Histopathological Dataset Research Articles

Investigating the impact of class-dependent label noise in medical image classification.

Label noise is inevitable in medical image databases developed for deep learning due to the inter-observer variability caused by the different levels of expertise of the experts annotating the images, and, in some cases, the automated methods that generate labels from medical reports. It is known that incorrect annotations or label noise can degrade the actual performance of supervised deep learning models and can bias the model's evaluation. Existing literature show that noise in one class has minimal impact on the model's performance for another class in natural image classification problems where different target classes have a relatively distinct shape and share minimal visual cues for knowledge transfer among the classes. However, it is not clear how class-dependent label noise affects the model's performance when operating on medical images, for which different output classes can be difficult to distinguish even for experts, and there is a high possibility of knowledge transfer across classes during the training period. We hypothesize that for medical image classification tasks where the different classes share a very similar shape with differences only in texture, the noisy label for one class might affect the performance across other classes, unlike the case when the target classes have different shapes and are visually distinct. In this paper, we study this hypothesis using two publicly available datasets: a 2D organ classification dataset with target organ classes being visually distinct, and a histopathology image classification dataset where the target classes look very similar visually. Our results show that the label noise in one class has a much higher impact on the model's performance on other classes for the histopathology dataset compared to the organ dataset.

A Comparative Study of Transfer Learning based Models for Lung Cancer Histopathology Classification

Lung cancer is the deadliest form of cancer, which attracted a lot of attention in the past. Transfer learning is a very popular approach in deep learning as it can apply the knowledge obtained from a previous task to improve the performance in another. In this research, four transfer learning models with different complexity are utilized to detect lung cancer, which are AlexNet, VGG16, ResNet50 and Inception-v3. Since the early detection and histopathological diagnosis can considerably decrease the likelihood of mortality, the lung cancer histopathological images dataset is considered. This dataset contains histopathological images of 3 classes, all of them are considered in this study. Firstly, the four models are trained on the histopathological database from random initialization for 10 epochs. Next, the four models are first pre-trained on ImageNet and then trained on the histopathological dataset for 10 epochs. For each epoch, the testing accuracy is recorded so as to find the optimal number of epochs and determine whether transfer learning models are capable in lung cancer detection. Then, various evaluation metrics e.g., accuracy and precision are used to measure and compare the four models’ performance. The study’s finding shows that AlexNet, VGG16, ResNet50 and Inception-v3 pre-trained on ImageNet are adequate in lung cancer detection. There corresponding accuracy rates are 99.367%, 99.800%, 100% and 100% respectively, which are much higher than that trained from random initialization. Among the four transfer learning models, ResNet50 and Inception-v3 perform the best on lung cancer classification.

An efficient transfer learning based cross model classification (TLBCM) technique for the prediction of breast cancer.

Breast cancer has been the most life-threatening disease in women in the last few decades. The high mortality rate among women is due to breast cancer because of less awareness and a minimum number of medical facilities to detect the disease in the early stages. In the recent era, the situation has changed with the help of many technological advancements and medical equipment to observe breast cancer development. The machine learning technique supports vector machines (SVM), logistic regression, and random forests have been used to analyze the images of cancer cells on different data sets. Although the particular technique has performed better on the smaller data set, accuracy still needs to catch up in most of the data, which needs to be fairer to apply in the real-time medical environment. In the proposed research, state-of-the-art deep learning techniques, such as transfer learning, based cross model classification (TLBCM), convolution neural network (CNN) and transfer learning, residual network (ResNet), and Densenet proposed for efficient prediction of breast cancer with the minimized error rating. The convolution neural network and transfer learning are the most prominent techniques for predicting the main features in the data set. The sensitive data is protected using a cyber-physical system (CPS) while using the images virtually over the network. CPS act as a virtual connection between human and networks. While the data is transferred in the network, it must monitor using CPS. The ResNet changes the data on many layers without compromising the minimum error rate. The DenseNet conciliates the problem of vanishing gradient issues. The experiment is carried out on the data sets Breast Cancer Wisconsin (Diagnostic) and Breast Cancer Histopathological Dataset (BreakHis). The convolution neural network and the transfer learning have achieved a validation accuracy of 98.3%. The results of these proposed methods show the highest classification rate between the benign and the malignant data. The proposed method improves the efficiency and speed of classification, which is more convenient for discovering breast cancer in earlier stages than the previously proposed methodologies.

