scholarly journals A Promising and Challenging Approach: Radiologists’ Perspective on Deep Learning and Artificial Intelligence for Fighting COVID-19

Diagnostics ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 1924
Author(s):  
Tianming Wang ◽  
Zhu Chen ◽  
Quanliang Shang ◽  
Cong Ma ◽  
Xiangyu Chen ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Medical Imaging ◽  
Treatment Decision ◽  
Disease Diagnosis ◽  
Future Research ◽  
X Rays ◽  
Imaging Data ◽  
Efficacy Evaluation ◽  
Treatment Decision Making ◽  
Diagnosis And Classification

Chest X-rays (CXR) and computed tomography (CT) are the main medical imaging modalities used against the increased worldwide spread of the 2019 coronavirus disease (COVID-19) epidemic. Machine learning (ML) and artificial intelligence (AI) technology, based on medical imaging fully extracting and utilizing the hidden information in massive medical imaging data, have been used in COVID-19 research of disease diagnosis and classification, treatment decision-making, efficacy evaluation, and prognosis prediction. This review article describes the extensive research of medical image-based ML and AI methods in preventing and controlling COVID-19, and summarizes their characteristics, differences, and significance in terms of application direction, image collection, and algorithm improvement, from the perspective of radiologists. The limitations and challenges faced by these systems and technologies, such as generalization and robustness, are discussed to indicate future research directions.

Treatment Decision Making

2021 ◽  
pp. 573-577
Author(s):  
Allison Marziliano ◽  
Michael A. Diefenbach
Keyword(s):  
Decision Making ◽  
Cultural Differences ◽  
Gold Standard ◽  
Ethnic Disparities ◽  
Treatment Decision ◽  
Optimal Treatment ◽  
Future Research ◽  
Decision Tools ◽  
Treatment Decision Making ◽  
Racial Ethnic

This chapter focuses on the different facets of treatment decision making that have been empirically derived and are part of the peer-reviewed literature. These facets are approaches of treatment decision making (i.e. exploration and uptake of shared decision making, the current gold standard of treatment decision making); optimal treatment decision making (i.e. barriers and facilitators to engaging in optimal treatment decision making); support for treatment decision making (i.e. decision tools, nomograms, and seeking guidance on the Internet); the psychosocial state of patients following treatment decisions; and considerations related to studying treatment decision making (i.e. racial/ethnic disparities, cultural differences in decision making). Areas in which research is lacking or nonexistent (i.e. ensuring the patient understands the goals of treatment before making a treatment decision) are also highlighted as directions for future research.

scholarly journals Effective Diagnosis and Treatment through Content-Based Medical Image Retrieval (CBMIR) by Using Artificial Intelligence

2019 ◽  
Vol 8 (4) ◽  
pp. 462 ◽  
Author(s):  
Muhammad Owais ◽  
Muhammad Arsalan ◽  
Jiho Choi ◽  
Kang Ryoung Park
Keyword(s):  
Artificial Intelligence ◽  
Medical Imaging ◽  
Image Retrieval ◽  
Medical Image ◽  
Medical Images ◽  
Diagnosis And Treatment ◽  
Imaging Modalities ◽  
Imaging Data ◽  
Medical Database ◽  
Medical Image Retrieval

Medical-image-based diagnosis is a tedious task‚ and small lesions in various medical images can be overlooked by medical experts due to the limited attention span of the human visual system, which can adversely affect medical treatment. However, this problem can be resolved by exploring similar cases in the previous medical database through an efficient content-based medical image retrieval (CBMIR) system. In the past few years, heterogeneous medical imaging databases have been growing rapidly with the advent of different types of medical imaging modalities. Recently, a medical doctor usually refers to various types of imaging modalities all together such as computed tomography (CT), magnetic resonance imaging (MRI), X-ray, and ultrasound, etc of various organs in order for the diagnosis and treatment of specific disease. Accurate classification and retrieval of multimodal medical imaging data is the key challenge for the CBMIR system. Most previous attempts use handcrafted features for medical image classification and retrieval, which show low performance for a massive collection of multimodal databases. Although there are a few previous studies on the use of deep features for classification, the number of classes is very small. To solve this problem, we propose the classification-based retrieval system of the multimodal medical images from various types of imaging modalities by using the technique of artificial intelligence, named as an enhanced residual network (ResNet). Experimental results with 12 databases including 50 classes demonstrate that the accuracy and F1.score by our method are respectively 81.51% and 82.42% which are higher than those by the previous method of CBMIR (the accuracy of 69.71% and F1.score of 69.63%).

