Manual Quantification Research Articles

Investigating the Analytical Variability and Agreement of Manual Leukocyte Quantification Methods in Eastern Box Turtles (Terrapene carolina carolina).

Leukogram evaluation provides valuable information about inflammation, infection, and stress in free-living and zoo-maintained wildlife. While multiple protocols for quantifying leukocytes are available in reptiles, agreement between methods is infrequently described and analytical variability (including repeatability and reproducibility) has not been critically evaluated. This study addresses these knowledge gaps for two hematological methods in eastern box turtles (Terrapene carolina carolina): Avian Leukopet™ (LO) and total white blood cell (WBC) estimates from blood films (EST). The objectives of this study were (1) to evaluate agreement in total WBC and individual leukocyte counts between the LO and EST methods, (2) to document repeatability (intra-assay variability) and reproducibility (inter-assay variability) for the LO method, and (3) to investigate whether biological drivers of WBC counts differ between quantification methods. Box turtles (n = 120) were sampled from five study sites in Illinois during the 2018 active season. The LO method produced significantly higher WBC counts than the EST method, and constant and proportional error was variable for each leukocyte type. The LO method demonstrated an intra-assay variability of 8.2% and an inter-assay variability of 12%, independent of biological variation. WBC counts were significantly affected by age class using both LO and EST methods, but WBC differences between locations and sexes were only observed using the LO method. These findings emphasize the importance of considering leukocyte determination method when analyzing reptilian hematology results. The inherent variability in currently available methods creates uncertainty in resulting data and highlights the need of a gold standard for reptilian WBC quantification.

Fully Automated CT Quantification of Epicardial Adipose Tissue by Deep Learning: A Multicenter Study.

To evaluate the performance of deep learning for robust and fully automated quantification of epicardial adipose tissue (EAT) from multicenter cardiac CT data. In this multicenter study, a convolutional neural network approach was trained to quantify EAT on non-contrast material-enhanced calcium-scoring CT scans from multiple cohorts, scanners, and protocols (n = 850). Deep learning performance was compared with the performance of three expert readers and with interobserver variability in a subset of 141 scans. The deep learning algorithm was incorporated into research software. Automated EAT progression was compared with expert measurements for 70 patients with baseline and follow-up scans. Automated quantification was performed in a mean (± standard deviation) time of 1.57 seconds ± 0.49, compared with 15 minutes for experts. Deep learning provided high agreement with expert manual quantification for all scans (R = 0.974; P < .001), with no significant bias (0.53 cm3; P = .13). Manual EAT volumes measured by two experienced readers were highly correlated (R = 0.984; P < .001) but with a bias of 4.35 cm3 (P < .001). Deep learning quantifications were highly correlated with the measurements of both experts (R = 0.973 and R = 0.979; P < .001), with significant bias for reader 1 (5.11 cm3; P < .001) but not for reader 2 (0.88 cm3; P = .26). EAT progression by deep learning correlated strongly with manual EAT progression (R = 0.905; P < .001) in 70 patients, with no significant bias (0.64 cm3; P = .43), and was related to an increased noncalcified plaque burden quantified from coronary CT angiography (5.7% vs 1.8%; P = .026). Deep learning allows rapid, robust, and fully automated quantification of EAT from calcium scoring CT. It performs as well as an expert reader and can be implemented for routine cardiovascular risk assessment.© RSNA, 2019See also the commentary by Schoepf and Abadia in this issue.

