ABSTRACT
OBJECTIVE: To evaluate the utility of low-cost simulation models to teach surgical techniques for placenta accreta spectrum (PAS), included in a multimodal education workshop for PAS. METHODS: This was an observational, survey-based study. Participants were surveyed before and after the use of low-fidelity mannequins to simulate two surgical techniques for PAS (one-step conservative surgery [OSCS] and modified subtotal hysterectomy [MSTH]), within a multimodal educational workshop. The workshops included pre-course preparation, didactics, simulated practice of the techniques using low-cost models, and viewing live surgery. RESULTS: Six OSCS/MSTH training workshops occurred across six countries and a total of 270 participants were surveyed. The responses of 127 certified obstetricians and gynecologists (OB-GYNs) were analyzed. Participants expressed favorable impressions of all components of the simulated session. Perceived anatomical simulator fidelity, scenario realism, educational component effectiveness, and self-assessed performance improvement received ratings of 4-5 (positive end of the Likert scale) from over 90% of respondents. When asked about simulation's role in technique comprehension, comfort level in technique performance, and likelihood of recommending this workshop to others, more than 75% of participants rated these aspects with a score of 4-5 (positively) on the five-point scale. CONCLUSION: Low-cost simulation, within a multimodal education strategy, is a well-accepted intervention for teaching surgical techniques for PAS.
ABSTRACT
PURPOSE: Triple-negative breast cancer (TNBC) is a highly aggressive subtype of breast cancer that lacks effective diagnostic and therapeutic options. Membrane type 1 matrix metalloproteinase (MT1-MMP) is an attractive biomarker for improving patient selection. This study aimed to develop a theranostic tool using a highly tumour-selective anti-MT1-MMP antibody (LEM2/15) radiolabelled with 89Zr for PET and 177Lu for therapy in a TNBC murine model. METHODS: The LEM2/15 antibody and IgG isotype control were radiolabelled with 89Zr. PET imaging was performed in a TNBC orthotopic mouse model at 1, 2, 4, and 7 days after administration. Tissue biodistribution and pharmacokinetic parameters were analysed and Patlak linearisation was used to calculate the influx rate of irreversible uptake. The TNBC mice were treated with [177Lu]Lu-DOTA-LEM2/15 (single- or 3-dose regimen) or saline. Efficacy of [177Lu]Lu-DOTA-LEM2/15 was evaluated as tumour growth and DNA damage (γH2AX) in MDA 231-BrM2-831 tumours. RESULTS: At 7 days post-injection, PET uptake in tumour xenografts revealed a 1.6-fold and 2.4-fold higher tumour-to-blood ratio for [89Zr]Zr-Df-LEM2/15 in the non-blocked group compared to the blocked and IgG isotype control groups, respectively. Specific uptake of LEM2/15 in TBNC tumours mediated by MT1-MMP-binding was demonstrated by the Patlak linearisation method, providing insights into the potential efficacy of LEM2/15-based treatments. A similar uptake was found for [89Zr]Zr-Df-LEM2/15 and [177Lu]Lu-DOTA-LEM2/15 in tumours 7 days post-injection (6.80 ± 1.31 vs. 5.61 ± 0.66 %ID/g). Tumour doubling time was longer in the [177Lu]Lu-DOTA-LEM2/15 3-dose regimen treated group compared to the control (50 vs. 17 days, respectively). The percentage of cells with γH2AX-foci was higher in tumours treated with [177Lu]Lu-DOTA-LEM2/15 3-dose regimen compared to tumours non-treated or treated with [177Lu]Lu-DOTA-LEM2/15 single-dose (12 % vs. 4-5 %). CONCLUSIONS: The results showed that the 89Zr/177Lu-labelled anti-MT1-MMP mAb (LEM2/15) pair facilitated immune-PET imaging and reduced tumour growth in a preclinical TNBC xenograft model.
