Deep Learning-based Outcome Prediction in Progressive Fibrotic Lung Disease Using High-resolution Computed Tomography

Explainable fully automated CT scoring of interstitial lung disease for patients suspected of systemic sclerosis by cascaded regression neural networks and its comparison with experts

Visual scoring of interstitial lung disease in systemic sclerosis (SSc-ILD) from CT scans is laborious, subjective and time-consuming. This study aims to develop a deep learning framework to automate SSc-ILD scoring. The automated framework is a cascade of two neural networks. The first network selects the craniocaudal positions of the five scoring levels. Subsequently, for each level, the second network estimates the ratio of three patterns to the total lung area: the total extent of disease (TOT), ground glass (GG) and reticulation (RET). To overcome the score imbalance in the second network, we propose a method to augment the training dataset with synthetic data. To explain the network's output, a heat map method is introduced to highlight the candidate interstitial lung disease regions. The explainability of heat maps was evaluated by two human experts and a quantitative method that uses the heat map to produce the score. The results show that our framework achieved a κ of 0.66, 0.58, and 0.65, for the TOT, GG and RET scoring, respectively. Both experts agreed with the heat maps in 91%, 90% and 80% of cases, respectively. Therefore, it is feasible to develop a framework for automated SSc-ILD scoring, which performs competitively with human experts and provides high-quality explanations using heat maps. Confirming the model's generalizability is needed in future studies.

Correlation between CT-based phenotypes and serum biomarker in interstitial lung diseases

BACKGROUND

The quantitative analysis of computed tomography (CT) and Krebs von den Lungen-6 (KL-6) serum level has gained importance in the diagnosis, monitoring, and prognostication of interstitial lung disease (ILD). However, the associations between quantitative analysis of CT and serum KL-6 level remain poorly understood.

METHODS

In this retrospective observational study conducted at tertiary hospital between June 2020 and March 2022, quantitative analysis of CT was performed using the deep learning-based method including reticulation, ground glass opacity (GGO), honeycombing, and consolidation. We investigated the associations between CT-based phenotypes and serum KL-6 measured within three months of the CT scan. Furthermore, we evaluated the performance of the combined CT-based phenotypes and KL-6 levels in predicting hospitalizations due to respiratory reasons of ILD patients.

RESULTS

A total of 131 ILD patients (104 males) with a median age of 67 years were included in this study. Reticulation, GGO, honeycombing, and consolidation extents showed a positive correlation with KL-6 levels. [Reticulation, correlation coefficient (r) = 0.567, p < 0.001; GGO, r = 0.355, p < 0.001; honeycombing, r = 0.174, p = 0.046; and consolidation, r = 0.446, p < 0.001]. Additionally, the area under the ROC of the combined reticulation and KL-6 for hospitalizations due to respiratory reasons was 0.810 (p < 0.001).

CONCLUSIONS

Quantitative analysis of CT features and serum KL-6 levels ascertained a positive correlation between the two. In addition, the combination of reticulation and KL-6 shows potential for predicting hospitalizations of ILD patients due to respiratory causes. The combination of reticulation, focusing on phenotypic change in lung parenchyma, and KL-6, as an indicator of lung injury extent, could be helpful for monitoring and predicting the prognosis of various types of ILD.

ESR Essentials: imaging in fibrotic lung diseases-practice recommendations by the European Society of Thoracic Imaging

Fibrotic lung diseases (FLDs) represent a subgroup of interstitial lung diseases (ILDs), which can progress over time and carry a poor prognosis. Imaging has increased diagnostic discrimination in the evaluation of FLDs. International guidelines have stated the role of radiologists in the diagnosis and management of FLDs, in the context of the interdisciplinary discussion. Chest computed tomography (CT) with high-resolution technique is recommended to correctly recognise signs, patterns, and distribution of individual FLDs. Radiologists may be the first to recognise the presence of previously unknown interstitial lung abnormalities (ILAs) in various settings. A systematic approach to CT images may lead to a non-invasive diagnosis of FLDs. Careful comparison of serial CT exams is crucial in determining either disease progression or supervening complications. This 'Essentials' aims to provide radiologists a concise and practical approach to FLDs, focusing on CT technical requirements, pattern recognition, and assessment of disease progression and complications. Hot topics such as ILAs and progressive pulmonary fibrosis (PPF) are also discussed. KEY POINTS: Chest CT with high-resolution technique is the recommended imaging modality to diagnose pulmonary fibrosis. CT pattern recognition is central for an accurate diagnosis of fibrotic lung diseases (FLDs) by interdisciplinary discussion. Radiologists are to evaluate disease behaviour by accurately comparing serial CT scans.