An automated method for segmentation and quantification of blood vessels in histology images

Alzheimer's disease (AD) is a chronic neuro-degenerative disease that adversely affect many people on a global scale. Despite different diagnostic and therapeutic treatment, there is no cure for AD. The brain is one of the most complex organ and researchers are still trying to understand so as to find a cure. Objective: To complement the efforts of clinical researchers engaged in research in alzheimer's disease, accurate segmentation and quantification of blood vessels in brain images is required. Method: For robust segmentation of blood vessels even in the presence of colour variation, we introduce a fully automated morphological tool that can extract and quantify vessels from haematoxylin and diaminobenzidine stained histology brain image. The method, exploits saturation channel of stained image slides, ISODATA threshold method is applied to obtain a binary image. This helps in eliminating background and remaining with only blood vessels. A one-stage procedure that includes eliminating small artefacts is performed on the binary mask. The intensity of the image is transformed. Joining is performed to deal with fragmentation of intact blood vessels on the images, and artefactual appearance of the blood vessel structures. The artefactual fragments based on measured incoherence with neighbouring tissue are removed. The vessels are then labelled to facilitate quantification. Morphometric measurements are used during the vessel quantification assess both vessels with lumen and vessels without lumen. We have quantified the diameter of blood vessels. Results: The image processing technique is developed in close collaboration with neuroscientist experts to help clinician. We have evaluated our proposed approach qualitatively. The method was validated against their manual quantification results. Qualitative results show that the method can indeed segment the blood vessels in the presence of colour variations and artefacts. The quantitative method produces fairly better results.

Automated and Manual Quantification of Tumour Cellularity in Digital Slides for Tumour Burden Assessment

The residual cancer burden index is an important quantitative measure used for assessing treatment response following neoadjuvant therapy for breast cancer. It has shown to be predictive of overall survival and is composed of two key metrics: qualitative assessment of lymph nodes and the percentage of invasive or in situ tumour cellularity (TC) in the tumour bed (TB). Currently, TC is assessed through eye-balling of routine histopathology slides estimating the proportion of tumour cells within the TB. With the advances in production of digitized slides and increasing availability of slide scanners in pathology laboratories, there is potential to measure TC using automated algorithms with greater precision and accuracy. We describe two methods for automated TC scoring: 1) a traditional approach to image analysis development whereby we mimic the pathologists’ workflow, and 2) a recent development in artificial intelligence in which features are learned automatically in deep neural networks using image data alone. We show strong agreements between automated and manual analysis of digital slides. Agreements between our trained deep neural networks and experts in this study (0.82) approach the inter-rater agreements between pathologists (0.89). We also reveal properties that are captured when we apply deep neural network to whole slide images, and discuss the potential of using such visualisations to improve upon TC assessment in the future.

5963Automated quantification of epicardial adipose tissue from non-contrast CT on multi-center and multi-vendor data using deep learning

Abstract Background Epicardial adipose tissue (EAT), a metabolically active visceral fat depot surrounding the coronary arteries, has been shown to promote the development of atherosclerosis in underlying coronary vasculature. Purpose We evaluate the performance of deep learning (DL), a sub-group of machine learning algorithms, for robust and fully automated quantification of EAT on multi-center cardiac CT data. Methods In this study, 850 non-contrast calcium scoring CT scans, from multiple cohorts, scanners and protocols, with manual measurements of EAT from 3 different readers were considered. The DL method was based on a convolutional neural network trained to reproduce the expert measurement. DL global performance was first assessed using all the scans, and then compared to inter-observer variability on a subset of 141 scans. Finally, automated EAT progression was compared to manual measurement using baseline and follow-up serial scans available for 70 subjects. The proposed model was validated using 10-fold cross validation. Results Automated quantification was performed in 1.57±0.49 seconds compared to 15 minutes for manual measurement. DL provided high agreement with expert manual quantification for all scans (R=0.974, p&lt;0.001) with no significant bias (0.53 cm3, p=0.13). EAT volume was higher in patients with hypertension (+18.02 cm3, p&lt;0.001, N=442), with diabetes (+18.33 cm3, p&lt;0.001, N=75) and with hypercholesterolemia (+7.33 cm3, p=0.039, N=508). Manual EAT volumes measured by two experienced readers on 141 scans were highly correlated (R=0.984, p&lt;0.001) but presented a significant difference of 4.35 cm3 (p&lt;0.001). On these 141 scans, DL quantifications were highly correlated to both experts' measurements (R=0.973, p&lt;0.001; R=0.979, p&lt;0.001) with significant and non-significant bias for readers 1 and 2 (5.19 cm3, p&lt;0.001; 0.84 cm3, p=0.26), respectively. In 70 subjects, EAT progression quantified by DL correlated strongly with EAT progression measured by the expert reader (R=0.905, p&lt;0.001) with no significant bias (0.64 cm3, p=0.43), and was related to increased non-calcified plaque burden quantified from coronary CT angiography (5.7% vs 1.8%, p=0.026). Automated vs. manual EAT volume Conclusion Deep learning allows rapid, robust and fully automated quantification of EAT from calcium scoring CT. It performs as an expert reader and can be implemented for routine cardiovascular risk assessment. Acknowledgement/Funding 1R01HL133616/01EX1012B/Adelson Medical Research Foundation