ABSTRACT
The study examines the complex impact of climatic patterns, driven by the North Atlantic Oscillation (NAO), on regional climate, hydrology, and sea surface temperatures. Focused on the period from 2003 to 2012, the research specifically investigates the influence of thermal variability on decapod larval communities. Monthly zooplanktonic sampling conducted at the Mondego Estuary, Portugal, entrance over a decade revealed the prevalence of Carcinus maenas, Diogenes pugilator, and Pachigrapsus marmoratus larvae. These assemblages displayed notable interannual and seasonal fluctuations, often corresponding with changes in sea surface temperatures. Significant system shifts around 2007, instigated by the large-scale NAO, led to subsequent modifications in sea surface temperature and decapod larvae communities' dynamics. Post-2007, there was an upward trajectory in both species' abundance and richness. Phenologically during the former period, the community exhibited two abundance peaks, with the earlier peak occurring sooner, attributed to heightened temperatures instead of the unique peak exhibited before 2007. The research further elucidated the occurrences of Marine Heatwaves (MHW) in the region, delving into their temporal progression influenced by the NAO. Although water temperature emerged as a crucial factor influencing decapod larvae communities annually and seasonally, the study did not observe discernible impacts of MHW events on these communities. These communities represent essential trophic links and are crucial for the survival success of adult decapods. Given the rapid pace of climate change and increasing temperatures, it is imperative to assess whether these environmental shifts, particularly in thermal conditions, affect these meroplanktonic communities.
Subject(s)
Climate Change , Estuaries , Larva , Temperature , Animals , Larva/growth & development , Larva/physiology , Portugal , Decapoda/physiology , Seasons , Environmental Monitoring , Climate , Biodiversity , Zooplankton/physiologyABSTRACT
Colonoscopy is the choice procedure to diagnose, screening, and treat the colon and rectum cancer, from early detection of small precancerous lesions (polyps), to confirmation of malign masses. However, the high variability of the organ appearance and the complex shape of both the colon wall and structures of interest make this exploration difficult. Learned visuospatial and perceptual abilities mitigate technical limitations in clinical practice by proper estimation of the intestinal depth. This work introduces a novel methodology to estimate colon depth maps in single frames from monocular colonoscopy videos. The generated depth map is inferred from the shading variation of the colon wall with respect to the light source, as learned from a realistic synthetic database. Briefly, a classic convolutional neural network architecture is trained from scratch to estimate the depth map, improving sharp depth estimations in haustral folds and polyps by a custom loss function that minimizes the estimation error in edges and curvatures. The network was trained by a custom synthetic colonoscopy database herein constructed and released, composed of 248400 frames (47 videos), with depth annotations at the level of pixels. This collection comprehends 5 subsets of videos with progressively higher levels of visual complexity. Evaluation of the depth estimation with the synthetic database reached a threshold accuracy of 95.65%, and a mean-RMSE of 0.451cm, while a qualitative assessment with a real database showed consistent depth estimations, visually evaluated by the expert gastroenterologist coauthoring this paper. Finally, the method achieved competitive performance with respect to another state-of-the-art method using a public synthetic database and comparable results in a set of images with other five state-of-the-art methods. Additionally, three-dimensional reconstructions demonstrated useful approximations of the gastrointestinal tract geometry. Code for reproducing the reported results and the dataset are available at https://github.com/Cimalab-unal/ColonDepthEstimation.
Subject(s)
Colon , Colonoscopy , Databases, Factual , Humans , Colonoscopy/methods , Colon/diagnostic imaging , Neural Networks, Computer , Colonic Polyps/diagnostic imaging , Image Processing, Computer-Assisted/methodsABSTRACT
Angiosperms are the cornerstone of most terrestrial ecosystems and human livelihoods1,2. A robust understanding of angiosperm evolution is required to explain their rise to ecological dominance. So far, the angiosperm tree of life has been determined primarily by means of analyses of the plastid genome3,4. Many studies have drawn on this foundational work, such as classification and first insights into angiosperm diversification since their Mesozoic origins5-7. However, the limited and biased sampling of both taxa and genomes undermines confidence in the tree and its implications. Here, we build the tree of life for almost 8,000 (about 60%) angiosperm genera using a standardized set of 353 nuclear genes8. This 15-fold increase in genus-level sampling relative to comparable nuclear studies9 provides a critical test of earlier results and brings notable change to key groups, especially in rosids, while substantiating many previously predicted relationships. Scaling this tree to time using 200 fossils, we discovered that early angiosperm evolution was characterized by high gene tree conflict and explosive diversification, giving rise to more than 80% of extant angiosperm orders. Steady diversification ensued through the remaining Mesozoic Era until rates resurged in the Cenozoic Era, concurrent with decreasing global temperatures and tightly linked with gene tree conflict. Taken together, our extensive sampling combined with advanced phylogenomic methods shows the deep history and full complexity in the evolution of a megadiverse clade.
