Multiple Magnifications Research Articles

PathoDuet: Foundation models for pathological slide analysis of H&E and IHC stains

Large amounts of digitized histopathological data display a promising future for developing pathological foundation models via self-supervised learning methods. Foundation models pretrained with these methods serve as a good basis for downstream tasks. However, the gap between natural and histopathological images hinders the direct application of existing methods. In this work, we present PathoDuet, a series of pretrained models on histopathological images, and a new self-supervised learning framework in histopathology. The framework is featured by a newly-introduced pretext token and later task raisers to explicitly utilize certain relations between images, like multiple magnifications and multiple stains. Based on this, two pretext tasks, cross-scale positioning and cross-stain transferring, are designed to pretrain the model on Hematoxylin and Eosin (H&E) images and transfer the model to immunohistochemistry (IHC) images, respectively. To validate the efficacy of our models, we evaluate the performance over a wide variety of downstream tasks, including patch-level colorectal cancer subtyping and whole slide image (WSI)-level classification in H&E field, together with expression level prediction of IHC marker, tumor identification and slide-level qualitative analysis in IHC field. The experimental results show the superiority of our models over most tasks and the efficacy of proposed pretext tasks. The codes and models are available at https://github.com/openmedlab/PathoDuet.

An AI based, open access screening tool for early diagnosis of Burkitt lymphoma.

Burkitt Lymphoma (BL) is a highly treatable cancer. However, delayed diagnosis of BL contributes to high mortality in BL endemic regions of Africa. Lack of enough pathologists in the region is a major reason for delayed diagnosis. The work described in this paper is a proof-of-concept study to develop a targeted, open access AI tool for screening of histopathology slides in suspected BL cases. Slides were obtained from a total of 90 BL patients. 70 Tonsillectomy samples were used as controls. We fine-tuned 6 pre-trained models and evaluated the performance of all 6 models across different configurations. An ensemble-based consensus approach ensured a balanced and robust classification. The tool applies novel features to BL diagnosis including use of multiple image magnifications, thus enabling use of different magnifications of images based on the microscope/scanner available in remote clinics, composite scoring of multiple models and utilizing MIL with weak labeling and image augmentation, enabling use of relatively low sample size to achieve good performance on the inference set. The open access model allows free access to the AI tool from anywhere with an internet connection. The ultimate aim of this work is making pathology services accessible, efficient and timely in remote clinics in regions where BL is endemic. New generation of low-cost slide scanners/microscopes is expected to make slide images available immediately for the AI tool for screening and thus accelerate diagnosis by pathologists available locally or online.

A Structure-aware Hierarchical Graph-based Multiple Instance Learning Framework for pT Staging in Histopathological Image.

Pathological primary tumor (pT) stage focuses on the infiltration degree of the primary tumor to surrounding tissues, which relates to the prognosis and treatment choices. The pT staging relies on the field-of-views from multiple magnifications in the gigapixel images, which makes pixel-level annotation difficult. Therefore, this task is usually formulated as a weakly supervised whole slide image (WSI) classification task with the slide-level label. Existing weakly-supervised classification methods mainly follow the multiple instance learning paradigm, which takes the patches from single magnification as the instances and extracts their morphological features independently. However, they cannot progressively represent the contextual information from multiple magnifications, which is critical for pT staging. Therefore, we propose a structure-aware hierarchical graph-based multi-instance learning framework (SGMF) inspired by the diagnostic process of pathologists. Specifically, a novel graph-based instance organization method is proposed, namely structure-aware hierarchical graph (SAHG), to represent the WSI. Based on that, we design a novel hierarchical attention-based graph representation (HAGR) network to capture the critical patterns for pT staging by learning cross-scale spatial features. Finally, the top nodes of SAHG are aggregated by a global attention layer for bag-level representation. Extensive studies on three large-scale multi-center pT staging datasets with two different cancer types demonstrate the effectiveness of SGMF, which outperforms state-of-the-art up to 5.6% in the F1 score.