Real-world concordance of clinical practice with ASCO and NCCN guidelines for EGFR/ALK testing in aNSCLC.

2017 ◽  
Vol 35 (8_suppl) ◽  
pp. 212-212 ◽  
Author(s):  
John E. Ruggiero ◽  
Jay Rughani ◽  
Josh Neiman ◽  
Steven Swanson ◽  
Cindy Revol ◽  
...  
Keyword(s):  
Clinical Oncology ◽  
Real World ◽  
Treatment Decision ◽  
Disease Diagnosis ◽  
First Line ◽  
Nccn Guidelines ◽  
Treatment Decision Making ◽  
First Line Therapy ◽  
Line Therapy ◽  
Biomarker Testing

212 Background: Timely and appropriate biomarker testing guides evidence-based treatment decision-making in advanced non-small cell lung cancer (aNSCLC). American Society of Clinical Oncology (ASCO) and National Comprehensive Cancer Network (NCCN) guidelines recommend that all treatment-eligible patients with non-squamous, or squamous histology in non-smokers undergo EGFR and ALK biomarker testing prior to initiating first line therapy. Genentech’s Learning and Clinical Integration team and Flatiron Health explored the frequency of EGFR/ALK testing and overall time between advanced disease diagnosis, results receipt and treatment initiation in clinical oncology practices. Methods: Structured and unstructured data were obtained from Flatiron’s electronic health record database. 6,991 patients from 166 clinics diagnosed after 1/1/14 with at least 2 visits before 8/31/15 were randomly selected from the Flatiron aNSCLC national cohort of > 25,000 patients. Dates of specimen collection, results receipt and treatment start were collected. Results: EGFR/ALK testing was conducted in 75% of non-squamous patients with wide variation across practices (< 20% to 100%). For squamous patients, 15% were tested overall, but with dramatic variation across practices (0% to 100%). For patients with a positive test result available prior to initiation of first line treatment, 79% of EGFR+ and 94% of ALK+ patients received the appropriate targeted therapy. However, for those patients tested after initiation of first line therapy, only 41% of EGFR+ and 65% of ALK+ patients received appropriate targeted first line therapy. EGFR/ALK tests results were received > 4 weeks from aNSCLC diagnosis in 32% and 34% of patients, respectively. Validation testing indicated that delays were attributed to non-lab factors, as test results were returned in < 2 weeks in 95% of cases. Conclusions: Wide variation in real-world practice illustrates the need to improve adherence to ASCO and NCCN biomarker testing guidelines. Educational intervention to improve quality of care in aNSCLC should focus on ensuring testing of almost all non-squamous patients, limiting testing to the non-smoking squamous cell population, and ensuring timely ordering of testing by clinicians.

scholarly journals RadImageNet: A Large-scale Radiologic Dataset for Enhancing Deep Learning Transfer Learning Research

2021 ◽  
Author(s):  
Yang Yang ◽  
Xueyan Mei ◽  
Philip Robson ◽  
Brett Marinelli ◽  
Mingqian Huang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Medical Imaging ◽  
Transfer Learning ◽  
Large Scale ◽  
Medical Images ◽  
Bone Age ◽  
Natural World ◽  
X Rays ◽  
Starting Point ◽  
Size Diversity