Subject(s)
Evolution, Molecular , Genes, Plant , Genomics , Magnoliopsida , Phylogeny , Fossils , Genes, Plant/genetics , Magnoliopsida/genetics , Magnoliopsida/classification , Nuclear Proteins/geneticsABSTRACT
Subsequent to mass vaccination programs against COVID-19, diverse side effects have been described, both at the injection site, such as pain, redness and swelling, and systemic effects such as fatigue, headache, muscle or joint pain. On rare occasions, a lymphadenopathic syndrome may develop, raising the clinical suspicion of a lymphoproliferative disorder. We present the case of a 30-year-old woman who developed self-limiting left axillary lymphadenopathy following COVID-19 vaccination. To date, only seven similar cases with a complete clinicopathological description have been published, and fourteen cases have been notified to the European adverse events databases (Eudravigilance) in relationship with vaccination against COVID-19. It is important to be aware of this potential complication when a lymphadenopathic syndrome develops following vaccination, to avoid unnecessary treatment.
Subject(s)
COVID-19 Vaccines , COVID-19 , Histiocytic Necrotizing Lymphadenitis , Adult , Female , Humans , COVID-19/prevention & control , COVID-19 Vaccines/adverse effects , Dendritic Cells , Histiocytic Necrotizing Lymphadenitis/etiology , Lymph Nodes , VaccinationABSTRACT
Disease interpretation by computer-aided diagnosis systems in digital pathology depends on reliable detection and segmentation of nuclei in hematoxylin and eosin (HE) images. These 2 tasks are challenging since appearance of both cell nuclei and background structures are very variable. This paper presents a method to improve nuclei detection and segmentation in HE images by removing tiles that only contain background information. The method divides each image into smaller patches and uses their projection to the noiselet space to capture different spatial features from non-nuclei background and nuclei structures. The noiselet features are clustered by a K-means algorithm and the resultant partition, defined by the cluster centroids, is herein named the noiselet code-book. A part of an image, a tile, is divided into patches and represented by the histogram of occurrences of the projected patches in the noiselet code-book. Finally, with these histograms, a classifier learns to differentiate between nuclei and non-nuclei tiles. By applying a conventional watershed-marked method to detect and segment nuclei, evaluation consisted in comparing pure watershed method against denoising-plus-watershed in an open database with 8 different types of tissues. The averaged F-score of nuclei detection improved from 0.830 to 0.86 and the dice score after segmentation increased from 0.701 to 0.723.
ABSTRACT
Proton therapy allows the treatment of specific areas and avoids the surrounding tissues. However, this technique has uncertainties in terms of the distal dose fall-off. A promising approach to studying the proton range is the use of nanoparticles as proton-activatable agents that produce detectable signals. For this, we developed an iron oxide nanoparticle doped with Zn (IONP@Zn-cit) with a hydrodynamic size of 10 nm and stability in serum. Cytotoxicity, defined as half of the surveillance, was 100 µg Zn/mL in the U251 cell line. The effect on clonogenic cell death was tested after X-ray irradiation, which suggested a radioprotective effect of these nanoparticles at low concentrations (1-10 µg Zn/mL). To evaluate the production of positron emitters and prompt-gamma signals, IONP@Zn-cit was irradiated with protons, obtaining prompt-gamma signals at the lowest measured concentration (10 mg Zn/mL). Finally, 67Ga-IONP@Zn-cit showed accumulation in the liver and spleen and an accumulation in the tumor tissue of 0.95% ID/g in a mouse model of U251 cells. These results suggest the possibility of using Zn nanoparticles as proton-activatable agents to verify the range by prompt gamma detection and face the challenges of prompt gamma detection in a specific biological situation, opening different avenues to go forward in this field.
