Digital Histopathology Images Research Articles

Enhanced gastric cancer classification and quantification interpretable framework using digital histopathology images

Recent developments have highlighted the critical role that computer-aided diagnosis (CAD) systems play in analyzing whole-slide digital histopathology images for detecting gastric cancer (GC). We present a novel framework for gastric histology classification and segmentation (GHCS) that offers modest yet meaningful improvements over existing CAD models for GC classification and segmentation. Our methodology achieves marginal improvements over conventional deep learning (DL) and machine learning (ML) models by adaptively focusing on pertinent characteristics of images. This contributes significantly to our study, highlighting that the proposed model, which performs well on normalized images, is robust in certain respects, particularly in handling variability and generalizing to different datasets. We anticipate that this robustness will lead to better results across various datasets. An expectation-maximizing Naïve Bayes classifier that uses an updated Gaussian Mixture Model is at the heart of the suggested GHCS framework. The effectiveness of our classifier is demonstrated by experimental validation on two publicly available datasets, which produced exceptional classification accuracies of 98.87% and 97.28% on validation sets and 98.47% and 97.31% on test sets. Our framework shows a slight but consistent improvement over previously existing techniques in gastric histopathology image classification tasks, as demonstrated by comparative analysis. This may be attributed to its ability to capture critical features of gastric histopathology images better. Furthermore, using an improved Fuzzy c-means method, our study produces good results in GC histopathology picture segmentation, outperforming state-of-the-art segmentation models with a Dice coefficient of 65.21% and a Jaccard index of 60.24%. The model’s interpretability is complemented by Grad-CAM visualizations, which help understand the decision-making process and increase the model’s trustworthiness for end-users, especially clinicians.

Assessment of a Deep-Learning System for Colorectal Cancer Diagnosis Using Histopathology Images

Colorectal Cancer is one of the most common and lethal forms of cancer hence, an early and accurate detection is crucial. Traditional manual diagnosis is a tedious and time-consuming job susceptible to human errors; therefore, it is imperative to use computer-aided detection systems to interpret medical images for a quicker and more accurate diagnosis. In recent years deep-learning approaches have proved to be efficacious in predicting cancer from pathological images. This study assesses several deep-learning techniques for cancer diagnosis on digitized histopathology images, amongst which GoogLeNet and Xception emerged as the most effective, with GoogLeNet exhibiting slightly better precision in identifying cancerous tissues. Building on these findings the study proposes a new model (Xception+) by borrowing the idea from Xception architecture, which outperforms existing architectures with an accuracy of 99.37% for cancer diagnosis and 94.48% for cancer-grade classification. The primary inference of our research is assisting pathologists in detecting colorectal cancer from pathological images faster and more accurately. With notable accuracy and robustness, our proposed model has significant potential to analyze pathological images and detect the patterns associated with other types of cancer. Our study holds promise for driving the advancement of innovative medical diagnostic tools, aiding pathologists and medical practitioners in expediting cancer diagnosis processes.

Validation of an AI-based solution for breast cancer risk stratification using routine digital histopathology images

BackgroundStratipath Breast is a CE-IVD marked artificial intelligence-based solution for prognostic risk stratification of breast cancer patients into high- and low-risk groups, using haematoxylin and eosin (H&E)-stained histopathology whole slide images (WSIs). In this validation study, we assessed the prognostic performance of Stratipath Breast in two independent breast cancer cohorts.MethodsThis retrospective multi-site validation study included 2719 patients with primary breast cancer from two Swedish hospitals. The Stratipath Breast tool was applied to stratify patients based on digitised WSIs of the diagnostic H&E-stained tissue sections from surgically resected tumours. The prognostic performance was evaluated using time-to-event analysis by multivariable Cox Proportional Hazards analysis with progression-free survival (PFS) as the primary endpoint.ResultsIn the clinically relevant oestrogen receptor (ER)-positive/human epidermal growth factor receptor 2 (HER2)-negative patient subgroup, the estimated hazard ratio (HR) associated with PFS between low- and high-risk groups was 2.76 (95% CI: 1.63–4.66, p-value < 0.001) after adjusting for established risk factors. In the ER+/HER2- Nottingham histological grade (NHG) 2 subgroup, the HR was 2.20 (95% CI: 1.22–3.98, p-value = 0.009) between low- and high-risk groups.ConclusionThe results indicate an independent prognostic value of Stratipath Breast among all breast cancer patients, as well as in the clinically relevant ER+/HER2- subgroup and the NHG2/ER+/HER2- subgroup. Improved risk stratification of intermediate-risk ER+/HER2- breast cancers provides information relevant for treatment decisions of adjuvant chemotherapy and has the potential to reduce both under- and overtreatment. Image-based risk stratification provides the added benefit of short lead times and substantially lower cost compared to molecular diagnostics and therefore has the potential to reach broader patient groups.