Deep Multi-Magnification Similarity Learning for Histopathological Image Classification.

Precise classification of histopathological images is crucial to computer-aided diagnosis in clinical practice. Magnification-based learning networks have attracted considerable attention for their ability to improve performance in histopathological classification. However, the fusion of pyramids of histopathological images at different magnifications is an under-explored area. In this paper, we proposed a novel deep multi-magnification similarity learning (DSML) approach that can be useful for the interpretation of multi-magnification learning framework and easy to visualize feature representation from low-dimension (e.g., cell-level) to high-dimension (e.g., tissue-level), which has overcome the difficulty of understanding cross-magnification information propagation. It uses a similarity cross entropy loss function designation to simultaneously learn the similarity of the information among cross-magnifications. In order to verify the effectiveness of DMSL, experiments with different network backbones and different magnification combinations were designed, and its ability to interpret was also investigated through visualization. Our experiments were performed on two different histopathological datasets: a clinical nasopharyngeal carcinoma and a public breast cancer BCSS2021 dataset. The results show that our method achieved outstanding performance in classification with a higher value of area under curve, accuracy, and F-score than other comparable methods. Moreover, the reasons behind multi-magnification effectiveness were discussed.

Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation

Learning discriminative representations of unlabelled data is a challenging task. Contrastive self-supervised learning provides a framework to learn meaningful representations using learned notions of similarity measures from simple pretext tasks. In this work, we propose a simple and efficient framework for self-supervised image segmentation using contrastive learning on image patches, without using explicit pretext tasks or any further labeled fine-tuning. A fully convolutional neural network (FCNN) is trained in a self-supervised manner to discern features in the input images and obtain confidence maps which capture the network's belief about the objects belonging to the same class. Positive- and negative- patches are sampled based on the average entropy in the confidence maps for contrastive learning. Convergence is assumed when the information separation between the positive patches is small, and the positive-negative pairs is large. The proposed model only consists of a simple FCNN with 10.8k parameters and requires about 5 minutes to converge on the high resolution microscopy datasets, which is orders of magnitude smaller than the relevant self-supervised methods to attain similar performance. We evaluate the proposed method for the task of segmenting nuclei from two histopathology datasets, and show comparable performance with relevant self-supervised and supervised methods.

Modality Specific CBAM-VGGNet Model for the Classification of Breast Histopathology Images via Transfer Learning

Histopathology images are very distinctive, and one image may contain thousands of objects. Transferring features from natural images to histopathology images may not provide impressive outcomes. In this study, we have proposed a novel modality-specific CBAM-VGGNet model for classifying H and E stained breast histopathology images. Instead of using pre-trained models on ImageNet, we have trained VGG16 and VGG19 models on the same domain cancerous histopathology datasets which are then used as fixed feature extractors. We have added GAP layer and Convolutional block attention module (CBAM) after the first convolutional layer of convolutional blocks. CBAM is an effective module for neural networks to focus on relevant features. We have implemented the VGG16 and VGG19 in a novel way following the configuration of state-of-the-art models with our own concatenated layers. The addition of the GAP layer in VGGNet has reduced the number of parameters and hence requiring less computational power. Both models are ensembled using the averaging ensemble technique. Features are extracted from the final ensembled model then passed to the feed-forward neural network. A hybrid pre-processing technique is proposed that first use median filter and afterwards contrast limited adaptive histogram equalization (CLAHE). Median filter is utilized to remove the highly significant noise and is directly related to image quality. CLAHE improve the local contrast present in an image and boost the weak boundary edges in each image pixel. The proposed CBAM ensemble model has outperformed state-of-the-art models with an accuracy of 98.96% and 97.95% F1-score on 400X data of BreakHis dataset.

