An official website of the United States government
Abstract BackgroundLung cancer is the deadliest and second most common cancer in the United States due to the lack of symptoms for early diagnosis. Pulmonary nodules are small abnormal regions that can be potentially correlated to the occurrence of lung cancer. Early detection of these nodules is critical because it can significantly improve the patient's survival rates. Thoracic thin‐sliced computed tomography (CT) scanning has emerged as a widely used method for diagnosing and prognosis lung abnormalities. PurposeThe standard clinical workflow of detecting pulmonary nodules relies on radiologists to analyze CT images to assess the risk factors of cancerous nodules. However, this approach can be error‐prone due to the various nodule formation causes, such as pollutants and infections. Deep learning (DL) algorithms have recently demonstrated remarkable success in medical image classification and segmentation. As an ever more important assistant to radiologists in nodule detection, it is imperative ensure the DL algorithm and radiologist to better understand the decisions from each other. This study aims to develop a framework integrating explainable AI methods to achieve accurate pulmonary nodule detection. MethodsA robust and explainable detection (RXD) framework is proposed, focusing on reducing false positives in pulmonary nodule detection. Its implementation is based on an explanation supervision method, which uses nodule contours of radiologists as supervision signals to force the model to learn nodule morphologies, enabling improved learning ability on small dataset, and enable small dataset learning ability. In addition, two imputation methods are applied to the nodule region annotations to reduce the noise within human annotations and allow the model to have robust attributions that meet human expectations. The 480, 265, and 265 CT image sets from the public Lung Image Database Consortium and Image Database Resource Initiative (LIDC‐IDRI) dataset are used for training, validation, and testing. ResultsUsing only 10, 30, 50, and 100 training samples sequentially, our method constantly improves the classification performance and explanation quality of baseline in terms of Area Under the Curve (AUC) and Intersection over Union (IoU). In particular, our framework with a learnable imputation kernel improves IoU from baseline by 24.0% to 80.0%. A pre‐defined Gaussian imputation kernel achieves an even greater improvement, from 38.4% to 118.8% from baseline. Compared to the baseline trained on 100 samples, our method shows less drop in AUC when trained on fewer samples. A comprehensive comparison of interpretability shows that our method aligns better with expert opinions. ConclusionsA pulmonary nodule detection framework was demonstrated using public thoracic CT image datasets. The framework integrates the robust explanation supervision (RES) technique to ensure the performance of nodule classification and morphology. The method can reduce the workload of radiologists and enable them to focus on the diagnosis and prognosis of the potential cancerous pulmonary nodules at the early stage to improve the outcomes for lung cancer patients.
more »
« less
Multi‐scale, domain knowledge‐guided attention + random forest: a two‐stage deep learning‐based multi‐scale guided attention models to diagnose idiopathic pulmonary fibrosis from computed tomography images
Abstract BackgroundIdiopathic pulmonary fibrosis (IPF) is a progressive, irreversible, and usually fatal lung disease of unknown reasons, generally affecting the elderly population. Early diagnosis of IPF is crucial for triaging patients’ treatment planning into anti‐fibrotic treatment or treatments for other causes of pulmonary fibrosis. However, current IPF diagnosis workflow is complicated and time‐consuming, which involves collaborative efforts from radiologists, pathologists, and clinicians and it is largely subject to inter‐observer variability. PurposeThe purpose of this work is to develop a deep learning‐based automated system that can diagnose subjects with IPF among subjects with interstitial lung disease (ILD) using an axial chest computed tomography (CT) scan. This work can potentially enable timely diagnosis decisions and reduce inter‐observer variability. MethodsOur dataset contains CT scans from 349 IPF patients and 529 non‐IPF ILD patients. We used 80% of the dataset for training and validation purposes and 20% as the holdout test set. We proposed a two‐stage model: at stage one, we built a multi‐scale, domain knowledge‐guided attention model (MSGA) that encouraged the model to focus on specific areas of interest to enhance model explainability, including both high‐ and medium‐resolution attentions; at stage two, we collected the output from MSGA and constructed a random forest (RF) classifier for patient‐level diagnosis, to further boost model accuracy. RF classifier is utilized as a final decision stage since it is interpretable, computationally fast, and can handle correlated variables. Model utility was examined by (1) accuracy, represented by the area under the receiver operating characteristic curve (AUC) with standard deviation (SD), and (2) explainability, illustrated by the visual examination of the estimated attention maps which showed the important areas for model diagnostics. ResultsDuring the training and validation stage, we observe that when we provide no guidance from domain knowledge, the IPF diagnosis model reaches acceptable performance (AUC±SD = 0.93±0.07), but lacks explainability; when including only guided high‐ or medium‐resolution attention, the learned attention maps are not satisfactory; when including both high‐ and medium‐resolution attention, under certain hyperparameter settings, the model reaches the highest AUC among all experiments (AUC±SD = 0.99±0.01) and the estimated attention maps concentrate on the regions of interests for this task. Three best‐performing hyperparameter selections according to MSGA were applied to the holdout test set and reached comparable model performance to that of the validation set. ConclusionsOur results suggest that, for a task with only scan‐level labels available, MSGA+RF can utilize the population‐level domain knowledge to guide the training of the network, which increases both model accuracy and explainability.