A systematic comparison of deep learning methods for Gleason grading and scoring

Prostate cancer is the second most frequent cancer in men worldwide after lung cancer. Its diagnosis is based on the identification of the Gleason score that evaluates the abnormality of cells in glands through the analysis of the different Gleason patterns within tissue samples. The recent advancements in computational pathology, a domain aiming at developing algorithms to automatically analyze digitized histopathology images, lead to a large variety and availability of datasets and algorithms for Gleason grading and scoring. However, there is no clear consensus on which methods are best suited for each problem in relation to the characteristics of data and labels. This paper provides a systematic comparison on nine datasets with state-of-the-art training approaches for deep neural networks (including fully-supervised learning, weakly-supervised learning, semi-supervised learning, Additive-MIL, Attention-Based MIL, Dual-Stream MIL, TransMIL and CLAM) applied to Gleason grading and scoring tasks. The nine datasets are collected from pathology institutes and openly accessible repositories. The results show that the best methods for Gleason grading and Gleason scoring tasks are fully supervised learning and CLAM, respectively, guiding researchers to the best practice to adopt depending on the task to solve and the labels that are available.

Abstract LB290: Whole exome analysis of oral squamous cell carcinoma in local patients at tertiary care hospitals in Peshawar, Pakistan

Abstract The Precision Medicine Lab (PML) has been mandated by the Federal Government in 2018 to pilot precision medicine in Pakistan using genomics in oral cancer. With the Indian subcontinent as its capital, oral squamous cell carcinoma (OSCC), also dubbed as ‘poor man’s cancer', constitutes 90% of all head and neck cancers and is the highest incidence cancer found in Pakistani males. Backed by a bio-repository of clinical samples as well as a catalogue of primary cell clines, PML takes a multi-omic approach to discovering new, actionable biomarkers for diagnostic, prognostic and therapeutic applications. With all necessary ethical approvals obtained from IRBs at each site along with written informed consent from each patient, treatment-naive biopsy-confirmed patients of OSCC were recruited in two main tertiary care hospitals in Peshawar, Pakistan. Our cohort was predominantly older with 37.84% between 41-60 years, late-stage with 78.46% presenting in stage IV and self-reportedly non-alcohol consuming (96.9%). About 44.6% reported the use of smokeless tobacco while 30.8% reported the use of both smoked and smokeless tobacco. Majority of the tumours were located in the buccal mucosa (29.2%), alveolar region (27.7%) or the vestibular region (24.6%). We obtained blood and tumour samples for matched-pair whole exome sequencing, transcriptomics and metabolomics as well as generation of primary cell lines. We also obtained saliva samples for oral microbiome analysis. Combined with the patient’s clinical history and digital histopathology images, this helps us create a multi-omic stack that we intend to make available for integrated machine learning experiments. With our whole exome sequencing now complete, we undertook a preliminary analysis for this late breaking abstract. Raw reads were aligned to the GRCh38.p14 reference genome and were called for germline and somatic SNPs and INDELs using GATK (v4.5). Mutational analysis was conducted using the maftools (v2.18.0) package in R (v4.3) by comparing against the COSMIC SBS Signature database (v3.2). We report MUC12 (100%), ZNF717 (100%), FOLR3 (86%), EPPK1 (79%) and SPATA31A6 (79%) as the top mutated genes in the subset of exomes analysed thus far for our cohort. Genes reported previously including TP53, NOTCH1 and PIK3CA appear to rank lower on the list. In terms of cancer-related pathways, RTK-RAS (92.8%), Hippo (92.8%) and Notch (78.5%) were affected in most of the samples. To our knowledge, we describe for the first time the mutational landscape in an OSCC cohort from the Pakistani population. We also go beyond whole exomes as our multi-omic approach offers the potential on machine learning experiments to identify putative mutational signatures and biomarkers for OSCC that can be of diagnostic, prognostic and therapeutic value to the local (Pakistani and Afghan) patient population. With the availability of primary cell lines for every patient, we also intend to undertake experimental validation of high priority targets using primary patient-derived cell lines in the lab. Citation Format: Hina Zamir, Khudeja Salim, Madina Sherdil, Aqsa Hussain, Yusra Ilyas, Arsalan Riaz, Momal Agha, Zainab Jahan, Khadim Shah, Yasir Rehman Khattak, Fahim Uddin, Zahid Qayyum Shah, Zubair Durrani, Muhammad Mushtaq Khattak, Johar Ali, Faisal F. Khan. Whole exome analysis of oral squamous cell carcinoma in local patients at tertiary care hospitals in Peshawar, Pakistan [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB290.

