Tissue Segmentation Algorithm Research Articles

Enhanced Spatial Fuzzy C-Means Algorithm for Brain Tissue Segmentation in T1 Images.

Magnetic Resonance Imaging (MRI) plays an important role in neurology, particularly in the precise segmentation of brain tissues. Accurate segmentation is crucial for diagnosing brain injuries and neurodegenerative conditions. We introduce an Enhanced Spatial Fuzzy C-means (esFCM) algorithm for 3D T1 MRI segmentation to three tissues, i.e. White Matter (WM), Gray Matter (GM), and Cerebrospinal Fluid (CSF). The esFCM employs a weighted least square algorithm utilizing the Structural Similarity Index (SSIM) for polynomial bias field correction. It also takes advantage of the information from the membership function of the last iteration to compute neighborhood impact. This strategic refinement enhances the algorithm's adaptability to complex image structures, effectively addressing challenges such as intensity irregularities and contributing to heightened segmentation accuracy. We compare the segmentation accuracy of esFCM against four variants of FCM, Gaussian Mixture Model (GMM) and FSL and ANTs algorithms using four various dataset, employing three measurement criteria. Comparative assessments underscore esFCM's superior performance, particularly in scenarios involving added noise and bias fields.The obtained results emphasize the significant potential of the proposed method in the segmentation of MRI images.

A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitis

Over the past decade, automation of digital image analysis has become commonplace in both research and clinical settings. Spurred by recent advances in artificial intelligence and machine learning (AI/ML), tissue sub-compartments and cellular phenotypes within those compartments can be identified with higher throughput and accuracy than ever before. Recently, immune checkpoints have emerged as potential targets for auto-immune diseases. As such, spatial identification of these proteins along with immune cell markers (e.g., CD3+/LAG3+ T-cells) is a crucial step in understanding the potential and/or efficacy of such treatments. Here, we describe a semi-automated imaging and analysis pipeline that identifies CD3+/LAG3+ cells in colorectal tissue sub-compartments. While chromogenic staining has been a clinical mainstay and the resulting brightfield images have been utilized in AI/ML approaches in the past, there are associated drawbacks in phenotyping algorithms that can be overcome by fluorescence imaging. To address these tradeoffs, we developed an analysis pipeline combining the strengths of brightfield and fluorescence images. In this assay, immunofluorescence imaging was conducted to identify phenotypes followed by coverslip removal and hematoxylin and eosin staining of the same section to inform an AI/ML tissue segmentation algorithm. This assay proved to be robust in both tissue segmentation and phenotyping, was compatible with automated workflows, and revealed presence of LAG3+ T-cells in ulcerative colitis biopsies with spatial context preserved.

Brain Logistic Segmentation (BLS): an efficient algorithm for whole-brain tissue segmentation in structural magnetic resonance imaging

Brain Logistic Segmentation (BLS): an efficient algorithm for whole-brain tissue segmentation in structural magnetic resonance imaging

Abstract 4625: A comprehensive guided workflow for highplex imaging, tissue segmentation, and multiplex cellular phenotyping for tumor microenvironment analysis