Automated quantification of choroidal neovascularization on Optical Coherence Tomography Angiography images

ObjectivesTo report the design of an automated quantification algorithm for choroidal neovascularization (CNV) in the context of neovascular age-related macular degeneration (AMD), based on Optical Coherence Tomography Angiography (OCTA) images. Material and methodsIn this study, 54 patients (mean age 75.80 ± 14.29 years) with neovascular AMD (type 1 and type 2 CNV) were included retrospectively and separated into two groups (Group 1–24 images; Group 2–30 images), according to the lesion topology. All patients underwent a 3 × 3 mm OCTA examination (AngioVue, Optovue, Freemont, California). The proposed algorithm is based on segmentation and enhancement methods including Frangi filter, Gabor wavelets and Fuzzy-C-Means Classification. Our results were compared to the manual quantifications given by the embedded quantification software “AngioAnalytics”. ResultsAutomated CNV segmentation and quantification of three neovascular AMD biomarkers: the total vascular area (TVA), the total area (TA) and the vascular density (VD) were possible in all cases. Automated versus manual quantification comparison revealed a statistically significant difference for TVA and VD measurements for both groups (p = 0.00036 for Group 1 TVA, p < 0.0001 for Group 1 VD and Group 2 TVA and VD). The difference in TA measurements was not significant in Group 2 (p = 0.143). Bland-Altman analysis revealed low inter-method bias for TA measurements and higher bias for TVA and VD. ConclusionThis paper presents a method for segmenting and quantifying CNV that constitutes a valid option for clinicians. Complementary validations have to be carried out to compare our method's accuracy to “AngioAnalytics”.

A Freely Available, Self-Calibrating Software for Automatic Measurement of Freezing Behavior.

Freezing behavior is commonly used as a measure of associative fear memory. It can be measured by a trained observer, but this task is time-consuming and subject to variation. Commercially available software packages can also be used to quantify freezing; however, they can be expensive and usually require various parameters to be adjusted by the researcher, leading to additional work and variability in results. With this in mind, we developed Phobos, a freely available, self-calibrating software that measures freezing in a set of videos using a brief manual quantification performed by the user to automatically adjust parameters. To optimize the software, we used four different video sets with different features in order to determine the most relevant parameters, the amount of videos needed for calibration and the minimum criteria to consider it reliable. The results of four different users were compared in order to test intra- and interobserver variability in manual and automated freezing scores. Our results suggest that Phobos can be an inexpensive, simple and reliable tool for measurement of fear-related behavior, with intra- and interuser variability similar to that obtained with manual scoring.

Reliability of cervical muscle volume quantification using magnetic resonance imaging

