reduce their computational cost to enable their use with large tissue image datasets. Methods: We propose a method called Network Auto-Reduction (NAR) that simplifies a Convolutional Neural Network (CNN) by reducing the network to minimize the computational cost of doing a prediction. NAR performs a compound scaling in which the width, depth, and resolution dimensions of the network are reduced together to maintain a balance among them in the resulting simplified network. We compare our method with a state-of-the-art solution called ResRep. The evaluation is carried out with popular CNN architectures and a real-world application that identifies distributions of tumor-infiltrating lymphocytes in tissue images. Results: The experimental results show that both ResRep and NAR are able to generate simplified, more efficient versions of ResNet50 V2. The simplified versions by ResRep and NAR require 1.32× and 3.26× fewer floating-point operations (FLOPs), respectively, than the original network without a loss in classification power as measured by the Area under the Curve (AUC) metric. When applied to a deeper and more computationally expensive network, Inception V4, NAR is able to generate a version that requires 4× lower than the original version with the same AUC performance. Conclusions: NAR is able to achieve substantial reductions in the execution cost of two popular CNN architectures, while resulting in small or no loss in model accuracy. Such cost savings can significantly improve the use of deep learning methods in digital pathology. They can enable studies with larger tissue image datasets and facilitate the use of less expensive and more accessible graphics processing units (GPUs), thus reducing the computing costs of a study.

Artificial intelligence based liver portal tract region identification and quantification with transplant biopsy whole-slide images.

Liver fibrosis staging is clinically important for liver disease progression prediction. As the portal tract fibrotic quantity and size in a liver biopsy correlate with the fibrosis stage, an accurate analysis of portal tract regions is clinically critical. Manual annotations of portal tract regions, however, are time-consuming and subject to large inter- and intra-observer variability. To address such a challenge, we develop a Multiple Up-sampling and Spatial Attention guided UNet model (MUSA-UNet) to segment liver portal tract regions in whole-slide images of liver tissue slides. To enhance the segmentation performance, we propose to use depth-wise separable convolution, the spatial attention mechanism, the residual connection, and multiple up-sampling paths in the developed model. This study includes 53 histopathology whole slide images from patients who received liver transplantation. In total, 6,012 patches derived from 30 images are used for our deep learning model training and validation. The remaining 23 whole slide images are utilized for the model testing. The average liver portal tract segmentation performance of the developed MUSA-UNet is 0.94 (Precision), 0.85 (Recall), 0.89 (F1 Score), 0.89 (Accuracy), 0.80 (Jaccard Index), and 0.91 (Fowlkes-Mallows Index), respectively. The clinical Scheuer fibrosis stage presents a strong correlation with the resulting average portal tract fibrotic area (R = 0.681, p<0.001) and portal tract percentage (R = 0.335, p = 0.02) computed from the MUSA-UNet segmentation results. In conclusion, our developed deep learning model MUSA-UNet can accurately segment portal tract regions from whole-slide images of liver tissue biopsies, presenting its promising potential to assist liver disease diagnosis in a computational manner.

Deep Learning-Based Pathology Image Analysis Enhances Magee Feature Correlation With Oncotype DX Breast Recurrence Score.

Background: Oncotype DX Recurrence Score (RS) has been widely used to predict chemotherapy benefits in patients with estrogen receptor-positive breast cancer. Studies showed that the features used in Magee equations correlate with RS. We aimed to examine whether deep learning (DL)-based histology image analyses can enhance such correlations. Methods: We retrieved 382 cases with RS diagnosed between 2011 and 2015 from the Emory University and the Ohio State University. All patients received surgery. DL models were developed to detect nuclei of tumor cells and tumor-infiltrating lymphocytes (TILs) and segment tumor cell nuclei in hematoxylin and eosin (H&E) stained histopathology whole slide images (WSIs). Based on the DL-based analysis, we derived image features from WSIs, such as tumor cell number, TIL number variance, and nuclear grades. The entire patient cohorts were divided into one training set (125 cases) and two validation sets (82 and 175 cases) based on the data sources and WSI resolutions. The training set was used to train the linear regression models to predict RS. For prediction performance comparison, we used independent variables from Magee features alone or the combination of WSI-derived image and Magee features. Results: The Pearson's correlation coefficients between the actual RS and predicted RS by DL-based analysis were 0.7058 (p-value = 1.32 × 10-13) and 0.5041 (p-value = 1.15 × 10-12) for the validation sets 1 and 2, respectively. The adjusted R 2 values using Magee features alone are 0.3442 and 0.2167 in the two validation sets, respectively. In contrast, the adjusted R 2 values were enhanced to 0.4431 and 0.2182 when WSI-derived imaging features were jointly used with Magee features. Conclusion: Our results suggest that DL-based digital pathological features can enhance Magee feature correlation with RS.