Software-based manual segmentation is critical to the supervision of diffuse low-grade glioma patients and to the optimal treatment's choice. However, manual segmentation being time-consuming, it is difficult to include it in the clinical routine. An alternative to circumvent the time cost of manual segmentation could be to share the task among different practitioners, providing it can be reproduced. The goal of our work is to assess diffuse low-grade gliomas' manual segmentation's reproducibility on MRI scans, with regard to practitioners, their experience and field of expertise. A panel of 13 experts manually segmented 12 diffuse low-grade glioma clinical MRI datasets using the OSIRIX software. A statistical analysis gave promising results, as the practitioner factor, the medical specialty and the years of experience seem to have no significant impact on the average values of the tumor volume variable.

Diffuse low-grade gliomas are rare primitive cerebral tumours of adults. These tumors progress continuously over time and then turn to a higher grade of malignancy associated with neurological disability, leading ultimately to death. Tumour size is one of the most important prognostic factors. Thus, it is of great importance to be able to assess the volume of the tumor during the patients' monitoring. MRI is nowadays the recommended modality to achieve this. Furthermore, if surgery remains the first option for diffuse low-grade gliomas, chemotherapy is increasingly used (before or after a possible surgery). However, crucial and difficult questions remain to be answered: identifying subgroups of patients who could benefit from chemotherapy, determining the best time to initiate chemotherapy, defining the duration of chemotherapy and evaluating the optimal time to perform surgery, or otherwise radiotherapy. In this study, we propose to help clinicians in decision-making, by designing new predictive models dedicated to the evolution of the diameter of the tumor. Two proposed statistical models (linear and exponential) have been validated on a database of 16 patients whose temozolomide-based chemotherapy lasted between 14 and 32 months, with an average duration of 22.8 months. The selection of the most appropriate model has been achieved with the corrected Akaike's Information Criterion. The results are very promising, with coefficients of determination varying from 0.79 to 0.97 with an average value of 0.90 for the linear model. This shows it is possible to alert the clinician to a change in the tumor diameter's dynamics.

Histopathological analysis is crucial for the diagnosis of a large number of cancer types. A lot of progress has been made in the development of molecular based assays, but many of the cases still require the careful analysis of the stained tissue under a bright-field microscope and its analysis. This procedure is costly and time-consuming. We present a novel method for classification of cancer cells in lymph node images. It is based on the measurement of the spectral image of hematoxylin and eosin stained sample under the microscope and the analysis of the acquired data using state of the art machine learning techniques. The method is based on the analysis of the spectral information of the cells as well as their morphological properties. A large number of descriptors is extracted for each cell location, which are used to train a supervised classifier which discriminates between normal and cancer cells. We show that a reliable analysis can be made with detection rate (recall) of 81%-100% for the cancer class.

Breast cancer is the second leading cause of death in women in the United States due to cancer. Early detection of breast cancerous regions will aid the diagnosis, staging, and treatment of breast cancer. Optical coherence tomography (OCT), a non-invasive imaging modality with high resolution, has been widely used to visualize various tissue types within the human breast and has demonstrated great potential for assessing tumor margins. Imaging large resected samples with a fast imaging speed can be accomplished by under-sampling in the spatial domain, resulting in a large image scale. However, it is unclear whether there is an impact on the ability to classify tissue types based on the selected imaging scale. Our objective is to evaluate how the scale at which the images are acquired impacts texture features and the accuracy of an automated classification algorithm. To this end, we present a comparative study of texture features in OCT images at two image scales for human breast tissue classification. Texture features and attenuation coefficients were inputs to a statistical classification model, relevance vector machine. The automated classification results from the two image scales were compared. We found that more informative tissue features are preserved in small image scale and accordingly, small image scale leads to more accurate tissue type classification.

Asymmetry is one of key characteristics for early diagnosis of melanoma according to medical algorithms such as (ABCD, CASH etc.). Besides shape information, cues such as irregular distribution of colors and structures within the lesion area are assessed by dermatologists to determine lesion asymmetry. Motivated by the clinical practices, we have used Kullback-Leibler divergence of color histogram and Structural Similarity metric as a measures of these irregularities. We have presented performance of several classifiers using these features on publicly available PH2 dataset. The obtained result shows better asymmetry classification than available literature. Besides being a new benchmark, the proposed technique can be used for early diagnosis of melanoma by both clinical experts and other automated diagnosis systems.