TGMIL: A hybrid multi-instance learning model based on the Transformer and the Graph Attention Network for whole-slide images classification of renal cell carcinoma

The pathological diagnosis of renal cell carcinoma is crucial for treatment. Currently, the multi-instance learning method is commonly used for whole-slide image classification of renal cell carcinoma, which is mainly based on the assumption of independent identical distribution. But this is inconsistent with the need to consider the correlation between different instances in the diagnosis process. Furthermore, the problem of high resource consumption of pathology images is still urgent to be solved. Therefore, we propose a new multi-instance learning method to solve this problem. In this study, we proposed a hybrid multi-instance learning model based on the Transformer and the Graph Attention Network, called TGMIL, to achieve whole-slide image of renal cell carcinoma classification without pixel-level annotation or region of interest extraction. Our approach is divided into three steps. First, we designed a feature pyramid with the multiple low magnifications of whole-slide image named MMFP. It makes the model incorporates richer information, and reduces memory consumption as well as training time compared to the highest magnification. Second, TGMIL amalgamates the Transformer and the Graph Attention's capabilities, adeptly addressing the loss of instance contextual and spatial. Within the Graph Attention network stream, an easy and efficient approach employing max pooling and mean pooling yields the graph adjacency matrix, devoid of extra memory consumption. Finally, the outputs of two streams of TGMIL are aggregated to achieve the classification of renal cell carcinoma. On the TCGA-RCC validation set, a public dataset for renal cell carcinoma, the area under a receiver operating characteristic (ROC) curve (AUC) and accuracy of TGMIL were 0.98±0.0015,0.9191±0.0062, respectively. It showcased remarkable proficiency on the private validation set of renal cell carcinoma pathology images, attaining AUC of 0.9386±0.0162 and ACC of 0.9197±0.0124. Furthermore, on the public breast cancer whole-slide image test dataset, CAMELYON 16, our model showed good classification performance with an accuracy of 0.8792. TGMIL models the diagnostic process of pathologists and shows good classification performance on multiple datasets. Concurrently, the MMFP module efficiently diminishes resource requirements, offering a novel angle for exploring computational pathology images.

Multi-scale pathology image texture signature is a prognostic factor for resectable lung adenocarcinoma: a multi-center, retrospective study

BackgroundTumor histomorphology analysis plays a crucial role in predicting the prognosis of resectable lung adenocarcinoma (LUAD). Computer-extracted image texture features have been previously shown to be correlated with outcome. However, a comprehensive, quantitative, and interpretable predictor remains to be developed.MethodsIn this multi-center study, we included patients with resectable LUAD from four independent cohorts. An automated pipeline was designed for extracting texture features from the tumor region in hematoxylin and eosin (H&E)-stained whole slide images (WSIs) at multiple magnifications. A multi-scale pathology image texture signature (MPIS) was constructed with the discriminative texture features in terms of overall survival (OS) selected by the LASSO method. The prognostic value of MPIS for OS was evaluated through univariable and multivariable analysis in the discovery set (n = 111) and the three external validation sets (V1, n = 115; V2, n = 116; and V3, n = 246). We constructed a Cox proportional hazards model incorporating clinicopathological variables and MPIS to assess whether MPIS could improve prognostic stratification. We also performed histo-genomics analysis to explore the associations between texture features and biological pathways.ResultsA set of eight texture features was selected to construct MPIS. In multivariable analysis, a higher MPIS was associated with significantly worse OS in the discovery set (HR 5.32, 95%CI 1.72–16.44; P = 0.0037) and the three external validation sets (V1: HR 2.63, 95%CI 1.10–6.29, P = 0.0292; V2: HR 2.99, 95%CI 1.34–6.66, P = 0.0075; V3: HR 1.93, 95%CI 1.15–3.23, P = 0.0125). The model that integrated clinicopathological variables and MPIS had better discrimination for OS compared to the clinicopathological variables-based model in the discovery set (C-index, 0.837 vs. 0.798) and the three external validation sets (V1: 0.704 vs. 0.679; V2: 0.728 vs. 0.666; V3: 0.696 vs. 0.669). Furthermore, the identified texture features were associated with biological pathways, such as cytokine activity, structural constituent of cytoskeleton, and extracellular matrix structural constituent.ConclusionsMPIS was an independent prognostic biomarker that was robust and interpretable. Integration of MPIS with clinicopathological variables improved prognostic stratification in resectable LUAD and might help enhance the quality of individualized postoperative care.