Predictive models for lymph node metastasis in endometrial cancer: A systematic review and bibliometric analysis.

Lymph node metastasis is associated with a poorer prognosis in endometrial cancer. The objective was to synthesize and critically appraise existing predictive models for lymph node metastasis risk stratification in endometrial cancer. This study is a systematic review. We searched the Web of Science for articles reporting models predicting lymph node metastasis in endometrial cancer, with a systematic review and bibliometric analysis conducted based upon which. Risk of bias was assessed by the Prediction model Risk Of BiAS assessment Tool (PROBAST). A total of 64 articles were included in the systematic review, published between 2010 and 2023. The most common articles were "development only." Traditional clinicopathological parameters remained the mainstream in models, for example, serum tumor marker, myometrial invasion and tumor grade. Also, models based upon gene-signatures, radiomics and digital histopathological images exhibited an acceptable self-reported performance. The most frequently validated models were the Mayo criteria, which reached a negative predictive value of 97.1%-98.2%. Substantial variability and inconsistency were observed through PROBAST, indicating significant between-study heterogeneity. A further bibliometric analysis revealed a relatively weak link between authors and organizations on models predicting lymph node metastasis in endometrial cancer. A number of predictive models for lymph node metastasis in endometrial cancer have been developed. Although some exhibited promising performance as they demonstrated adequate to good discrimination, few models can currently be recommended for clinical practice due to lack of independent validation, high risk of bias and low consistency in measured predictors. Collaborations between authors, organizations and countries were weak. Model updating, external validation and collaborative research are urgently needed. None.

Self-Supervised Digital Histopathology Image Disentanglement for Arbitrary Domain Stain Transfer.

Diagnosis of cancerous diseases relies on digital histopathology images from stained slides. However, the staining varies among medical centers, which leads to a domain gap of staining. Existing generative adversarial network (GAN) based stain transfer methods highly rely on distinct domains of source and target, and cannot handle unseen domains. To overcome these obstacles, we propose a self-supervised disentanglement network (SDN) for domain-independent optimization and arbitrary domain stain transfer. SDN decomposes an image into features of content and stain. By exchanging the stain features, the staining style of an image is transferred to the target domain. For optimization, we propose a novel self-supervised learning policy based on the consistency of stain and content among augmentations from one instance. Therefore, the process of training SDN is independent on the domain of training data, and thus SDN is able to tackle unseen domains. Exhaustive experiments demonstrate that SDN achieves the top performance in intra-dataset and cross-dataset stain transfer compared with the state-of-the-art stain transfer models, while the number of parameters in SDN is three orders of magnitude smaller parameters than that of compared models. Through stain transfer, SDN improves AUC of downstream classification model on unseen data without fine-tuning. Therefore, the proposed disentanglement framework and self-supervised learning policy have significant advantages in eliminating the stain gap among multi-center histopathology images.

Multi-scale statistical deformation based co-registration of prostate MRI and post-surgical whole mount histopathology.