A new framework has been introduced in this paper for tumor radiosensitization and therapy response monitoring using low-frequency ultrasound. Human fibrosarcoma xenografts grown in severe combined immunodeficiency (SCID) mice (n = 108) were treated using ultrasound-stimulated microbubbles at various concentration and exposed to different doses of radiation. Low-frequency ultrasound radiofrequency (RF) data were acquired from tumors prior to and at different times after treatment. Quantitative ultrasound (QUS) techniques were applied to generate spectral parametric maps of tumors. Textural analysis were performed to quantify spatial heterogeneities within QUS parametric maps. A hybrid model was developed using multiple regression analysis to predict extent of histological tumor cell death non-invasively based on QUS spectral and textural biomarkers. Results of immunohistochemistry on excised tumor sections demonstrated increases in cell death with higher concentration of microbubbles and radiation dose. Quantitative ultrasound results indicated changes that paralleled increases in histological cell death. Specifically, the hybrid QUS biomarker demonstrated a good correlation with extent of tumor cell death observed from immunohistochemistry. A linear discriminant analysis applied in conjunction with the receiver operating characteristic (ROC) curve analysis indicated that the hybrid QUS biomarker can classify tumor cell death fractions with an area under the curve of 91.2. The results obtained in this research suggest that low-frequency ultrasound can concurrently be used to enhance radiation therapy and evaluate tumor response to treatment.

Basal cell carcinoma (BCC) is the most common non-melanoma skin cancer. Conventional diagnosis of BCC requires invasive biopsies. Recently, a high-definition optical coherence tomography (HD-OCT) technique has been developed, which provides a non-invasive in vivo imaging method of skin. Good agreements of BCC features between HD-OCT images and histopathological architecture have been found. Therefore it is possible to automatically detect BCC using HD-OCT. This paper presents a novel BCC detection method that consists of four steps: graph based skin surface segmentation, surface flattening, deep feature extraction and the BCC classification. The effectiveness of the proposed method is well demonstrated on a dataset of 5,040 images. It can therefore serve as an automatic tool for screening BCC.

Pan-cancer analyses attempt to discover similar features among multiple cancers to identify fundamental patterns common to cancer development and progression. A pan-cancer analysis integrating both protein expression and transcriptomic data is important because it can identify genes that are linked to proteins potentially responsible for a patient's status. This study aims to identify differentially expressed (DE) genes between early and advanced cases of multiple cancer types through the usage of RNA sequencing data. The relevance of these genes is further investigated by developing predictive models using K-nearest neighbor and linear discriminant analysis classifiers. The use of cancer-specific and non-cancer specific features resulted in several moderately performing models. Highlighted genes were further investigated to determine if they encoded for proteins identified in a previously conducted pan-cancer analysis. The results of this study suggest that a pan-cancer analysis may be highly complementary to standard analyses of individual cancers for identifying biologically relevant DE genes and can assist in developing effective predictive models for cancer progression.

The exact measure of mitotic nuclei is a crucial parameter in breast cancer grading and prognosis. This can be achieved by improving the mitotic detection accuracy by careful design of segmentation and classification techniques. In this paper, segmentation of nuclei from breast histopathology images are carried out by Localized Active Contour Model (LACM) utilizing bio-inspired optimization techniques in the detection stage, in order to handle diffused intensities present along object boundaries. Further, the application of a new optimal machine learning algorithm capable of classifying strong non-linear data such as Random Kitchen Sink (RKS), shows improved classification performance. The proposed method has been tested on Mitosis detection in breast cancer histological images (MITOS) dataset provided for MITOS-ATYPIA CONTEST 2014. The proposed framework achieved 95% recall, 98% precision and 96% F-score.

Breast cancer is the most common malignant tumor in women worldwide. In recent years, there has been an increasing use of immunohistochemistry (the process of detecting the expression of certain proteins in cytological images) to obtain useful information for diagnosis. This paper presents an efficient algorithm that automatically detects breast cancer cell nuclei and divides them into two groups: those that express the ER marker and those that do not. First, the areas that belong to the carcinoma are automatically identified. Then, the algorithm evaluates features such as size and shape to correctly segment the nuclei in these fields. Finally, the Fuzzy C-Means algorithm is used to classify the detected nuclei. The method proposed was evaluated with a set of 10 images which contained 4093 cell nuclei. The algorithm correctly identified 93.1% of the nuclei, and sensitivity and specificity of the classification were 95.7% and 93.2% respectively.