An AI-assisted tool for efficient prostate cancer diagnosis in low-grade and low-volume cases

Pathologists diagnose prostate cancer by core needle biopsy. In low-grade and low-volume cases, they look for a few malignant glands out of hundreds within a core. They may miss a few malignant glands, resulting in repeat biopsies or missed therapeutic opportunities. This study developed a multi-resolution deep-learning pipeline to assist pathologists in detecting malignant glands in core needle biopsies of low-grade and low-volume cases. Analyzing a gland at multiple resolutions, our model exploited morphology and neighborhood information, which were crucial in prostate gland classification. We developed and tested our pipeline on the slides of a local cohort of 99 patients in Singapore. Besides, we made the images publicly available, becoming the first digital histopathology dataset of patients of Asian ancestry with prostatic carcinoma. Our multi-resolution classification model achieved an area under the receiver operating characteristic curve (AUROC) value of 0.992 (95% confidence interval [CI]: 0.985-0.997) in the external validation study, showing the generalizability of our multi-resolution approach.

GC-EnC: A Copula based ensemble of CNNs for malignancy identification in breast histopathology and cytology images

In the present work, we have explored the potential of Copula-based ensemble of CNNs(Convolutional Neural Networks) over individual classifiers for malignancy identification in histopathology and cytology images. The Copula-based model that integrates three best performing CNN architectures, namely, DenseNet-161/201, ResNet-101/34, InceptionNet-V3 is proposed. Also, the limitation of small dataset is circumvented using a Fuzzy template based data augmentation technique that intelligently selects multiple region of interests (ROIs) from an image. The proposed framework of data augmentation amalgamated with the ensemble technique showed a gratifying performance in malignancy prediction surpassing the individual CNN’s performance on breast cytology and histopathology datasets. The proposed method has achieved accuracies of 84.37%, 97.32%, 91.67% on the JUCYT, BreakHis and BI datasets respectively. This automated technique will serve as a useful guide to the pathologist in delivering the appropriate diagnostic decision in reduced time and effort. The relevant codes of the proposed ensemble model are publicly available on GitHub.

A Federated Learning Framework for Breast Cancer Histopathological Image Classification

Quantities and diversities of datasets are vital to model training in a variety of medical image diagnosis applications. However, there are the following problems in real scenes: the required data may not be available in a single institution due to the number of patients or the type of pathology, and it is often not feasible to share patient data due to medical data privacy regulations. This means keeping private data safe is required and has become an obstacle in fusing data from multi-party to train a medical model. To solve the problems, we propose a federated learning framework, which allows knowledge fusion achieved by sharing the model parameters of each client through federated training rather than sharing data. Based on breast cancer histopathological dataset (BreakHis), our federated learning experiments achieve the expected results which are similar to the performances of the centralized learning and verify the feasibility and efficiency of the proposed framework.

Weakly Supervised Learning using Attention gates for colon cancer histopathological image segmentation

Recently, Artificial Intelligence namely Deep Learning methods have revolutionized a wide range of domains and applications. Besides, Digital Pathology has so far played a major role in the diagnosis and the prognosis of tumors. However, the characteristics of the Whole Slide Images namely the gigapixel size, high resolution and the shortage of richly labeled samples have hindered the efficiency of classical Machine Learning methods. That goes without saying that traditional methods are poor in generalization to different tasks and data contents. Regarding the success of Deep learning when dealing with Large Scale applications, we have resorted to the use of such models for histopathological image segmentation tasks. First, we review and compare the classical UNet and Att-UNet models for colon cancer WSI segmentation in a sparsely annotated data scenario. Then, we introduce novel enhanced models of the Att-UNet where different schemes are proposed for the skip connections and spatial attention gates positions in the network. In fact, spatial attention gates assist the training process and enable the model to avoid irrelevant feature learning. Alternating the presence of such modules namely in our Alter-AttUNet model adds robustness and ensures better image segmentation results. In order to cope with the lack of richly annotated data in our AiCOLO colon cancer dataset, we suggest the use of a multi-step training strategy that also deals with the WSI sparse annotations and unbalanced class issues. All proposed methods outperform state-of-the-art approaches but Alter-AttUNet generates the best compromise between accurate results and light network. The model achieves 95.88% accuracy with our sparse AiCOLO colon cancer datasets. Finally, to evaluate and validate our proposed architectures we resort to publicly available WSI data: the NCT-CRC-HE-100K, the CRC-5000 and the Warwick colon cancer histopathological dataset. Respective accuracies of 99.65%, 99.73% and 79.03% were reached. A comparison with state-of-art approaches is established to view and compare the key solutions for histopathological image segmentation.

Transfer Learning Approach and Nucleus Segmentation with MedCLNet Colon Cancer Database.