BackgroundMagnetic resonance imaging (MRI) is used to quantify the size and structure of the architecturally complex cervical spine musculature of individuals with traumatic and idiopathic neck pain. However, to our knowledge, no scan-rescan reliability data is available on neck muscle volumes. ObjectivesThis study investigates the intra- and inter-rater reliability and scan-rescan reliability in cervical muscle volume investigations. DesignClinical Measurement, Reliability study. MethodsMRI scans were performed and repeated (within 1 h) for five asymptomatic individuals. Two raters manually traced levator scapulae, multifidus including semispinalis cervicis, semispinalis capitis, splenius capitis including splenius cervicis, and sternocleidomastoid using Analyze software (v12.0). Reliability was determined using intra-class correlation coefficients, Lin's concordance coefficient and Bland-Altman plots, with interpretation of reliability coefficients using the criteria from Fleiss. ResultsIntra-rater reliability of muscle quantification was excellent (ICCs ranging from 0.78 to 0.96). Inter-rater reliability was excellent for sternocleidomastoid(ICC 0.92, 95% CI 0.80, 0.97) and splenius capitis (ICC 0.77, 0.51, 0.90), and ranged from fair to good for levator scapulae (0.63, 0.18, 0.85), multifidus (0.73, 0.44, 0.88), and semispinalis capitis (0.50, 0.08, 0.77). The scan-rescan reliability was excellent for all muscles (ICCs ranging from 0.94 to 0.98). ConclusionThreats to reliability appear to be more related to manual quantification of muscles on images rather than protocols related to re-positioning a participant in the scanner and repeating the same protocol.The current findings suggest that the proposed methods can be used in establishing normative data for cervical muscle volume and comparing individuals with and without neck pain.

Quantitative and Qualitative Coronary Plaque Assessment Using Computed Tomography Coronary Angiography: A Comparison With Intravascular Ultrasound

To compare computed tomography coronary angiography (CTCA) with intravascular ultrasound (IVUS) in quantitative and qualitative plaque assessment. Patients who underwent IVUS and CTCA within 3 months for suspected coronary artery disease were retrospectively studied. Plaque volumes on CTCA were quantified manually and with automated-software and were compared to IVUS. High-risk plaque features were compared between CTCA and IVUS. There were 769 slices in 32 vessels (27 patients). Manual plaque quantification on CTCA was comparable to IVUS per slice (mean difference of 0.06±0.07, p=0.44; Bland-Altman 95% limits of agreement -2.19-2.08 mm3, bias of -0.06mm3) and per vessel (3.1mm3 ± -2.85mm3, p=0.92). In contrast, there was significant difference between automated-software and IVUS per slice (2.3±0.09mm3, p<0.001; 95% LoA -6.78 to 2.25mm3, bias of -2.2mm3) and per vessel (33.04±10.3 mm3, p<0.01). The sensitivity, specificity, positive and negative predictive value of CTCA to detect plaques that had features of echo-attenuation on IVUS was 93.3%, 99.6%, 93.3% and 99.6% respectively. The association of ≥2 high-risk plaque features on CTCA with echo attenuation (EA) plaque features on IVUS was excellent (86.7%, 99.6%, 92.9% and 99.2%). In comparison, the association of high-risk plaque features on CTCA and plaques with echo-lucency on IVUS was only modest. Plaque volume quantification by manual CTCA method is accurate when compared to IVUS. The presence of at least two high-risk plaque features on CTCA is associated with plaque features of echo attenuation on IVUS.

High-throughput quantitative detection of basal autophagy and autophagic flux using image cytometry.

Quantitative assessment of changes in macro-autophagy is often performed through manual quantification of the number of LC3B foci in immunofluorescence microscopy images. This method is highly laborious, subject to image-field selection and foci-counting bias, and is not sensitive for analyzing changes in basal autophagy. Alternative methods such as flow cytometry and transmission electron microscopy require highly specialized, expensive instruments and time-consuming sample preparation. Immunoblots are prone to exposure-related variations and noise that prevents accurate quantification. We report a high-throughput, inexpensive, reliable and objective method for studying basal level and flux changes in late-stage autophagy using image cytometry and acridine orange staining.

