The TB Portals: an Open-Access, Web-Based Platform for Global Drug-Resistant-Tuberculosis Data Sharing and Analysis.

The TB Portals program is an international consortium of physicians, radiologists, and microbiologists from countries with a heavy burden of drug-resistant tuberculosis working with data scientists and information technology professionals. Together, we have built the TB Portals, a repository of socioeconomic/geographic, clinical, laboratory, radiological, and genomic data from patient cases of drug-resistant tuberculosis backed by shareable, physical samples. Currently, there are 1,299 total cases from five country sites (Azerbaijan, Belarus, Moldova, Georgia, and Romania), 976 (75.1%) of which are multidrug or extensively drug resistant and 38.2%, 51.9%, and 36.3% of which contain X-ray, computed tomography (CT) scan, and genomic data, respectively. The top Mycobacterium tuberculosis lineages represented among collected samples are Beijing, T1, and H3, and single nucleotide polymorphisms (SNPs) that confer resistance to isoniazid, rifampin, ofloxacin, and moxifloxacin occur the most frequently. These data and samples have promoted drug discovery efforts and research into genomics and quantitative image analysis to improve diagnostics while also serving as a valuable resource for researchers and clinical providers. The TB Portals database and associated projects are continually growing, and we invite new partners and collaborations to our initiative. The TB Portals data and their associated analytical and statistical tools are freely available at https://tbportals.niaid.nih.gov/.

Cell calcification reverses the chemoresistance of cancer cells via the conversion of glycolipid metabolism.

Drug resistance is an inherent challenge during cancer chemotherapy. Cancer cells favor fatty acid metabolism through metabolic reprogramming to achieve therapeutic resistance. However, an effective approach to overcoming the switch from glycolysis-dependent to fatty acid beta-oxidation-dependent anabolic and energy metabolism remains elusive. Here, we developed a macromolecular drug (folate-polySia, FpSA) to induce the extracellular microcalcification of cervical cancer cells with cisplatin resistance. Microcalcification attenuated the uptake of fatty acids and the beta-oxidation of fatty acids by mitochondrial dysfunction but boosted the glycolysis pathway. Consequently, cotreatment with Pt and FpSA inhibited cisplatin-resistant tumor growth and improved tumor-bearing mice's survival rates, indicating that FpSA switched fatty acid metabolism to glycolysis to sensitize cisplatin-resistant cells further. Taken together, cancer cell calcification induced by FpSA provides a reprogramming metabolic strategy for the treatment of chemotherapy-resistant tumors.

Rapid artificial intelligence solutions in a pandemic-The COVID-19-20 Lung CT Lesion Segmentation Challenge.

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge - 2020.

Rapid Artificial Intelligence Solutions in a Pandemic - The COVID-19-20 Lung CT Lesion Segmentation Challenge.

Artificial intelligence (AI) methods for the automatic detection and quantification of COVID-19 lesions in chest computed tomography (CT) might play an important role in the monitoring and management of the disease. We organized an international challenge and competition for the development and comparison of AI algorithms for this task, which we supported with public data and state-of-the-art benchmark methods. Board Certified Radiologists annotated 295 public images from two sources (A and B) for algorithms training (n=199, source A), validation (n=50, source A) and testing (n=23, source A; n=23, source B). There were 1,096 registered teams of which 225 and 98 completed the validation and testing phases, respectively. The challenge showed that AI models could be rapidly designed by diverse teams with the potential to measure disease or facilitate timely and patient-specific interventions. This paper provides an overview and the major outcomes of the COVID-19 Lung CT Lesion Segmentation Challenge - 2020.

Grayscale representation of infrared microscopy images by extended multiplicative signal correction for registration with histological images.

Fourier-transform infrared (FTIR) microspectroscopy is rounding the corner to become a label-free routine method for cancer diagnosis. In order to build infrared-spectral based classifiers, infrared images need to be registered with Hematoxylin and Eosin (H&E) stained histological images. While FTIR images have a deep spectral domain with thousands of channels carrying chemical and scatter information, the H&E images have only three color channels for each pixel and carry mainly morphological information. Therefore, image representations of infrared images are needed that match the morphological information in H&E images. In this paper, we propose a novel approach for representation of FTIR images based on extended multiplicative signal correction highlighting morphological features that showed to correlate well with morphological information in H&E images. Based on the obtained representations, we developed a strategy for global-to-local image registration for FTIR images and H&E stained histological images of parallel tissue sections.