Machine learning has been recently used especially in the medical field. In the diagnosis of serious diseases such as cancer, deep learning techniques can be used to reduce the workload of experts and to produce quick solutions. The nuclei found in the histopathology dataset are an essential parameter in disease detection. The nucleus segmentation was performed using the colorectal histology MNIST dataset for nucleus detection in this study. The graph theory, PSO, watershed, and random walker algorithms were used for the segmentation process. In addition, we present the 10-class MedCLNet visual dataset consisting of the NCT-CRC-HE-100K dataset, LC25000 dataset, and GlaS dataset that can be used in transfer learning studies from deep learning techniques. The study proposes a transfer learning technique using the MedCLNet database. Deep neural networks pre-trained with the proposed transfer learning method were used in the classification with the colorectal histology MNIST dataset in the experimental process. DenseNet201, DenseNet169, InceptionResNetV2, InceptionV3, ResNet152V2, ResNet101V2, and Xception deep learning algorithms were used in transfer learning and the classification studies. The proposed approach was analyzed before and after transfer learning with different methods (DenseNet169 + SVM, DenseNet169 + GRU). In the performance measurement, using the colorectal histology MNIST dataset, 94.29% accuracy was obtained in the DenseNet169 model, which was initiated with random weights in the multi-classification study, and 95.00% accuracy after transfer learning was applied. In comparison with the results obtained from empirical studies, it was demonstrated that the proposed method produced satisfactory outcomes. The application is expected to provide a secondary evaluation for physicians in colon cancer detection and the segmentation.

Tumour Incidence in Dogs in Germany: a Retrospective Analysis of 109,616 Histopathological Diagnoses (2014–2019)

Characterization of a tumour entity is based on the precise histopathological diagnosis taking into account the signalment of the diseased animal. The present study is a comprehensive, up-to-date statistical investigation on the type, frequency and breed distribution of neoplasia in dogs in Germany. The histopathological datasets of 109,616 German canine tissue samples (2014-2019) were processed and statistically examined in retrospect. Non-neoplastic diseases were found in 38,650 samples (35.3%) and 70,966 neoplasms (64.7%) were diagnosed. The most common neoplasms were mammary tumours (21.9%), benign epithelial skin tumours (15.4%), mast cell tumour (9.7%), histiocytoma (7.0%), soft tissue sarcoma (5.8%), lipoma (5.8%), melanocytic tumours (5.2%) and odontogenic tumours (4.7%). In general, Beagles, Magyar Vizslas, Boxers, Schnauzers, Spaniels, French Bulldogs and Golden Retrievers had an increased risk of neoplasia (odds ratio 1.17-1.46; all: P ≤0.001) compared with crossbreed dogs. In particular, Boxers, Golden Retrievers, Rottweilers and Schnauzers were often affected by malignant neoplasms, whereas some breeds (eg, West Highland White Terrier, Magyar Vizsla, Chihuahua, Dachshund and Yorkshire Terrier) were frequently affected by numerous benign tumour types. Despite the known risk of haemangiosarcoma in German Shepherd Dogs, other malignant tumours were rare in this breed. Depending on the type of tumour, some purebred dog breeds can have an increased, reduced or identical risk for certain neoplasms compared with crossbreeds. Discussion of breed predispositions to tumour diseases must therefore be conducted critically and with a view to clinical relevance.

Rethinking ImageNet Pre-training for Computational Histopathology.

Transfer learning from ImageNet pretrained weights is widely used when training Deep Learning models on a Histopathology dataset. However, the visual features of the two domains are different. Rather than ImageNet pretrained weights, pre-training on a Histopathology dataset may provide better initialization. To prove this hypothesis, we train two commonly used Deep Learning model architectures - ResNet and DenseNet on a complex Histopathology classification dataset, and compare transfer learning performance with ImageNet pretrained weights. Based on the fine-tuning on three histopathology datasets including two different stains (H&E and IHC), we show that the domain specific pretrained weights are better suited for transfer learning. This is reflected by higher performance, lower training time as well as better feature reuse. Clinical Relevance - The paper establishes merit of using Histopathology domain specific pretrained weights rather than ImageNet pretrained weights.

Cross-Boosted Multi-Target Domain Adaptation for Multi-Modality Histopathology Image Translation and Segmentation.