Subject(s)
Nanoparticles , Proton Therapy , Animals , Mice , Protons , Proton Therapy/methods , Zinc/pharmacology , Magnetic Iron Oxide NanoparticlesABSTRACT
Acute leukemia is usually diagnosed when a test of peripheral blood shows at least 20% of abnormal immature cells (blasts), a figure even lower in case of recurrent cytogenetic abnormalities. Blast identification is crucial for white blood cell (WBC) counting, which depends on both identifying the cell type and characterizing the cellular morphology, processes susceptible of inter- and intraobserver variability. The present work introduces an image combined-descriptor to detect blasts and determine their probable lineage. This strategy uses an intra-nucleus mosaic pattern (InMop) descriptor that captures subtle nuclei differences within WBCs, and Haralick's statistics which quantify the local structure of both nucleus and cytoplasm. The InMop captures WBC inner-nucleus structure by applying a multiscale Shearlet decomposition over a repetitive pattern (mosaic) of automatically-segmented nuclei. As a complement, Haralick's statistics characterize the local structure of the whole cell from an intensity co-occurrence matrix representation. Both InMoP and Haralick-based descriptors are calculated using the b-channel from Lab color-space. The combined-descriptor is assessed by differentiating blasts from nonleukemic cells with support vector machine (SVM) classifiers and different transformation kernels, in two public and independent databases. The first database-D1 (n = 260) is composed of healthy and acute lymphoid leukemia (ALL) single cell images, and second database-D2 contains acute myeloid leukemia (AML) blasts (n = 3294) and nonblast (n = 15,071) cell images. In a first experiment, blasts versus nonblast differentiation is performed by training with a subset of D2 (n = 6588) and testing in D1 (n = 260), obtaining a training AUC of 0.991 ± 0.002 and AUC = 0.782 for the independent validation. A second experiment automatically differentiates AML blasts (260 images from D2) from ALL blasts (260 images from D1), with an AUC of 0.93. In a third experiment, state-of-the-art strategies, VGG16 and RESNEXT convolutional neural networks (CNN), separate blast from nonblast cells in both databases. The VGG16 showed an AUC of 0.673 and the RESNEXT of 0.75. Reported metrics for all the experiments are area under the ROC curve (AUC), accuracy and F1-score.
Subject(s)
Leukemia, Myeloid, Acute , Humans , Leukemia, Myeloid, Acute/diagnosis , Leukocytes , Leukocyte Count , CytoplasmABSTRACT
The tumor immune composition influences prognosis and treatment sensitivity in lung cancer. The presence of effective adaptive immune responses is associated with increased clinical benefit after immune checkpoint blockers. Conversely, immunotherapy resistance can occur as a consequence of local T-cell exhaustion/dysfunction and upregulation of immunosuppressive signals and regulatory cells. Consequently, merely measuring the amount of tumor-infiltrating lymphocytes (TILs) may not accurately reflect the complexity of tumor-immune interactions and T-cell functional states and may not be valuable as a treatment-specific biomarker. In this work, we investigate an immune-related biomarker (PhenoTIL) and its value in associating with treatment-specific outcomes in non-small cell lung cancer (NSCLC). PhenoTIL is a novel computational pathology approach that uses machine learning to capture spatial interplay and infer functional features of immune cell niches associated with tumor rejection and patient outcomes. PhenoTIL's advantage is the computational characterization of the tumor immune microenvironment extracted from H&E-stained preparations. Association with clinical outcome and major non-small cell lung cancer (NSCLC) histology variants was studied in baseline tumor specimens from 1,774 lung cancer patients treated with immunotherapy and/or chemotherapy, including the clinical trial Checkmate 057 (NCT01673867).
ABSTRACT
Dispersal shapes population connectivity and plays a critical role in marine metacommunities. Prominent species for coastal socioecological systems, such as jellyfish and spiny lobsters, feature long pelagic dispersal phases (LPDPs), which have long been overlooked. Here, we use a cross-scale approach combining field surveys of these species with a high-resolution hydrodynamic model to decipher the underlying mechanisms of LPDP patterns in northwestern Mediterranean shores. We identified basin-scale prevailing dispersal routes and synchronic year-to-year patterns tightly linked to prominent circulation features typical of marginal seas and semienclosed basins, with an outstanding role of a retentive source area replenishing shores and potentially acting as a pelagic nursery area. We show how the atmospheric forcing of the ocean, a marked hydrological driver of the Mediterranean Sea, modulates dispersal routes and sources of LPDP at interannual scales. These findings represent a crucial advance in our understanding of the functioning of metapopulations of species with LPDP in marginal seas and may contribute to the effective management of coastal ecosystem services in the face of climate change.
