Histopathology images involve the analysis of tissue samples to diagnose several diseases, such as cancer. The analysis of tissue samples is a time-consuming procedure, manually made by medical experts, namely pathologists. Computational pathology aims to develop automatic methods to analyze Whole Slide Images (WSI), which are digitized histopathology images, showing accurate performance in terms of image analysis. Although the amount of available WSIs is increasing, the capacity of medical experts to manually analyze samples is not expanding proportionally. This paper presents a full automatic pipeline to classify lung cancer WSIs, considering four classes: Small Cell Lung Cancer (SCLC), non-small cell lung cancer divided into LUng ADenocarcinoma (LUAD) and LUng Squamous cell Carcinoma (LUSC), and normal tissue. The pipeline includes a self-supervised algorithm for pre-training the model and Multiple Instance Learning (MIL) for WSI classification. The model is trained with 2,226 WSIs and it obtains an AUC of 0.8558 ± 0.0051 and a weighted f1-score of 0.6537 ± 0.0237 for the 4-class classification on the test set. The capability of the model to generalize was evaluated by testing it on the public The Cancer Genome Atlas (TCGA) dataset on LUAD and LUSC classification. In this task, the model obtained an AUC of 0.9433 ± 0.0198 and a weighted f1-score of 0.7726 ± 0.0438.
With a prevalence of 1-2% Celiac Disease (CD) is one of the most commonly known genetic and autoimmune diseases, which is induced by the intake of gluten in genetically predisposed persons. Diagnosing CD involves the analysis of duodenum biopsies to determine the small intestine condition. In this study, we propose a singlescale pipeline and the combination of two single-scale pipelines, forming a multi-scale approach, to accurately classify CD signs in histopathology whole slide images with automatically generated labels. The automatic classification of CD signs in histopathological images of these biopsies has not been extensively studied, resulting in the absence of a standardized guidelines or best-practices for this purpose. To fill this gap, we evaluated different magnifications and architectures, including a pre-trained MoCov2 model, for both single- and multiscale approaches. Furthermore, for the multi-scale approach, methods for aggregating feature vectors from several magnifications are explored. For the single-scale pipeline we achieved an AUC of 0.9975 and a weighted F1-score of 0.9680, while for the multiscale Pipeline an AUC of 0.9966 and a weighted F1-score of 0.9250 was achieved. On large datasets, no significant differences were observed; however, with only 10% of the dataset, the multi-scale framework outperforms the single-scale framework significantly. Moreover, the multi-scale approach requires only half of the dataset and half of the time compared to the best single-scale result to identify the optimal model. In conclusion, the multi-scale framework emerges as an exceptionally efficient solution, capable of delivering superior results with minimal data and resource demands.
In this work, we propose a deep learning system for weakly supervised object detection in digital pathology whole slide images. We designed the system to be organ- and object-agnostic, and to be adapted on-the-fly to detect novel objects based on a few examples provided by the user. We tested our method on detection of healthy glands in colon biopsies and ductal carcinoma in situ (DCIS) of the breast, showing that (1) the same system is capable of adapting to detect requested objects with high accuracy, namely 87% accuracy assessed on 582 detections in colon tissue, and 93% accuracy assessed on 163 DCIS detections in breast tissue; (2) in some settings, the system is capable of retrieving similar cases with little to none false positives (i.e., precision equal to 1.00); (3) the performance of the system can benefit from previously detected objects with high confidence that can be reused in new searches in an iterative fashion.
Classification of non-small-cell lung cancer (NSCLC) into adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) via histopathology is a vital prerequisite to select the appropriate treatment for lung cancer patients. Most machine learning approaches rely on manually annotating large numbers of whole slide images (WSI) for training. However, manually delineating cancer areas or even single cancer cells on hundreds or thousands of slides is tedious, subjective and requires highly trained pathologists. We propose to use Neural Image Compression (NIC), which requires only slide-level labels, to classify NSCLC into LUSC and LUAD. NIC consists of two phases/networks. In the first phase the slides are compressed with a convolutional neural network (CNN) acting as an encoder. In the second phase the compressed slides are classified with a second CNN. We trained our classification model on >2,000 NIC-compressed slides from the TCGA and TCIA databases and evaluated the model performance additionally on several internal and external cohorts. We show that NIC approaches state of the art performance on lung cancer classification, with an average AUC of 0.94 on the TCGA and TCIA testdata, and AUCs between 0.84 and 0.98 on other independent datasets.
When diagnosing and reporting lung adenocarcinoma (LAC), pathologists currently include an assessment of histologic tumor growth patterns because the predominant growth pattern has been reported to impact prognosis. However, the subjective nature of manual slide evaluation contributes to suboptimal inter-pathologist variability in tumor growth pattern assessment. We applied a deep learning approach to identify and automatically delineate areas of four tumor growth patterns (solid, acinar, micropapillary, and cribriform) and non-tumor areas in whole slide images (WSI) from resected LAC specimens. We trained a DenseNet model using patches from 109 slides collected at two institutions. The model was tested using 56 WSIs including 20 that were collected at a third institution. Using the same slide set, the concordance between the DenseNet model and an experienced pathologist (blinded to the DenseNet results) in determining the predominant tumor growth pattern was substantial (kappa score = 0.603). Using a subset of 36 test slides that were manually annotated for tumor growth patterns, we also measured the F1-score for each growth pattern: 0.95 (solid), 0.78 (acinar), 0.76 (micropapillary), 0.28 (cribriform) and 0.97 (non-tumor). Our results suggest that DenseNet assessment of WSIs with solid, acinar, and micropapillary predominant tumor growth is more robust than for the WSIs with predominant cribriform growth which are less frequently encountered.