Progress in the radiologic diagnosis of idiopathic pulmonary fibrosis

PURPOSE OF REVIEW

To discuss the most recent applications of radiological imaging, from conventional to quantitative, in the setting of idiopathic pulmonary fibrosis (IPF) diagnosis.

RECENT FINDINGS

In this article, current concepts on radiological diagnosis of IPF, from high-resolution computed tomography (CT) to other imaging modalities, are reviewed. In a separate section, advances in quantitative CT and development of novel imaging biomarkers, as well as current limitations and future research trends, are described.

SUMMARY

Radiological imaging in IPF, particularly quantitative CT, is an evolving field which holds promise in the future to allow for an increasingly accurate disease assessment and prognostication of IPF patients. However, further standardization and validation studies of alternative imaging applications and quantitative biomarkers are needed.

From pixels to prognosis: unlocking the potential of deep learning in fibrotic lung disease imaging analysis

The licensing of antifibrotic therapy for fibrotic lung diseases, including idiopathic pulmonary fibrosis (IPF), has created an urgent need for reliable biomarkers to predict disease progression and treatment response. Some patients experience stable disease trajectories, while others deteriorate rapidly, making treatment decisions challenging. High-resolution chest CT has become crucial for diagnosis, but visual assessments by radiologists suffer from low reproducibility and high interobserver variability. To address these issues, computer-based image analysis, called quantitative CT, has emerged. However, many quantitative CT methods rely on human input for training, therefore potentially incorporating human error into computer training. Rapid advances in artificial intelligence, specifically deep learning, aim to overcome this limitation by enabling autonomous quantitative analysis. While promising, deep learning also presents challenges including the need to minimize algorithm biases, ensuring explainability, and addressing accessibility and ethical concerns. This review explores the development and application of deep learning in improving the imaging process for fibrotic lung disease.

Deep Learning-based Segmentation of Computed Tomography Scans Predicts Disease Progression and Mortality in Idiopathic Pulmonary Fibrosis

Rationale: Despite evidence demonstrating a prognostic role for computed tomography (CT) scans in idiopathic pulmonary fibrosis (IPF), image-based biomarkers are not routinely used in clinical practice or trials. Objectives: To develop automated imaging biomarkers using deep learning-based segmentation of CT scans. Methods: We developed segmentation processes for four anatomical biomarkers, which were applied to a unique cohort of treatment-naive patients with IPF enrolled in the PROFILE (Prospective Observation of Fibrosis in the Lung Clinical Endpoints) study and tested against a further United Kingdom cohort. The relationships among CT biomarkers, lung function, disease progression, and mortality were assessed. Measurements and Main Results: Data from 446 PROFILE patients were analyzed. Median follow-up duration was 39.1 months (interquartile range, 18.1-66.4 mo), with a cumulative incidence of death of 277 (62.1%) over 5 years. Segmentation was successful on 97.8% of all scans, across multiple imaging vendors, at slice thicknesses of 0.5-5 mm. Of four segmentations, lung volume showed the strongest correlation with FVC (r = 0.82; P < 0.001). Lung, vascular, and fibrosis volumes were consistently associated across cohorts with differential 5-year survival, which persisted after adjustment for baseline gender, age, and physiology score. Lower lung volume (hazard ratio [HR], 0.98 [95% confidence interval (CI), 0.96-0.99]; P = 0.001), increased vascular volume (HR, 1.30 [95% CI, 1.12-1.51]; P = 0.001), and increased fibrosis volume (HR, 1.17 [95% CI, 1.12-1.22]; P < 0.001) were associated with reduced 2-year progression-free survival in the pooled PROFILE cohort. Longitudinally, decreasing lung volume (HR, 3.41 [95% CI, 1.36-8.54]; P = 0.009) and increasing fibrosis volume (HR, 2.23 [95% CI, 1.22-4.08]; P = 0.009) were associated with differential survival. Conclusions: Automated models can rapidly segment IPF CT scans, providing prognostic near and long-term information, which could be used in routine clinical practice or as key trial endpoints.

Lung ultrasound among Expert operator'S: ScOring and iNter-rater reliability analysis (LESSON study) a secondary COWS study analysis from ITALUS group

BACKGROUND

Lung ultrasonography (LUS) is a non-invasive imaging method used to diagnose and monitor conditions such as pulmonary edema, pneumonia, and pneumothorax. It is precious where other imaging techniques like CT scan or chest X-rays are of limited access, especially in low- and middle-income countries with reduced resources. Furthermore, LUS reduces radiation exposure and its related blood cancer adverse events, which is particularly relevant in children and young subjects. The score obtained with LUS allows semi-quantification of regional loss of aeration, and it can provide a valuable and reliable assessment of the severity of most respiratory diseases. However, inter-observer reliability of the score has never been systematically assessed. This study aims to assess experienced LUS operators' agreement on a sample of video clips showing predefined findings.

