EDICNet: An end-to-end detection and interpretable malignancy classification network for pulmonary nodules in computed tomography

Lin, Yannan; Wei, Leihao; Han, Steve; Aberle, Denise R.; Hsu, William

doi:10.1117/12.2551220

Cited by 12 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…were frequently used to establish transparent systems. There existed two main ways to use human-understandable features in medical imaging: (1) Extracting hand-crafted features, e.g., morphological and radiomic features, from predicted segmentation masks generated by a non-transparent model [70][71][72][73][74][75][76][77][78][79] followed by analysis of those hand-crafted features using a separate classification module; (2) Directly predicting human-understandable features together with the main classification and detection task [80][81][82][83][84] . In these approaches, all tasks usually shared the same network architecture and parameter weights.…”

Section: In: Interpretabilitymentioning

confidence: 99%

“…Morphological features, e.g., texture, shape and edge features were frequently considered and used to support the transparency of ML systems 70,72,73,75,76,81,83,93 . Biomarkers for specific problems, e.g., end-diastolic volume (EDV) in cardiac MRI 78,79 and mean diameter, consistency, and margin of pulmonary nodules 80 were commonly computed to establish transparency. For problems with a well-established image reporting and diagnosis systems, routinely-used clinical features, e.g., Liver Imaging Reporting and Data System (LI-RADS) features for Hepatocellular carcinoma (HCC) classification 84 or BI-RADS for breast mass 82 suggested that the ML systems may be intuitively interpretable to experts that are already familiar with these guidelines.…”

Section: Pr: Priorsmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: In: Interpretabilitymentioning

confidence: 99%

Section: Pr: Priorsmentioning

confidence: 99%

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

show abstract

“…Although CADe attains a high-metric evaluation, only a few studies have verified the effectiveness of clinical practice by evaluating and comparing the performance of radiologists (Cui et al 2020, Lin et al 2020.…”

Section: Lack Of Clinical Evaluation and Applicationmentioning

confidence: 99%

Computer-aided detection of pulmonary nodules based on convolutional neural networks: a review

Min¹,

Hu²,

Long³

et al. 2022

Phys. Med. Biol.

View full text Add to dashboard Cite

Computer-aided detection (CADe) technology has been proven to increase the detection rate of pulmonary nodules that has important clinical significance for the early diagnosis of lung cancer. In this study, we systematically review the latest techniques in pulmonary nodule CADe based on deep learning models with convolutional neural networks in computed tomography images. First, the brief descriptions and popular architecture of convolutional neural networks are introduced. Second, several common public databases and evaluation metrics are briefly described. Third, state-of-the-art approaches with excellent performances are selected. Subsequently, we combine the clinical diagnostic process and the traditional four steps of pulmonary nodule CADe into two stages, namely, data preprocessing and image analysis. Further, the major optimizations of deep learning models and algorithms are highlighted according to the progressive evaluation effect of each method, and some clinical evidence is added. Finally, various methods are summarized and compared. The innovative or valuable contributions of each method are expected to guide future research directions. The analyzed results show that deep learning-based methods significantly transformed the detection of pulmonary nodules, and the design of these methods can be inspired by clinical imaging diagnostic procedures. Moreover, focusing on the image analysis stage will result in improved returns. In particular, optimal results can be achieved by optimizing the steps of candidate nodule generation and false positive reduction. End-to-end methods, with greater operating speeds and lower computational consumptions, are superior to other methods in CADe of pulmonary nodules.

show abstract

“…were frequently used to establish transparent systems. There existed two main ways to use human-understandable features in medical imaging: 1) Extracting hand-crafted features, e. g., morphological and radiomic features, from predicted segmentation masks generated by a nontransparent model [26,27,33,61,63,47,86,50,78,104] followed by analysis of those hand-crafted features using a separate classification module; 2) Directly predicting human-understandable features together with the main classification and detection task [55,44,45,77,100]. In these approaches, all tasks usually shared the same network architecture and parameter weights.…”

Section: The Use Of An Attention Mechanism Was the Most Commonmentioning

confidence: 99%

“…Morphological features, e. g., texture, shape and edge features were frequently considered and used to support the transparency of ML systems [26,33,52,61,44,47,86,77]. Biomarkers for specific problems, e. g., end-diastolic volume (EDV) in cardiac MRI [78,104] and mean diameter, consistency, and margin of pulmonary nodules [55] were commonly computed to establish transparency. For problems with a well-established image reporting and diagnosis systems, routinely-used clinical features, e. g., Liver Imaging Reporting and Data System (LI-RADS) features for Hepatocellular carcinoma (HCC) classification [100] or BI-RADS for breast mass [45] suggested that the ML systems may be intuitively interpretable to experts that are already familiar with these guidelines.…”

Section: Pr: Priorsmentioning

confidence: 99%

INTRPRT: A Systematic Review of and Guidelines for Designing and Validating Transparent AI in Medical Image Analysis

Chen¹,

Gómez²,

Huang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Transparency in Machine Learning (ML), including interpretable or explainable ML, attempts to reveal the working mechanisms of complex models, including deep neural networks. Transparent ML promises to advance human factors engineering goals of human-centered AI, such as increasing trust or reducing automation bias, in the target users. However, a core requirement in achieving these aims is that the method is indeed transparent to the users. 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 user; as a result, iterative prototyping and evaluation with users is critical to attaining adequate solutions that afford transparency. However, following human-centered design principles in highly specialized and high stakes domains, such as healthcare and medical image analysis, is challenging due to the limited availability of and access to end users, such as domain experts, providers, or patients. This dilemma is further exacerbated by the high knowledge imbalance between ML designers and those end users, which implies an even greater need for iterated development.To investigate the state of transparent ML in medical image analysis, we conducted and now present a systematic review of the literature. Our review reveals multiple severe shortcomings in the design and validation of transparent ML for medical image analysis applications. We find that most studies to date approach transparency as a property of the model itself, similar to task performance, without considering end users during neither development nor evaluation. Despite the considerable difference between the roles and knowledge of ML developers and clinical stakeholders, no study reported formative user research to inform the design and development of transparent ML models; moreover, only a few studies validated transparency claims through empirical user evaluations. The oversight of considering ML transparency as a relationship with end users, the lack of user research, and the sporadic validation of transparency claims put contemporary research on transparent ML for medical image analysis at risk of being incomprehensible to users, and thus, clinically irrelevant. To alleviate these shortcomings in forthcoming research while acknowledging the challenges of human-centered design in healthcare, we introduce the INTRPRT guideline, a systematic design directive for transparent ML systems in medical image analysis. To bridge the disconnect between ML system designers and end users and avoid misspending costly development efforts on models that are finally validated as non-transparent to end users, the INTRPRT guideline suggests formative user research as the first step of transparent model design to understand user needs and domain requirements. Following this process produces evidence to support * Joint first authors.Preprint. Under review.

show abstract

EDICNet: An end-to-end detection and interpretable malignancy classification network for pulmonary nodules in computed tomography

Cited by 12 publications

References 22 publications

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

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

Computer-aided detection of pulmonary nodules based on convolutional neural networks: a review

INTRPRT: A Systematic Review of and Guidelines for Designing and Validating Transparent AI in Medical Image Analysis

Contact Info

Product

Resources

About