Automatic Acquisition of Immune Cells Location Using Deep Learning for Automated Analysis

Abstract To investigate the performance of a deep learning-based algorithm for fully automated quantification of left ventricular (LV) volumes and function in cardiac MRI. We retrospectively analysed MR examinations of 50 patients (74% men, median age 57 years). The most common indications were known or suspected ischemic heart disease, cardiomyopathies or myocarditis. Fully automated analysis of LV volumes and function was performed using a deep learning-based algorithm. The analysis was subsequently corrected by a senior cardiovascular radiologist. Manual volumetric analysis was performed by two radiology trainees. Volumetric results were compared using Bland–Altman statistics and intra-class correlation coefficient. The frequency of clinically relevant differences was analysed using re-classification rates. The fully automated volumetric analysis was completed in a median of 8 s. With expert review and corrections, the analysis required a median of 110 s. Median time required for manual analysis was 3.5 min for a cardiovascular imaging fellow and 9 min for a radiology resident (p < 0.0001 for all comparisons). The correlation between fully automated results and expert-corrected results was very strong with intra-class correlation coefficients of 0.998 for end-diastolic volume, 0.997 for end-systolic volume, 0.899 for stroke volume, 0.972 for ejection fraction and 0.991 for myocardial mass (all p < 0.001). Clinically meaningful differences between fully automated and expert corrected results occurred in 18% of cases, comparable to the rate between the two manual readers (20%). Deep learning-based fully automated analysis of LV volumes and function is feasible, time-efficient and highly accurate. Clinically relevant corrections are required in a minority of cases.

Download Full-text

Instance segmentation of immune cells in human lupus nephritis using deep learning: comparing performance on sample preparation and staining panels

Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues XVIII ◽

10.1117/12.2545110 ◽

2020 ◽

Cited By ~ 1

Author(s):

Madeleine S. Durkee ◽

Rebecca Abraham ◽

Adam R. Sibley ◽

Benjamin A. Cifu ◽

Junting Ai ◽

...

Keyword(s):

Deep Learning ◽

Lupus Nephritis ◽

Sample Preparation ◽

Immune Cells ◽

Instance Segmentation

Download Full-text

Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey

Contrast Media & Molecular Imaging ◽

10.1155/2017/9512370 ◽

2017 ◽

Vol 2017 ◽

pp. 1-10 ◽

Cited By ~ 17

Author(s):

Yong Xue ◽

Shihui Chen ◽

Jing Qin ◽

Yong Liu ◽

Bingsheng Huang ◽

...

Keyword(s):

Deep Learning ◽

Molecular Imaging ◽

Automated Analysis ◽

Visual Assessment ◽

Cellular Level ◽

Machine Learning Techniques ◽

Survival Prediction ◽

Learning Techniques ◽

Tumor Lesion ◽

Molecular Images

Molecular imaging enables the visualization and quantitative analysis of the alterations of biological procedures at molecular and/or cellular level, which is of great significance for early detection of cancer. In recent years, deep leaning has been widely used in medical imaging analysis, as it overcomes the limitations of visual assessment and traditional machine learning techniques by extracting hierarchical features with powerful representation capability. Research on cancer molecular images using deep learning techniques is also increasing dynamically. Hence, in this paper, we review the applications of deep learning in molecular imaging in terms of tumor lesion segmentation, tumor classification, and survival prediction. We also outline some future directions in which researchers may develop more powerful deep learning models for better performance in the applications in cancer molecular imaging.

Download Full-text

The spatial localization of CD163+ tumor-associated macrophages predicts prognosis and response to therapy in inflammatory breast cancer.

Journal of Clinical Oncology ◽

10.1200/jco.2020.38.15_suppl.3086 ◽

2020 ◽

Vol 38 (15_suppl) ◽

pp. 3086-3086

Author(s):

Christophe Van Berckelaer ◽

Charlotte Rypens ◽

Steven Van Laere ◽

Koen Marien ◽

Pieter-Jan Van Dam ◽

...

