Search

Computer-aided detection or diagnosing support methods aims to improve breast cancer screening programs by helping radiologists to evaluate digital mammography (DM) exams. This system relates to the use of deep learning for automated detection and segmentation of soft tissue lesions at the early stage. This paper presents a novel deep learning approach, based on a two stage object detector combining an enhanced Faster R-CNN with the Libra R-CNN structure for the Object Detection segment. A segmentation network is placed on top of previous structure in order to provide accurate extraction and localization of masses various features, i.e: margin, shape. The segmentation head is based on a Recurrent Residual Convolutional Neural Network and can lead to an additional feature classification for specific instance properties. A database of digital mammograms was collected from one vendor, Hologic, of which 1,200 images contained masses. The performance for our automated detection system was assessed with the sensitivity of the model which reached a micro average recall: 0.892, micro average precision: 0.734, micro average F1 score: 0.805. Macro average recall: 0.896, macro average precision: 0.819, macro average F1 score: 0.843. The segmentation performance for the same test set was evaluated to a mean IOU of 0.859.

Expansion microscopy (ExM), a method for improving the resolution of light microscopy by physically expanding a specimen, has not been applied to clinical tissue samples. Here we report a clinically optimized form of ExM that supports nanoscale imaging of human tissue specimens that have been fixed with formalin, embedded in paraffin, stained with hematoxylin and eosin, and/or fresh frozen. The method, which we call expansion pathology (ExPath), converts clinical samples into an ExM-compatible state, then applies an ExM protocol with protein anchoring and mechanical homogenization steps optimized for clinical samples. ExPath enables ∼70-nm-resolution imaging of diverse biomolecules in intact tissues using conventional diffraction-limited microscopes and standard antibody and fluorescent DNA in situ hybridization reagents. We use ExPath for optical diagnosis of kidney minimal-change disease, a process that previously required electron microscopy, and we demonstrate high-fidelity computational discrimination between early breast neoplastic lesions for which pathologists often disagree in classification. ExPath may enable the routine use of nanoscale imaging in pathology and clinical research.

We developed an automated 2-tiered Fuhrman’s grading system for clear cell renal cell carcinoma (ccRCC). Whole slide images (WSI) and clinical data were retrieved for 395 The Cancer Genome Atlas (TCGA) ccRCC cases. Pathologist 1 reviewed and selected regions of interests (ROIs). Nuclear segmentation was performed. Quantitative morphological, intensity, and texture features (n=72) were extracted. Features associated with grade were identified by constructing a Lasso model using data from cases with concordant 2-tiered Fuhrman’s grades between TCGA and Pathologist 1 (training set n=235; held-out test set n=42). Discordant cases (n=118) were additionally reviewed by Pathologist 2. Cox proportional hazard model evaluated the prognostic efficacy of the predicted grades in an extended test set which was created by combining the test set and discordant cases (n=160). The Lasso model consisted of 26 features and predicted grade with 84.6% sensitivity and 81.3% specificity in the test set. In the extended test set, predicted grade was significantly associated with overall survival after adjusting for age and gender (Hazard Ratio 2.05; 95% CI 1.21-3.47); manual grades were not prognostic. Future work can adapt our computational system to predict WHO/ISUP grades, and validating this system on other ccRCC cohorts.