METHODS

Twenty-five anonymized video clips comprehensively depicting the different values of LUS score were shown to renowned LUS experts blinded to patients' clinical data and the study's aims using an online form. Clips were acquired from five different ultrasound machines. Fleiss-Cohen weighted kappa was used to evaluate experts' agreement.

RESULTS

Over a period of 3 months, 20 experienced operators completed the assessment. Most worked in the ICU (10), ED (6), HDU (2), cardiology ward (1), or obstetric/gynecology department (1). The proportional LUS score mean was 15.3 (SD 1.6). Inter-rater agreement varied: 6 clips had full agreement, 3 had 19 out of 20 raters agreeing, and 3 had 18 agreeing, while the remaining 13 had 17 or fewer people agreeing on the assigned score. Scores 0 and score 3 were more reproducible than scores 1 and 2. Fleiss' Kappa for overall answers was 0.87 (95% CI 0.815-0.931, p < 0.001).

CONCLUSIONS

The inter-rater agreement between experienced LUS operators is very high, although not perfect. The strong agreement and the small variance enable us to say that a 20% tolerance around a measured value of a LUS score is a reliable estimate of the patient's true LUS score, resulting in reduced variability in score interpretation and greater confidence in its clinical use.

Deep learning-enabled classification of kidney allograft rejection on whole slide histopathologic images

Background

Diagnosis of kidney transplant rejection currently relies on manual histopathological assessment, which is subjective and susceptible to inter-observer variability, leading to limited reproducibility. We aim to develop a deep learning system for automated assessment of whole-slide images (WSIs) from kidney allograft biopsies to enable detection and subtyping of rejection and to predict the prognosis of rejection.

Method

We collected H&E-stained WSIs of kidney allograft biopsies at 400x magnification from January 2015 to September 2023 at two hospitals. These biopsy specimens were classified as T cell-mediated rejection, antibody-mediated rejection, and other lesions based on the consensus reached by two experienced transplant pathologists. To achieve feature extraction, feature aggregation, and global classification, we employed multi-instance learning and common convolution neural networks (CNNs). The performance of the developed models was evaluated using various metrics, including confusion matrix, receiver operating characteristic curves, the area under the curve (AUC), classification map, heat map, and pathologist-machine confrontations.

Results

In total, 906 WSIs from 302 kidney allograft biopsies were included for analysis. The model based on multi-instance learning enables detection and subtyping of rejection, named renal rejection artificial intelligence model (RRAIM), with the overall 3-category AUC of 0.798 in the independent test set, which is superior to that of three transplant pathologists under nearly routine assessment conditions. Moreover, the prognosis models accurately predicted graft loss within 1 year following rejection and treatment response for rejection, achieving AUC of 0.936 and 0.756, respectively.

Conclusion

We first developed deep-learning models utilizing multi-instance learning for the detection and subtyping of rejection and prediction of rejection prognosis in kidney allograft biopsies. These models performed well and may be useful in assisting the pathological diagnosis.

Computed tomography machine learning classifier correlates with mortality in interstitial lung disease

BACKGROUND

A machine learning classifier system, Fibresolve, was designed and validated as an adjunct to non-invasive diagnosis in idiopathic pulmonary fibrosis (IPF). The system uses a deep learning algorithm to analyze chest computed tomography (CT) imaging. We hypothesized that Fibresolve is a useful predictor of mortality in interstitial lung diseases (ILD).

METHODS

Fibresolve was previously validated in a multi-site >500-patient dataset. In this analysis, we assessed the usefulness of Fibresolve to predict mortality in a subset of 228 patients with IPF and other ILDs in whom follow up data was available. We applied Cox regression analysis adjusting for the Gender, Age, and Physiology (GAP) score and for other known predictors of mortality in IPF. We also analyzed the role of Fibresolve as tertiles adjusting for GAP stages.

RESULTS

During a median follow-up of 2.8 years (range 5 to 3434 days), 89 patients died. After adjusting for GAP score and other mortality risk factors, the Fibresolve score significantly predicted the risk of death (HR: 7.14; 95% CI: 1.31-38.85; p = 0.02) during the follow-up period, as did forced vital capacity and history of lung cancer. After adjusting for GAP stages and other variables, Fibresolve score split into tertiles significantly predicted the risk of death (p = 0.027 for the model; HR 1.37 for 2nd tertile; 95% CI: 0.77-2.42. HR 2.19 for 3rd tertile; 95% CI: 1.22-3.93).