Abstract The growth in cancer immunotherapy agents requires an understanding of the immune contexture of the tumor microenvironment (TME). Understanding immune contexture requires multiplex staining, imaging, and analysis to obtain multi-marker phenotypes of specific cells and analyze their biodistribution in the TME. Imaging Mass Cytometry™ (IMC) is the method of choice for single-step staining and highplex imaging of FFPE tissues. FFPE tissue is autofluorescent, which limits the utility of immunofluorescence methods. Lung and colorectal tissue (and bone, skin, etc) are highly autofluorescent, and therefore good targets for IMC. However, developments in analysis software for highplex imagery have not kept pace with imaging advances. We present a comprehensive workflow designed specifically for highplex image analysis, covering tissue segmentation, cell segmentation based on IMC DNA images, cellular phenotyping, and spatial analyses. Lung and colorectal tissue sections with a 30-marker IMC panel of structural, tumor, stroma, immune cell, and immune activation markers were imaged (Hyperion+™, Standard BioTools). Highplex image analysis (Phenoplex™, Visiopharm) was performed as a multi-step workflow in a single software package that includes: conversion of IMC images to pyramidal format; easy visualization methods for displaying different marker subsets; a paint-to-train algorithm for tissue segmentation (into tumor, stroma, blood vessels, etc.); deep-learning-based nuclear segmentation pre-trained on IMC DNA channels; cellular phenotyping based on thresholds based on visual assessment of positivity; spatial biodistribution metrics for cell populations; and a flexible set of outputs for downstream analysis. Tissue segmentation was used to divide the tissue into tumor, stromal, and tumor margin regions, and these regions were used to compare the immune contexture through a series of t-SNE images partitioned by spatial region. We demonstrate that a simple analysis workflow can be used for highplex images of different tissue types by users with no programming knowledge. Visualization templates for the marker subsets and the pre-trained IMC nuclear segmentation are reusable. A new tissue segmentation algorithm for each tissue type is required, as are new thresholds for biomarker positivity. Spatial biodistribution metrics, heatmaps and partitioned t-SNE plots were generated for each tissue type with a minimum of work. Highplex IMC imaging of lung and colorectal tumor samples is a simple and effective means of obtaining high-parameter images without interfering autofluorescence. Having a comprehensive workflow for the analysis of this complex data makes obtaining useful results from highplex images more accessible to biologists and immunologists by circumventing the requirement for expert programming for each specific application. Citation Format: Brenna O'Neill, Smriti Kala, Sam Lim, Clinton Hupple, Nina Lane, Rasmus Norre Sorensen, Rasmus A. Lyngby, Alessandro Massaro, Andreas Hussing, Jeppe Thagaard, Johan Dore-Hansen, James Robert Mansfield. A comprehensive guided workflow for highplex imaging, tissue segmentation, and multiplex cellular phenotyping for tumor microenvironment analysis. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 4625.

An Algorithm for Segmentation of Kidney Tissues on CT Images Based on a U-Net Convolutional Neural Network

An Algorithm for Segmentation of Kidney Tissues on CT Images Based on a U-Net Convolutional Neural Network

Radiation dose estimates based on Monte Carlo simulation for spiral breast computed tomography imaging in a large cohort of patients.

Spiral breast computed tomography (BCT) equipped with a photon-counting detector (PCD) is a new radiological modality allowing for the compression-free acquisition of high-resolution 3-D datasets of the breast. Optimized dose exposu04170/re setups according to breast size were previously proposed but could not effectively be applied in a clinical environment due to ambiguity in measuring breast size. This study aims to report the standard radiation dose values in a large cohort of patients examined with BCT, and to provide a mathematical model to estimate radiation dose based on morphological features of the breast. This retrospective study was conducted on 1657 BCT examinations acquired between 2018 and 2021 from 829 participants (57±10 years, all female). Applying a dedicated breast tissue segmentation algorithm and Monte Carlo (MC) simulation, mean absorbed dose (MAD), mean glandular dose (MGD), mean skin dose (MSD), maximum glandular dose (maxGD), and maximum skin dose (maxSD) were calculated and related to morphological features such as breast volume, effective diameter, breast length, skin volume, and glandularity. Effective dose (ED) was calculated by applying the corresponding beam and tissue weighting factors, 1Sv/Gy and 0.12 per breast. Relevant morphological features predicting dose values were identified based on the Spearman's rank correlation coefficient. Exponential or bi-exponential models predicting the dose values as a function of morphological features were fitted by using a non-linear least squares (LS) method. The models were validated by assessing R2 and residual standard error (RSE). The most relevant morphological features for radiation dose estimation were the breast volume (correlation coefficient: -0.8), diameter (-0.7), and length (-0.6). The glandularity presented a weak-positive correlation (0.4) with MGD and maxGD due to the inhomogeneous distribution of the glandularity and absorbed dose in the 3-D breast volume. The standard MGDs were calculated to be 7.3±0.7, 6.5±0.3, and 5.9±0.3 mGy, MADs to 7.6±0.8, 6.8±0.3, and 6.2±0.3 mGy, maxSDs to 19.9±1.6, 19.5±0.5, and 18.9±0.5 mGy, and EDs to 0.88±0.08, 0.78±0.04, and 0.72±0.04 mSv for small, medium, and large breasts with average breast lengths of 5.9±1.6, 8.7±1.3, and 12.2±2.0cm, respectively. The estimated glandularity - 23.1±16.9, 12.5±11.4, and 6.9±7.3% from small to large breasts. The mathematical models were able to estimate the MAD, MGD, MSD, and maxSD as a function of each morphological feature with only upto 0.5 mGy RSE. We presented the typical morphological features and standard dose values according to the breast size acquired from a large patient cohort. We established radiation dose estimation models allowing accurate estimation of dose values including MGD with an acceptable RSE based on each of the easily measured morphological features of the breast. Clinicians could use the breast length to operate as a dosimetric alert of the scanner prior to a BCT scan. Radiation exposure for BCT was lower than diagnostic mammography (MG) and cone-beam breast CT (BCT).