Subject(s)
Ecosystem , Scyphozoa , Animals , Mediterranean Sea , Climate ChangeABSTRACT
The rising demand of ecosystem services, due to the increasing human population in coastal areas, and the subsequent need to secure healthy and sustainable seas constitute a major challenge for marine ecosystems management. In addition, global anthropogenic changes have transformed the marine realm, thereby challenging ecosystem health and the services necessary for human welfare. These changes have opened ecological space for opportunistic organisms, such as jellyfish, resulting in ecosystem-wide and economic implications that threaten marine ecosystem services. Here, we used a comprehensive dataset of jellyfish hazards over the period 1960-2019 to track their dynamics and implications for human welfare. Our results revealed that their large-scale patterns have been mainly enhanced in human-perturbed Large Marine Ecosystems, although the contribution of jellyfish Class to hazard type changed across ocean regions. The long-term variability of these events suggests that their temporal patterns mirror the pace of ocean warming and ocean health degradation nurtured by global anthropogenic changes in recent decades. These results warn of the wide socioecological risks of jellyfish hazards, and their implications advocate for transboundary, regional cooperation to develop effective ecosystem-based management actions. Failure to integrate jellyfish into ocean surveys will compromise coastal ecosystem services governance. Classification: Social Sciences/Sustainability Science, Biological Sciences/Ecology.
Subject(s)
Ecosystem , Humans , Oceans and SeasABSTRACT
Triple-negative breast cancer (TNBC) is characterized by aggressiveness and high rates of metastasis. The identification of relevant biomarkers is crucial to improve outcomes for TNBC patients. Membrane type 1-matrix metalloproteinase (MT1-MMP) could be a good candidate because its expression has been reported to correlate with tumor malignancy, progression and metastasis. Moreover, single-domain variable regions (VHHs or Nanobodies) derived from camelid heavy-chain-only antibodies have demonstrated improvements in tissue penetration and blood clearance, important characteristics for cancer imaging. Here, we have developed a nanobody-based PET imaging strategy for TNBC detection that targets MT1-MMP. A llama-derived library was screened against the catalytic domain of MT1-MMP and a panel of specific nanobodies were identified. After a deep characterization, two nanobodies were selected to be labeled with gallium-68 (68Ga). ImmunoPET imaging with both ([68Ga]Ga-NOTA-3TPA14 and [68Ga]Ga-NOTA-3CMP75) in a TNBC mouse model showed precise tumor-targeting capacity in vivo with high signal-to-background ratios. (68Ga)Ga-NOTA-3CMP75 exhibited higher tumor uptake compared to (68Ga)Ga-NOTA-3TPA14. Furthermore, imaging data correlated perfectly with the immunohistochemistry staining results. In conclusion, we found a promising candidate for nanobody-based PET imaging to be further investigated as a diagnostic tool in TNBC.
ABSTRACT
BACKGROUND: Most studies using diffusion-weighted MRI (DW-MRI) in Alzheimer's disease (AD) have focused their analyses on white matter (WM) microstructural changes using the diffusion (kurtosis) tensor model. Although recent works have addressed some limitations of the tensor model, such as the representation of crossing fibers and partial volume effects with cerebrospinal fluid (CSF), the focus remains in modeling and analyzing the WM. OBJECTIVE: In this work, we present a brain analysis approach for DW-MRI that disentangles multiple tissue compartments as well as micro- and macroscopic effects to investigate differences between groups of subjects in the AD continuum and controls. METHODS: By means of the multi-tissue constrained spherical deconvolution of multi-shell DW-MRI, underlying brain tissue is modeled with a WM fiber orientation distribution function along with the contributions of gray matter (GM) and CSF to the diffusion signal. From this multi-tissue model, a set of measures capturing tissue diffusivity properties and morphology are extracted. Group differences were interrogated following fixel-, voxel-, and tensor-based morphometry approaches while including strong FWE control across multiple comparisons. RESULTS: Abnormalities related to AD stages were detected in WM tracts including the splenium, cingulum, longitudinal fasciculi, and corticospinal tract. Changes in tissue composition were identified, particularly in the medial temporal lobe and superior longitudinal fasciculus. CONCLUSION: This analysis framework constitutes a comprehensive approach allowing simultaneous macro and microscopic assessment of WM, GM, and CSF, from a single DW-MRI dataset.