CONCLUSIONS

The machine learning classifier Fibresolve demonstrated to be an independent predictor of mortality in ILDs, with prognostic performance equivalent to GAP based solely on CT images.

Radiomics based on HRCT can predict RP-ILD and mortality in anti-MDA5 + dermatomyositis patients: a multi-center retrospective study

OBJECTIVES

To assess the effectiveness of HRCT-based radiomics in predicting rapidly progressive interstitial lung disease (RP-ILD) and mortality in anti-MDA5 positive dermatomyositis-related interstitial lung disease (anti-MDA5 + DM-ILD).

METHODS

From August 2014 to March 2022, 160 patients from Institution 1 were retrospectively and consecutively enrolled and were randomly divided into the training dataset (n = 119) and internal validation dataset (n = 41), while 29 patients from Institution 2 were retrospectively and consecutively enrolled as external validation dataset. We generated four Risk-scores based on radiomics features extracted from four areas of HRCT. A nomogram was established by integrating the selected clinico-radiologic variables and the Risk-score of the most discriminative radiomics model. The RP-ILD prediction performance of the models was evaluated by using the area under the receiver operating characteristic curves, calibration curves, and decision curves. Survival analysis was conducted with Kaplan-Meier curves, Mantel-Haenszel test, and Cox regression.

RESULTS

Over a median follow-up time of 31.6 months (interquartile range: 12.9-49.1 months), 24 patients lost to follow-up and 46 patients lost their lives (27.9%, 46/165). The Risk-score based on bilateral lungs performed best, attaining AUCs of 0.869 and 0.905 in the internal and external validation datasets. The nomogram outperformed clinico-radiologic model and Risk-score with AUCs of 0.882 and 0.916 in the internal and external validation datasets. Patients were classified into low- and high-risk groups with 50:50 based on nomogram. High-risk group patients demonstrated a significantly higher risk of mortality than low-risk group patients in institution 1 (HR = 4.117) and institution 2 cohorts (HR = 7.515).

CONCLUSION

For anti-MDA5 + DM-ILD, the nomogram, mainly based on radiomics, can predict RP-ILD and is an independent predictor of mortality.

Predicting COPD exacerbations based on quantitative CT analysis: an external validation study

Purpose

Quantitative computed tomography (CT) analysis is an important method for diagnosis and severity evaluation of lung diseases. However, the association between CT-derived biomarkers and chronic obstructive pulmonary disease (COPD) exacerbations remains unclear. We aimed to investigate its potential in predicting COPD exacerbations.

Methods

Patients with COPD were consecutively enrolled, and their data were analyzed in this retrospective study. Body composition and thoracic abnormalities were analyzed from chest CT scans. Logistic regression analysis was performed to identify independent risk factors of exacerbation. Based on 2-year follow-up data, the deep learning system (DLS) was developed to predict future exacerbations. Receiver operating characteristic (ROC) curve analysis was conducted to assess the diagnostic performance. Finally, the survival analysis was performed to further evaluate the potential of the DLS in risk stratification.

Results

A total of 1,150 eligible patients were included and followed up for 2 years. Multivariate analysis revealed that CT-derived high affected lung volume/total lung capacity (ALV/TLC) ratio, high visceral adipose tissue area (VAT), and low pectoralis muscle cross-sectional area (CSA) were independent risk factors causing COPD exacerbations. The DLS outperformed exacerbation history and the BMI, airflow obstruction, dyspnea, and exercise capacity (BODE) index, with an area under the ROC (AUC) value of 0.88 (95%CI, 0.82-0.92) in the internal cohort and 0.86 (95%CI, 0.81-0.89) in the external cohort. The DeLong test revealed significance between this system and conventional scores in the test cohorts (p < 0.05). In the survival analysis, patients with higher risk were susceptible to exacerbation events.

Conclusion

The DLS could allow accurate prediction of COPD exacerbations. The newly identified CT biomarkers (ALV/TLC ratio, VAT, and pectoralis muscle CSA) could potentially enable investigation into underlying mechanisms responsible for exacerbations.

Worldwide research landscape of artificial intelligence in lung disease: A scientometric study

Purpose

To perform a comprehensive bibliometric analysis of the application of artificial intelligence (AI) in lung disease to understand the current status and emerging trends of this field.

Materials and methods

AI-based lung disease research publications were selected from the Web of Science Core Collection. Citespace, VOS viewer and Excel were used to analyze and visualize co-authorship, co-citation, and co-occurrence analysis of authors, keywords, countries/regions, references and institutions in this field.

