Deep neural network incorporating domain and resolution transformations model for histopathological image classification

Automated classification of histopathological images is an important research problem in medical imaging. Digital histopathology exhibits two principally distinct characteristics: 1) invariably histopathological images are multi-channel (color) with key geometric information spread across the color channels instead of being captured by luminance alone, and 2) the richness of geometric structures in such tissue imagery makes feature extraction for classification very demanding. Inspired by recent work in the use of sparsity for single channel image classification, we propose a new simultaneous Sparsity model for multi-channel Histopathological Image Representation and Classification (SHIRC). Essentially, we represent a multi-channel histopathological image as a sparse linear combination of training examples under suitable channel-wise constraints and classification is performed by solving a newly formulated simultaneous sparsity-based optimization problem. Experiments on two challenging real-world image databases: 1) provided by pathologists of the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 2) histopathological images corresponding to intraductal breast lesions [1], reveal the merits of the proposed SHIRC model over state of the art alternatives.

Breast cancer is a big concern for women due to its higher mortality compared to other cancers. Objective and accurate early diagnosis is primordial for the treatment and survival improvement of patients. Histopathological image classification is considered the gold standard and is usually the last and most dependent diagnosis approach for doctors to make patient treatment proposals. In particular, recent deep learning-based methods provide remarkable classification results. However, these methods ignore rationale or logical explanation that is important for diagnosis reliability and human-level understanding. This paper proposes a multi-instance classification network (MICNet) with the mechanism of visual explanation to achieve the explainable classification of histopathological breast cancer images. The method uses a simple two-dimensional convolution kernel to generate explanation maps (i.e., visual explanation) through features coming from the end of the feature extractor in the VGG11 model pre-trained by ImageNet. Multiple instance learning (MIL) based on mirror padding and overlap cropping is adopted to improve the network’s classification performance. We also design a weighted average pooling method to encourage the network to learn more accurate visual explanation. Experiments on BreakHis and Camelyon16 patch-based datasets demonstrate that our MICNet outperforms other CNN models in classification and is able to provide a logical visual explanation that supports the network’s prediction.

MF-OMKT: Model fusion based on online mutual knowledge transfer for breast cancer histopathological image classification

Breast cancer is a common and fatal disease among women worldwide. Therefore, the early and precise diagnosis of breast cancer plays a pivotal role to improve the prognosis of patients with this disease. Several studies have developed automated techniques using different medical imaging modalities to predict breast cancer development. However, few review studies are available to recapitulate the existing literature on breast cancer classification. These studies provide an overview of the classification, segmentation, or grading of many cancer types, including breast cancer, by using traditional machine learning approaches through hand-engineered features. This review focuses on breast cancer classification by using medical imaging multimodalities through state-of-the-art artificial deep neural network approaches. It is anticipated to maximize the procedural decision analysis in five aspects, such as types of imaging modalities, datasets and their categories, pre-processing techniques, types of deep neural network, and performance metrics used for breast cancer classification. Forty-nine journal and conference publications from eight academic repositories were methodically selected and carefully reviewed from the perspective of the five aforementioned aspects. In addition, this study provided quantitative, qualitative, and critical analyses of the five aspects. This review showed that mammograms and histopathologic images were mostly used to classify breast cancer. Moreover, about 55% of the selected studies used public datasets, and the remaining used exclusive datasets. Several studies employed augmentation, scaling, and image normalization pre-processing techniques to minimize inconsistencies in breast cancer images. Several types of shallow and deep neural network architecture were employed to classify breast cancer using images. The convolutional neural network was utilized frequently to construct an effective breast cancer classification model. Some of the selected studies employed a pre-trained network or developed new deep neural networks to classify breast cancer. Most of the selected studies used accuracy and area-under-the-curve metrics followed by sensitivity, precision, and F-measure metrics to evaluate the performance of the developed breast cancer classification models. Finally, this review presented 10 open research challenges for future scholars who are interested to develop breast cancer classification models through various imaging modalities. This review could serve as a valuable resource for beginners on medical image classification and for advanced scientists focusing on deep learning-based breast cancer classification through different medical imaging modalities.