Accurate delineations of regions of interest (ROIs) on multi-parametric magnetic resonance imaging (mpMRI) are crucial for development of automated, machine learning-based prostate cancer (PCa) detection and segmentation models. However, manual ROI delineations are labor-intensive and susceptible to inter-reader variability. Histopathology images from radical prostatectomy (RP) represent the "gold standard" in terms of the delineation of disease extents, for example, PCa, prostatitis, and benign prostatic hyperplasia (BPH). Co-registering digitized histopathology images onto pre-operative mpMRI enables automated mapping of the ground truth disease extents onto mpMRI, thus enabling the development of machine learning tools for PCa detection and risk stratification. Still, MRI-histopathology co-registration is challenging due to various artifacts and large deformation between in vivo MRI and ex vivo whole-mount histopathology images (WMHs). Furthermore, the artifacts on WMHs, such as tissue loss, may introduce unrealistic deformation during co-registration. This study presents a new registration pipeline, MSERgSDM, a multi-scale feature-based registration (MSERg) with a statistical deformation (SDM) constraint, which aims to improve accuracy of MRI-histopathology co-registration. In this study, we collected 85 pairs of MRI and WMHs from 48 patients across three cohorts. Cohort 1 (D1), comprised of a unique set of 3D printed mold data from six patients, facilitated the generation of ground truth deformations between ex vivo WMHs and in vivo MRI. The other two clinically acquired cohorts (D2 and D3) included 42 patients. Affine and nonrigid registrations were employed to minimize the deformation between ex vivo WMH and ex vivo T2-weighted MRI (T2WI) in D1. Subsequently, ground truth deformation between in vivo T2WI and ex vivo WMH was approximated as the deformation between in vivo T2WI and ex vivo T2WI. In D2 and D3, the prostate anatomical annotations, for example, tumor and urethra, were made by a pathologist and a radiologist in collaboration. These annotations included ROI boundary contours and landmark points. Before applying the registration, manual corrections were made for flipping and rotation of WMHs. MSERgSDM comprises two main components: (1) multi-scale representation construction, and (2) SDM construction. For the SDM construction, we collected N=200 reasonable deformation fields generated using MSERg, verified through visual inspection. Three additional methods, including intensity-based registration, ProsRegNet, and MSERg, were also employed for comparison against MSERgSDM. Our results suggest that MSERgSDM performed comparably to the ground truth (p>0.05). Additionally, MSERgSDM (ROI Dice ratio=0.61, landmark distance=3.26mm) exhibited significant improvement over MSERg (ROI Dice ratio=0.59, landmark distance=3.69mm) and ProsRegNet (ROI Dice ratio=0.56, landmark distance=4.00mm) in local alignment. This study presents a novel registration method, MSERgSDM, for mapping ex vivo WMH onto in vivo prostate MRI. Our preliminary results demonstrate that MSERgSDM can serve as a valuable tool to map ground truth disease annotations from histopathology images onto MRI, thereby assisting in the development of machine learning models for PCa detection on MRI.

Artificial intelligence-based cancer progression prediction of oral premalignant lesions via self-supervised deep learning on histopathology.