MMSRNet: Pathological image super-resolution by multi-task and multi-scale learning

Pathological diagnosis is the gold standard for disease assessment in clinical practice. It is conducted by inspecting the specimen at the microscopical level. Therefore, a very high-resolution pathological image that precisely describes the submicron-scale appearance is essential in the era of digital pathology, which is not easily obtained. Recently, pathological image super-resolution (SR) has shown promising prospects in bridging this gap. However, existing studies have not fully explored the peculiarity of pathological data, which contains several gradually enlarged images describing the specimen at different magnifications. In this paper, we propose a novel MMSRNet that formulates the pathological image SR in a multi-task learning way. It adds an image magnification classification branch on top of the CNN-based SR network, e.g., RCAN. Therefore, the learning objective is transformed into performing the SR while classifying the magnification as accurately as possible. The incorporated classification label guides the network to learn a more powerful feature representation. Meanwhile, the multi-task learning paradigm also encourages the joint learning of multi-scale mapping functions corresponding to multiple magnifications. It thus enables the learned model to adaptively accommodate the magnification variants, overcoming the problem that performing SR from different magnifications is treated as independent tasks in existing studies. Extensive experiments are conducted to validate the effectiveness of MMSRNet. It not only gains better performance in performing SR across magnifications and scaling factors, but also exhibits attractive plug-and-play nature when RCAN is substituted by other SR networks. The generated images are also supposed to be helpful in clinical diagnosis.

XDEEP-MSI: Explainable Bias-Rejecting Microsatellite Instability Deep Learning System in Colorectal Cancer.

The prediction of microsatellite instability (MSI) using deep learning (DL) techniques could have significant benefits, including reducing cost and increasing MSI testing of colorectal cancer (CRC) patients. Nonetheless, batch effects or systematic biases are not well characterized in digital histology models and lead to overoptimistic estimates of model performance. Methods to not only palliate but to directly abrogate biases are needed. We present a multiple bias rejecting DL system based on adversarial networks for the prediction of MSI in CRC from tissue microarrays (TMAs), trained and validated in 1788 patients from EPICOLON and HGUA. The system consists of an end-to-end image preprocessing module that tile samples at multiple magnifications and a tissue classification module linked to the bias-rejecting MSI predictor. We detected three biases associated with the learned representations of a baseline model: the project of origin of samples, the patient’s spot and the TMA glass where each spot was placed. The system was trained to directly avoid learning the batch effects of those variables. The learned features from the bias-ablated model achieved maximum discriminative power with respect to the task and minimal statistical mean dependence with the biases. The impact of different magnifications, types of tissues and the model performance at tile vs patient level is analyzed. The AUC at tile level, and including all three selected tissues (tumor epithelium, mucin and lymphocytic regions) and 4 magnifications, was 0.87 ± 0.03 and increased to 0.9 ± 0.03 at patient level. To the best of our knowledge, this is the first work that incorporates a multiple bias ablation technique at the DL architecture in digital pathology, and the first using TMAs for the MSI prediction task.