Spleen Tissue Segmentation Algorithm for Cryo-Imaging Data.

Spleen tissue segmentation is an essential process for analyzing various immunological diseases as observed in the cryo-imaging data. Because manual labeling of the spleen tissue by human experts is not efficient, an automatic segmentation algorithm is needed. In this study, we developed a novel algorithm for automatically segmenting spleen substructures including white pulp and red pulp for the first time. The algorithm is designed for datasets created by a cryo-imaging system. This unique technology can effectively enable cellular tracking anywhere in the whole mouse with single-cell sensitivity. The proposed algorithm consists of four components: initial spleen mask creation, feature extraction, Supervised Patch-based Fuzzy c-Mean (spFCM) classification, and post-processing. The algorithm accurately and efficiently labeled spleen tissues in all experiment settings. The algorithm also improved the spleen segmentation throughput by 90 folds as compared to the manual segmentation. Moreover, we show that our novel spFCM algorithm outperformed traditional fast-learning classifiers as well as the U-Net deep-learning model in many aspects. Two major contributions of this paper are (1) an explainable algorithm for segmenting spleen tissues in cryo-images for the first time and (2) an spFCM algorithm as a new classifier. We also discussed that our work can be beneficial to researchers who work not only in the fields of graft-versus-host disease (GVHD) mouse models, but also in that of other immunological disease models where spleen analysis is essential. Future work building upon our research may lay the foundations for biomedical studies that utilize cryo-imaging technology.

DORIS: A diffusion MRI-based 10 tissue class deep learning segmentation algorithm tailored to improve anatomically-constrained tractography.

Modern tractography algorithms such as anatomically-constrained tractography (ACT) are based on segmentation maps of white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). These maps are generally estimated from a T1-weighted (T1w) image and then registered in diffusion weighted images (DWI) space. Registration of T1w to diffusion space and partial volume estimation are challenging and rarely voxel-perfect. Diffusion-based segmentation would, thus, potentially allow not to have higher quality anatomical priors injected in the tractography process. On the other hand, even if FA-based tractography is possible without T1 registration, the literature shows that this technique suffers from multiple issues such as holes in the tracking mask and a high proportion of generated broken and anatomically implausible streamlines. Therefore, there is an important need for a tissue segmentation algorithm that works directly in the native diffusion space. We propose DORIS, a DWI-based deep learning segmentation algorithm. DORIS outputs 10 different tissue classes including WM, GM, CSF, ventricles, and 6 other subcortical structures (putamen, pallidum, hippocampus, caudate, amygdala, and thalamus). DORIS was trained and validated on a wide range of subjects, including 1,000 individuals from 22 to 90 years old from clinical and research DWI acquisitions, from 5 public databases. In the absence of a "true" ground truth in diffusion space, DORIS used a silver standard strategy from Freesurfer output registered onto the DWI. This strategy is extensively evaluated and discussed in the current study. Segmentation maps provided by DORIS are quantitatively compared to Freesurfer and FSL-fast and the impacts on tractography are evaluated. Overall, we show that DORIS is fast, accurate, and reproducible and that DORIS-based tractograms produce bundles with a longer mean length and fewer anatomically implausible streamlines.