90 Background: Premalignant lesions within the oral cavity demonstrate varied degrees of dysplasia. Oral stratified squamous epithelium is sensitive to carcinogenic insults and lesions progress to cancer at variable rates. The current diagnostic standard involves visual and tactile inspection followed by a biopsy. However, thus far, there is clinical ambiguity about which lesions may progress to carcinoma and there are insufficient prognostic tools available to guide clinical decision-making for follow-up. Deep learning is a form of artificial intelligence which can be applied to images. Self-supervised learning (SSL) and attention-based multiple instance learning (aMIL), are deep learning extensions which eliminate the need for pathologist annotations of histology and are more generalizable as the model learns general representations of unlabeled data, compared to traditional tile-based methods. We developed a novel artificial intelligence pipeline to predict progression to oral carcinoma using histological images from oral premalignant lesions. Methods: Digital histopathology images and clinical data cohorts were obtained from the US National Cancer Institute (n=561) and the University of Iowa (n=193) for training, and from the University of Chicago (n=214) for external validation. Patients were defined as progressing if initially non-malignant lesions had documented progression to carcinoma within 12 months of follow-up. Model training and evaluation was done in Python using our publicly available open-source Slideflow platform. We developed a deep learning pipeline utilizing SimCLR as an SSL method for feature extraction paired with an aMIL head for classification. The SimCLR feature generator was trained on only the training cohort, then used to generate features for both training and validation data. The aMIL model was trained on SimCLR-generated features. Trained model performance was evaluated on the external University of Chicago cohort and measured via areas under the receiver operating characteristic curve and precision recall curve (AUROC and AUPRC, respectively). During training and validation, model reliability was interpreted using Class Activation Mapping (Grad-CAM) and generative adversarial network (GAN) methods. Results: On training data, the model achieved average 3-fold cross validation AUROC of 0.86 with AUPRC of 0.83. In the external validation data from UC, the model achieved an AUROC of 0.80 with an AUPRC of 0.79. Deployed as a “rule-in” test for early progression prediction, the model achieved a validation data set specificity of 91% with a sensitivity of 40%. Conclusions: We developed a deep learning model to automatically predict cancer progression from premalignant lesions histopathology using a multi-institutional cohort, with promising external validation performance.

Histopathological Images Analysis and Predictive Modeling Implemented in Digital Pathology-Current Affairs and Perspectives.

In modern clinical practice, digital pathology has an essential role, being a technological necessity for the activity in the pathological anatomy laboratories. The development of information technology has majorly facilitated the management of digital images and their sharing for clinical use; the methods to analyze digital histopathological images, based on artificial intelligence techniques and specific models, quantify the required information with significantly higher consistency and precision compared to that provided by optical microscopy. In parallel, the unprecedented advances in machine learning facilitate, through the synergy of artificial intelligence and digital pathology, the possibility of diagnosis based on image analysis, previously limited only to certain specialties. Therefore, the integration of digital images into the study of pathology, combined with advanced algorithms and computer-assisted diagnostic techniques, extends the boundaries of the pathologist's vision beyond the microscopic image and allows the specialist to use and integrate his knowledge and experience adequately. We conducted a search in PubMed on the topic of digital pathology and its applications, to quantify the current state of knowledge. We found that computer-aided image analysis has a superior potential to identify, extract and quantify features in more detail compared to the human pathologist's evaluating possibilities; it performs tasks that exceed its manual capacity, and can produce new diagnostic algorithms and prediction models applicable in translational research that are able to identify new characteristics of diseases based on changes at the cellular and molecular level.

Learning from deep learning and pathomics

The suffix -omics has been applied to a variety of approaches with the overarching aim to identify, describe, and quantify processes that contribute to the form and function of cells and tissues. Historically, histopathologic approaches have relied on assessment of lesions to describe a pattern of injury and when possible, give a specific etiologic diagnosis. Broad pathologic entities have been split into smaller groups to provide more individualized diagnostic, prognostic, and etiologic information as a step towards precision medicine. More recently, pathomics has emerged as a complement to traditional histopathology, applying deep learning algorithms to digital histopathology images for detailed quantitative mining of visible or subvisual features that correlate with specific diagnoses, disease trajectories, or shared injury patterns. In a recent publication in Nature Communications, Hölscher and colleagues describe this exciting new approach of pathomics, with the potential to provide insights into kidney disease diagnosis, prognosis, and mechanisms ( 1 Hölscher D.L. Bouteldja N. Joodaki M. et al. Next-Generation Morphometry for pathomics-data mining in histopathology. Nat Commun. 2023; 14: 470 Crossref PubMed Scopus (1) Google Scholar ).

Machine learning in computational histopathology: Challenges and opportunities.