On the double-plane plasma lensing

ABSTRACT Plasma lensing is the refraction of low-frequency electromagnetic rays due to cold free electrons in the universe. For sources at a cosmological distance, there is observational evidence of elongated, complex plasma structures along the line of sight requiring a multi-lens-plane description. To investigate the limits of single-plane plasma lensing, we set up a double-plane lens with a projected Gaussian electron density in each lens plane. We compare double-plane scenarios with corresponding effective single-plane configurations. Our results show how double-plane lenses can be distinguished from single-plane lenses by observables, i.e. resolved multiple image positions, relative magnifications, time delays, and pulse shapes. For plasma lensing of fast radio bursts, the observed pulse shape may be dominated by the lensing effect, allowing us to neglect the intrinsic source pulse shape to distinguish different lensing configurations. The time-domain observables turn out to be the most salient features to tell multi- and single-plane lenses apart.

Multiscale, multi-perspective imaging assisted robotic microinjection of 3D biological structures.

Microinjection is a widely used technique employed by biologists with applications in transgenesis, cryopreservation, mutagenesis, labeling/dye injection and in-vitro fertilization. However, microinjection is an extremely laborious manual procedure, which makes it a critical bottleneck in the field and thus ripe for automation. Here, we present a computer-guided robot that automates the targeted microinjection of Drosophila melanogaster and zebrafish (Danio rerio) embryos, two important model organisms in biological research. The robot uses a series of cameras to image an agar plate containing embryos at multiple magnifications and perspectives. This imaging is combined with machine learning and computer vision algorithms to pinpoint a location on the embryo for targeted microinjection with microscale precision. We demonstrate the utility of this microinjection robot to successfully microinject Drosophila melanogaster and zebrafish embryos. Results obtained indicate that the robotic microinjection approach can significantly increase the throughput of microinjection as compared to manual microinjection while maintaining survival rates comparable to human operators. In the future, this robotic platform can be used to perform high throughput microinjection experiments and can be extended to automatically microinject a host of organisms such as roundworms (Caenorhabditis elegans), mosquito (Culicidae) embryos, sea urchins (Echinoidea) and frog (Xenopus) oocytes.

A deep-learning-based workflow to deal with the defocusing problem in high-throughput experiments

The increasing throughput of experiments in biomaterials research makes automatic techniques more and more necessary. Among all the characterization methods, microscopy makes fundamental contributions to biomaterials science where precisely focused images are the basis of related research. Although automatic focusing has been widely applied in all kinds of microscopes, defocused images can still be acquired now and then due to factors including background noises of materials and mechanical errors. Herein, we present a deep-learning-based method for the automatic sorting and reconstruction of defocused cell images. First, the defocusing problem is illustrated on a high-throughput cell microarray. Then, a comprehensive dataset of phase-contrast images captured from varied conditions containing multiple cell types, magnifications, and substrate materials is prepared to establish and test our method. We obtain high accuracy of over 0.993 on the dataset using a simple network architecture that requires less than half of the training time compared with the classical ResNetV2 architecture. Moreover, the subcellular-level reconstruction of heavily defocused cell images is achieved with another architecture. The applicability of the established workflow in practice is finally demonstrated on the high-throughput cell microarray. The intelligent workflow does not require a priori knowledge of focusing algorithms, possessing widespread application value in cell experiments concerning high-throughput or time-lapse imaging.

Characterization and microfabrication of natural porous rocks: From micro-CT imaging and digital rock modelling to micro-3D-printed rock analogs