Subject(s)
Alzheimer Disease , White Matter , Humans , Diffusion Magnetic Resonance Imaging , Alzheimer Disease/diagnostic imaging , Diffusion Tensor Imaging , White Matter/diagnostic imaging , White Matter/anatomy & histology , Brain/diagnostic imaging , Brain/anatomy & histologyABSTRACT
We determine the presence of four open-form configurational isomers for an unsubstituted metastable-state photoacid (mPAH) of the tricyanofuran (TCF) type in solution, at room temperature, via 2D NMR experiments. Electronic structure calculations are carried out to predict the relative stability of the isomers found experimentally and their isomerization barriers. According to the calculated rate constants for isomerization, the molecule can freely interconvert between the open-form isomers, thereby providing a thermal pathway between the isomers that might be better suited to access the cyclized closed-form configuration and those that are not. In establishing the open form isomeric makeup of the TCF mPAH under study, this work establishes the need to consider the four isomers in further studies on the thermal and excited-state isomerization processes and substituent effect thereon.
ABSTRACT
Pancreatic cancer (PC) has a reported mortality of 98% and a 5-y survival rate of 6.7%. Experienced gastroenterologists detect 80% of those with early-stage PC by endoscopic ultrasonography (EUS). Here we propose an automatic second reader strategy to detect PC in an entire EUS procedure, rather than focusing on pre-selected frames, as the state-of-the-art methods do. The method unmasks echo tumoral patterns in frames with a high probability of tumor. First, speeded up robust features define a set of interest points with correlated heterogeneities among different filtering scales. Afterward, intensity gradients of each interest point are summarized by 64 features at certain locations and scales. A frame feature vector is built by concatenating statistics of each feature of the 15 groups of scales. Then, binary classification is performed by Support Vector Machine and Adaboost models. Evaluation was performed using a data set comprising 55 participants, 18 of PC class (16,585 frames) and 37 subjects of non-PC class (49,664 frames), randomly splitting 10 times. The proposed method reached an accuracy of 92.1%, sensitivity of 96.3% and specificity of 87.8.3%. The observed results are also stable in noisy experiments while deep learning approaches fail to maintain similar performance.
Subject(s)
Endosonography , Pancreatic Neoplasms , Endosonography/methods , Humans , Pancreas/diagnostic imaging , Pancreas/pathology , Pancreatic Neoplasms/diagnostic imaging , Pancreatic Neoplasms/pathology , Support Vector Machine , Pancreatic NeoplasmsABSTRACT
INTRODUCTION AND OBJECTIVES: Myocardial dysfunction contributes to early mortality (24-72 hours) among survivors of a cardiac arrest (CA). The benefits of mechanical support in refractory shock should be balanced against the patient's potential for neurological recovery. To date, these early treatment decisions have been taken based on limited information leading mainly to undertreatment. Therefore, there is a need for early, reliable, accessible, and simple tools that offer information on the possibilities of neurological improvement. METHODS: We collected data from bispectral index (BIS) and suppression ratio (SR) monitoring of adult comatose survivors of CA managed with targeted temperature management (TTM). Neurological status was assessed according to the Cerebral Performance Category (CPC) scale. RESULTS: We included 340 patients. At the first full neurological evaluation, 211 patients (62.1%) achieved good outcome or CPC 1-2. Mean BIS values were significantly higher and median SR lower in patients with CPC 1-2. An average BIS> 26 during first 12 hours of TTM predicted good outcome with 89.5% sensitivity and 75.8% specificity (AUC of 0.869), while average SR values> 24 during the first 12 hours of TTM predicted poor outcome (CPC 3-5) with 91.5% sensitivity and 81.8% specificity (AUC, 0.906). Hourly BIS and SR values exhibited good predictive performance (AUC> 0.85), as soon as hour 2 for SR and hour 4 for BIS. CONCLUSIONS: BIS/SR are associated with patients' potential for neurological recovery after CA. This finding could help to create awareness of the possibility of a better outcome in patients who might otherwise be wrongly considered as nonviable and to establish personalized treatment escalation plans.