CD163+ immune cell infiltrates and presence of CD54+ microvessels are prognostic markers for patients with embryonal rhabdomyosarcoma

Rhabdomyosarcomas (RMS) are rare and often lethal diseases. It is assumed that the tumor microenvironment (TME) of RMS exerts an immunosuppressive function, but there is currently no systematic analysis of the immune cells infiltrating sarcoma tissue. Focusing on two common types of RMS (alveolar [RMA] and embryonal [RME]), we performed a comprehensive immunohistochemical analysis of tumor-infiltrating immune cells in the TME. We performed a qualitative estimation of infiltrating immune cells in the tumor microenvironment by an experienced pathologist as well as a quantitative digital pathology analysis. We found that (1) manual and automatic quantification of tumor-infiltrating immune cells were consistent; (2) RME tumors showed a higher degree of immune cell infiltration than RMA tumors but (3) the number of tumor infiltrating lymphocytes was low compared to other solid tumor types; (4) microvascular density correlated with immune cell infiltration and (5) CD163 positive macrophages as well as CD54 positive microvessels were more often detected in RME than in RMA and correlated with patient overall and event free survival. Our systematic analysis provides a comprehensive view of the immune landscape of RMS which needs to be taken into account for developing immunotherapies for this rare type of cancer.

A multispectral camera system for automated minirhizotron image analysis

Roots are vital organs for plants, but the assessment of root traits is difficult, particularly in deep soil layers under natural field conditions. A popular technique to investigate root growth under field or semi-field conditions is the use of minirhizotrons. However, the subsequent manual quantification process is time-consuming and prone to error. We developed a multispectral minirhizotron imaging system and a subsequent image analysis strategy for automated root detection. Five wavelengths in the visible (VIS) and near-infrared (NIR) spectrum are used to enhance living roots by a multivariate grouping of pixels based on differences in reflectance; background noise is suppressed by a vesselness enhancement filter. The system was tested against manual analysis of grid intersections for both spring barley (Hordeum vulgare L.) and perennial ryegrass (Lolium perenne L.) cultivars at two time-points. The images of living roots were captured in wet subsoil conditions with dead roots present from a previous crop. Under the soil conditions used in the study, NIR reflectance (940 nm), provided limited ability to separate between rhizosphere components, compared to reflectance in the violet and blue light spectrum (405 nm and 450 nm). Multivariate image analysis of the spectral data, combined with vesselness enhancement and thresholding allowed for automated detection of living roots. Automated image analysis largely replicated the root intensity found during manual grid intersect analysis of the same images. Although some misclassification occurred, caused by elongated structures of dew and chalkstone with similar reflectance pattern as living root, the system provided similar or in some cases improved detection of genotypic differences in the total root length within each tube. The multispectral imaging system allows for automated detection of living roots in minirhizotron studies. The system requires considerably less time than traditional manual recording using grid intersections. The flexible training strategy used for root segmentation offers hope for the transfer to other rhizosphere components and other soil types of interest.

PB2111 DIGITAL ENUMERATION OF PLASMA CELL BURDEN BY MUM1 IMMUNOPHENOTYPING: IMPLICATIONS FOR MULTIPLE MYELOMA DIAGNOSTICS

