Predicting endometrial cancer subtypes and molecular features from histopathology images using multi-resolution deep learning models.
Ontology highlight
ABSTRACT:
SUBMITTER: Hong R
PROVIDER: S-EPMC8484685 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:N-staging is a determining factor for prognostic assessment and decision-making for stage-based cancer therapeutic strategies. Visual inspection of whole-slides of intact lymph nodes is currently the main method used by pathologists to calculate the number of metastatic lymph nodes (MLNs). Moreover, even at the same N stage, the outcome of patients varies dramatically. Here, we propose a deep-learning framework for analyzing lymph node whole-slide images (WSIs) to identify lymph nodes and tumor regions, and then to uncover tumor-area-to-MLN-area ratio (T/MLN). After training, our model's tumor detection performance was comparable to that of experienced pathologists and achieved similar performance on two independent gastric cancer validation cohorts. Further, we demonstrate that T/MLN is an interpretable independent prognostic factor. These findings indicate that deep-learning models could assist not only pathologists in detecting lymph nodes with metastases but also oncologists in exploring new prognostic factors, especially those that are difficult to calculate manually.
| S-EPMC7954798 | biostudies-literature
Project description:Breast cancer is a common malignancy and a leading cause of cancer-related deaths in women worldwide. Its early diagnosis can significantly reduce the morbidity and mortality rates in women. To this end, histopathological diagnosis is usually followed as the gold standard approach. However, this process is tedious, labor-intensive, and may be subject to inter-reader variability. Accordingly, an automatic diagnostic system can assist to improve the quality of diagnosis. This paper presents a deep learning approach to automatically classify hematoxylin-eosin-stained breast cancer microscopy images into normal tissue, benign lesion, in situ carcinoma, and invasive carcinoma using our collected dataset. Our proposed model exploited six intermediate layers of the Xception (Extreme Inception) network to retrieve robust and abstract features from input images. First, we optimized the proposed model on the original (unnormalized) dataset using 5-fold cross-validation. Then, we investigated its performance on four normalized datasets resulting from Reinhard, Ruifrok, Macenko, and Vahadane stain normalization. For original images, our proposed framework yielded an accuracy of 98% along with a kappa score of 0.969. Also, it achieved an average AUC-ROC score of 0.998 as well as a mean AUC-PR value of 0.995. Specifically, for in situ carcinoma and invasive carcinoma, it offered sensitivity of 96% and 99%, respectively. For normalized images, the proposed architecture performed better for Makenko normalization compared to the other three techniques. In this case, the proposed model achieved an accuracy of 97.79% together with a kappa score of 0.965. Also, it attained an average AUC-ROC score of 0.997 and a mean AUC-PR value of 0.991. Especially, for in situ carcinoma and invasive carcinoma, it offered sensitivity of 96% and 99%, respectively. These results demonstrate that our proposed model outperformed the baseline AlexNet as well as state-of-the-art VGG16, VGG19, Inception-v3, and Xception models with their default settings. Furthermore, it can be inferred that although stain normalization techniques offered competitive performance, they could not surpass the results of the original dataset.
| S-EPMC9649689 | biostudies-literature
Project description:PurposeThe purpose of this study was to explore the performance of different parameter combinations of deep learning (DL) models (Xception, DenseNet121, MobileNet, ResNet50 and EfficientNetB0) and input image resolutions (REZs) (224 × 224, 320 × 320 and 488 × 488 pixels) for breast cancer diagnosis.MethodsThis multicenter study retrospectively studied gray-scale ultrasound breast images enrolled from two Chinese hospitals. The data are divided into training, validation, internal testing and external testing set. Three-hundreds images were randomly selected for the physician-AI comparison. The Wilcoxon test was used to compare the diagnose error of physicians and models under P=0.05 and 0.10 significance level. The specificity, sensitivity, accuracy, area under the curve (AUC) were used as primary evaluation metrics.ResultsA total of 13,684 images of 3447 female patients are finally included. In external test the 224 and 320 REZ achieve the best performance in MobileNet and EfficientNetB0 respectively (AUC: 0.893 and 0.907). Meanwhile, 448 REZ achieve the best performance in Xception, DenseNet121 and ResNet50 (AUC: 0.900, 0.883 and 0.871 respectively). In physician-AI test set, the 320 REZ for EfficientNetB0 (AUC: 0.896, P < 0.1) is better than senior physicians. Besides, the 224 REZ for MobileNet (AUC: 0.878, P < 0.1), 448 REZ for Xception (AUC: 0.895, P < 0.1) are better than junior physicians. While the 448 REZ for DenseNet121 (AUC: 0.880, P < 0.05) and ResNet50 (AUC: 0.838, P < 0.05) are only better than entry physicians.ConclusionBased on the gray-scale ultrasound breast images, we obtained the best DL combination which was better than the physicians.