Abstract Most current medical imaging Artificial Intelligence (AI) relies upon transfer learning using convolutional neural networks (CNNs) created using ImageNet, a large database of natural world images, including cats, dogs, and vehicles. Size, diversity, and similarity of the source data determine the success of the transfer learning on the target data. ImageNet is large and diverse, but there is a significant dissimilarity between its natural world images and medical images, leading Cheplygina to pose the question, “Why do we still use images of cats to help Artificial Intelligence interpret CAT scans?”. We present an equally large and diversified database, RadImageNet, consisting of 5 million annotated medical images consisting of CT, MRI, and ultrasound of musculoskeletal, neurologic, oncologic, gastrointestinal, endocrine, and pulmonary pathologies over 450,000 patients. The database is unprecedented in scale and breadth in the medical imaging field, constituting a more appropriate basis for medical imaging transfer learning applications. We found that RadImageNet transfer learning outperformed ImageNet in multiple independent applications, including improvements for bone age prediction from hand and wrist x-rays by 1.75 months (p<0.0001), pneumonia detection in ICU chest x-rays by 0.85% (p<0.0001), ACL tear detection on MRI by 10.72% (p<0.0001), SARS-CoV-2 detection on chest CT by 0.25% (p<0.0001) and hemorrhage detection on head CT by 0.13% (p<0.0001). The results indicate that our pre-trained models that are open-sourced on public domains will be a better starting point for transfer learning in radiologic imaging AI applications, including applications involving medical imaging modalities or anatomies not included in the RadImageNet database.

scholarly journals Review and Prospect: Artificial Intelligence in Advanced Medical Imaging

2021 ◽  
Vol 1 ◽  
Author(s):  
Shanshan Wang ◽  
Guohua Cao ◽  
Yan Wang ◽  
Shu Liao ◽  
Qian Wang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Medical Imaging ◽  
Imaging Data ◽  
Resonance Imaging ◽  
Volumetric Imaging ◽  
Positron Emission ◽  
Potential Applications ◽  
Magnetic Resonance Imaging Mri

Artificial intelligence (AI) as an emerging technology is gaining momentum in medical imaging. Recently, deep learning-based AI techniques have been actively investigated in medical imaging, and its potential applications range from data acquisition and image reconstruction to image analysis and understanding. In this review, we focus on the use of deep learning in image reconstruction for advanced medical imaging modalities including magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET). Particularly, recent deep learning-based methods for image reconstruction will be emphasized, in accordance with their methodology designs and performances in handling volumetric imaging data. It is expected that this review can help relevant researchers understand how to adapt AI for medical imaging and which advantages can be achieved with the assistance of AI.

scholarly journals Nail Disease: Clinical Decisions among Portuguese Dermatologists and Family Physicians

2020 ◽  
pp. 1-5
Author(s):  
Ana Filipe Monteiro ◽  
Rita Ramos Pinheiro ◽  
Célia Galhardas ◽  
André Lencastre
Keyword(s):  
Online Survey ◽  
Correct Diagnosis ◽  
Family Physicians ◽  
Treatment Decision ◽  
Disease Diagnosis ◽  
Diagnostic Methods ◽  
Treatment Decision Making ◽  
Local Institution ◽  
The Family ◽  
Nail Disease

Onychomycosis is one of the most common nail disorders and may be difficult to distinguish from other causes of nail dystrophy, based on clinical grounds alone. With this study, we aimed to describe the use of fungal testing by dermatologists and family physicians in their daily current practice, analyze their respective familiarity with nail disease diagnosis, and ultimately treatment decision-making by both groups. An online survey was distributed among Portuguese dermatologists, trainees, and family physicians by email. The survey focused on the diagnostic impression, use of diagnostic methods to confirm a fungal infection, and the subsequent assessment of treatment. One hundred fifty-one responses were obtained, 60 (39.7%) from dermatologists and 91 (60.3%) from family physicians; 98.3% of dermatologists mentioned usually requesting a fungal testing at their local institution or outside, while this percentage was 50.5% among family physicians (<i>p</i> &#x3c; 0.001). Regarding the diagnosis, the median of correct diagnosis by the dermatologist group was higher (10/15) than the family physicians (6/15). Considering the treatment strategy, we observed that in the dermatologists’ group it would result in unnecessary treatment in a median of 2 cases, while in the family physicians’ group, in a median of 4 cases.

scholarly journals Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations

2021 ◽  
Author(s):  
Laleh Seyyed-Kalantari ◽  
Haoran Zhang ◽  
Matthew B. A. McDermott ◽  
Irene Y. Chen ◽  
Marzyeh Ghassemi
Keyword(s):  
Artificial Intelligence ◽  
Medical Imaging ◽  
Low Socioeconomic Status ◽  
Disease Diagnosis ◽  
Low Socioeconomic ◽  
X Ray ◽  
Female Patients ◽  
Pathology Classification ◽  
Black Patients ◽  
Chest X Ray