Keyword(s):

Breast Cancer ◽

T Cells ◽

Deep Learning ◽

Tumor Cells ◽

Inflammatory Breast Cancer ◽

Immune Cells ◽

Multivariate Model ◽

Response To Therapy ◽

Tumor Associated Macrophages ◽

Cd8 Cells

3086 Background: The mechanisms contributing to the aggressive biology of inflammatory breast cancer (IBC) are under investigation. A specific immune response seems to be an important driver, but the functional role of infiltrating immune cells in IBC remains unclear. Tumor-associated macrophages (TAMs) are associated with worse outcome, while CD8+ cytotoxic T cells demonstrate anti-tumor properties in breast cancer. In this study, we assessed spatial associations between CD163+ TAMs, CD8+ cells and cancer cells in IBC, using deep-learning and ecological statistics. Methods: We collected clinicopathological variables, evaluated PDL1-positivity (SP142, Ventana) and scored TILs according to the TIL working group guidelines on H&E slides for 144 IBC patients. Immunostainings for CD8 and CD163 (Hematoxylin-DAB) were done according to validated protocols. All slides were digitized, underwent virtual multiplexing and were evaluated in Visiopharm to quantify the number of DAB+ immune cells. Each immune cell was located using XY coordinates and spatial interactions were examined using a Morisita Horn Index (MHI). Tumor cell coordinates were collected using a deep-learning algorithm applied to the CD8-stained slide. This algorithm was trained in 18 images with more than 150.000 iterations (Deeplabv3+). Results: Complete pathological response (pCR) after neo-adjuvant chemotherapy was achieved by 30.6% (n= 30/98) of the patients with initially localized disease. Besides PDL1-postivity ( P= .03), infiltration with CD8+ T cells ( P= .02) and TAMs ( P= .01) also predicted pCR. However, a likelihood ratio test showed no difference between a model using CD8+ cells, TAMs or TILs. Interestingly, the colocalization of CD163+ and CD8+ cells (MHI >0.83) was associated with pCR (P= .01) and remained significant in a multivariate model (OR: 3.18; 95% CI: 1.04 – 10.6; P= .05) including TIL score, PDL1-positivity and hormone receptor (HR) status. Furthermore, a shorter disease-free survival (DFS) was associated with HR- status, no pCR and the colocalization of TAMs near tumor cells (HR: 3.3; 95% CI: 1.6 – 7.1; P= .002) in a multivariate model. The density of TAMs was not associated with outcome. Conclusions: The impact of TAMs on clinical outcome appears to depend on the spatial arrangement. The number of TAMs solely was not associated with outcome, but patients with more TAMs in proximity of the tumor cells had a worse DFS. Surprisingly, the clustering of TAMs near CD8+ cells was associated with pCR independent of the number of TAMs or TILs.

Download Full-text

CoRE-ATAC: A deep learning model for the functional classification of regulatory elements from single cell and bulk ATAC-seq data

PLoS Computational Biology ◽

10.1371/journal.pcbi.1009670 ◽

2021 ◽

Vol 17 (12) ◽

pp. e1009670

Author(s):

Asa Thibodeau ◽

Shubham Khetan ◽

Alper Eroglu ◽

Ryan Tewhey ◽

Michael L. Stitzel ◽

...

Keyword(s):

Deep Learning ◽

Immune Cells ◽

Single Cells ◽

Cell Types ◽

Regulatory Elements ◽

Enhancer Activity ◽

Specific Variation ◽

Single Nucleus ◽

Model Training ◽

Gain Loss

Cis-Regulatory elements (cis-REs) include promoters, enhancers, and insulators that regulate gene expression programs via binding of transcription factors. ATAC-seq technology effectively identifies active cis-REs in a given cell type (including from single cells) by mapping accessible chromatin at base-pair resolution. However, these maps are not immediately useful for inferring specific functions of cis-REs. For this purpose, we developed a deep learning framework (CoRE-ATAC) with novel data encoders that integrate DNA sequence (reference or personal genotypes) with ATAC-seq cut sites and read pileups. CoRE-ATAC was trained on 4 cell types (n = 6 samples/replicates) and accurately predicted known cis-RE functions from 7 cell types (n = 40 samples) that were not used in model training (mean average precision = 0.80, mean F1 score = 0.70). CoRE-ATAC enhancer predictions from 19 human islet samples coincided with genetically modulated gain/loss of enhancer activity, which was confirmed by massively parallel reporter assays (MPRAs). Finally, CoRE-ATAC effectively inferred cis-RE function from aggregate single nucleus ATAC-seq (snATAC) data from human blood-derived immune cells that overlapped with known functional annotations in sorted immune cells, which established the efficacy of these models to study cis-RE functions of rare cellswithout the need for cell sorting. ATAC-seq maps from primary human cells reveal individual- and cell-specific variation in cis-RE activity. CoRE-ATAC increases the functional resolution of these maps, a critical step for studying regulatory disruptions behind diseases.