A Fuzzy Consensus Clustering Algorithm for MRI Brain Tissue Segmentation

Brain tissue segmentation is an important component of the clinical diagnosis of brain diseases using multi-modal magnetic resonance imaging (MR). Brain tissue segmentation has been developed by many unsupervised methods in the literature. The most commonly used unsupervised methods are K-Means, Expectation-Maximization, and Fuzzy Clustering. Fuzzy clustering methods offer considerable benefits compared with the aforementioned methods as they are capable of handling brain images that are complex, largely uncertain, and imprecise. However, this approach suffers from the intrinsic noise and intensity inhomogeneity (IIH) in the data resulting from the acquisition process. To resolve these issues, we propose a fuzzy consensus clustering algorithm that defines a membership function resulting from a voting schema to cluster the pixels. In particular, we first pre-process the MRI data and employ several segmentation techniques based on traditional fuzzy sets and intuitionistic sets. Then, we adopted a voting schema to fuse the results of the applied clustering methods. Finally, to evaluate the proposed method, we used the well-known performance measures (boundary measure, overlap measure, and volume measure) on two publicly available datasets (OASIS and IBSR18). The experimental results show the superior performance of the proposed method in comparison with the recent state of the art. The performance of the proposed method is also presented using a real-world Autism Spectrum Disorder Detection problem with better accuracy compared to other existing methods.

Association of abnormal pulmonary vasculature on CT scan for COVID-19 infection with decreased diffusion capacity in follow up: A retrospective cohort study.

Coronavirus Disease 2019 (COVID-19) is a respiratory viral illness causing pneumonia and systemic disease. Abnormalities in pulmonary function tests (PFT) after COVID-19 infection have been described. The determinants of these abnormalities are unclear. We hypothesized that inflammatory biomarkers and CT scan parameters at the time of infection would be associated with abnormal gas transfer at short term follow-up. We retrospectively studied subjects who were hospitalized for COVID-19 pneumonia and discharged. Serum inflammatory biomarkers, CT scan and clinical characteristics were assessed. CT images were evaluated by Functional Respiratory Imaging with automated tissue segmentation algorithms of the lungs and pulmonary vasculature. Volumes of the pulmonary vessels that were ≤5mm (BV5), 5-10mm (BV5_10), and ≥10mm (BV10) in cross sectional area were analyzed. Also the amount of opacification on CT (ground glass opacities). PFT were performed 2-3 months after discharge. The diffusion capacity of carbon monoxide (DLCO) was obtained. We divided subjects into those with a DLCO <80% predicted (Low DLCO) and those with a DLCO ≥80% predicted (Normal DLCO). 38 subjects were included in our cohort. 31 out of 38 (81.6%) subjects had a DLCO<80% predicted. The groups were similar in terms of demographics, body mass index, comorbidities, and smoking status. Hemoglobin, inflammatory biomarkers, spirometry and lung volumes were similar between groups. CT opacification and BV5 were not different between groups, but both Low and Normal DLCO groups had lower BV5 measures compared to healthy controls. BV5_10 and BV10 measures were higher in the Low DLCO group compared to the normal DLCO group. Both BV5_10 and BV10 in the Low DLCO group were greater compared to healthy controls. BV5_10 was independently associated with DLCO<80% in multivariable logistic regression (OR 1.29, 95% CI 1.01, 1.64). BV10 negatively correlated with DLCO% predicted (r = -0.343, p = 0.035). Abnormalities in pulmonary vascular volumes at the time of hospitalization are independently associated with a low DLCO at follow-up. There was no relationship between inflammatory biomarkers during hospitalization and DLCO. Pulmonary vascular abnormalities during hospitalization for COVID-19 may serve as a biomarker for abnormal gas transfer after COVID-19 pneumonia.