| S-EPMC9302001 | biostudies-literature
Project description:Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with cancer in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through a deep learning-based model. When applied to a cohort of 1,010 patients with breast cancer (Training set: n = 858, Test set: n = 152) from The Cancer Genome Atlas where 485 patients have high CIN status, our model accurately classified CIN status, achieving an area under the curve of 0.822 with 81.2% sensitivity and 68.7% specificity in the test set. Patch-level predictions of CIN status suggested intra-tumor heterogeneity within slides. Moreover, presence of patches with high predicted CIN score within an entire slide was more predictive of clinical outcome than the average CIN score of the slide, thus underscoring the clinical importance of intra-tumor heterogeneity.
| S-EPMC8099498 | biostudies-literature
Project description:Radiographic imaging is routinely used to evaluate treatment response in solid tumors. Current imaging response metrics do not reliably predict the underlying biological response. Here, we present a multi-task deep learning approach that allows simultaneous tumor segmentation and response prediction. We design two Siamese subnetworks that are joined at multiple layers, which enables integration of multi-scale feature representations and in-depth comparison of pre-treatment and post-treatment images. The network is trained using 2568 magnetic resonance imaging scans of 321 rectal cancer patients for predicting pathologic complete response after neoadjuvant chemoradiotherapy. In multi-institution validation, the imaging-based model achieves AUC of 0.95 (95% confidence interval: 0.91-0.98) and 0.92 (0.87-0.96) in two independent cohorts of 160 and 141 patients, respectively. When combined with blood-based tumor markers, the integrated model further improves prediction accuracy with AUC 0.97 (0.93-0.99). Our approach to capturing dynamic information in longitudinal images may be broadly used for screening, treatment response evaluation, disease monitoring, and surveillance.
| S-EPMC7994301 | biostudies-literature
Project description:High computational cost associated with digital pathology image analysis approaches is a challenge towards their translation in routine pathology clinic. Here, we propose a computationally efficient framework (SuperHistopath), designed to map global context features reflecting the rich tumor morphological heterogeneity. SuperHistopath efficiently combines i) a segmentation approach using the linear iterative clustering (SLIC) superpixels algorithm applied directly on the whole-slide images at low resolution (5x magnification) to adhere to region boundaries and form homogeneous spatial units at tissue-level, followed by ii) classification of superpixels using a convolution neural network (CNN). To demonstrate how versatile SuperHistopath was in accomplishing histopathology tasks, we classified tumor tissue, stroma, necrosis, lymphocytes clusters, differentiating regions, fat, hemorrhage and normal tissue, in 127 melanomas, 23 triple-negative breast cancers, and 73 samples from transgenic mouse models of high-risk childhood neuroblastoma with high accuracy (98.8%, 93.1% and 98.3% respectively). Furthermore, SuperHistopath enabled discovery of significant differences in tumor phenotype of neuroblastoma mouse models emulating genomic variants of high-risk disease, and stratification of melanoma patients (high ratio of lymphocyte-to-tumor superpixels (p = 0.015) and low stroma-to-tumor ratio (p = 0.028) were associated with a favorable prognosis). Finally, SuperHistopath is efficient for annotation of ground-truth datasets (as there is no need of boundary delineation), training and application (~5 min for classifying a whole-slide image and as low as ~30 min for network training). These attributes make SuperHistopath particularly attractive for research in rich datasets and could also facilitate its adoption in the clinic to accelerate pathologist workflow with the quantification of phenotypes, predictive/prognosis markers.
| S-EPMC7855703 | biostudies-literature
Project description:Pancreatic cancer is one of the most adverse diseases and it is very difficult to treat because the cancer cells formed in the pancreas intertwine themselves with nearby blood vessels and connective tissue. Hence, the surgical procedure of treatment becomes complicated and it does not always lead to a cure. Histopathological diagnosis is the usual approach for cancer diagnosis. However, the pancreas remains so deep inside the body that experts sometimes struggle to detect cancer in it. Computer-aided diagnosis can come to the aid of pathologists in this scenario. It assists experts by supporting their diagnostic decisions. In this research, we carried out a deep learning-based approach to analyze histopathology images. We collected whole-slide images of KPC mice to implement this work. The pancreatic abnormalities observed in KPC mice develop similar histological features to human beings. We created random patches from whole-slide images. Then, a convolutional autoencoder framework was used to embed these patches into an integrated latent space. We applied 'information maximization', a deep learning clustering technique to cluster the identical patches in an unsupervised manner since our dataset does not have annotation. Moreover, Uniform manifold approximation and projection, a nonlinear dimension reduction technique was utilized to visualize the embedded patches in a 2-dimensional space. Finally, we calculated a few internal cluster validation metrics to determine the optimal cluster set. Our work concentrated on patch-based anomaly detection in the whole slide histopathology images of KPC mice.