Tests on standard rock specimens with controlled and identical pore structure are critical to validating the analytical and numerical models. However, it is usually difficult to acquire two natural samples with the same internal structure for the destructive laboratory tests, for the sake of the heterogeneity of natural rock which is caused by the complex diagenetic processes. Three-dimensional (3D) printing technology provides an alternative approach to produce geometry-identical, features-controllable, and lab-testable analogs of natural rock from digital data in a faster and more cost-effective way. This paper presents a customized workflow of 3D-printed rock analogs from micro-CT images combining with digital rock modelling. Three types of natural rock specimens are imaged by micro-CT and processed as inputs for two types of 3D printing techniques. Rock analogs are printed at multiple magnifications from original CT volume in five curable resin materials. Petrophysical parameters of 3D-printed rock analogs are acquired through helium pycnometry (HP) and mercury intrusion porosimetry (MIP). The accuracy of 3D-printed rock analogs is evaluated by comparing the measured results with the benchmark data derived from the digital rock modelling. Both the advantages and the current challenges to reproduce the real pore structure of natural rock by the 3D-printed analogs are discussed. The results indicate that the gypsum-based printed analogs are prior to modelling the surface roughness and wettability properties to natural rock grains, while the resin-based printed analogs owe advantages on reproducing pore structure. As the first effort in literature, this study investigates the inherent relationship between digital rock and 3D-printed rock analogs via comprehensive comparison on petrophysical properties. The results approve that the 3D printing technique is a novel, feasible, and alternative approach for laboratory test to generate rock analogs from the digital model of the natural rock. However, it is still difficult to print the pore structure of the rock at the original dimension. • A customized framework of rock analogs 3D printed from micro-CT image was established. • As the first effort in literature, the inherent relationship between digital rock and 3D-printed rock was investigated. • The effects of different printing techniques, materials, and up-scaling factors on reproducing pore structure was discussed.

Deep Multi-Magnification Networks for multi-class breast cancer image segmentation.

Pathologic analysis of surgical excision specimens for breast carcinoma is important to evaluate the completeness of surgical excision and has implications for future treatment. This analysis is performed manually by pathologists reviewing histologic slides prepared from formalin-fixed tissue. In this paper, we present Deep Multi-Magnification Network trained by partial annotation for automated multi-class tissue segmentation by a set of patches from multiple magnifications in digitized whole slide images. Our proposed architecture with multi-encoder, multi-decoder, and multi-concatenation outperforms other single and multi-magnification-based architectures by achieving the highest mean intersection-over-union, and can be used to facilitate pathologists' assessments of breast cancer.

Robust Magnification Independent Colon Biopsy Grading System over Multiple Data Sources

Automated grading of colon biopsy images across all magnifications is challenging because of tailored segmentation and dependent features on each magnification. This work presents a novel approach of robust magnification-independent colon cancer grading framework to distinguish colon biopsy images into four classes: normal, well, moderate, and poor. The contribution of this research is to develop a magnification invariant hybrid feature set comprising cartoon feature, Gabor wavelet, wavelet moments, HSV histogram, color auto-correlogram, color moments, and morphological features that can be used to characterize different grades. Besides, the classifier is modeled as a multiclass structure with six binary class Bayesian optimized random forest (BO-RF) classifiers. This study uses four datasets (two collected from Indian hospitals—Ishita Pathology Center (IPC) of 4X, 10X, and 40X and Aster Medcity (AMC) of 10X, 20X, and 40X—two benchmark datasets—gland segmentation (GlaS) of 20X and IMEDIATREAT of 10X) comprising multiple microscope magnifications. Experimental results demonstrate that the proposed method outperforms the other methods used for colon cancer grading in terms of accuracy (97.25%-IPC, 94.40%-AMC, 97.58%-GlaS, 99.16%-Imediatreat), sensitivity (0.9725-IPC, 0.9440-AMC, 0.9807-GlaS, 0.9923-Imediatreat), specificity (0.9908-IPC, 0.9813-AMC, 0.9907-GlaS, 0.9971-Imediatreat) and F-score (0.9725-IPC, 0.9441-AMC, 0.9780-GlaS, 0.9923-Imediatreat). The generalizability of the model to any magnified input image is validated by training in one dataset and testing in another dataset, highlighting strong concordance in multiclass classification and evidencing its effective use in the first level of automatic biopsy grading and second opinion.