Predicting breast tumor proliferation from whole-slide images: The TUPAC16 challenge.

Tumor proliferation is an important biomarker indicative of the prognosis of breast cancer patients. Assessment of tumor proliferation in a clinical setting is a highly subjective and labor-intensive task. Previous efforts to automate tumor proliferation assessment by image analysis only focused on mitosis detection in predefined tumor regions. However, in a real-world scenario, automatic mitosis detection should be performed in whole-slide images (WSIs) and an automatic method should be able to produce a tumor proliferation score given a WSI as input. To address this, we organized the TUmor Proliferation Assessment Challenge 2016 (TUPAC16) on prediction of tumor proliferation scores from WSIs. The challenge dataset consisted of 500 training and 321 testing breast cancer histopathology WSIs. In order to ensure fair and independent evaluation, only the ground truth for the training dataset was provided to the challenge participants. The first task of the challenge was to predict mitotic scores, i.e., to reproduce the manual method of assessing tumor proliferation by a pathologist. The second task was to predict the gene expression based PAM50 proliferation scores from the WSI. The best performing automatic method for the first task achieved a quadratic-weighted Cohen's kappa score of κ = 0.567, 95% CI [0.464, 0.671] between the predicted scores and the ground truth. For the second task, the predictions of the top method had a Spearman's correlation coefficient of r = 0.617, 95% CI [0.581 0.651] with the ground truth. This was the first comparison study that investigated tumor proliferation assessment from WSIs. The achieved results are promising given the difficulty of the tasks and weakly-labeled nature of the ground truth. However, further research is needed to improve the practical utility of image analysis methods for this task.

Texture anisotropy of the brain's white matter as revealed by anatomical MRI.

The purpose of this work was to study specific texture properties of the brain's white matter (WM) based on conventional high-resolution T1-weighted magnetic resonance imaging (MRI) datasets. Quantitative parameters anisotropy and laminarity were derived from 3-D texture analysis. Differences in WM texture associated with gender were evaluated on an age-matched sample of 210 young healthy subjects (mean age 24.8, SD 3.97 years, 103 males and 107 females). Changes of WM texture with age were studied using 112 MRI-T1 datasets of healthy subjects aged 16 to 70 years (57 males and 55 females). Both texture measures indicated a "more regular" WM structure in females (p < 10(-6)). An age-related deterioration of WM structure manifests itself as a remarkable decline of both parameters (p < 10(-6)) that is more prominent in females (p < 10(-6)) than in males (p = 0.02). Texture analysis of anatomical MRI-T1 brain datasets provides quantitative information about macroscopic WM characteristics and helps discriminating between normal and pathological aging.

Three-dimensional nonlinear invisible boundary detection.

The human vision system can discriminate regions which differ up to the second-order statistics only. We present an algorithm designed to reveal "hidden" boundaries in gray level images, by computing gradients in higher order statistics of the data. We demonstrate it by applying it to the identification of possible "hidden" boundaries of glioblastomas as manifest themselves in three-dimensional (3-D) MRI scans, using a model driven approach. We also demonstrate the method using a nonmodel driven approach where we have no prior information about the location of possible boundaries. In this case, we use 3-D MRI data concerning schizophrenic patients and normal controls.

Detection of structural differences between the brains of schizophrenic patients and controls.

This paper investigates the validity of the null hypothesis: there are no structural differences between the brains of schizophrenic and normal control subjects that manifest themselves in MRI-T(2) data and distinguish the two populations in a statistically significant way. The data used refer to 21 schizophrenic patients and 19 normal controls, matched for age, sex and social background. The methodology used is based on three-dimensional texture analysis, which is used to quantify anisotropy in the data at scales of the order of a few millimetres. These data reject the null hypothesis. In addition, this article attempts to identify the regions of the brain that are responsible for the morphological characteristics that distinguish the two populations. For this purpose, it utilises a second texture analysis method that, in spite of being a global method, allows one to trace back to the data the origin of the features that most distinctly distinguish the two populations. This method indicates that the features that distinguish the two populations with P values smaller than 10(-6) are located in the most inferior part of the brain and in particular in the tissue that makes up the sulci. It is stressed that in order to preserve the integrity of the data for texture calculations, no registration of anatomical structures is performed, and the most inferior part of the brain is identified as referring to those slices of the scans that visually correspond to slices 1-12 of the Talairach and Tournoux brain atlas.