Background:Accurate plasma cell evaluations are required to diagnose multiple myeloma. Aspirate material is routinely assessed morphologically and by flow cytometry, but its reliability is hindered by peripheral blood haemodilution and patchy disease. Consequently, its sensitivity in diagnosing multiple myeloma is rated at only 75%. Alternatively, whole trephine estimations of plasma cell burden identified by membranous syndecan‐1 (CD138) or nuclear multiple myeloma oncogene‐1 (MUM1) expression may be undertaken. Routine “eye‐ball” estimations of CD138‐expressing plasma cells are grossly inaccurate and subject to extensive visual bias. Automated enumeration technology represents a robust alternative that is precise and overcomes these limitations. Digitally‐derived reference ranges for plasma cells identified by CD138 and MUM1 expression have been recently published. However, no previous studies have utilised enumeration software or these reference ranges to accurately assess plasma cells by MUM1 immunophenotyping in trephine specimens of multiple myeloma.Aims:We utilised an automated platform to digitally quantify plasma cells in trephine specimens obtained from patients with diagnostic, relapsing and remissive multiple myeloma. Variations between the manual and digital quantification of plasma cells immunophenotyped by MUM1 were evaluated, and the overall sensitivity of our automated approach was determined.MethodsWhole bone marrow trephine specimens (n = 91) were obtained from patients with new, relapsing and remissive multiple myeloma. Plasma cells were identified by the immunohistochemical detection of MUM1. Two blinded observers estimated the percent plasma cells per whole trephine specimen by light microscopy. Plasma cell burden per trephine was also quantified digitally with Tissue Image Analysis software (Leica, Ireland). Variations between observers’ manual estimations and digitally derived counts were evaluated using intraclass correlation analyses (ICC). The overall sensitivity of our digital platform in diagnosing multiple myeloma against published digital reference ranges for MUM1 was also determined.Results:We enumerated between 16,484–1,118,868 (mean = 100,084) cells per whole trephine. Interobserver agreement between observers for manual estimations was generally excellent (ICC = 0.94). Overall concordance between manual and digital counts were also high (ICC = 0.89), particularly among cases showing diffuse (ICC = 0.90) and nodular (ICC = 0.82) plasma cell distributions. Plasma cell microaggregates showed the poorest concordance between observers (ICC = 0.51) and when compared to digital counts (ICC = 0.17). Manual estimations typically overestimated MUM1‐expressing plasma cell counts by an average of 8.7% relative to digitally derived values. The overall sensitivity of our digital platform in diagnosing new or relapsing multiple myeloma was 91.7%.Summary/Conclusion:The automated enumeration of plasma cells identified by MUM1 immunoexpression in trephine specimens of multiple myeloma is highly accurate and precise. Concordance rates between manual and digital counts were strong for cases with diffuse and nodular disease distributions. Trephines with microaggregate foci of plasma cells showed poor agreement between manual and digital counts and may be incorrectly classified as “false negatives.” Such cases may require manual verification to ensure accurate diagnoses. Despite this, the overall sensitivity of our digital method was excellent (91.7%). Our data support the incorporation of automated digital enumeration technology as a useful adjunct to diagnose multiple myeloma.

Computer-assisted image analysis of the tumor microenvironment on an oral tongue squamous cell carcinoma tissue microarray

Oral tongue squamous cell carcinoma (OTSCC) displays variable levels of immune cells within the tumor microenvironment. The quantity and localization of tumor infiltrating lymphocytes (TILs), specific functional TIL subsets (e.g., CD8+), and biomarker-expressing cells (e.g., PD-L1+) may have prognostic and predictive value. The purpose of this study was to evaluate the robustness and utility of computer-assisted image analysis tools to quantify and localize immunohistochemistry-based biomarkers within the tumor microenvironment on a tissue microarray (TMA). We stained a 91-patient OTSCC TMA with antibodies targeting CD3, CD4, CD8, FOXP3, IDO, and PD-L1. Cell populations were segmented into epithelial (tumor) or stromal compartments according to a mask derived from a pan-cytokeratin stain. Definiens Tissue Studio was used to enumerate marker-positive cells or to quantify the staining intensity. Automated methods were validated against manual tissue segmentation, cell count, and stain intensity quantification. Univariate associations of cell count and stain intensity with smoking status, stage, overall survival (OS), and disease-free survival (DFS) were determined. Our results revealed that the accuracy of automated tissue segmentation was dependent on the distance of the tissue section from the cytokeratin mask and the proportion of the tissue containing tumor vs. stroma. Automated and manual cell counts and stain intensities were highly correlated (Pearson coefficient range: 0.46–0.90; p < 0.001). Within this OTSCC cohort, smokers had significantly stronger PD-L1 stain intensity and higher numbers of CD3+, CD4+ and FOXP3+ TILs. In the subset of patients who had received adjuvant radiotherapy, a higher number of CD8+ TILs was associated with inferior OS and DFS. Taken together, this proof-of-principle study demonstrates the robustness and utility of computer-assisted image analysis for high-throughput assessment of multiple IHC markers on TMAs, with potential implications for studies on prognostic and predictive biomarkers.