IMPORTANCE: Application of deep learning algorithms to whole-slide pathology imagescan potentially improve diagnostic accuracy and efficiency. OBJECTIVE: Assess the performance of automated deep learning algorithms at detecting metastases in hematoxylin and eosin-stained tissue sections of lymph nodes of women with breast cancer and compare it with pathologists' diagnoses in a diagnostic setting. DESIGN, SETTING, AND PARTICIPANTS: Researcher challenge competition (CAMELYON16) to develop automated solutions for detecting lymph node metastases (November 2015-November 2016). A training data set of whole-slide images from 2 centers in the Netherlands with (n = 110) and without (n = 160) nodal metastases verified by immunohistochemical staining were provided to challenge participants to build algorithms. Algorithm performance was evaluated in an independent test set of 129 whole-slide images (49 with and 80 without metastases). The same test set of corresponding glass slides was also evaluated by a panel of 11 pathologists with time constraint (WTC) from the Netherlands to ascertain likelihood of nodal metastases for each slide in a flexible 2-hour session, simulating routine pathology workflow, and by 1 pathologist without time constraint (WOTC). EXPOSURES: Deep learning algorithms submitted as part of a challenge competition or pathologist interpretation. MAIN OUTCOMES AND MEASURES: The presence of specific metastatic foci and the absence vs presence of lymph node metastasis in a slide or image using receiver operating characteristic curve analysis. The 11 pathologists participating in the simulation exercise rated their diagnostic confidence as definitely normal, probably normal, equivocal, probably tumor, or definitely tumor. RESULTS: The area under the receiver operating characteristic curve (AUC) for the algorithms ranged from 0.556 to 0.994. The top-performing algorithm achieved a lesion-level, true-positive fraction comparable with that of the pathologist WOTC (72.4% [95% CI, 64.3%-80.4%]) at a mean of 0.0125 false-positives per normal whole-slide image. For the whole-slide image classification task, the best algorithm (AUC, 0.994 [95% CI, 0.983-0.999]) performed significantly better than the pathologists WTC in a diagnostic simulation (mean AUC, 0.810 [range, 0.738-0.884]; P

Wireless sensors network is a network consists of sensors node, creating cluster and selection of cluster head is an issue for an efficient WSN. A new technique is proposed in this research which is termed as Wireless Active Sensors Network (WASN). We designed a novel protocol called interference aware Multi channel protocol based on MAC for sensors Network. The proposed algorithm is implemented using Matlab and the simulations are compared w.r.t to previous architecture. WASN consist of active and mobile sensors that's why it's called as WASN. In this research energy of sensors network is enhanced at maximum using IAMMAC protocol for WASN.

Meningioma subtypes classification is a real-world multiclass problem from the realm of neuropathology. The major challenge in solving this problem is the inherent complexity due to high intra-class variability and low inter-class variation in tissue samples. The development of computational methods to assist pathologists in characterization of these tissue samples would have great diagnostic and prognostic value. In this article, we proposed an optimized evolutionary framework for the classification of benign meningioma into four subtypes. This framework investigates the imperative role of RGB color channels for discrimination of tumor subtypes and compute structural, statistical and spectral phenotypes. An evolutionary technique, Genetic Algorithm, in combination with Support Vector Machine is applied to tune classifier parameters and to select the best possible combination of extracted phenotypes that improved the classification accuracy (94.88%) on meningioma histology dataset, provided by the Institute of Neuropathology, Bielefeld. These statistics show that computational framework can robustly discriminate four subtypes of benign meningioma and may aid pathologists in the diagnosis and classification of these lesions.

Digital pathology represents one of the major evolutions in modern medicine. Pathological examinations constitute the gold standard in many medical protocols, and also play a critical and legal role in the diagnosis process. In the conventional cancer diagnosis, pathologists analyze biopsies to make diagnostic and prognostic assessments, mainly based on the cell morphology and architecture distribution. Recently, computerized methods have been rapidly evolving in the area of digital pathology, with growing applications related to nuclei detection, segmentation, and classification. In cancer research, these approaches have played, and will continue to play a key (often bottleneck) role in minimizing human intervention, consolidating pertinent second opinions, and providing traceable clinical information. Pathological studies have been conducted for numerous cancer detection and grading applications, including brain, breast, cervix, lung, and prostate cancer grading. Our study presents, discusses, and extracts the major trends from an exhaustive overview of various nuclei detection, segmentation, feature computation, and classification techniques used in histopathology imagery, specifically in hematoxylin-eosin and immunohistochemical staining protocols. This study also enables us to measure the challenges that remain, in order to reach robust analysis of whole slide images, essential high content imaging with diagnostic biomarkers and prognosis support in digital pathology.

