Generate Structured Radiology Report from CT Images Using Image Annotation Techniques: Preliminary Results with Liver CT

Loveymi, Samira; Dezfoulian, Mir Hossein; Mansoorizadeh, Muharram

doi:10.1007/s10278-019-00298-w

Cited by 8 publications

(17 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accuracy is the sole measure for evaluation and comparison of the developed approaches,[ 4 5 6 12 13 31 ] and the performance of the systems is evaluated via accuracy: the ratio of correctly labeled instances to all the instances. In our work, for each question that is about liver and its lesions or vessels, a specific model is learned.…”

Section: Resultsmentioning

confidence: 99%

“…Table 2 reports the recognition rates of three deep features for individual questions, compared with that of a study by Loveymi et al .,[ 4 ] which uses handcrafted features and finds the best feature set for every question, separately. Question# in Table 2 and Figure 5 refers to the number in the rightmost column of Table 3 .…”

Section: Discussionmentioning

confidence: 99%

“…The automatic structured report generation system could be defined as a system that annotates medical images with clinical and specialized prior information, or a system that answers several clinical questions, given the patient's medical image. To this end, the medical image (e.g., radiology) automatic report generation involves conducting the following tasks: question answering,[ 2 3 ] image annotation,[ 4 5 6 ] or image classification tasks. [ 7 8 9 ] For the development of such systems, the main approaches in the literature are based on classic pattern recognition or modern deep learning methods.…”

Section: Introductionmentioning

confidence: 99%

“…In this method, SVMs, linear discriminant models, and logistic regression are used as binary classifiers and trained on the histogram of the gray levels (Hounsfield units) in the lesion regions. Loveymi et al .,[ 4 ] investigated the issue of the diversity of the question types and tried to alleviate it via learning question-specific models. Along with the classic shape and texture features, they introduced novel spatio-temporal texture features to address this issue.…”

Section: Introductionmentioning

confidence: 99%

“…[ 5 6 12 13 ] This is unavoidable if one ought to apply classic features. To circumvent this problem, in our previous work,[ 4 ] we analyzed every question independently and found the most discriminative handcrafted features for each question (task) through feature selection methods. Although the first strategy (using the same set of features for all tasks) has lower training overhead as it does not involve any feature-filtering process, it leads to poorer overall performance.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automatic Generation of Structured Radiology Reports for Volumetric Computed Tomography Images Using Question-Specific Deep Feature Extraction and Learning

Loveymi

Dezfoulian

Mansoorizadeh

2021

Journal of Medical Signals &Amp; Sensors

Self Cite

View full text Add to dashboard Cite

Background: In today's modern medicine, the use of radiological imaging devices has spread at medical centers. Therefore, the need for accurate, reliable, and portable medical image analysis and understanding systems has been increasing constantly. Accompanying images with the required clinical information, in the form of structured reports, is very important, because images play a pivotal role in detect, planning, and diagnosis of different diseases. Report-writing can be exposure to error, tedious and labor-intensive for physicians and radiologists; to address these issues, there is a need for systems that generate medical image reports automatically and efficiently. Thus, automatic report generation systems are among the most desired applications. Methods: This research proposes an automatic structured-radiology report generation system that is based on deep learning methods. Extracting useful and descriptive image features to model the conceptual contents of the images is one of the main challenges in this regard. Considering the ability of deep neural networks (DNNs) in soliciting informative and effective features as well as lower resource requirements, tailored convolutional neural networks and MobileNets are employed as the main building blocks of the proposed system. To cope with challenges such as multi-slice medical images and diversity of questions asked in a radiology report, our system develops volume-level and question-specific deep features using DNNs. Results: We demonstrate the effectiveness of the proposed system on ImageCLEF2015 Liver computed tomography (CT) annotation task, for filling in a structured radiology report about liver CT. The results confirm the efficiency of the proposed approach, as compared to classic annotation methods. Conclusion: We have proposed a question-specific DNNbased system for filling in structured radiology reports about medical images.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automatic Generation of Structured Radiology Reports for Volumetric Computed Tomography Images Using Question-Specific Deep Feature Extraction and Learning

Loveymi

Dezfoulian

Mansoorizadeh

2021

Journal of Medical Signals &Amp; Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

COVID-19–affected medical image analysis using DenserNet

Adak¹,

Ghosh²,

Chowdhury

et al. 2021

Data Science for COVID-19

View full text Add to dashboard Cite

Explainable medical imaging AI needs human-centered design: guidelines and evidence from a systematic review

et al. 2022

View full text Add to dashboard Cite

Transparency in Machine Learning (ML), often also referred to as interpretability or explainability, attempts to reveal the working mechanisms of complex models. From a human-centered design perspective, transparency is not a property of the ML model but an affordance, i.e., a relationship between algorithm and users. Thus, prototyping and user evaluations are critical to attaining solutions that afford transparency. Following human-centered design principles in highly specialized and high stakes domains, such as medical image analysis, is challenging due to the limited access to end users and the knowledge imbalance between those users and ML designers. To investigate the state of transparent ML in medical image analysis, we conducted a systematic review of the literature from 2012 to 2021 in PubMed, EMBASE, and Compendex databases. We identified 2508 records and 68 articles met the inclusion criteria. Current techniques in transparent ML are dominated by computational feasibility and barely consider end users, e.g. clinical stakeholders. Despite the different roles and knowledge of ML developers and end users, no study reported formative user research to inform the design and development of transparent ML models. Only a few studies validated transparency claims through empirical user evaluations. These shortcomings put contemporary research on transparent ML at risk of being incomprehensible to users, and thus, clinically irrelevant. To alleviate these shortcomings in forthcoming research, we introduce the INTRPRT guideline, a design directive for transparent ML systems in medical image analysis. The INTRPRT guideline suggests human-centered design principles, recommending formative user research as the first step to understand user needs and domain requirements. Following these guidelines increases the likelihood that the algorithms afford transparency and enable stakeholders to capitalize on the benefits of transparent ML.

show abstract

Generate Structured Radiology Report from CT Images Using Image Annotation Techniques: Preliminary Results with Liver CT

Cited by 8 publications

References 32 publications

Automatic Generation of Structured Radiology Reports for Volumetric Computed Tomography Images Using Question-Specific Deep Feature Extraction and Learning

Automatic Generation of Structured Radiology Reports for Volumetric Computed Tomography Images Using Question-Specific Deep Feature Extraction and Learning

COVID-19–affected medical image analysis using DenserNet

Explainable medical imaging AI needs human-centered design: guidelines and evidence from a systematic review

Contact Info

Product

Resources

About