Subject(s)
Heart Arrest , Hypothermia, Induced , Out-of-Hospital Cardiac Arrest , Adult , Humans , Prognosis , Hypothermia, Induced/adverse effectsABSTRACT
BACKGROUND AND OBJECTIVE: Abnormalities of the heart motion reveal the presence of a disease. However, a quantitative interpretation of the motion is still a challenge due to the complex dynamics of the heart. This work proposes a quantitative characterization of regional cardiac motion patterns in cine magnetic resonance imaging (MRI) by a novel spatio-temporal saliency descriptor. METHOD: The strategy starts by dividing the cardiac sequence into a progression of scales which are in due turn mapped to a feature space of regional orientation changes, mimicking the multi-resolution decomposition of oriented primitive changes of visual systems. These changes are estimated as the difference between a particular time and the rest of the sequence. This decomposition is then temporarily and regionally integrated for a particular orientation and then for the set of different orientations. A final spatio-temporal 4D saliency map is obtained as the summation of the previously integrated information for the available scales. The saliency dispersion of this map was computed in standard cardiac locations as a measure of the regional motion pattern and was applied to discriminate control and hypertrophic cardiomyopathy (HCM) subjects during the diastolic phase. RESULTS: Salient motion patterns were estimated from an experimental set, which consisted of 3D sequences acquired by MRI from 108 subjects (33 control, 35 HCM, 20 dilated cardiomyopathy (DCM), and 20 myocardial infarction (MINF) from heterogeneous datasets). HCM and control subjects were classified by an SVM that learned the salient motion patterns estimated from the presented strategy, by achieving a 94% AUC. In addition, statistical differences (test t-student, p<0.05) were found among groups of disease in the septal and anterior ventricular segments at both the ED and ES, with salient motion characteristics aligned with existing knowledge on the diseases. CONCLUSIONS: Regional wall motion abnormality in the apical, anterior, basal, and inferior segments was associated with the saliency dispersion in HCM, DCM, and MINF compared to healthy controls during the systolic and diastolic phases. This saliency analysis may be used to detect subtle changes in heart function.
Subject(s)
Cardiomyopathy, Hypertrophic , Myocardial Infarction , Cardiomyopathy, Hypertrophic/diagnosis , Cardiomyopathy, Hypertrophic/pathology , Heart/diagnostic imaging , Heart Ventricles , Humans , Magnetic Resonance Imaging/methods , Magnetic Resonance Imaging, Cine/methodsABSTRACT
In this study, six supervised classification algorithms were compared. The algorithms were based on cluster analysis, distance, deep learning, and object-based image analysis. Our objective was to determine which of these algorithms has the highest overall accuracy in both detection and automated estimation of agave cover in a given area to help growers manage their plantations. An orthomosaic with a spatial resolution of 2.5 cm was derived from 300 images obtained with a DJI Inspire 1 unmanned aerial system. Two training classes were defined: (1) sites where the presence of agaves was identified and (2) "absence" where there were no agaves but other plants were present. The object-oriented algorithm was found to have the highest overall accuracy (0.963), followed by the support-vector machine with 0.928 accuracy and the neural network with 0.914. The algorithms with statistical criteria for classification were the least accurate: Mahalanobis distance = 0.752 accuracy and minimum distance = 0.421. We further recommend that the object-oriented algorithm be used, because in addition to having the highest overall accuracy for the image segmentation process, it yields parameters that are useful for estimating the coverage area, size, and shapes, which can aid in better selection of agave individuals for harvest.
Subject(s)
Agave , Algorithms , Humans , Image Processing, Computer-Assisted , Machine Learning , Neural Networks, Computer , Unmanned Aerial DevicesABSTRACT
INTRODUCTION: Neuropsychological test scores are limited and standard outcomes may mask the heterogeneity of cognitive impairment. This article presents the calculation and evaluation of six composite scores that quantify domain-specific impairment. METHODS: Parameters for composite scores calculation were learned by performing confirmatory factor analysis in a sample of participants from the Alzheimer's Disease Neuroimaging Initiative database. The obtained scores were evaluated with a separate sample of mild cognitive impairment (MCI) in two automated tasks: unsupervised partition in different subgroups and prediction of progression to dementia for different time windows. RESULTS: MCI subgroups with distinctive cognitive profiles and risk of progression emerged from cluster analysis. Composite scores outperform standard neuropsychological tests when automatically predicting progression within time windows up to 5 years. CONCLUSIONS: Domain-specific composite scores are useful to delineate profiles of impairment, stratify the MCI risk, and predict progression to dementia.