The assessment of protein expression in immunohistochemistry (IHC) images provides important diagnostic, prognostic and predictive information for guiding cancer diagnosis and therapy. Manual scoring of IHC images represents a logistical challenge, as the process is labor intensive and time consuming. Since the last decade, computational methods have been developed to enable the application of quantitative methods for the analysis and interpretation of protein expression in IHC images. These methods have not yet replaced manual scoring for the assessment of IHC in the majority of diagnostic laboratories and in many large-scale research studies. An alternative approach is crowdsourcing the quantification of IHC images to an undefined crowd. The aim of this study is to quantify IHC images for labeling of ER status with two different crowdsourcing approaches, image-labeling and nuclei-labeling, and compare their performance with automated methods. Crowdsourcing- derived scores obtained greater concordance with the pathologist interpretations for both image-labeling and nuclei-labeling tasks (83% and 87%), as compared to the pathologist concordance achieved by the automated method (81%) on 5,338 TMA images from 1,853 breast cancer patients. This analysis shows that crowdsourcing the scoring of protein expression in IHC images is a promising new approach for large scale cancer molecular pathology studies.

Purpose/Objective: Collagen is a major extracellular matrix (ECM) constituent in normal breast and is extensively remodeled in breast carcinoma. Therefore, features of remodeled collagen in the stroma adjacent to ductal carcinoma in situ (DCIS) could indicate cancer progression. The major objective of this study is to identify potential tumor-associated collagen signatures unique to DCIS that will allow us to predict progression based on the collagen texture and nuclear morphology. In this present study, we develop two image analysis pipelines (SHG Texture Extraction and H&E Nuclear Morphology Extractor) to quantify 1) stromal changes, 2) collagen signatures and 3) nuclear morphology from normal breast to DCIS in order to predict local breast cancer recurrence. Method: We used second harmonic generation (SHG) images and H&E to analyze collagen features and to study nuclear morphology using a data set of 336 patients (from which 310 normal and 327 DCIS regions were imaged). The 336 patients were a subset of patients with pure DCIS taken from a case-control study. Clinical-pathologic factors were associated with risk of subsequent ipsilateral cancer (DCIS or invasive). The SHG framework consisted of collagen segmentation using 1) adaptive thresholding and 2) morphological operations. The H&E framework consisted of nuclear segmentation using adaptive thresholding and a maker-controlled watershed algorithm; and nuclear feature extractions including intensity, texture and morphology. Overall, the SHG framework segments collagen regions and computes textural features specifically at collagen regions. Furthermore, the H&E framework segments nuclei and computes nuclei morphology and textural features. These features were used in L1-regularized logistic regression to construct classification models to discriminate normal vs DCIS regions; and to distinguish regions from DCIS patients with vs. without local recurrences. Results: In first experiment, we performed L1-regularized logistic regression to construct a classification model to discriminate normal vs DCIS regions. Our results suggest that using only SHG collagen features, this logistic model selected 19 significant features to build a classification model that achieved area under curve (AUC) 90% and accuracy 83% using 5-Fold cross validation. When H&E nuclei features are used, the logistic model selected 88 significant features and achieved AUC 91% and accuracy 86%. By combined both SHG and H&E features, the model achieved classification AUC 93% and accuracy 88%. By using L1-regularized logistic model with combined significant SHG and H&E features, we achieved AUC 59% with an accuracy of 61% for DCIS and recurrent DCIS regions. Conclusions: Our study suggests that SHG and nuclear morphology features extracted from H&E can improve the classification of normal and DCIS regions. Overall, these results suggest that second harmonic generation and H&E nuclear morphology analysis could aid in the assessment of prognosis and risk of progression to invasive breast cancer. Citation Format: Park CC, Irshad H, Ziaee S, Martin-Tuite P, Habel L, Weaver VM, Schnitt SJ, Beck AH. Second harmonic generation in combination with nuclear morphometry in the evaluation of DCIS [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr P5-02-02.