more »
« less
- PAR ID:
- 10418987
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Medical Physics
- Volume:
- 50
- Issue:
- 2
- ISSN:
- 0094-2405
- Page Range / eLocation ID:
- p. 894-905
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Idiopathic pulmonary fibrosis (IPF) is a lethal lung disease targeting the alveolar gas exchange apparatus, leading to death by asphyxiation. IPF progresses on a tissue scale through aberrant matrix remodeling, enhanced cell contraction, and subsequent microenvironment densification. Although two pharmaceuticals modestly slow progression, IPF patient survival averages less than 5 years. A major impediment to therapeutic development is the lack of high-fidelity models that account for the fibrotic microenvironment. Our goal is to create a three-dimensional (3D) platform to enable lung fibrosis studies and recapitulate IPF tissue features. We demonstrate that normal lung fibroblasts encapsulated in collagen microspheres can be pushed toward an activated phenotype, treated with FDA-approved therapies, and their fibrotic function quantified using imaging assays (extracellular matrix deposition, contractile protein expression, and microenvironment compaction). Highlighting the system's utility, we further show that fibroblasts isolated from IPF patient lungs maintain fibrotic phenotypes and manifest reduced fibrotic function when treated with epigenetic modifiers. Our system enables enhanced screening due to improved predictability and fidelity compared to 2D systems combined with superior tractability and throughput compared to 3D systems.more » « less
-
Idiopathic pulmonary fibrosis (IPF) is a devastating lung disease that progressively and irreversibly alters the lung parenchyma, eventually leading to respiratory failure. The study of this disease has been historically challenging due to the myriad of complex processes that contribute to fibrogenesis and the inherent difficulty in accurately recreating the human pulmonary environment in vitro . Here, we describe a poly(ethylene glycol) PEG hydrogel-based three-dimensional model for the co-culture of primary murine pulmonary fibroblasts and alveolar epithelial cells that reproduces the micro-architecture, cell placement, and mechanical properties of healthy and fibrotic lung tissue. Co-cultured cells retained normal levels of viability up to at least three weeks and displayed differentiation patterns observed in vivo during IPF progression. Interrogation of protein and gene expression within this model showed that myofibroblast activation required both extracellular mechanical cues and the presence of alveolar epithelial cells. Differences in gene expression indicated that cellular co-culture induced TGF-β signaling and proliferative gene expression, while microenvironmental stiffness upregulated the expression of genes related to cell–ECM interactions. This biomaterial-based cell culture system serves as a significant step forward in the accurate recapitulation of human lung tissue in vitro and highlights the need to incorporate multiple factors that work together synergistically in vivo into models of lung biology of health and disease.more » « less
-
null (Ed.)Idiopathic Pulmonary Fibrosis (IPF) is a chronically progressive interstitial lung that affects over 3 M people worldwide and rising in incidence. With a median survival of 2–3 years, IPF is consequently associated with high morbidity, mortality, and healthcare burden. Although two antifibrotic therapies, pirfenidone and nintedanib, are approved for human use, these agents reduce the rate of decline of pulmonary function but are not curative and do not reverse established fibrosis. In this review, we discuss the prevailing epithelial injury hypothesis, wherein pathogenic airway epithelial cell-state changes known as Epithelial Mesenchymal Transition (EMT) promotes the expansion of myofibroblast populations. Myofibroblasts are principal components of extracellular matrix production that result in airspace loss and mortality. We review the epigenetic transition driving EMT, a process produced by changes in histone acetylation regulating mesenchymal gene expression programs. This mechanistic work has focused on the central role of bromodomain-containing protein 4 in mediating EMT and myofibroblast transition and initial preclinical work has provided evidence of efficacy. As nanomedicine presents a promising approach to enhancing the efficacy of such anti-IPF agents, we then focus on the state of nanomedicine formulations for inhalable delivery in the treatment of pulmonary diseases, including liposomes, polymeric nanoparticles (NPs), inorganic NPs, and exosomes. These nanoscale agents potentially provide unique properties to existing pulmonary therapeutics, including controlled release, reduced systemic toxicity, and combination delivery. NP-based approaches for pulmonary delivery thus offer substantial promise to modify epigenetic regulators of EMT and advance treatments for IPF.more » « less
-
Abstract PurposeTo develop a robust single breath‐hold approach for volumetric lung imaging at 0.55T. MethodA balanced‐SSFP (bSSFP) pulse sequence with 3D stack‐of‐spiral (SoS) out‐in trajectory for volumetric lung imaging at 0.55T was implemented. With 2.7× undersampling, the pulse sequence enables imaging during a 17‐s breath‐hold. Image reconstruction is performed using 3D SPIRiT and 3D l1‐Wavelet regularizations. In two healthy volunteers, single breath‐hold SoS out‐in bSSFP was compared against stack‐of‐spiral UTE (spiral UTE) and half‐radial dual‐echo bSSFP (bSTAR), based on signal intensity (SI), blood‐lung parenchyma contrast, and image quality. In six patients with pathologies including lung nodules, fibrosis, emphysema, and air trapping, single breath‐hold SoS out‐in and bSTAR were compared against low‐dose computed tomography (LDCT). ResultsSoS out‐in bSSFP achieved 2‐mm isotropic resolution lung imaging with a single breath‐hold duration of 17 s. SoS out‐in (2‐mm isotropic) provided higher lung parenchyma and blood SI and blood‐lung parenchyma contrast compared to spiral UTE (2.4 × 2.4 × 2.5 mm3) and bSTAR (1.6‐mm isotropic). When comparing SI normalized by voxel size, SoS out‐in has lower lung parenchyma signal, higher blood signal, and a higher blood‐lung parenchyma contrast compared to bSTAR. In patients, SoS out‐in bSSFP was able to identify lung fibrosis and lung nodules of size 4 and 8 mm, and breath‐hold bSTAR was able to identify lung fibrosis and 8 mm nodules. ConclusionSingle breath‐hold volumetric lung imaging at 0.55T with 2‐mm isotropic spatial resolution is feasible using SoS out‐in bSSFP. This approach could be useful for rapid lung disease screening, and in cases where free‐breathing respiratory navigated approaches fail.more » « less