Oral cancer is one of the most prevalent form of cancer and its severity is aggrandized specially among the socio-economically backward population in developing countries. A major fraction of patient population is unable to avail diagnosis for oral cancer due to scarcity of state-of-the-art infrastructure and experienced oral and maxillofacial pathologist. Contemporary gold standard of oral cancer confirmation relies on biopsy report. But biopsy is invasive and thus patients are usually reluctant to undergo this test. Moreover, biopsy yields considerable false negatives if investigated tissue is not collected precisely from the carcinogenic location. Till date, there is dearth of computer aided pre-screening tool for detection of oral cancer. The paper presents Digital Infrared Thermal Imaging as a viable modality for early screening of oral cancer. This is the pioneering attempt to discriminate normal subjects from patients by leveraging discriminating texture features on oral thermograms. Statistically significant texture features were selected from a) both halves of frontal face and b) right and left profile faces. Due to disparity of distribution of facial temperature between normal subjects and patients, the corresponding texture features form discriminative class specific local clusters. Such local conglomeration was exploited using k-means and fuzzy k-means clustering. We adopt the concept of cluster prototype classifier which assigns label to each cluster according to majority class labels within that cluster. Highest classification accuracy of 86.12% is attained on fusion of features from left and right half of frontal face of precancerous subject followed by fuzzy k-means guided cluster prototype classification. The proposed work outperforms our previously developed pre-screening framework by upto 6.5%. Such promising results boosts the viability of our approach.

Melanoma, most threatening type of skin cancer, is on the rise. In this paper an implementation of a deep-learning system on a computer server, equipped with graphic processing unit (GPU), is proposed for detection of melanoma lesions. Clinical (non-dermoscopic) images are used in the proposed system, which could assist a dermatologist in early diagnosis of this type of skin cancer. In the proposed system, input clinical images, which could contain illumination and noise effects, are preprocessed in order to reduce such artifacts. Afterward, the enhanced images are fed to a pre-trained convolutional neural network (CNN) which is a member of deep learning models. The CNN classifier, which is trained by large number of training samples, distinguishes between melanoma and benign cases. Experimental results show that the proposed method is superior in terms of diagnostic accuracy in comparison with the state-of-the-art methods.

Deep learning and unsupervised feature learning have received great attention in past years for their ability to transform input data into high level representations using machine learning techniques. Such interest has been growing steadily in the field of medical image diagnosis, particularly in melanoma classification. In this paper, a novel application of deep learning (stacked sparse auto-encoders) is presented for skin lesion classification task. The stacked sparse auto-encoder discovers latent information features in input images (pixel intensities). These high-level features are subsequently fed into a classifier for classifying dermoscopy images. In addition, we proposed a new deep neural network architecture based on bag-of-features (BoF) model, which learns high-level image representation and maps images into BoF space. Then, we examine how using this deep representation of BoF, compared with pixel intensities of images, can improve the classification accuracy. The proposed method is evaluated on a test set of 244 skin images. To test the performance of the proposed method, the area under the receiver operating characteristics curve (AUC) is utilized. The proposed method is found to achieve 95% accuracy.

This paper presents a robust segmentation method based on multi-scale classification to identify the lesion boundary in dermoscopic images. Our proposed method leverages a collection of classifiers which are trained at various resolutions to categorize each pixel as "lesion" or "surrounding skin". In detection phase, trained classifiers are applied on new images. The classifier outputs are fused at pixel level to build probability maps which represent lesion saliency maps. In the next step, Otsu thresholding is applied to convert the saliency maps to binary masks, which determine the border of the lesions. We compared our proposed method with existing lesion segmentation methods proposed in the literature using two dermoscopy data sets (International Skin Imaging Collaboration and Pedro Hispano Hospital) which demonstrates the superiority of our method with Dice Coefficient of 0.91 and accuracy of 94%.