Digital histopathological images, high-resolution images of stained tissue samples, are a vital tool for clinicians to diagnose and stage cancers. The visual analysis of patient state based on these images are an important part of oncology workflow. Although pathology workflows have historically been conducted in laboratories under a microscope, the increasing digitization of histopathological images has led to their analysis on computers in the clinic. The last decade has seen the emergence of machine learning, and deep learning in particular, a powerful set of tools for the analysis of histopathological images. Machine learning models trained on large datasets of digitized histopathology slides have resulted in automated models for prediction and stratification of patient risk. In this review, we provide context for the rise of such models in computational histopathology, highlight the clinical tasks they have found success in automating, discuss the various machine learning techniques that have been applied to this domain, and underscore open problems and opportunities.

Hist2RNA: An Efficient Deep Learning Architecture to Predict Gene Expression from Breast Cancer Histopathology Images.

Gene expression can be used to subtype breast cancer with improved prediction of risk of recurrence and treatment responsiveness over that obtained using routine immunohistochemistry (IHC). However, in the clinic, molecular profiling is primarily used for ER+ breast cancer, which is costly, tissue destructive, requires specialised platforms, and takes several weeks to obtain a result. Deep learning algorithms can effectively extract morphological patterns in digital histopathology images to predict molecular phenotypes quickly and cost-effectively. We propose a new, computationally efficient approach called hist2RNA inspired by bulk RNA sequencing techniques to predict the expression of 138 genes (incorporated from 6 commercially available molecular profiling tests), including luminal PAM50 subtype, from hematoxylin and eosin (H&E)-stained whole slide images (WSIs). The training phase involves the aggregation of extracted features for each patient from a pretrained model to predict gene expression at the patient level using annotated H&E images from The Cancer Genome Atlas (TCGA, n = 335). We demonstrate successful gene prediction on a held-out test set (n = 160, corr = 0.82 across patients, corr = 0.29 across genes) and perform exploratory analysis on an external tissue microarray (TMA) dataset (n = 498) with known IHC and survival information. Our model is able to predict gene expression and luminal PAM50 subtype (Luminal A versus Luminal B) on the TMA dataset with prognostic significance for overall survival in univariate analysis (c-index = 0.56, hazard ratio = 2.16 (95% CI 1.12-3.06), p < 5 × 10-3), and independent significance in multivariate analysis incorporating standard clinicopathological variables (c-index = 0.65, hazard ratio = 1.87 (95% CI 1.30-2.68), p < 5 × 10-3). The proposed strategy achieves superior performance while requiring less training time, resulting in less energy consumption and computational cost compared to patch-based models. Additionally, hist2RNA predicts gene expression that has potential to determine luminal molecular subtypes which correlates with overall survival, without the need for expensive molecular testing.

A deep learning model for lymph node metastasis prediction based on digital histopathological images of primary endometrial cancer.

The current study aimed to develop a deep learning (DL) model for prediction of lymph node metastasis (LNM) based on hematoxylin and eosin (HE)-stained histopathological images of endometrial cancer (EC). The model was validated using external data. A total of 2,104 whole slide image (WSI) from 564 patients with pathologically confirmed LNM status were collated from West China Second University Hospital. An artificial intelligence (AI) model was built on the multiple instance-learning (MIL) framework for automatic prediction of the probability of LNM and its performance compared with "Mayo criteria". An additional external data source comprising 533 WSI was collected from two independent medical institutions to validate the model's robustness. Heatmaps were generated to demonstrate regions of the WSI that made the greatest contributions to the DL network output to improve understanding of these processes. The proposed MIL model achieved an area under the curve (AUC) of 0.938, a sensitivity of 0.830 and a specificity of 0.911 for LNM prediction to EC. The AUC according to Mayo criteria was 0.666 for the same test dataset. For types I, II and mixed EC, AUCs were 0.927, 0.979 and 0.929, respectively. The predictive performance of the MIL model also achieved an AUC of 0.921 for early staging. In external validation data, the proposed model achieved an AUC of 0.770, a sensitivity of 0.814 and a specificity of 0.520 for LNM prediction. AUCs were 0.783 for type I and 0.818 for early stage EC. The proposed MIL model generated from histopathological images of EC has a much better LNM predictive performance than that of Mayo criteria. A novel DL-based biomarker trained on different histological subtypes of EC slides was revealed to predict metastatic status with improved accuracy, especially for early staging patients. The current study proves the concept of MIL-based prediction of LNM in EC for the first time, and brought a new sight to improve the accuracy of LNM prediction. Multicenter prospective validation data is required to further confirm the clinical utility.