SIGNIFICANT DYSPNEA IN POST-ACUTE COVID-19 IS ASSOCIATED WITH ABNORMAL PULMONARY VASCULATURE ON CT DURING THE ACUTE PHASE

TOPIC: Chest Infections TYPE: Original Investigations PURPOSE: SARS-CoV-2 is a highly contagious respiratory virus associated with significant morbidity and mortality in the acute phase. It is also associated with long-term morbidity in a subset of patients. It is not clear which patients will have persistent symptoms. SARS-CoV-2 affects the pulmonary vasculature. We hypothesize that differences in blood volume measurements on CT of the chest during the acute phase are associated with significant dyspnea after the acute phase. METHODS: We retrospectively studied subjects hospitalized for COVID-19 pneumonia who had an initial and follow-up CT chest, pulmonary function tests (PFTs), 6-minute walk test (6MWT), and a clinical assessment in our post-COVID-19 clinic. We excluded subjects with pre-existing lung disease based on prior PFTs. Serum inflammatory biomarkers, CT scan, and clinical characteristics were assessed during the hospitalization. CT images were evaluated by Functional Respiratory Imaging (deep learning trained) with automated tissue segmentation algorithms of the lungs and pulmonary vasculature. Volumes of the pulmonary vessels that were ≤5mm2 (BV5), 5-10mm2 (BV5_10), and ≥10mm2 (BV10) in cross-sectional area were analyzed. Additionally, the amount of opacification on CT (i.e., ground-glass opacities, crazy paving, reticular disease and edema) was quantified in each patient. PFTs were performed <3 months after discharge. We defined a modified Medical Research Council (mMRC) score≥2 as having significant dyspnea. We compared subjects with an mMRC score≥2 to those with an mMRC score<2. BV measures were also compared to a historical cohort of healthy controls. RESULTS: 50 subjects were included. 22 had mMRC score≥2. The groups had similar baseline characteristics. Admission hemoglobin, peak inflammatory biomarkers, and follow-up PFTs were similar between groups. On 6MWT, there were no differences between groups in resting SpO2, lowest SpO2, or walk distance. On admission CT, percent BV5 was lower, and percents BV5_10 and BV10 were higher in the mMRC≥2 group compared to the mMRC<2 group. All BV measures in both groups were different compared to healthy controls. At follow-up, BV5 measures in the mMRC≥2 group improved but remained abnormal compared to healthy controls, without a statistical difference compared to the mMRC<2 group. Opacification was similar between groups on admission and follow-up CTs. CONCLUSIONS: Despite similar baseline characteristics, lung function, degree of opacification and oxygenation, persistent dyspnea after COVID-19 pneumonia is related to pruning of the small pulmonary vessels (BV5) during the acute phase and not to differences in vascular abnormalities seen in short term follow-up. CLINICAL IMPLICATIONS: Identification of markers of persistent dyspnea in post-acute COVID-19 contributes to a better understanding of the natural course and prognosis of the disease. This will impact research and patient care in the near future. DISCLOSURES: No relevant relationships by Melinda Darnell, source=Web Response Owner/Founder relationship with Fluidda Please note: $20001 - $100000 by Jan De Backer, source=Web Response, value=Ownership interest No relevant relationships by Derlis Fleitas Sosa, source=Web Response No relevant relationships by Victor Kim, source=Web Response Employee relationship with FLUIDDA Please note: 02/01/2017 - Present Added 04/26/2021 by Maarten Lanclus, source=Web Response, value=Salary No relevant relationships by Ifeoma Oriaku, source=Web Response No relevant relationships by Daniel Salerno, source=Web Response

Multi-scale GCN-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary OCT images.

An accurate and automated tissue segmentation algorithm for retinal optical coherence tomography (OCT) images is crucial for the diagnosis of glaucoma. However, due to the presence of the optic disc, the anatomical structure of the peripapillary region of the retina is complicated and is challenging for segmentation. To address this issue, we develop a novel graph convolutional network (GCN)-assisted two-stage framework to simultaneously label the nine retinal layers and the optic disc. Specifically, a multi-scale global reasoning module is inserted between the encoder and decoder of a U-shape neural network to exploit anatomical prior knowledge and perform spatial reasoning. We conduct experiments on human peripapillary retinal OCT images. We also provide public access to the collected dataset, which might contribute to the research in the field of biomedical image processing. The Dice score of the proposed segmentation network is 0.820 ± 0.001 and the pixel accuracy is 0.830 ± 0.002, both of which outperform those from other state-of-the-art techniques.

Residual cyclegan for robust domain transformation of histopathological tissue slides.