FluoroCellTrack: An algorithm for automated analysis of high-throughput droplet microfluidic data.

High-throughput droplet microfluidic devices with fluorescence detection systems provide several advantages over conventional end-point cytometric techniques due to their ability to isolate single cells and investigate complex intracellular dynamics. While there have been significant advances in the field of experimental droplet microfluidics, the development of complementary software tools has lagged. Existing quantification tools have limitations including interdependent hardware platforms or challenges analyzing a wide range of high-throughput droplet microfluidic data using a single algorithm. To address these issues, an all-in-one Python algorithm called FluoroCellTrack was developed and its wide-range utility was tested on three different applications including quantification of cellular response to drugs, droplet tracking, and intracellular fluorescence. The algorithm imports all images collected using bright field and fluorescence microscopy and analyzes them to extract useful information. Two parallel steps are performed where droplets are detected using a mathematical Circular Hough Transform (CHT) while single cells (or other contours) are detected by a series of steps defining respective color boundaries involving edge detection, dilation, and erosion. These feature detection steps are strengthened by segmentation and radius/area thresholding for precise detection and removal of false positives. Individually detected droplet and contour center maps are overlaid to obtain encapsulation information for further analyses. FluoroCellTrack demonstrates an average of a ~92–99% similarity with manual analysis and exhibits a significant reduction in analysis time of 30 min to analyze an entire cohort compared to 20 h required for manual quantification.

Differential Classification Method in Different Teaching Models of Accounting Courses Based on Naive Bayesian Classification Algorithm

Accounting is an important management discipline with strong theoretical foundation and practical operation. Due to the differences between individuals in the process of learning, the mastery of the subject is different. This requires teachers to implement differential teaching from the differences in student personality in the process of teaching. However, when teachers use the concept of difference teaching to teach, the classification of students' differences is mostly calculated by manual quantification such as records, tests, surveys, etc. This kind of measurement and qualitative method not only wastes manpower, but also has personal subjectivity, blindly relies on individual subjective judgment to judge students' advantages and interests, and has accuracy and scientificity. This requires research on students' differential classification methods. Therefore, this paper proposes a student classification method based on naive Bayesian algorithm. It constructs a classifier based on historical data, and then uses a well-structured and stable classifier to classify the actual pre-classification objects, and actually applies it to the teaching of accounting courses, realizing the difference in the teaching process. Provide data support for future differential teaching research. The results show that the naive Bayesian classification algorithm can be used to analyze the difference in personality and learning of students. Presupposition and generative teaching objectivesand students improve their self-awareness to better promote self-development.

Immunofluorescence multiparamétrique in situ : vers l’amélioration du phénotype de l’infiltrat cellulaire au cours du rejet d’allogreffe rénale

BackgroundThe exact composition and localization of the inflammatory burden during allograft rejection is difficult to analyse on the same biopsy slide. We tested the feasibility of detecting four distinct markers in a same paraffin-embedded tissue section from human kidney allograft rejection by using an innovative process of multiplex immunofluorescence. MethodsKidney allograft biopsies from 20 antibody-mediated rejection, 20 T cell-mediated rejection and five non rejection were labelled against NKp46, CD163, CD3, and CD34 respectively for NK cells, macrophages, T cells and endothelial cells. Images were scanned and cells were automatically quantified and their extra- or intravascular location determined. Conventional immunohistochemistry against NKp46 with manual quantification and real time quantitative polymerase chain reaction for evaluation of the relative messenger ribonucleic acid (mRNA) expression levels of NK, T cell and macrophage transcripts were simultaneously performed. ResultsMultiplex immunofluorescence cell quantification was strongly correlated to manual quantification by immunohistochemistry (r=0.91, P<0.001) and to mRNA expression levels (r>0.46, P<0.021). T cells and macrophages were the two predominant populations involved in rejection (48.0±4.4% and 49.3±4.4% in antibody-mediated rejection; 51.8±6.0% and 45.3±5.8% in T cell-mediated rejection respectively) despite an important heterogeneity in the composition of the inflammatory burden. NK cells constituted a rare population for both T cell-mediated rejection (2.9±0.6%) and antibody-mediated rejection (2.7±0.7%). The intravascular compartment was mainly composed of T cells, including during antibody-mediated rejection. However, NK cells and macrophages densities were significantly higher in capillaries during antibody-mediated rejection. ConclusionMultiplex immunofluorescence staining is a reliable technology allowing studying the exact composition and localization of the inflammatory burden during kidney allograft rejection.

