Artificial Intelligence-based Eosinophil Counting in Gastrointestinal Biopsies

• URL: http://arxiv.org/abs/2211.15667v1
• Date: Fri, 25 Nov 2022 07:18:28 GMT
• Title: Artificial Intelligence-based Eosinophil Counting in Gastrointestinal Biopsies
• Authors: Harsh Shah, Thomas Jacob, Amruta Parulekar, Anjali Amarapurkar, Amit Sethi
• Abstract summary: Normally eosinophils are present in the gastrointestinal (GI) tract of healthy individuals. When the eosinophils increase beyond their usual amount in the GI tract, a patient gets varied symptoms. Histopathology is the gold standard in the diagnosis for this condition. In this study, we trained and tested a deep neural network based on UNet to detect and count eosinophils in GI tract biopsies.
• Score: 1.7869681025240884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Normally eosinophils are present in the gastrointestinal (GI) tract of healthy individuals. When the eosinophils increase beyond their usual amount in the GI tract, a patient gets varied symptoms. Clinicians find it difficult to diagnose this condition called eosinophilia. Early diagnosis can help in treating patients. Histopathology is the gold standard in the diagnosis for this condition. As this is an under-diagnosed condition, counting eosinophils in the GI tract biopsies is important. In this study, we trained and tested a deep neural network based on UNet to detect and count eosinophils in GI tract biopsies. We used connected component analysis to extract the eosinophils. We studied correlation of eosinophilic infiltration counted by AI with a manual count. GI tract biopsy slides were stained with H&E stain. Slides were scanned using a camera attached to a microscope and five high-power field images were taken per slide. Pearson correlation coefficient was 85% between the machine-detected and manual eosinophil counts on 300 held-out (test) images.

Related papers

• Automatic Tissue Differentiation in Parotidectomy using Hyperspectral Imaging [43.158227137013874]
  A 3D Convolutional Neural Network with hyperspectral data in the range of $400-1000$ nm is used in this work. The acquisition system consisted of two multispectral snapshot cameras creating a stereo-HSI-system.
  arXiv  Detail & Related papers  (2024-12-06T09:20:59Z)
• Cross-organ Deployment of EOS Detection AI without Retraining: Feasibility and Limitation [6.200516824977507]
  Chronic rhinosinusitis (CRS) is characterized by persistent inflammation in the paranasal sinuses. Eos, a crucial component in the mucosal immune response, have been linked to disease severity in CRS. The diagnosis of eosinophilic CRS typically uses a threshold of 10-20 eos per high-power field (HPF)
  arXiv  Detail & Related papers  (2024-11-24T18:01:13Z)
• Harnessing Artificial Intelligence to Infer Novel Spatial Biomarkers for the Diagnosis of Eosinophilic Esophagitis [0.0]
  Eosinophilic esophagitis (EoE) is a chronic allergic inflammatory condition of the esophagus associated with elevated esophageal eosinophils. EoE diagnosis requires enumerating the density of esophageal eosinophils in esophageal biopsies. Here, we develop an artificial intelligence platform that infers biomarkers based on semantic segmentation of intact eosinophils and basal zone distributions.
  arXiv  Detail & Related papers  (2022-05-26T18:59:47Z)
• Lymphocyte Classification in Hyperspectral Images of Ovarian Cancer Tissue Biopsy Samples [94.37521840642141]
  We present a machine learning pipeline to segment white blood cell pixels in hyperspectral images of biopsy cores. These cells are clinically important for diagnosis, but some prior work has struggled to incorporate them due to difficulty obtaining precise pixel labels.
  arXiv  Detail & Related papers  (2022-03-23T00:58:27Z)
• Automatic Classification of Neuromuscular Diseases in Children Using Photoacoustic Imaging [77.32032399775152]
  Neuromuscular diseases (NMDs) cause a significant burden for both healthcare systems and society. They can lead to severe progressive muscle weakness, muscle degeneration, contracture, deformity and progressive disability.
  arXiv  Detail & Related papers  (2022-01-27T16:37:19Z)
• COVID-19 Detection from Chest X-ray Images using Imprinted Weights Approach [67.05664774727208]
  Chest radiography is an alternative screening method for the COVID-19. Computer-aided diagnosis (CAD) has proven to be a viable solution at low cost and with fast speed. To address this challenge, we propose the use of a low-shot learning approach named imprinted weights.
  arXiv  Detail & Related papers  (2021-05-04T19:01:40Z)
• PECNet: A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Biopsy Diagnostics [0.0]
  Eosinophilic esophagitis (EoE) is an allergic inflammatory condition of the esophagus associated with elevated numbers of eosinophils. Herein, we aimed to use machine learning to identify, quantitate and diagnose EoE. PECNet was able to quantitate intact eosinophils with a mean absolute error of 0.611 eosinophils and classify EoE disease activity with an accuracy of 98.5%.
  arXiv  Detail & Related papers  (2021-03-02T20:37:57Z)
• Advancing Eosinophilic Esophagitis Diagnosis and Phenotype Assessment with Deep Learning Computer Vision [0.7915536524413249]
  Eosinophilic Esophagitis (EoE) is an inflammatory esophageal disease which is increasing in prevalence. We propose an automated approach for quantifying eosinophils using deep image segmentation. A U-Net model and post-processing system are applied to generate eosinophil-based statistics that can diagnose EoE as well as describe disease severity and progression.
  arXiv  Detail & Related papers  (2021-01-13T20:01:48Z)
• Machine learning approach for biopsy-based identification of eosinophilic esophagitis reveals importance of global features [0.0]
  Eosinophilic esophagitis (EoE) is an allergic inflammatory condition characterized by eosinophil accumulation in the esophageal mucosa. One of the main challenges in automating this process is detecting features that are small relative to the size of the biopsy. We developed a platform based on a deep convolutional neural network (DCNN) that can classify esophageal biopsies with an accuracy of 85%.
  arXiv  Detail & Related papers  (2021-01-13T10:38:46Z)
• JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation [95.57532063232198]
  coronavirus disease 2019 (COVID-19) has caused a pandemic disease in over 200 countries. To control the infection, identifying and separating the infected people is the most crucial step. This paper develops a novel Joint Classification and (JCS) system to perform real-time and explainable COVID-19 chest CT diagnosis.
  arXiv  Detail & Related papers  (2020-04-15T12:30:40Z)
• Lung Infection Quantification of COVID-19 in CT Images with Deep Learning [41.35413216175024]
  Deep learning system developed to automatically quantify infection regions of interest. Human-in-the-loop strategy adopted to assist radiologists for infection region segmentation.
  arXiv  Detail & Related papers  (2020-03-10T11:58:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.