Malaria detection using deep residual networks with mobile microscopy

Automatic segmentation of erythrocytes in microscopic blood smear phone images is a critical step to visualize and identify malaria using machine learning technologies. However, it still remains a challenging problem due to the scarcity of experts, low image qualities, slow manual and inefficient quality of diagnosis. To handle these issues to some extent, we proposed an effective multi-magnification deep residual neural network (MM-ResNet), where we fully automatically classify the microscopic blood smear images as either infected/ non-infected at multiple magnifications. We have experimentally evaluated our approach by using it to train more efficient variants of different compact deep convolutional neural networks (CNN), evaluated on phone datasets. The MM-ResNet end-to-end framework shows similar or superior accuracy than the baseline architectures, as measured by GPU timings on the publicly available microscopic blood smear phone images. This approach is the first application of a MM-ResNet for malaria-infected erythrocyte identification in microscopic blood smear images.

EVICAN-a balanced dataset for algorithm development in cell and nucleus segmentation.

MotivationDeep learning use for quantitative image analysis is exponentially increasing. However, training accurate, widely deployable deep learning algorithms requires a plethora of annotated (ground truth) data. Image collections must contain not only thousands of images to provide sufficient example objects (i.e. cells), but also contain an adequate degree of image heterogeneity.ResultsWe present a new dataset, EVICAN—Expert visual cell annotation, comprising partially annotated grayscale images of 30 different cell lines from multiple microscopes, contrast mechanisms and magnifications that is readily usable as training data for computer vision applications. With 4600 images and ∼26 000 segmented cells, our collection offers an unparalleled heterogeneous training dataset for cell biology deep learning application development.Availability and implementationThe dataset is freely available (https://edmond.mpdl.mpg.de/imeji/collection/l45s16atmi6Aa4sI?q=). Using a Mask R-CNN implementation, we demonstrate automated segmentation of cells and nuclei from brightfield images with a mean average precision of 61.6 % at a Jaccard Index above 0.5.

Determining uranium ore concentrates and their calcination products via image classification of multiple magnifications

Many tools, such as mass spectrometry, X-ray diffraction, X-ray fluorescence, ion chromatography, etc., are currently available to scientists investigating interdicted nuclear material. These tools provide an analysis of physical, chemical, or isotopic characteristics of the seized material to identify its origin. In this study, a novel technique that characterizes physical attributes is proposed to provide insight into the processing route of unknown uranium ore concentrates (UOCs) and their calcination products. In particular, this study focuses on the characteristics of the surface structure captured in scanning electron microscopy (SEM) images at different magnification levels. Twelve common commercial processing routes of UOCs and their calcination products are investigated. Multiple-input single-output (MISO) convolution neural networks (CNNs) are implemented to differentiate the processing routes. The proposed technique can determine the processing route of a given sample in under a second running on a graphics processing unit (GPU) with an accuracy of more than 95%. The accuracy and speed of this proposed technique enable nuclear scientists to provide the preliminary identification results of interdicted material in a short time period. Furthermore, this proposed technique uses a predetermined set of magnifications, which in turn eliminates the human bias in selecting the magnification during the image acquisition process.

Development of Optimal Multiscale Patterns for Digital Image Correlation via Local Grayscale Variation

In many applications of digital image correlation (DIC), it is advantageous to have measurements at multiple scales. Because it is rare to have natural features that can be used for DIC at multiple magnifications, an appropriately multiscale DIC pattern is needed. This work develops a multiscale DIC pattern that (1) contains features appropriate for both high and low magnification, (2) does not need to know the location of high magnification a priori, and (3) does not require specialized DIC equipment beyond what is necessary to achieve the two magnifications. The pattern is developed based on an optimization framework that minimizes expected DIC error while constraining sub-regions of the pattern to biased average grayscale values. The inclusion of local grayscale biases in the pattern has the effect of introducing resolvable features at a length scale much larger than the speckles of which the pattern is composed. Numerical and physical experiments were performed to illustrate the functionality and utility of the designed patterns. Notable among the findings is the trade off between DIC accuracy at the two scales and how it is controlled by grayscale bias.

A structured latent model for ovarian carcinoma subtyping from histopathology slides.