Variation between stains in histopathology is commonplace across different medical centers. This can have a significant effect on the reliability of machine learning algorithms. In this paper, we propose to reduce performance variability by using -consistent generative adversarial (CycleGAN) networks to remove staining variation. We improve upon the regular CycleGAN by incorporating residual learning. We comprehensively evaluate the performance of our stain transformation method and compare its usefulness in addition to extensive data augmentation to enhance the robustness of tissue segmentation algorithms. Our steps are as follows: first, we train a model to perform segmentation on tissue slides from a single source center, while heavily applying augmentations to increase robustness to unseen data. Second, we evaluate and compare the segmentation performance on data from other centers, both with and without applying our CycleGAN stain transformation. We compare segmentation performances in a colon tissue segmentation and kidney tissue segmentation task, covering data from 6 different centers. We show that our transformation method improves the overall Dice coefficient by 9% over the non-normalized target data and by 4% over traditional stain transformation in our colon tissue segmentation task. For kidney segmentation, our residual CycleGAN increases performance by 10% over no transformation and around 2% compared to the non-residual CycleGAN.

Immune Profiling of Histologic Growth Patterns of Colorectal Liver Metastases: Spatial Distribution and Phenotyping of T Lymphocytes, Cytotoxic T Cells and Tissue-resident Memory T Cells

Introduction: The nature of the of Colorectal Liver Metastases (CRCLM) display mainly three distinct histologic growths patterns that impact on disease progression and patient outcome after surgical resection. However limited studies indicate that immune cell infiltration is dictated by the CRCLM growth pattern. Methods: 22 CRCLM specimens were assessed by histological evaluation, and Multiplex Immunohistochemistry (OPALTM) was used to examine density and distribution of T lymphocytes (CD3+), cytotoxic T cells (CD3+CD8+), resident memory T cells (CD3+CD8+CD103+)(TRM). Cell phenotyping algorithm was performed using inForm® software v3.5. The tissue segmentation algorithm determined the adjacent liver parenchyma (LP), invasive tumor margin (IM) and tumor core (TC) regions. Results: Histological evaluation of the 22 CRCLM specimens defined 7 desmoplastic, 8 replacement and 7 pushing growth patterns. The evaluation of the entire cohort of CRCLM showed that the spatial distribution total T lymphocytes as well as cytotoxic and TRM were found in significantly higher levels at the IM when compared with LP or TC. There was no significant difference between the IM and TC in the T lymphocytes cell count displayed by replacement pattern, whereas the desmoplastic and pushing pattern showed higher accumulation in the IM compared to the TC. The highest cell count of cytotoxic T cells occurred in the IM for all three growth patterns but only significantly different from the TC in the desmoplastic and pushing pattern. Conclusion: This study unveiled the spatial variation of immune profiles according to histologic growth patterns of CRCLM using a powerful systematic imaging approach.

Segmentation of MRI brain scans using spatial constraints and 3D features.

This paper presents a novel unsupervised algorithm for brain tissue segmentation in magnetic resonance imaging (MRI). The proposed algorithm, named Gardens2, adopts a clustering approach to segment voxels of a given MRI into three classes: cerebrospinal fluid (CSF), gray matter (GM), and white matter (WM). Using an overlapping criterion, 3D feature descriptors and prior atlas information, Gardens2 generates a segmentation mask per class in order to parcellate the brain tissues. We assessed our method using three neuroimaging datasets: BrainWeb, IBSR18, and IBSR20, the last two provided by the Internet Brain Segmentation Repository. Its performance was compared with eleven well established as well as newly proposed unsupervised segmentation methods. Overall, Gardens2 obtained better segmentation performance than the rest of the methods in two of the three databases and competitive results when its performance was measured by class. Graphical Abstract Brain tissue segmentation using 3D features and an adjusted atlas template.

Segmentation Masks for the Mini-Mammographic Image Analysis Society (mini-MIAS) Database

Computer-aided diagnosis is a fast-developing area in medical practice and relies on the appropriate preprocessing of images from two dominant acquisition technologies, analog or film-based, and digital. Preprocessing consists of intensity equalization and segmentation of various objects in images. Here, we propose a methodology for the extraction of masks from manually segmented mammograms using affordable consumer electronic devices to provide manual segmentation performed by medical professionals. The result of this work is a database of hand-drawn segmentation masks for usage with the (mini)-MIAS database mammograms. This database can be used as a benchmarking tool for testing the accuracy of automatic breast tissue, pectoral muscle, and dense tissue segmentation algorithms.