Segmentation of cell nuclei in heterogeneous microscopy images: a reshapable templates approach.

Histological tissue images typically exhibit very sophisticated spatial color patterns. It is of great clinical importance to extract qualitative and quantitative information from these images. As an ad hoc solution, various unsupervised approaches address the object detection and segmentation problem which are suitable for limited classes of histology images. In this paper, we propose a general purpose localization and segmentation method which utilizes reshapable templates. The method combines both pixel- and object-level features for detecting regions of interest. Segmentation is carried out in two levels including both the coarse and fine ones. A set of simple-shaped templates is used for coarse segmentation. A content based template reshaping algorithm is proposed for fine segmentation of target objects. Experimentation was done using a publicly available image data set which contains 7931 manually labeled cells of heterogeneous histology images. The experiments have demonstrated acceptable level of detection and segmentation results for the proposed approach (precision=0.904, recall=0.870 and Zijdenbos similarity index=73%). Thus, the prototype software developed based on proposed method can be considered as a potential tool for pathologists in clinical process.

Computer-aided Image Processing of Angiogenic Histological.

UNLABELLED: This article reviews the questions regarding the image evaluation of angiogeneic histological samples, particularly the ovarian epithelial cancer. Review is focused on the principles of image analysis in the field of histology and pathology. The definition, classification, pathogenesis and angiogenesis regulation in the ovaries are also briefly discussed. It is hoped that the complex image analysis together with the patient's clinical parameters will allow an acquiring of a clear pathogenic picture of the disease, extension of the differential diagnosis and become a useful tool for the evaluation of drug effects. The challenge of the assessment of angiogenesis activity is the heterogeneity of several objects: parameters derived from patient's anamnesis as well as of pathology samples. The other unresolved problems are the subjectivity of the region of interest selection and performance of the whole slide scanning. KEYWORDS: Angiogenesis; Image processing; Microvessel density; Cancer; Pathology.

Axon tracing in the adult rat optic nerve and tract after intravitreal injection of MnDPDP using a semiautomatic segmentation technique.

PURPOSE: To develop and validate an objective technique for 3D segmentation of manganese-enhanced MR images of the optic nerve/tract (ON) in adult rats to improve contrast-to-noise (CNR) calculations and use the technique to ascertain if manganese dipyridoxyl diphosphate (MnDPDP) gives sufficient Mn(2+) enhancement compared to MnCl(2) when used for functional imaging of the visual pathway. MATERIALS AND METHODS: Intravitreous injection of the manganese-releasing MR contrast agent MnDPDP (30 nmol Mn(2+)) was performed to trace the ON in adult rats (n = 4). A positive control group of rats (n = 5) received a standard preparation of MnCl(2) (200 nmol Mn(2+)), while gadodiamide (1500 nmol Gd(3+)) was administered in negative control rats (n = 2). An objective technique for 3D segmentation of the enhanced ON was developed. CNR profiles along the ON were calculated by resampling the 3D image-volume in 2D planes perpendicular to the Mn(2+) enhanced ON in 0.2 mm steps, 4 mm along the segmented ON measured from the lamina cribrosa. RESULTS: The ON was successfully segmented and CNR calculated accurately within 2 minutes in a representative 3D MR image volume. Intravitreal MnDPDP injection resulted in significant MRI contrast enhancement of the retina and ON after 12-24 hours similar to that of MnCl(2) injection. CONCLUSION: 3D semiautomated image segmentation and the use of MnDPDP can improve in vivo axon tracing based on MRI. Mn(2+) was found to be released from MnDPDP after intravitreal injection in sufficient amounts to obtain functional tracing of the adult rat primary visual pathway.

Asymmetry of SPECT perfusion image patterns as a diagnostic feature for Alzheimer's disease.