The computer-assisted classification of breast cancer histopathological image in the future is an essential method for the improvement of the diagnostic performance, thus reducing breast cancer deaths. Although deep convolutional neural networks (DCNNs) have made dramatic breakthroughs, many image classification tasks still remain challenging due to the insufficiency of training data and the lack of the ability to focus on improving classification efficiency. To address these issues, we share a densely connected convolutional network (DenseNet) model that is composed of 3 layers DenseNet, pooling layer, and a classification layer for breast cancer classification in microscopic images. Each layer of DenseNet contains 4 dense blocks. Each dense block jointly uses the dense connection and a novel attention learning mechanisms to increase its ability for discriminative representation. Meanwhile, the transfer learning algorithm is applied to determine the model parameters to extract the features of the patient image that is performed. In order to ensure sufficient data volume, a data enhancement method based on the quad-tree principle is proposed for high-resolution images. On the other hand, the classification probability of each part after dicing is fused by three algorithms of addition, product, and maximum. We evaluated our DenseNet model on the BreastKHis dataset. Our results indicate that the DenseNet model and data enhancement method we adopted can adaptively focus on the study of breast cancer histopathological image classification, thus achieving the state-of-the-art performance in breast cancer classification. The results of the experiments are in terms of patient-level and image-level accuracy. The best recognition accuracy increased to 90.9%-92.5% and 89.3%-91.8%, respectively, compared with previous studies.

The field of histopathological image analysis has evolved significantly with the advent of digital pathology, leading to the development of automated models capable of classifying tissues and structures within diverse pathological images. Artificial intelligence algorithms, such as convolutional neural networks, have shown remarkable capabilities in pathology image analysis tasks, including tumor identification, metastasis detection, and patient prognosis assessment. However, traditional manual analysis methods have generally shown low accuracy in diagnosing colorectal cancer using histopathological images. This study investigates the use of AI in image classification and image analytics using histopathological images using the histogram of oriented gradients method. The study develops an AI-based architecture for image classification using histopathological images, aiming to achieve high performance with less complexity through specific parameters and layers. In this study, we investigate the complicated state of histopathological image classification, explicitly focusing on categorizing nine distinct tissue types. Our research used open-source multi-centered image datasets that included records of 100.000 non-overlapping images from 86 patients for training and 7180 non-overlapping images from 50 patients for testing. The study compares two distinct approaches, training artificial intelligence-based algorithms and manual machine learning models, to automate tissue classification. This research comprises two primary classification tasks: binary classification, distinguishing between normal and tumor tissues, and multi-classification, encompassing nine tissue types, including adipose, background, debris, stroma, lymphocytes, mucus, smooth muscle, normal colon mucosa, and tumor. Our findings show that artificial intelligence-based systems can achieve 0.91 and 0.97 accuracy in binary and multi-class classifications. In comparison, the histogram of directed gradient features and the Random Forest classifier achieved accuracy rates of 0.75 and 0.44 in binary and multi-class classifications, respectively. Our artificial intelligence-based methods are generalizable, allowing them to be integrated into histopathology diagnostics procedures and improve diagnostic accuracy and efficiency. The CNN model outperforms existing machine learning techniques, demonstrating its potential to improve the precision and effectiveness of histopathology image analysis. This research emphasizes the importance of maintaining data consistency and applying normalization methods during the data preparation stage for analysis. It particularly highlights the potential of artificial intelligence to assess histopathological images.

BackgroundHistopathology image analysis is a gold standard for cancer recognition and diagnosis. Automatic analysis of histopathology images can help pathologists diagnose tumor and cancer subtypes, alleviating the workload of pathologists. There are two basic types of tasks in digital histopathology image analysis: image classification and image segmentation. Typical problems with histopathology images that hamper automatic analysis include complex clinical representations, limited quantities of training images in a dataset, and the extremely large size of singular images (usually up to gigapixels). The property of extremely large size for a single image also makes a histopathology image dataset be considered large-scale, even if the number of images in the dataset is limited.ResultsIn this paper, we propose leveraging deep convolutional neural network (CNN) activation features to perform classification, segmentation and visualization in large-scale tissue histopathology images. Our framework transfers features extracted from CNNs trained by a large natural image database, ImageNet, to histopathology images. We also explore the characteristics of CNN features by visualizing the response of individual neuron components in the last hidden layer. Some of these characteristics reveal biological insights that have been verified by pathologists. According to our experiments, the framework proposed has shown state-of-the-art performance on a brain tumor dataset from the MICCAI 2014 Brain Tumor Digital Pathology Challenge and a colon cancer histopathology image dataset.ConclusionsThe framework proposed is a simple, efficient and effective system for histopathology image automatic analysis. We successfully transfer ImageNet knowledge as deep convolutional activation features to the classification and segmentation of histopathology images with little training data. CNN features are significantly more powerful than expert-designed features.