A Novel Type-2 Fuzzy C-Means Clustering for Brain MR Image Segmentation.

The fuzzy C -means (FCM) clustering procedure is an unsupervised form of grouping the homogenous pixels of an image in the feature space into clusters. A brain magnetic resonance (MR) image is affected by noise and intensity inhomogeneity (IIH) during the acquisition process. FCM has been used in MR brain tissue segmentation. However, it does not consider the neighboring pixels for computing the membership values, thereby misclassifying the noisy pixels. The inaccurate cluster centers obtained in FCM do not address the problem of IIH. A fixed value of the fuzzifier ( m ) used in FCM brings uncertainty in controlling the fuzziness of the extracted clusters. To resolve these issues, we suggest a novel type-2 adaptive weighted spatial FCM (AWSFCM) clustering algorithm for MR brain tissue segmentation. The idea of type-2 FCM applied to the problem on hand is new and is reported in this article. The application of the proposed technique to the problem of MR brain tissue segmentation replaces the fixed fuzzifier value with a fuzzy linguistic fuzzifier value ( M ). The introduction of the spatial information in the membership function reduces the misclassification of noisy pixels. Furthermore, the incorporation of adaptive weights into the cluster center update function improves the accuracy of the final cluster centers, thereby reducing the effect of IIH. The suggested algorithm is evaluated using T1-w, T2-w, and proton density (PD) brain MR image slices. The performance is justified in terms of qualitative and quantitative measures followed by statistical analysis. The outcomes demonstrate the superiority and robustness of the algorithm in comparison to the state-of-the-art methods. This article is useful for the cybernetics application.

Dynamic programming and automated segmentation of optical coherence tomography images of the neonatal subglottis: enabling efficient diagnostics to manage subglottic stenosis.

.Subglottic stenosis (SGS) is a challenging disease to diagnose in neonates. Long-range optical coherence tomography (OCT) is an optical imaging modality that has been described to image the subglottis in intubated neonates. A major challenge associated with OCT imaging is the lack of an automated method for image analysis and micrometry of large volumes of data that are acquired with each airway scan (1 to 2 Gb). We developed a tissue segmentation algorithm that identifies, measures, and conducts image analysis on tissue layers within the mucosa and submucosa and compared these automated tissue measurements with manual tracings. We noted small but statistically significant differences in thickness measurements of the mucosa and submucosa layers in the larynx (), subglottis (), and trachea (). The automated algorithm was also shown to be over 8 times faster than the manual approach. Moderate Pearson correlations were found between different tissue texture parameters and the patient’s gestational age at birth, age in days, duration of intubation, and differences with age (mean age 17 days). Automated OCT data analysis is necessary in the diagnosis and monitoring of SGS, as it can provide vital information about the airway in real time and aid clinicians in making management decisions for intubated neonates.

Automatic proximal airway volume segmentation using optical coherence tomography for assessment of inhalation injury.