Lung cancer histopathological image classification using wavelets and AlexNet.

Among malignant tumors, lung cancer has the highest morbidity and fatality rates worldwide. Screening for lung cancer has been investigated for decades in order to reduce mortality rates of lung cancer patients, and treatment options have improved dramatically in recent years. Pathologists utilize various techniques to determine the stage, type, and subtype of lung cancers, but one of the most common is a visual assessment of histopathology slides. The most common subtypes of lung cancer are adenocarcinoma and squamous cell carcinoma, lung benign, and distinguishing between them requires visual inspection by a skilled pathologist. The purpose of this article was to develop a hybrid network for the categorization of lung histopathology images, and it did so by combining AlexNet, wavelet, and support vector machines. In this study, we feed the integrated discrete wavelet transform (DWT) coefficients and AlexNet deep features into linear support vector machines (SVMs) for lung nodule sample classification. The LC25000 Lung and colon histopathology image dataset, which contains 5,000 digital histopathology images in three categories of benign (normal cells), adenocarcinoma, and squamous carcinoma cells (both are cancerous cells) is used in this study to train and test SVM classifiers. The study results of using a 10-fold cross-validation method achieve an accuracy of 99.3% and an area under the curve (AUC) of 0.99 in classifying these digital histopathology images of lung nodule samples.

Data-driven color augmentation for H&E stained images in computational pathology

Computational pathology targets the automatic analysis of Whole Slide Images (WSI). WSIs are high-resolution digitized histopathology images, stained with chemical reagents to highlight specific tissue structures and scanned via whole slide scanners. The application of different parameters during WSI acquisition may lead to stain color heterogeneity, especially considering samples collected from several medical centers. Dealing with stain color heterogeneity often limits the robustness of methods developed to analyze WSIs, in particular Convolutional Neural Networks (CNN), the state-of-the-art algorithm for most computational pathology tasks. Stain color heterogeneity is still an unsolved problem, although several methods have been developed to alleviate it, such as Hue-Saturation-Contrast (HSC) color augmentation and stain augmentation methods. The goal of this paper is to present Data-Driven Color Augmentation (DDCA), a method to improve the efficiency of color augmentation methods by increasing the reliability of the samples used for training computational pathology models. During CNN training, a database including over 2 million H&E color variations collected from private and public datasets is used as a reference to discard augmented data with color distributions that do not correspond to realistic data. DDCA is applied to HSC color augmentation, stain augmentation and H&E-adversarial networks in colon and prostate cancer classification tasks. DDCA is then compared with 11 state-of-the-art baseline methods to handle color heterogeneity, showing that it can substantially improve classification performance on unseen data including heterogeneous color variations.

Lung and colon cancer classification using hybrid principle component analysis network‐extreme learning machine

SummaryLung and colon cancers are dangerous diseases that can grow in organs and create a negative impact on human life in certain cases. The histological detection of such malignancies is one of the most critical parts of optimal treatment. As a result, the important objective of this article is to create an effective computerized diagnosis system for identifying adenocarcinomas of the colon as well as, adenocarcinomas and squamous cell carcinomas of the lungs using digital histopathology images and the combination of deep and machine learning techniques. For this, an effective optimized hybrid deep and machine learning framework is developed. This framework consists of two stages. In the first stage, the features of lung and colon images are extracted by principle component analysis network. Then the effective classification is conducted based on extreme learning machine (ELM) with the rider optimization algorithm which classifies lung and colon cancer into five types. The empirical investigation shows that the classification results on the benchmark LC25000 dataset have improved significantly. The use of this model will aid medical professionals in the development of an automatic and reliable system for detecting various forms of lung and colon cancers.

Artificial intelligence in histopathology: enhancing cancer research and clinical oncology

Artificial intelligence (AI) methods have multiplied our capabilities to extract quantitative information from digital histopathology images. AI is expected to reduce workload for human experts, improve the objectivity and consistency of pathology reports, and have a clinical impact by extracting hidden information from routinely available data. Here, we describe how AI can be used to predict cancer outcome, treatment response, genetic alterations and gene expression from digitized histopathology slides. We summarize the underlying technologies and emerging approaches, noting limitations, including the need for data sharing and standards. Finally, we discuss the broader implications of AI in cancer research and oncology.