Breast cancer is one of the major public health issues and is considered a leading cause of cancer-related deaths among women worldwide. Its early diagnosis can effectively help in increasing the chances of survival rate. To this end, biopsy is usually followed as a gold standard approach in which tissues are collected for microscopic analysis. However, the histopathological analysis of breast cancer is non-trivial, labor-intensive, and may lead to a high degree of disagreement among pathologists. Therefore, an automatic diagnostic system could assist pathologists to improve the effectiveness of diagnostic processes. This paper presents an ensemble deep learning approach for the definite classification of non-carcinoma and carcinoma breast cancer histopathology images using our collected dataset. We trained four different models based on pre-trained VGG16 and VGG19 architectures. Initially, we followed 5-fold cross-validation operations on all the individual models, namely, fully-trained VGG16, fine-tuned VGG16, fully-trained VGG19, and fine-tuned VGG19 models. Then, we followed an ensemble strategy by taking the average of predicted probabilities and found that the ensemble of fine-tuned VGG16 and fine-tuned VGG19 performed competitive classification performance, especially on the carcinoma class. The ensemble of fine-tuned VGG16 and VGG19 models offered sensitivity of for carcinoma class and overall accuracy of . Also, it offered an F1 score of . These experimental results demonstrated that our proposed deep learning approach is effective for the automatic classification of complex-natured histopathology images of breast cancer, more specifically for carcinoma images.

Accurate histopathological image classification plays a crucial role in cancer detection and diagnosis. In automated cancer detection methods, extraction of histological features of malignant and benign tissues is a challenging task. This paper presents a modified approach on octave convolution to extract high and low-frequency features which help to provide a comprehensive representation of histopathological images. Proposed octave convolution model is used to perform histopathological image classification using three different optimization strategies. Firstly, an optimal alpha value of 0.5 is used to give equal importance to both high-frequency and low-frequency feature maps. This balanced approach ensures that the model effectively considers critical high-frequency features as well as low-frequency features of cancerous tissues. Secondly, high-frequency and low-frequency feature maps are extracted and down sampled into half the spatial dimension size to reduce the computational cost compared to standard CNN. Thirdly, training and validation was conducted using ReLU, PReLU, LeakyReLU, ELU, GELU and Swish activation functions. From the experiment, it was concluded that PReLU is the best activation function for capturing intricate patterns inherent in cancer-related histopathological images. Combining all these optimization strategies, the proposed method proved to provide a classification accuracy of 93% and also to reduce the computational cost by 50%. Performance validation against pre-trained models, CNN variants and vision transformer-based models has also been conducted, which proved superior performance of the proposed model.

Deep feature learning for histopathological image classification of canine mammary tumors and human breast cancer

Breast cancer is the most common cancer worldwide with high death rate especially for women, early diagnosis can increase the survival opportunity with correct treatment in the hospital. The Computer-Assisted Diagnosis (CAD) system is of vital significant for improving the diagnostic accuracy as the diagnosis process is tedious and the result may be different between pathologists. In this paper, we proceed research on breast cancer histopathological images classification based on deep Convolutional Neural Network (CNN). The approach proposed in this work utilize CNN to extract features of histopathological images and classify the images into begin tumors and malignant tumors by softmax function. Eliminate overfitting phenomenon by data augmentation and fine tune technology while improving the performance of networks by cross validation training strategy. The experiments in this paper were conducted on BreaKHis database [4] available to scientific study from 2014 and the results proved the algorithm's advantage on accuracy.

Breast cancer remains a major global health concern, particularly among women, where early detection is crucial for effective treatment and increased survival rates. Manual diagnosis through histopathological examination is often time-consuming, prone to human error, and requires expert interpretation. In response to this challenge, we developed a deep learning-based system to automate the detection and classification of breast cancer using microscopic biopsy images, aimed at enhancing diagnostic accuracy and speed in clinical workflows. Our project employs convolutional neural networks (CNNs) to classify histopathological images into three distinct categories: normal, benign, and malignant. We utilized a publicly available dataset containing high-resolution microscopic images and implemented preprocessing techniques to improve image quality, normalize input dimensions, and optimize feature extraction. The model was developed and trained using TensorFlow with GPU support, allowing for efficient computation and faster training cycles. Key Words: Breast cancer, Cancer detection, Cancer classification, Histopathological images, microscopic images, Digital pathology, medical imaging