Recent digital pathology workflows mainly focus on mono-modality histopathology image analysis. However, they ignore the complementarity between Haematoxylin & Eosin (H&E) and Immunohistochemically (IHC) stained images, which can provide comprehensive gold standard for cancer diagnosis. To resolve this issue, we propose a cross-boosted multi-target domain adaptation pipeline for multi-modality histopathology images, which contains Cross-frequency Style-auxiliary Translation Network (CSTN) and Dual Cross-boosted Segmentation Network (DCSN). Firstly, CSTN achieves the one-to-many translation from fluorescence microscopy images to H&E and IHC images for providing source domain training data. To generate images with realistic color and texture, Cross-frequency Feature Transfer Module (CFTM) is developed to pertinently restructure and normalize high-frequency content and low-frequency style features from different domains. Then, DCSN fulfills multi-target domain adaptive segmentation, where a dual-branch encoder is introduced, and Bidirectional Cross-domain Boosting Module (BCBM) is designed to implement cross-modality information complementation through bidirectional inter-domain collaboration. Finally, we establish Multi-modality Thymus Histopathology (MThH) dataset, which is the largest publicly available H&E and IHC image benchmark. Experiments on MThH dataset and several public datasets show that the proposed pipeline outperforms state-of-the-art methods on both histopathology image translation and segmentation.

Deep and dense convolutional neural network for multi category classification of magnification specific and magnification independent breast cancer histopathological images

Nowadays, breast cancer is the leading cause of mortality among all other cancers affecting women. Histopathological images serve as an appropriate template for the pathological investigation of this disease. However, a proper and precise classification of these images is indispensable for an accurate prognosis. Over the time numerous attempts have been made for classification of histopathological images. However, most of the research works produced on this subject deal with identifying benign and malignant categories only. Since specific treatments and therapeutic schedules exist for different sub-categories of this disease, identifying the actual sub-class on a sample image is highly desirable. The present study proposes a deep learning based framework for automatic classification of breast cancer images into sub-classes of benign and malignant categories performed on magnification dependent and magnification independent samples of the BreakHis dataset. The proposed framework based on DenseNet architecture achieved respective mean patient recognition scores of 96.55% and 91.82% for binary and multi-classifications of H&E stained images of the BreakHis dataset. Likewise, at the image level mean recognition scores of 91.72% and 96.72% achieved by the proposed framework outperform the results reported in various latest available studies employing deep convolutional neural networks and state-of-the-art architectures. Further, the generalization ability of the proposed framework is tested on a different histopathological dataset - ICIAR 2018, yielding competitive accuracy scores of 93.25% and 92.3% at patient and image levels respectively.

Brightness as an Augmentation Technique for Image Classification

Augmentation techniques are crucial for accurately training convolution neural networks (CNNs). Therefore, these techniques have become the preprocessing methods. However, not every augmentation technique can be beneficial, especially those that change the image’s underlying structure, such as color augmentation techniques. In this study, the effect of eight brightness scales was investigated in the task of classifying a large histopathology dataset. Four state-of-the-art CNNs were used to assess each scale’s performance. The use of brightness was not beneficial in all the experiments. Among the different brightness scales, the [0.75–1.00] scale, which closely resembles the original brightness of the images, resulted in the best performance. The use of geometric augmentation yielded better performance than any brightness scale. Moreover, the results indicate that training the CNN without applying any augmentation techniques led to better results than considering brightness augmentation. Therefore, experimental results support the hypothesis that brightness augmentation techniques are not beneficial for image classification using deep-learning models and do not yield any performance gain. Furthermore, brightness augmentation techniques can significantly degrade the model’s performance when they are applied with extreme values. Doi: 10.28991/ESJ-2022-06-04-015 Full Text: PDF

Self-Distilled Supervised Contrastive Learning for diagnosis of breast cancers with histopathological images