The categorization of intraductal proliferative lesions of the breast based on routine light microscopic examination of histopathologic sections is in many cases challenging, even for experienced pathologists. The development of computational tools to aid pathologists in the characterization of these lesions would have great diagnostic and clinical value. As a first step to address this issue, we evaluated the ability of computational image analysis to accurately classify DCIS and UDH and to stratify nuclear grade within DCIS. Using 116 breast biopsies diagnosed as DCIS or UDH from the Massachusetts General Hospital (MGH), we developed a computational method to extract 392 features corresponding to the mean and standard deviation in nuclear size and shape, intensity, and texture across 8 color channels. We used L1-regularized logistic regression to build classification models to discriminate DCIS from UDH. The top-performing model contained 22 active features and achieved an AUC of 0.95 in cross-validation on the MGH data-set. We applied this model to an external validation set of 51 breast biopsies diagnosed as DCIS or UDH from the Beth Israel Deaconess Medical Center, and the model achieved an AUC of 0.86. The top-performing model contained active features from all color-spaces and from the three classes of features (morphology, intensity, and texture), suggesting the value of each for prediction. We built models to stratify grade within DCIS and obtained strong performance for stratifying low nuclear grade vs. high nuclear grade DCIS (AUC = 0.98 in cross-validation) with only moderate performance for discriminating low nuclear grade vs. intermediate nuclear grade and intermediate nuclear grade vs. high nuclear grade DCIS (AUC = 0.83 and 0.69, respectively). These data show that computational pathology models can robustly discriminate benign from malignant intraductal proliferative lesions of the breast and may aid pathologists in the diagnosis and classification of these lesions.

The development of tools in computational pathology to assist physicians and biomedical scientists in the diagnosis of disease requires access to high-quality annotated images for algorithm learning and evaluation. Generating high-quality expert-derived annotations is time-consuming and expensive. We explore the use of crowdsourcing for rapidly obtaining annotations for two core tasks in com- putational pathology: nucleus detection and nucleus segmentation. We designed and implemented crowdsourcing experiments using the CrowdFlower platform, which provides access to a large set of labor channel partners that accesses and manages millions of contributors worldwide. We obtained annotations from four types of annotators and compared concordance across these groups. We obtained: crowdsourced annotations for nucleus detection and segmentation on a total of 810 images; annotations using automated methods on 810 images; annotations from research fellows for detection and segmentation on 477 and 455 images, respectively; and expert pathologist-derived annotations for detection and segmentation on 80 and 63 images, respectively. For the crowdsourced annotations, we evaluated performance across a range of contributor skill levels (1, 2, or 3). The crowdsourced annotations (4,860 images in total) were completed in only a fraction of the time and cost required for obtaining annotations using traditional methods. For the nucleus detection task, the research fellow-derived annotations showed the strongest concordance with the expert pathologist- derived annotations (F-M =93.68%), followed by the crowd-sourced contributor levels 1,2, and 3 and the automated method, which showed relatively similar performance (F-M = 87.84%, 88.49%, 87.26%, and 86.99%, respectively). For the nucleus segmentation task, the crowdsourced contributor level 3-derived annotations, research fellow-derived annotations, and automated method showed the strongest concordance with the expert pathologist-derived annotations (F-M = 66.41%, 65.93%, and 65.36%, respectively), followed by the contributor levels 2 and 1 (60.89% and 60.87%, respectively). When the research fellows were used as a gold-standard for the segmentation task, all three con- tributor levels of the crowdsourced annotations significantly outperformed the automated method (F-M = 62.21%, 62.47%, and 65.15% vs. 51.92%). Aggregating multiple annotations from the crowd to obtain a consensus annotation resulted in the strongest performance for the crowd-sourced segmentation. For both detection and segmentation, crowd-sourced performance is strongest with small images (400 × 400 pixels) and degrades significantly with the use of larger images (600 × 600 and 800 × 800 pixels). We conclude that crowdsourcing to non-experts can be used for large-scale labeling microtasks in computational pathology and offers a new approach for the rapid generation of labeled images for algorithm development and evaluation.