Automatic and reliable diagnosis of skin cancer, as a smartphone application, is of great interest. Among different types of skin cancers, melanoma is the most dangerous one which causes most deaths. Meanwhile, melanoma is curable if it were diagnosed in its early stages. In this paper we propose an efficient system for prescreening of pigmented skin lesions for malignancy using general-purpose digital cameras. These images can be captured by a smartphone or a digital camera. This could be beneficial in different applications, such as computer aided diagnosis and telemedicine applications. It could assist dermatologists, or smartphone users, evaluate risk of suspicious moles. The proposed method enhances borders and extracts a broad set of dermatologically important features. These discriminative features allow classification of lesions into two groups of melanoma and benign. This method is computationally appropriate as a smartphone application. Experimental results show that our proposed method is superior in diagnosis accuracy compared to state-of-the-art methods.

Automated prostate diagnoses and treatments have gained much attention due to the high mortality rate of prostate cancer. In particular, unsupervised (automatic) prostate segmentation is an active and challenging research. Most conventional works usually utilize handcrafted (low-level) features for prostate segmentation; however they often fail to extract the intrinsic structure of the prostate, especially on images with blurred boundaries. In this paper, we propose a novel automated prostate segmentation model with learned features from deep network. Specifically, we first generate a set of prostate proposals in transverse plane via recognizing the position and coarse estimate of the shape of the prostate on the global prostate image and using the deep network to extract highly effective features for the boundary refinement in a finer scale. With consideration of the correlations among different sequential images, we then construct a graph to select the best prostate proposals from proposal set for its use in 3D prostate segmentation. Experimental evaluation demonstrates that our proposed deep network and graph based method is superior to state-of-the-art couterparts, in terms of both dice similarity coefficient and Hausdorff distance, on public dataset.

Nrf2 acts as a sensor of oxidative or electrophilic stress and prevents genome instability. The activation of Nrf2 signaling induces ARE-dependent expression of detoxifying and antioxidant defense proteins. Nrf2-ARE signaling has become an attractive target for cancer chemoprevention. On the other hand, constitutive over-activation of Nrf2 in cancer cells has been implicated in cancer progression as well as in resistance to cancer chemotherapeutics. Two basic Nrf2 activation pathways were described. The canonical pathway is the primary mechanism of Nrf2 activation and is based on dissociation of Nrf2 from its inactive complex with the repressor protein Keap1 and the subsequent translocation of Nrf2 into the nucleus. Numerous proteins which compete with Nrf2 for Keap1 binding stabilize Nrf2 and are involved in non-canonical pathways of Nrf2 activation. However, growing evidence indicates that the regulation of Keap1-Nrf2-ARE is more complex than was previously thought and that other molecular mechanisms are also involved. Among them is epigenetic regulation of Nrf2 and Keap1, which seems to be a particularly interesting subject for future studies. Nrf2 has become an important chemopreventive and therapeutic target, and many natural and synthetic chemicals have been described as its modulators. However, most small molecules which are either inducers or inhibitors of Nrf2 may provoke "off-target" toxic effects because of their electrophilic character. This review highlights Nrf2-ARE activation pathways and their role in cancer prevention and therapy. A critical evaluation of currently available Nrf2 inducers and inhibitors is also presented.

The delivery of safe and effective radiation therapy relies on accurate target delineation, particularly in the era of highly conformal treatment techniques. Current contouring resources are fragmented and can be cumbersome to use. The present study reports on the efficacy and usability of a web-based contouring atlas compared with those of existing contouring resources in a randomized trial.

We describe the case of a sinonasal adamantinoma-like Ewing sarcoma in a 41-year-old male. Histologically, the tumor exhibited distinctive areas of nested growth pattern with prominent stromal fibrosis and metaplastic bone formation. The tumor cells were small and uniform with minimal amount of pale eosinophilic to clear cytoplasm and round or oval nuclei with finely dispersed chromatin and small nucleoli. Approximately 20% of the tumor parenchyma comprised of small clusters of basaloid cells within an osteofibrous background resembling adamantinoma. The tumor showed strong expression of keratins, p63, CD99 and Fli-1, and EWSR1 rearrangement. The diagnosis of sinonasal Ewing family tumors is particularly problematic owing to the large number of potential mimics. For any poorly differentiated or undifferentiated head and neck tumor, cellular monotony and CD99 immunoreactivity should prompt consideration for molecular studies that include analysis of both EWSR1 and FLI1, even in the presence of strong cytokeratin expression or focal keratinization.