| S-EPMC10707605 | biostudies-literature
Project description:Automatic multi-classification of breast cancer histopathological images has remained one of the top-priority research areas in the field of biomedical informatics, due to the great clinical significance of multi-classification in providing diagnosis and prognosis of breast cancer. In this work, two machine learning approaches are thoroughly explored and compared for the task of automatic magnification-dependent multi-classification on a balanced BreakHis dataset for the detection of breast cancer. The first approach is based on handcrafted features which are extracted using Hu moment, color histogram, and Haralick textures. The extracted features are then utilized to train the conventional classifiers, while the second approach is based on transfer learning where the pre-existing networks (VGG16, VGG19, and ResNet50) are utilized as feature extractor and as a baseline model. The results reveal that the use of pre-trained networks as feature extractor exhibited superior performance in contrast to baseline approach and handcrafted approach for all the magnifications. Moreover, it has been observed that the augmentation plays a pivotal role in further enhancing the classification accuracy. In this context, the VGG16 network with linear SVM provides the highest accuracy that is computed in two forms, (a) patch-based accuracies (93.97% for 40×, 92.92% for 100×, 91.23% for 200×, and 91.79% for 400×); (b) patient-based accuracies (93.25% for 40×, 91.87% for 100×, 91.5% for 200×, and 92.31% for 400×) for the classification of magnification-dependent histopathological images. Additionally, "Fibro-adenoma" (benign) and "Mucous Carcinoma" (malignant) classes have been found to be the most complex classes for the entire magnification factors.
| S-EPMC7256154 | biostudies-literature
Project description:Providing prognostic information at the time of cancer diagnosis has important implications for treatment and monitoring. Although cancer staging, histopathological assessment, molecular features, and clinical variables can provide useful prognostic insights, improving risk stratification remains an active research area. We developed a deep learning system (DLS) to predict disease specific survival across 10 cancer types from The Cancer Genome Atlas (TCGA). We used a weakly-supervised approach without pixel-level annotations, and tested three different survival loss functions. The DLS was developed using 9,086 slides from 3,664 cases and evaluated using 3,009 slides from 1,216 cases. In multivariable Cox regression analysis of the combined cohort including all 10 cancers, the DLS was significantly associated with disease specific survival (hazard ratio of 1.58, 95% CI 1.28-1.70, p<0.0001) after adjusting for cancer type, stage, age, and sex. In a per-cancer adjusted subanalysis, the DLS remained a significant predictor of survival in 5 of 10 cancer types. Compared to a baseline model including stage, age, and sex, the c-index of the model demonstrated an absolute 3.7% improvement (95% CI 1.0-6.5) in the combined cohort. Additionally, our models stratified patients within individual cancer stages, particularly stage II (p = 0.025) and stage III (p<0.001). By developing and evaluating prognostic models across multiple cancer types, this work represents one of the most comprehensive studies exploring the direct prediction of clinical outcomes using deep learning and histopathology images. Our analysis demonstrates the potential for this approach to provide significant prognostic information in multiple cancer types, and even within specific pathologic stages. However, given the relatively small number of cases and observed clinical events for a deep learning task of this type, we observed wide confidence intervals for model performance, thus highlighting that future work will benefit from larger datasets assembled for the purposes for survival modeling.
| S-EPMC7299324 | biostudies-literature
Project description:Histopathological diagnosis of lymphomas represents a challenge requiring either expertise or centralised review, and greatly depends on the technical process of tissue sections. Hence, we developed an innovative deep-learning framework, empowered with a certainty estimation level, designed for haematoxylin and eosin-stained slides analysis, with special focus on follicular lymphoma (FL) diagnosis. Whole-slide images of lymph nodes affected by FL or follicular hyperplasia were used for training, validating, and finally testing Bayesian neural networks (BNN). These BNN provide a diagnostic prediction coupled with an effective certainty estimation, and generate accurate diagnosis with an area under the curve reaching 0.99. Through its uncertainty estimation, our network is also able to detect unfamiliar data such as other small B cell lymphomas or technically heterogeneous cases from external centres. We demonstrate that machine-learning techniques are sensitive to the pre-processing of histopathology slides and require appropriate training to build universal tools to aid diagnosis.
| S-EPMC7195401 | biostudies-literature