Acute respiratory distress syndrome (ARDS) is a severe form of acute lung injury with a mortality rate of up to 40%. Early management of ARDS has been difficult due to the lack of sensitive imaging tools and robust analysis software. We previously designed an optical coherence tomography (OCT) system to evaluate mucosa thickness (MT) after smoke inhalation, but the analysis relied on manual segmentation. The aim of this study is to assess in vivo proximal airway volume (PAV) after inhalation injury using automated OCT segmentation and correlate the PAV to lung function for rapid indication of ARDS. Anesthetized female Yorkshire pigs (n = 14) received smoke inhalation injury (SII) and 40% total body surface area thermal burns. Measurements of PaO2-to-FiO2 ratio (PFR), peak inspiratory pressure (PIP), dynamic compliance, airway resistance, and OCT bronchoscopy were performed at baseline, postinjury, 24 hours, 48 hours, 72 hours after injury. A tissue segmentation algorithm based on graph theory was used to reconstruct a three-dimensional (3D) model of lower respiratory tract and estimate PAV. Proximal airway volume was correlated with PFR, PIP, compliance, resistance, and MT measurement using a linear regression model. Proximal airway volume decreased after the SII: the group mean of proximal airway volume at baseline, postinjury, 24 hours, 48 hours, 72 hours were 20.86 cm (±1.39 cm), 17.61 cm (±0.99 cm), 14.83 cm (±1.20 cm), 14.88 cm (±1.21 cm), and 13.11 cm (±1.59 cm), respectively. The decrease in the PAV was more prominent in the animals that developed ARDS after 24 hours after the injury. PAV was significantly correlated with PIP (r = 0.48, p < 0.001), compliance (r = 0.55, p < 0.001), resistance (r = 0.35, p < 0.01), MT (r = 0.60, p < 0.001), and PFR (r = 0.34, p < 0.01). Optical coherence tomography is a useful tool to quantify changes in MT and PAV after SII and burns, which can be used as predictors of developing ARDS at an early stage. Prognostic, level III.

Abstract 220: Intra-tumor immune heterogeneity is associated with prognosis of oropharyngeal head and neck squamous cell carcinoma

Abstract As cell-cell interactions among tumor and immune cells are known to contribute to tumor progression, in depth evaluation of tumor-immune heterogeneity will enable biomarker-guided patient stratification and improvement of treatment response. Here we examined head and neck squamous cell carcinomas (HNSCC) to reveal the prognostic significance of leukocytes in tumors with regards to their complexity, effector status and spatial characteristics via multiplex immunohistochemistry and image cytometry. To accomplish this, we examined oropharyngeal HNSCC (N = 38), where lymphoid, myeloid, and hypo-inflamed leukocyte complexity correlated with HPV-status (Tsujikawa et al. Cell Reports, 2017). In the present study, quantitative analysis of cell density and distribution of 14-distinct immune cell lineages (e.g., CD8+ T cells, regulatory T cells, Th1, Th2, Th17, Th0 lymphocytes, B cells, NK cells, CD163+ and CD163- macrophages, mature and immature dendritic cells, mast cells, granulocytes) was analyzed via immune cell density mapping and tissue segmentation algorithms. We revealed tropism of polarized Th1-type cells within tumor nests versus stroma in HPV-associated HNSCC. In addition, Cox regression analysis of cell density and distribution of the 14 immune populations revealed that CD66b+ granulocyte infiltration within tumor nests reflected a negative prognostic indicator for HNSCC outcome. Furthermore, cell-cell proximity analysis in HPV-associated HNSCC further revealed a correlation between PD-L1 positive immune cells, and micro-regionally polarized immune characteristics biased towards Th1, coincident with high density of CD8+ T cells. These results reveal intra-tumor immune heterogeneity is associated with micro-regional immune complexity profiles, and provide insight into in situ immune characteristics that may aid patient stratification for immune therapy going forward. Acknowledgement: This project was supported by the Japan Society for the Promotion of Science Grant-in-Aid for Young Scientists (Start-up, 17H07016), Oregon Clinical and Translational Research Institute (OCTRI), grant number (UL1TR000128) from the National Center for Advancing Translational Sciences (NCATS) at the National Institutes of Health (NIH), and P30 CA069533-17 OHSU Knight Cancer Institute. LMC acknowledges support from the NIH/NCI, DOD BCRP Era of Hope Scholar Expansion Award, Susan G. Komen Foundation, Stand Up To Cancer - Lustgarten Foundation Pancreatic Cancer Convergence Dream Team Translational Research Grant, Breast Cancer Research Foundation, and the Brenden-Colson Center for Pancreatic Health. Citation Format: Takahiro Tsujikawa, Guillaume Thibault, Young Hwan Chang, Edward El Rassi, Daniel R. Clayburgh, David Sauer, Akihito Arai, Molly F. Kulesz-Martin, Motomi Mori, Shigeru Hirano, Paul W. Flint, Lisa M. Coussens. Intra-tumor immune heterogeneity is associated with prognosis of oropharyngeal head and neck squamous cell carcinoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2018; 2018 Apr 14-18; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2018;78(13 Suppl):Abstract nr 220.