PL01.5.A Towards modernizing intraoperative histopathological assessment in brain and spinal tumors - Comparison of the novel Stimulated Raman Histology with conventional H&amp;E staining

Abstract Background By intraoperative analysis of fresh frozen sections, neuropathologists provide important information of different brain and spinal tumors to the neurosurgeon during surgery. This facilitates characterization of these tumors intraoperatively to optimize the surgical strategy and patient management. However, preparation and staining are time consuming using conventional techniques of intraoperative fresh frozen section. Stimulated Raman Histology (SRH) was introduced as novel technique providing high-resolution digital images of unprocessed tissue samples directly in the operating room comparable to conventional histopathological images. Additionally, SRH images are fast and easily accessible by neuropathologists. Recently, first data showed promising results on the accuracy and feasibility of SRH in comparison to conventional H&amp;E staining. Material and Methods In a time period of 4 months, patients with different brain or spinal tumors who underwent neurosurgical resection or open/stereotactic biopsy at the Dept. of Neurosurgery, Medical University Vienna were included in this study. Tumor tissue samples were collected intraoperatively whenever safely possible for analysis with SRH. Subsequently, unprocessed tissue samples were scanned by SRH, and intraoperative histopathological images were created directly in the operating room within a few minutes. All collected tissue samples were then sent for routine neuropathological workup. In an overall analysis, SRH images and H&amp;E staining of all patients were analyzed separately by two board certified neuropathologists. Information on age, localization and suspected diagnosis was provided in each case in order to simulate the situation of intraoperative fresh frozen section. In a next step the technical feasibility and diagnostic accuracy of SRH was calculated. Results In this study, tissue samples of 95 patients who underwent neurosurgical resection or open/stereotactic biopsy of different brain and spinal tumors were collected intraoperatively and analyzed by SRH. In total, 31 gliomas, 30 meningiomas, 19 metastases, 7 neurinomas and 8 rare tumors were analyzed. In the present study the use of SRH was technically feasible in all cases and could be easily integrated in the neurosurgical workflow to provide rapid digital histopathological images for the analyzing neuropathologists. According to our data, SRH provided high diagnostic accuracy (&amp;gt;95%) in the investigated different brain and spinal tumors. Conclusion Based on our preliminary data the technical use of SRH is feasible and showed a high rate of diagnostic accuracy in a large series of different brain and spinal tumors. By using this promising technique, we intend to modernize intraoperative histopathological assessment by providing rapid digital images of brain and spinal tumors to optimize the management of these patients.

Automated Detection and Characterization of Colon Cancer with Deep Convolutional Neural Networks.

Colon cancer is a momentous reason for illness and death in people. The conclusive diagnosis of colon cancer is made through histological examination. Convolutional neural networks are being used to analyze colon cancer via digital image processing with the introduction of whole-slide imaging. Accurate categorization of colon cancers is necessary for capable analysis. Our objective is to promote a system for detecting and classifying colon adenocarcinomas by applying a deep convolutional neural network (DCNN) model with some preprocessing techniques on digital histopathology images. It is a leading cause of cancer-related death, despite the fact that both traditional and modern methods are capable of comparing images that may encompass cancer regions of various sorts after looking at a significant number of colon cancer images. The fundamental problem for colon histopathologists is differentiating benign from malignant illnesses to having some complicated factors. A cancer diagnosis can be automated through artificial intelligence (AI), enabling us to appraise more patients in less time and at a decreased cost. Modern deep learning (MDL) and digital image processing (DIP) approaches are used to accomplish this. The results indicate that the proposed structure can accurately analyze cancer tissues to a maximum of 99.80%. By implementing this approach, medical practitioners will establish an automated and reliable system for detecting various forms of colon cancer. Moreover, CAD systems will be built in the near future to extract numerous aspects from colonoscopic images for use as a preprocessing module for colon cancer diagnosis.