Accurate counting of mitosis in breast cancer histopathology plays a critical role in the grading process. Manual counting of mitosis is tedious and subject to considerable inter- and intra-reader variations. This work aims at improving the accuracy of mitosis detection by selecting the color channels that better capture the statistical and morphological features having mitosis discrimination from other objects. The proposed framework includes comprehensive analysis of first and second order statistical features together with morphological features in selected color channels and a study on balancing the skewed dataset using SMOTE method for increasing the predictive accuracy of mitosis classification. The proposed framework has been evaluated on MITOS data set during an ICPR 2012 contest and ranked second from 17 finalists. The proposed framework achieved 74% detection rate, 70% precision and 72% F-Measure. In future work, we plan to apply our mitosis detection tool to images produced by different types of slide scanners, including multi-spectral and multi-focal microscopy.

This document describes an extension of ITK to handle both primal and dual meshes simultaneously. This paper describe in particular the data structure, an extension of itk::QuadEdgeMesh, a filter to compute and add to the the structure the dual of an existing mesh, and an adaptor which let a down- ward pipeline process the dual mesh as if it was a native itk::QuadEdgeMesh. The new data structure, itk::QuadEdgeMeshWithDual, is an extension of the already existing itk::QuadEdgeMesh, which already included by default the due topology, to handle dual geometry as well. Two types of primal meshes have been specifically illustrated: triangular / simplex meshes and Voronoi / Delaunay. A functor mechanism has been implemented to allow for different kind of computation of the dual geometry. This paper is accompanied with the source code and examples.

This paper presents a survey of latest image segmentation techniques using fuzzy clustering. Fuzzy C-Means (FCM) Clustering is the most wide spread clustering approach for image segmentation because of its robust characteristics for data classification. In this paper, four image segmentation algorithms using clustering, taken from the literature are reviewed. To address the drawbacks of conventional FCM, all these approaches have modified the objective function of conventional FCM and have incorporated spatial information in the objective function of the standard FCM. The techniques that have been reviewed in this survey are Segmentation for noisy medical images with spatial probability, Novel Fuzzy C-Means Clustering (NFCM), Fuzzy Local Information C-Means (FLICM) Clustering Algorithm and Improved Spatial Fuzzy C-Means Clustering (ISFCM) algorithm.

Image fusion is a process to combine information from different images of the identical scene to make an image that has more information. Main focus of this survey is on image fusion techniques using Computational Intelligence. Image fusion techniques have agreed upon few standards, whereas most of the schemes rely upon multi-scale decompositions. It contains many steps and complex decision models that may be difficult to implement in real-time systems. They are also susceptible to artifacts and noise enhancement because they treat source images as equally likely contributors to the fused result. This research survey will focus on the study of existing and new image fusion techniques.