Cancer is one of the leading causes of death in the world. It is the main reason why research in this field becomes challenging. Not only for the pathologist but also from the view of a computer scientist. Hematoxylin and Eosin (H&E) images are the most common modalities used by the pathologist for cancer detection. The status of cancer with histopathology images can be classified based on the shape, morphology, intensity, and texture of the image. The use of full high-resolution histopathology images will take a longer time for the extraction of all information due to the huge amount of data. This study proposed advance texture extraction by multi-patch images pixel method with sliding windows that minimize loss of information in each pixel patch. We use texture feature Gray Level Co-Occurrence Matrix (GLCM) with a mean-shift filter as the data pre-processing of the images. The mean-shift filter is a low-pass filter technique that considers the surrounding pixels of the images. The proposed GLCM method is then trained using Deep Neural Networks (DNN) and compared to other classification techniques for benchmarking. For training, we use two hardware: NVIDIA GPU GTX-980 and TESLA K40c. According to the study, Deep Neural Network outperforms other classifiers with the highest accuracy and deviation standard 96.72±0.48 for four cross-validations. The additional information is that training using Theano framework is faster than Tensorflow for both in GTX-980 and Tesla K40c.

Breast cancer encompasses various subtypes with distinct prognoses, necessitating accurate stratification methods. Current techniques rely on quantifying gene expression in limited subsets. Given the complexity of breast tissues, effective detection and classification of breast cancer is crucial in medical imaging. This study introduces a novel method, MPa-DCAE, which uses a multi-patch-based deep convolutional auto-encoder (DCAE) framework combined with VGG19 to detect and classify breast cancer in histopathology images. The proposed MPa-DCAE model leverages the hierarchical feature extraction capabilities of VGG19 within a DCAE framework, designed to capture intricate patterns in histopathology images. By using a multi-patch approach, regions of interest are extracted from pathology images to facilitate localized feature learning, enhancing the model's discriminatory power. The auto-encoder component enables unsupervised feature learning, increasing resilience and adaptability to variations in image features. Experiments were conducted at various magnifications on the CBIS-DDSM and MIAS datasets to validate model performance. Experimental results demonstrated that the MPa-DCAE model outperformed existing methods. For the CBIS-DDSM dataset, the model achieved a precision of 97.96%, a recall of 94.85%, and an accuracy of 98.36%. For the MIAS dataset, it achieved a precision of 97.99%, a recall of 97.2%, and an accuracy of 98.95%. These results highlight the model's robustness and potential for clinical application in computer-assisted diagnosis. The MPa-DCAE model, integrating VGG19 and DCAE, proves to be an effective, automated approach for diagnosing breast cancer. Its high accuracy and generalizability make it a promising tool for clinical practice, potentially improving patient care in histopathology-based breast cancer diagnosis.

Histopathological image contains rich pathological information that is valued for the aided diagnosis of many diseases such as cancer. An important issue in histopathological image classification is how to learn a high-quality discriminative dictionary due to diverse tissue pattern, a variety of texture, and different morphologies structure. In this paper, we propose a discriminative dictionary learning algorithm with pairwise local constraints (PLCDDL) for histopathological image classification. Inspired by the one-to-one mapping between dictionary atom and profile, we learn a pair of discriminative graph Laplacian matrices that are less sensitive to noise or outliers to capture the locality and discriminating information of data manifold by utilizing the local geometry information of category-specific dictionaries rather than input data. Furthermore, graph-based pairwise local constraints are designed and incorporated into the original dictionary learning model to effectively encode the locality consistency with intra-class samples and the locality inconsistency with inter-class samples. Specifically, we learn the discriminative localities for representations by jointly optimizing both the intra-class locality and inter-class locality, which can significantly improve the discriminability and robustness of dictionary. Extensive experiments on the challenging datasets verify that the proposed PLCDDL algorithm can achieve a better classification accuracy and powerful robustness compared with the state-of-the-art dictionary learning methods. Graphical abstract The proposed PLCDDL algorithm. 1) A pair of graph Laplacian matrices are first learned based on the class-specific dictionaries. 2) Graph-based pairwise local constraints are designed to transfer the locality for coding coefficients. 3) Class-specific dictionaries can be further updated.