Accurate subtyping of ovarian carcinomas is an increasingly critical and often challenging diagnostic process. This work focuses on the development of an automatic classification model for ovarian carcinoma subtyping. Specifically, we present a novel clinically inspired contextual model for histopathology image subtyping of ovarian carcinomas. A whole slide image is modelled using a collection of tissue patches extracted at multiple magnifications. An efficient and effective feature learning strategy is used for feature representation of a tissue patch. The locations of salient, discriminative tissue regions are treated as latent variables allowing the model to explicitly ignore portions of the large tissue section that are unimportant for classification. These latent variables are considered in a structured formulation to model the contextual information represented from the multi-magnification analysis of tissues. A novel, structured latent support vector machine formulation is defined and used to combine information from multiple magnifications while simultaneously operating within the latent variable framework. The structural and contextual nature of our method addresses the challenges of intra-class variation and pathologists' workload, which are prevalent in histopathology image classification. Extensive experiments on a dataset of 133 patients demonstrate the efficacy and accuracy of the proposed method against state-of-the-art approaches for histopathology image classification. We achieve an average multi-class classification accuracy of 90%, outperforming existing works while obtaining substantial agreement with six clinicians tested on the same dataset.

Multi-Contrast Imaging and Digital Refocusing on a Mobile Microscope with a Domed LED Array.

We demonstrate the design and application of an add-on device for improving the diagnostic and research capabilities of CellScope—a low-cost, smartphone-based point-of-care microscope. We replace the single LED illumination of the original CellScope with a programmable domed LED array. By leveraging recent advances in computational illumination, this new device enables simultaneous multi-contrast imaging with brightfield, darkfield, and phase imaging modes. Further, we scan through illumination angles to capture lightfield datasets, which can be used to recover 3D intensity and phase images without any hardware changes. This digital refocusing procedure can be used for either 3D imaging or software-only focus correction, reducing the need for precise mechanical focusing during field experiments. All acquisition and processing is performed on the mobile phone and controlled through a smartphone application, making the computational microscope compact and portable. Using multiple samples and different objective magnifications, we demonstrate that the performance of our device is comparable to that of a commercial microscope. This unique device platform extends the field imaging capabilities of CellScope, opening up new clinical and research possibilities.

Application of direct oral microscopy in evaluating mucosal margins around invasive oral squamous cell carcinoma.

IntroductionDirect oral microscopy constitutes a novel, non-invasive diagnostic technique, which aids clinical examination of the oral cavity. The oral mucosa is examined at multiple magnifications and features such as sub-epithelial mucosal vessels, surface patterns, colour tone, transparency and the exact demarcation of mucosal lesions are estimated. The incidence of oral squamous cell carcinoma (OSCC) oscillates between 1.9% and 3.5%, which makes it the eighth most common carcinoma occurring around the world and in Poland. The 5-year survival rates oscillate between 20% and 30%.AimThe aim of the study was to evaluate clinically unchanged mucosal margins around OSCC by direct oral microscopy. The authors approached the question whether the borders of mucosal margins around OSCC established via direct oral microscopy differ from those established based on clinical examination.Material and methodsFifteen patients diagnosed with OSCC were enrolled. Patients were first clinically examined to evaluate the extent of the tumour and to plan resection margins. Eventually, direct oral microscopy was performed to establish the width of the subclinically unchanged mucosal margins based on a standard picture of healthy oral mucosae, followed by comparison with those established by clinical evaluation.ResultsHistopathologic results of biopsies from areas indicated by direct oral microscopy revealed dysplasia in 86.7% of patients, whereas biopsies from areas indicated by clinical examination revealed dysplasia only in 40% of individuals, resulting in the need for widening of mucosal margins.ConclusionsDirect oral microscopy enables detection of dysplasia within clinically unaltered mucosal margins around OSCC, which results in more precise establishing of resection boundaries, contributing to improvement of resection totality.