BACKGROUND: Since the early 20th century, the pathological classification of breast cancer has been based primarily on the visual analysis of H&E stained images using conventional 2D microscopy. With the recent development of new state-of-the-art microscopy platforms, such as fluorescent Lightsheet microscopy (LSM), the rapid acquisition of three dimensional (3D) images directly from tissue samples up to several millimeters in thickness is now possible. The aim of this project is to develop methods to perform LSM on formalin fixed paraffin embedded (FFPE) breast tissue samples and to use this approach to identify 3D morphological hallmarks of breast carcinogenesis, which may aid in breast cancer research and diagnostics. METHODS: 30 breast tissue samples, including normal breast, ductal carcinoma in situ (DCIS) and invasive breast cancer (IBC), were collected. To prepare the tissue for LSM, we obtained 1 mm diameter tissue cores from the FFPE blocks, which we deparaffinized, permeabilized with Triton X-100, treated with sodium borohydride for autofluorescence reduction, stained with Gel Green for nucleus detection and clarified using a modified Scale A2 solution to increase light penetration. We then designed and implemented an image analysis pipeline to obtain measurements from the 3D images and to build classification models. The pipeline for nuclear segmentation consisted of adaptive thresholding, morphological operations and watershed segmentation, followed by the extraction of morphometric features (11 morphology, 7 intensity, 18 texture, and 5 spatial graph-based features). Lastly, we performed logistic regression with Lasso regularization to build LSM image feature-based models to classify cases into diagnostic categories. Model performance was assessed by computing the area under the curve (AUC) in cross-validation. RESULTS AND CONCLUSIONS: The deparaffinization, permabilization, clarification, and fluorescent staining protocol we developed enabled visualization of 3D breast architecture with sub-cellular resolution from FFPE specimens. To assess the diagnostic utility of LSM in breast pathology, we used the LSM-derived features to build classification models, which showed strong performance for the discrimination of normal breast from both DCIS and IBC (AUC = 0.94 in cross validation for both tasks). Morphological and spatial graph-based features were the strongest predictors of pathological diagnoses in the classification models. These data suggest that 3D morphometric and spatial features are highly informative of pathological diagnosis and may supplement conventional morphological and molecular approaches in breast cancer diagnostics. These results lay the ground work for future larger scale studies to more fully evaluate the utility of LSM for breast cancer research and diagnostics. Citation Format: Octavian Bucur, Humayun Irshad, Laleh Montaser-Kouhsari, Nicholas W. Knoblauch, Eun-Yeong Oh, Jonathan Nowak, Andrew H. Beck. 3D morphological hallmarks of breast carcinogenesis: Diagnosis of non-invasive and invasive breast cancer with Lightsheet microscopy. [abstract]. In: Proceedings of the 106th Annual Meeting of the American Association for Cancer Research; 2015 Apr 18-22; Philadelphia, PA. Philadelphia (PA): AACR; Cancer Res 2015;75(15 Suppl):Abstract nr 3477. doi:10.1158/1538-7445.AM2015-3477

Context: According to Nottingham grading system, mitosis count in breast cancer histopathology is one of three components required for cancer grading and prognosis. Manual counting of mitosis is tedious and subject to considerable inter- and intra-reader variations. Aims: The aim is to investigate the various texture features and Hierarchical Model and X (HMAX) biologically inspired approach for mitosis detection using machine-learning techniques. Materials and Methods: We propose an approach that assists pathologists in automated mitosis detection and counting. The proposed method, which is based on the most favorable texture features combination, examines the separability between different channels of color space. Blue-ratio channel provides more discriminative information for mitosis detection in histopathological images. Co-occurrence features, run-length features, and Scale-invariant feature transform (SIFT) features were extracted and used in the classification of mitosis. Finally, a classification is performed to put the candidate patch either in the mitosis class or in the non-mitosis class. Three different classifiers have been evaluated: Decision tree, linear kernel Support Vector Machine (SVM), and non-linear kernel SVM. We also evaluate the performance of the proposed framework using the modified biologically inspired model of HMAX and compare the results with other feature extraction methods such as dense SIFT. Results: The proposed method has been tested on Mitosis detection in breast cancer histological images (MITOS) dataset provided for an International Conference on Pattern Recognition (ICPR) 2012 contest. The proposed framework achieved 76% recall, 75% precision and 76% F-measure. Conclusions: Different frameworks for classification have been evaluated for mitosis detection. In future work, instead of regions, we intend to compute features on the results of mitosis contour segmentation and use them to improve detection and classification rate.