In this paper we propose a new diagnostic feature for Alzheimer's Disease (AD) which is based on assessment of the degree of inter-hemispheric asymmetry using Single Photon Emission Computed Tomography (SPECT). The asymmetry measure used represents differences in 3D perfusion image patterns in the cerebral hemispheres. We start from the simplest descriptors of brain perfusion such as the mean intensity within pairs of brain lobes, gradually increasing the resolution up to five-dimensional co-occurrence matrices. Evaluation of the method was performed using SPECT scans of 79 subjects including 42 patients with clinical diagnosis of AD and 37 controls. It was found that combination of intensity and gradient features in co-occurrence matrices captures significant differences in asymmetry values between AD and normal controls (p < 0.00003 for all cerebral lobes). Our results suggest that the asymmetry feature is useful for discriminating AD patients from normal controls as detected by SPECT.

Gender and age effects in structural brain asymmetry as measured by MRI texture analysis.

Effects of gender and age on structural brain asymmetry were studied by 3D texture analysis in 380 adults. Asymmetry is detected by comparing the complex 3D gray-scale image patterns in the left and right cerebral hemispheres as revealed by anatomical T1-weighted MRI datasets. The Talairach and Tournoux parcellation system was applied to study the asymmetry on five levels: the whole cerebrum, nine coronal sections, 12 axial sections, boxes resulting from both coronal and axial subdivisions, and by a sliding spherical window of 9 mm diameter. The analysis revealed that the brain asymmetry increases in the anterior-posterior direction starting from the central region onward. Male brains were found to be more asymmetric than female. This gender-related effect is noticeable in all brain areas but is most significant in the superior temporal gyrus, Heschl's gyrus, the adjacent white matter regions in the temporal stem and the knee of the optic radiation, the thalamus, and the posterior cingulate. The brain asymmetry increases significantly with age in the inferior frontal gyrus, anterior insula, anterior cingulate, parahippocampal gyrus, retrosplenial cortex, coronal radiata, and knee region of the internal capsule. Asymmetry decreases with age in the optic radiation, precentral gyrus, and angular gyrus. The texture-based method reported here is based on extended multisort cooccurrence matrices that employ intensity, gradient, and anisotropy features in a uniform way. It is sensitive, simple to reproduce, robust, and unbiased in the sense that segmentation of brain compartments and spatial transformations are not necessary. Thus, it should be considered as another tool for digital morphometry in neuroscience.

A new approach for improving diagnostic accuracy in Alzheimer's disease and frontal lobe dementia utilising the intrinsic properties of the SPET dataset.

Alzheimer's disease (AD) and frontal lobe dementia (FLD) show characteristic patterns of regional cerebral blood flow (rCBF). However, these patterns may overlap with those observed in the aging brain in elderly normal individuals. The aim of this study was to develop a new method for better classification and recognition of AD and FLD cases as compared with normal controls. Forty-six patients with AD, 7 patients with FLD and 34 normal controls (CTR) were included in the study. rCBF was assessed by technetium-99m hexamethylpropylene amine oxime and a three-headed single-photon emission tomography (SPET) camera. A brain atlas was used to define volumes of interest (VOIs) corresponding to the brain lobes. In addition to conventional image processing methods, based on count density/voxel, the new approach also analysed other intrinsic properties of the data by means of gradient computation steps. Hereby, five factors were assessed and tested separately: the mean count density/voxel and its histogram, the mean gradient and its histogram, and the gradient angle co-occurrence matrix. A feature vector concatenating single features was also created and tested. Preliminary feature discrimination was performed using a two-sided t-test and a K-means clustering was then used to classify the image sets into categories. Finally, five-dimensional co-occurrence matrices combining the different intrinsic properties were computed for each VOI, and their ability to recognise the group to which each individual scan belonged was investigated. For correct classification of the AD-CTR groups, the gradient histogram in the parieto-temporal lobes was the most useful single feature (accuracy 91%). FLD and CTR were better classified by the count density/voxel histogram (frontal and occipital lobes) and by the mean gradient (frontal, temporal and parietal lobes, accuracy 98%). For AD and FLD the count density/voxel histogram in the frontal, parietal and occipital lobes classified the groups with the highest accuracy (85%). The concatenated joint feature correctly classified 96% of the AD-CTR, 98% of the FLD-CTR and 94% of the AD-FLD cases. 5D co-occurrence matrices correctly recognised 98% of the AD-CTR cases, 100% of the FLD-CTR cases and 98% of the AD-FLD cases. The proposed approach classified and diagnosed AD and FLD patients with higher accuracy than conventional analytical methods used for rCBF-SPET. This was achieved by extracting from the SPET data the intrinsic information content in each of the selected VOIs.