Download Full-text

Automated Analysis of Three-dimensional CBCT Images Taken in Natural Head Position That Combines Facial Profile Processing and Multiple Deep-learning Models

10.21203/rs.3.rs-795041/v1 ◽

2021 ◽

Author(s):

Janghoon Ahn ◽

Thong Phi Nguyen ◽

Yoon-Ji Kim ◽

Taeyong Kim ◽

Jonghun Yoon

Keyword(s):

Deep Learning ◽

Profile Analysis ◽

Traditional Approach ◽

Three Dimensional ◽

Image Data ◽

Automated Analysis ◽

Head Position ◽

X Rays ◽

Learning Models ◽

Facial Profile

Abstract Analysing cephalometric X-rays, which is mostly performed by orthodontists or dentists, is an indispensable procedure for diagnosis and treatment planning with orthodontic patients. Artificial intelligence, especially deep-learning techniques for analysing image data, shows great potential for medical and dental image analysis and diagnosis. To explore the feasibility of automating measurement of 13 geometric parameters from three-dimensional cone beam computed tomography (CBCT) images taken in a natural head position, we here describe a smart system that combines a facial profile analysis algorithm with deep-learning models. Using multiple views extracted from the CBCT data as the dataset, our proposed method partitions and detects regions of interest by extracting the facial profile and applying Mask-RCNN, a trained decentralized convolutional neural network (CNN) that positions the key parameters. All the techniques are integrated into a software application with a graphical user interface designed for user convenience. To demonstrate the system’s ability to replace human experts, we validated the performance of the proposed method by comparing it with measurements made by two orthodontists and one advanced general dentist using a commercial dental program. The time savings compared with the traditional approach was remarkable, reducing the processing time from about 30 minutes to about 30 seconds.

Download Full-text

Deep Learning-Based Segmentation and Uncertainty Assessment for Automated Analysis of Myocardial Perfusion MRI Datasets Using Patch-Level Training and Advanced Data Augmentation

10.1109/embc46164.2021.9629581 ◽

2021 ◽

Cited By ~ 1

Author(s):

Dilek Mirgun Yalcinkaya ◽

Khalid Youssef ◽

Bobby Heydari ◽

Luis Zamudio ◽

Rohan Dharmakumar ◽

...

Keyword(s):

Deep Learning ◽

Myocardial Perfusion ◽

Data Augmentation ◽

Automated Analysis ◽

Uncertainty Assessment ◽

Perfusion Mri ◽

Level Training

Download Full-text

Image intelligent automatic processing analysis based on artificial intelligence vision generator

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189447 ◽

2020 ◽

pp. 1-10

Author(s):

Ruijuan Wang ◽

Wei Zhuo

Keyword(s):

Artificial Intelligence ◽

Image Processing ◽

Deep Learning ◽

Human Error ◽

Processing System ◽

Image Data ◽

Visual Image ◽

Automated Analysis ◽

Learning Method ◽

Deep Learning Model

The image intelligent processing analysis technology uses a computer to imitate and execute some intellectual functions of the human brain, and realizes an image processing system with artificial intelligence, that is, an image processing analysis technology is an understanding of an image. The degree of intelligent automated analysis and processing is low, many operations need to be done manually, causing human error, inaccurate detection, and time-consuming and laborious. Deep learning method can extract features step by step in the original image from the bottom to the top. Therefore, based on feature analysis technology, this paper uses the deep learning method to intelligently and automatically analyse the visual image. This method only needs to send the image into the system, and then the manual analysis is not needed, and the analysis result of the final image can be obtained. The process is completely intelligent and automatically processed. First, improve the deep learning model and use massive image data to choose and optimize parameters. Results indicate that our method not only automatically derives the semantic information of the image, but also accurately understands the image accurately and improve the work efficiency.

Download Full-text