Convolutional neural networks (CNN) and its variants have been widely used for developing the histopathological image based computer-aided diagnosis (CAD). However, the annotated data are scarce in clinical practice, and limited training samples generally cannot well train the CNN model, resulting in degraded predictive performance. To this end, we propose a novel Self-Distilled Supervised Contrastive Learning (SDSCL) algorithm to improve the diagnostic performance of a CNN-based CAD for breast cancer. In particular, the original histopathological images are first decomposed into H and E stain views, which are served as the augmented sample pairs in the supervised contrastive learning (SCL). Due to the complementary characteristic of the two stain views, this data-driven SCL guide the CNN model to efficiently learn the discriminative features, alleviating the problem of small sample size. Furthermore, self-distillation is embedded into the SCL framework, in which the CNN model jointly distills itself and conducts SCL to further improve feature representation. The proposed SDSCL is evaluated on two public breast histopathological datasets, which outperforms all the compared algorithms. Its average classification accuracy, precision, recall, and F1 scores are 94.28%, 94.64%, 94.58%, 94.34%, respectively, on Bioimaging dataset, and 80.44%, 81.92%, 80.57%, 80.10% on Databiox dataset. The experimental results on two datasets indicate that SDSCL has the potential for the histopathological image based CAD.

Multi-Class Classification of Breast Cancer Using 6B-Net with Deep Feature Fusion and Selection Method.

Breast cancer has now overtaken lung cancer as the world’s most commonly diagnosed cancer, with thousands of new cases per year. Early detection and classification of breast cancer are necessary to overcome the death rate. Recently, many deep learning-based studies have been proposed for automatic diagnosis and classification of this deadly disease, using histopathology images. This study proposed a novel solution for multi-class breast cancer classification from histopathology images using deep learning. For this purpose, a novel 6B-Net deep CNN model, with feature fusion and selection mechanism, was developed for multi-class breast cancer classification. For the evaluation of the proposed method, two large, publicly available datasets, namely, BreaKHis, with eight classes containing 7909 images, and a breast cancer histopathology dataset, containing 3771 images of four classes, were used. The proposed method achieves a multi-class average accuracy of 94.20%, with a classification training time of 226 s in four classes of breast cancer, and a multi-class average accuracy of 90.10%, with a classification training time of 147 s in eight classes of breast cancer. The experimental outcomes show that the proposed method achieves the highest multi-class average accuracy for breast cancer classification, and hence, the proposed method can effectively be applied for early detection and classification of breast cancer to assist the pathologists in early and accurate diagnosis of breast cancer.

Renal Cancer Detection: Fusing Deep and Texture Features from Histopathology Images.

Histopathological images contain morphological markers of disease progression that have diagnostic and predictive values, with many computer-aided diagnosis systems using common deep learning methods that have been proposed to save time and labour. Even though deep learning methods are an end-to-end method, they perform exceptionally well given a large dataset and often show relatively inferior results for a small dataset. In contrast, traditional feature extraction methods have greater robustness and perform well with a small/medium dataset. Moreover, a texture representation-based global approach is commonly used to classify histological tissue images expect in explicit segmentation to extract the structure properties. Considering the scarcity of medical datasets and the usefulness of texture representation, we would like to integrate both the advantages of deep learning and traditional machine learning, i.e., texture representation. To accomplish this task, we proposed a classification model to detect renal cancer using a histopathology dataset by fusing the features from a deep learning model with the extracted texture feature descriptors. Here, five texture feature descriptors from three texture feature families were applied to complement Alex-Net for the extensive validation of the fusion between the deep features and texture features. The texture features are from (1) statistic feature family: histogram of gradient, gray-level cooccurrence matrix, and local binary pattern; (2) transform-based texture feature family: Gabor filters; and (3) model-based texture feature family: Markov random field. The final experimental results for classification outperformed both Alex-Net and a singular texture descriptor, showing the effectiveness of combining the deep features and texture features in renal cancer detection.

Medical image super‐resolution using correlation filter interleaved progressive convolution network (CFIPC)

In medical image diagnosis, performance is affected because of degradation in image resolution, imaging equipment and imaging parameters. Currently, deep learning has gained much attention from researchers due to its capability to maintain perceptual quality after reconstruction. Therefore, this letter is motivated by the advantages of deep learning and proposes a novel model termed as the correlation filter interleaved progressive convolution network (CFIPC). In this letter, dilated convolution interleaved with a correlation filter expands the receptive field without any pixel information losses. The result analysis was performed on DRIVE, CHASEB1, MRI, ultrasound and histopathological dataset medical datasets at 2x/4x/8x/16x upscaling factors and achieved the highest PSNR/SSIM value of 50.54/0.9986 at a 2x upscaling factor on the histopathological dataset.