Serial Coronary Plaque Assessment Using Computed Tomography Coronary Angiography

Serial Coronary Plaque Assessment Using Computed Tomography Coronary Angiography

Combination of hand-crafted and unsupervised learned features for ischemic stroke lesion detection from Magnetic Resonance Images

Detection of ischemic stroke lesions plays a vital role in the assessment of stroke treatments such as thrombolytic therapy and embolectomy. Manual detection and quantification of stroke lesions is a time-consuming and cumbersome process. In this paper, we present a novel automatic method to detect acute ischemic stroke lesions from Magnetic Resonance Image (MRI) volumes using textural and unsupervised learned features. The proposed method proficiently exploits the 3D contextual evidence using a patch-based approach, which extracts patches randomly from the input MR volumes. Textural feature extraction (TFE) using Gray Level Co-occurrence Matrix (GLCM) and unsupervised feature learning (UFL) based on k-means clustering approaches are employed independently to extract features from the input patches. These features obtained from the two feature extractors are then given as input to the Random Forest (RF) classifier to discriminate between normal and lesion classes. A hybrid approach based on the combination of TFE using GLCM and UFL based on the k-means clustering is proposed in this work. Hybrid combination approach results in more discriminative feature set compared with the traditional approaches. The proposed method has been evaluated on the Ischemic Stroke Lesion Segmentation (ISLES) 2015 training dataset. The proposed method achieved an overall dice coefficient (DC) of 0.886, precision of 0.979, recall of 0.831 and accuracy of 0.8201. Quantitative measures show that the proposed approach is 28.4%, 27.14%, and 5.19% higher than the existing methods in terms of DC, precision, and recall, respectively.

Predicting survival from colorectal cancer histology slides using deep learning: A retrospective multicenter study.

BackgroundFor virtually every patient with colorectal cancer (CRC), hematoxylin–eosin (HE)–stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract prognosticators directly from these widely available images.Methods and findingsWe hand-delineated single-tissue regions in 86 CRC tissue slides, yielding more than 100,000 HE image patches, and used these to train a CNN by transfer learning, reaching a nine-class accuracy of >94% in an independent data set of 7,180 images from 25 CRC patients. With this tool, we performed automated tissue decomposition of representative multitissue HE images from 862 HE slides in 500 stage I–IV CRC patients in the The Cancer Genome Atlas (TCGA) cohort, a large international multicenter collection of CRC tissue. Based on the output neuron activations in the CNN, we calculated a “deep stroma score,” which was an independent prognostic factor for overall survival (OS) in a multivariable Cox proportional hazard model (hazard ratio [HR] with 95% confidence interval [CI]: 1.99 [1.27–3.12], p = 0.0028), while in the same cohort, manual quantification of stromal areas and a gene expression signature of cancer-associated fibroblasts (CAFs) were only prognostic in specific tumor stages. We validated these findings in an independent cohort of 409 stage I–IV CRC patients from the “Darmkrebs: Chancen der Verhütung durch Screening” (DACHS) study who were recruited between 2003 and 2007 in multiple institutions in Germany. Again, the score was an independent prognostic factor for OS (HR 1.63 [1.14–2.33], p = 0.008), CRC-specific OS (HR 2.29 [1.5–3.48], p = 0.0004), and relapse-free survival (RFS; HR 1.92 [1.34–2.76], p = 0.0004). A prospective validation is required before this biomarker can be implemented in clinical workflows.ConclusionsIn our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.