AbstractArtificial intelligence (AI) systems have increasingly achieved expert-level performance in medical imaging applications. However, there is growing concern that such AI systems may reflect and amplify human bias, and reduce the quality of their performance in historically under-served populations such as female patients, Black patients, or patients of low socioeconomic status. Such biases are especially troubling in the context of underdiagnosis, whereby the AI algorithm would inaccurately label an individual with a disease as healthy, potentially delaying access to care. Here, we examine algorithmic underdiagnosis in chest X-ray pathology classification across three large chest X-ray datasets, as well as one multi-source dataset. We find that classifiers produced using state-of-the-art computer vision techniques consistently and selectively underdiagnosed under-served patient populations and that the underdiagnosis rate was higher for intersectional under-served subpopulations, for example, Hispanic female patients. Deployment of AI systems using medical imaging for disease diagnosis with such biases risks exacerbation of existing care biases and can potentially lead to unequal access to medical treatment, thereby raising ethical concerns for the use of these models in the clinic.

scholarly journals P099 Evaluation of endoscopic mayo score with an artificial intelligence algorithm

2021 ◽  
Vol 15 (Supplement_1) ◽  
pp. S195-S196
Author(s):  
H T Kani ◽  
I Ergenc ◽  
G Polat ◽  
Y Ozen Alahdab ◽  
A Temizel ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Treatment Plan ◽  
Treatment Decision ◽  
Diagnostic Algorithm ◽  
Disease Diagnosis ◽  
High Accuracy ◽  
Mayo Score ◽  
Artificial Intelligence Algorithm ◽  
The Mean ◽  
Scoring Tool

Abstract Background Multi-layered convolutional neural networks are artificial intelligence (AI) algorithms that allow to process specific datasets. Endoscopic mayo score (EMS) is an endoscopic scoring tool for ulcerative colitis (UC) that is widely using for evaluating the disease activity to make a further treatment plan. EMS is an endoscopist-depended subjective tool that varies according to the physician’s experience. In this study, our aim was to create a high accuracy EMS diagnostic algorithm to minimize endoscopist-depended inconsistency and standardize the patient care. Methods We collected the endoscopic images of UC patients between December 2011 and July 2019 from electronic database of our gastroenterology institute. Images with insufficient bowel cleaning, artifact, retroflection images, terminal ileum images and pouch patients were excluded. Two blinded gastroenterologists evaluated and tagged the images according to the EMS. Images with a disagreement were excluded for a further evaluation. AI algorithm was performed with Python by using PyTorch library. The dataset was divided into two (85% was used for training and %15 was used for test). ResNet18 model was also used for training. Results A total of 19690 images of 572 patients from 1053 colonoscopies were identified for the study. The mean procedure number was 1.8 per patient and the mean image number was 18.7 for per colonoscopy. Four thousand and six hundred images without any disagreement between two gastroenterologists were included to the analysis. Two thousand eight hundred and thirteen (61.65%) images were tagged as EMS 0, 956 (20.66%) were tagged as EMS 1, 406 (8.77%) were tagged as EMS 2 and 413 (8.92%) were tagged as EMS 3. Accuracy was found 73.16% with a sensitivity of 773.2% and specifity of 92.9% in assessment of all EMS groups (Image 1). Also, the accuracy of severe mucosal disease diagnosis (EMS 0 and 1 vs EMS 2 and 3) was 96.3% with a sensitivity of 98.2% and specifity of 86.5% (Image 2) with a perfect reproductivity (к: 1.00). The performance of the remission diagnosis (EMS 0 vs EMS 1,2 and 3) was done with a 92% accuracy. Conclusion This is an ongoing study and the preliminary results of our EMS diagnosis algorithm was promising with a high accuracy. The accuracy and sensitivity would be improved by including more images and improving the algorithm. The use of AI in daily IBD practice can eliminate the subjectivity according to the endoscopist in diagnosis and assessing the disease severity for treatment decision.

Sign in / Sign up

Export Citation Format

Share Document