The number of mitotic figures per tumor area observed in hematoxylin and eosin (H and E) histological tissue sections under light microscopy is an important biomarker for breast cancer prognosis. Whole-slide imaging and computational pathology have enabled the development of automatic mitosis detection algorithms based on convolutional neural networks (CNNs). These models can suffer from high generalization error, i.e. trained networks often underperform on datasets originating from pathology laboratories different than the one that provided the training data, mainly due to the presence of inter-laboratory stain variations. We propose a novel data augmentation strategy that exploits the properties of the H and E color space to simulate a broad range of realistic H and E stain variations. To our best knowledge, this is the first time that data augmentation is performed directly in the H and E color space, instead of RGB. The proposed technique uses color deconvolution to transform RGB images into the H and E color space, modifies the H and E color channels stochastically, and projects them back to RGB space. We trained a CNN-based mitosis detector on homogeneous data from a single institution, and tested its performance on an external, multicenter cohort that contained a wide range of unseen H and E stain variations. We compared CNNs trained with and without the proposed augmentation strategy and observed a significant improvement in performance and robustness to unseen stain variations when the new color augmentation technique was included. In essence, we have shown that CNNs can be made robust to inter-lab stain variation by incorporating extensive stain augmentation techniques.
The amount of calcifications in the coronary arteries is a powerful and independent predictor of cardiovascular events and is used to identify subjects at high risk who might benefit from preventive treatment. Routine quantification of coronary calcium scores can complement screening programs using low-dose chest CT, such as lung cancer screening. We present a system for automatic coronary calcium scoring based on deep convolutional neural networks (CNNs). The system uses three independently trained CNNs to estimate a bounding box around the heart. In this region of interest, connected components above 130 HU are considered candidates for coronary artery calcifications. To separate them from other high intensity lesions, classification of all extracted voxels is performed by feeding two-dimensional 50 mm × 50 mm patches from three orthogonal planes into three concurrent CNNs. The networks consist of three convolutional layers and one fully-connected layer with 256 neurons. In the experiments, 1028 non-contrast-enhanced and non-ECG-triggered low-dose chest CT scans were used. The network was trained on 797 scans. In the remaining 231 test scans, the method detected on average 194.3 mm3 of 199.8 mm3 coronary calcifications per scan (sensitivity 97.2 %) with an average false-positive volume of 10.3 mm3 . Subjects were assigned to one of five standard cardiovascular risk categories based on the Agatston score. Accuracy of risk category assignment was 84.4 % with a linearly weighted κ of 0.89. The proposed system can perform automatic coronary artery calcium scoring to identify subjects undergoing low-dose chest CT screening who are at risk of cardiovascular events with high accuracy.
We present a fully automatic method for the assessment of spiculation of pulmonary nodules in low-dose Computed Tomography (CT) images. Spiculation is considered as one of the indicators of nodule malignancy and an important feature to assess in order to decide on a patient-tailored follow-up procedure. For this reason, lung cancer screening scenario would benefit from the presence of a fully automatic system for the assessment of spiculation. The presented framework relies on the fact that spiculated nodules mainly differ from non-spiculated ones in their morphology. In order to discriminate the two categories, information on morphology is captured by sampling intensity profiles along circular patterns on spherical surfaces centered on the nodule, in a multi-scale fashion. Each intensity profile is interpreted as a periodic signal, where the Fourier transform is applied, obtaining a spectrum. A library of spectra is created by clustering data via unsupervised learning. The centroids of the clusters are used to label back each spectrum in the sampling pattern. A compact descriptor encoding the nodule morphology is obtained as the histogram of labels along all the spherical surfaces and used to classify spiculated nodules via supervised learning. We tested our approach on a set of nodules from the Danish Lung Cancer Screening Trial (DLCST) dataset. Our results show that the proposed method outperforms other 3-D descriptors of morphology in the automatic assessment of spiculation.
Computer-Aided Detection (CAD) has been shown to be a promising tool for automatic detection of pulmonary nodules from computed tomography (CT) images. However, the vast majority of detected nodules are benign and do not require any treatment. For effective implementation of lung cancer screening programs, accurate identification of malignant nodules is the key. We investigate strategies to improve the performance of a CAD system in detecting nodules with a high probability of being cancers. Two strategies were proposed: (1) combining CAD detections with a recently published lung cancer risk prediction model and (2) the combination of multiple CAD systems. First, CAD systems were used to detect the nodules. Each CAD system produces markers with a certain degree of suspicion. Next, the malignancy probability was automatically computed for each marker, given nodule characteristics measured by the CAD system. Last, CAD degree of suspicion and malignancy probability were combined using the product rule. We evaluated the method using 62 nodules which were proven to be malignant cancers, from 180 scans of the Danish Lung Cancer Screening Trial. The malignant nodules were considered as positive samples, while all other findings were considered negative. Using a product rule, the best proposed system achieved an improvement in sensitivity, compared to the best individual CAD system, from 41.9% to 72.6% at 2 false positives (FPs)/scan and from 56.5% to 88.7% at 8 FPs/scan. Our experiment shows that combining a nodule malignancy probability with multiple CAD systems can increase the performance of computerized detection of lung cancer.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.