Results

Our study included a total of 5210 papers. The number of publications on AI in lung disease showed explosive growth since 2017. China and the United States lead in publication numbers. The most productive author were Li, Weimin and Qian Wei, with Shanghai Jiaotong University as the most productive institution. Radiology was the most co-cited journal. Lung cancer and COVID-19 emerged as the most studied diseases. Deep learning, convolutional neural network, lung cancer, radiomics will be the focus of future research.

Conclusions

AI-based diagnosis and treatment of lung disease has become a research hotspot in recent years, yielding significant results. Future work should focus on establishing multimodal AI models that incorporate clinical, imaging and laboratory information. Enhanced visualization of deep learning, AI-driven differential diagnosis model for lung disease and the creation of international large-scale lung disease databases should also be considered.

Machine learning classifier is associated with mortality in interstitial lung disease: a retrospective validation study leveraging registry data

BACKGROUND

Mortality prediction in interstitial lung disease (ILD) poses a significant challenge to clinicians due to heterogeneity across disease subtypes. Currently, forced vital capacity (FVC) and Gender, Age, and Physiology (GAP) score are the two most utilized metrics in prognostication. Recently, a machine learning classifier system, Fibresolve, designed to identify a variety of computed tomography (CT) patterns associated with idiopathic pulmonary fibrosis (IPF), was demonstrated to have a significant association with mortality across multiple subtypes of ILD. The purpose of this follow-up study was to retrospectively validate these findings in a large, external cohort of patients with ILD.

METHODS

In this multi-center validation study, Fibresolve was applied to chest CT scans of patients with confirmed ILD that had available follow-up data. Fibresolve scores categorized by tertile were analyzed using Cox regression analysis adjusted for tobacco use and modified GAP (mGAP) score.

RESULTS

Of 643 patients included, 446 (69.3%) died over a median follow-up time of 144 [1-821] weeks. The median [range] mGAP score was 5 [3-7]. In multivariable analysis, Fibresolve score categorized by tertile was significantly associated with mortality (Tertile 2 HR 1.47, 95% CI 0.82-2.37, p = 0.11; Tertile 3 HR 3.12, 95% CI 1.98-4.90, p < 0.001). Subgroup analyses revealed significant associations amongst those with non-IPF ILDs (Tertile 2 HR 1.95, 95% CI 1.28-2.97, Tertile 3 HR 4.66, 95% CI 2.94-7.38) and severe disease, defined by a FVC ≤ 75% (Tertile 2 HR 2.29, 95% CI 1.43-3.67, Tertile 3 HR 4.80, 95% CI 2.93-7.86).

CONCLUSIONS

Fibresolve is independently associated with mortality in ILD, particularly amongst patients with non-IPF ILDs and in those with severe disease.

Deep Learning Classification of Usual Interstitial Pneumonia Predicts Outcomes

Rationale: Computed tomography (CT) enables noninvasive diagnosis of usual interstitial pneumonia (UIP), but enhanced image analyses are needed to overcome the limitations of visual assessment. Objectives: Apply multiple instance learning (MIL) to develop an explainable deep learning algorithm for prediction of UIP from CT and validate its performance in independent cohorts. Methods: We trained an MIL algorithm using a pooled dataset (n = 2,143) and tested it in three independent populations: data from a prior publication (n = 127), a single-institution clinical cohort (n = 239), and a national registry of patients with pulmonary fibrosis (n = 979). We tested UIP classification performance using receiver operating characteristic analysis, with histologic UIP as ground truth. Cox proportional hazards and linear mixed-effects models were used to examine associations between MIL predictions and survival or longitudinal FVC. Measurements and Main Results: In two cohorts with biopsy data, MIL improved accuracy for histologic UIP (area under the curve, 0.77 [n = 127] and 0.79 [n = 239]) compared with visual assessment (area under the curve, 0.65 and 0.71). In cohorts with survival data, MIL-UIP classifications were significant for mortality (n = 239, mortality to April 2021: unadjusted hazard ratio, 3.1; 95% confidence interval [CI], 1.96-4.91; P < 0.001; and n = 979, mortality to July 2022: unadjusted hazard ratio, 3.64; 95% CI, 2.66-4.97; P < 0.001). Individuals classified as UIP positive by the algorithm had a significantly greater annual decline in FVC than those classified as UIP negative (-88 ml/yr vs. -45 ml/yr; n = 979; P < 0.01), adjusting for extent of lung fibrosis. Conclusions: Computerized assessment using MIL identifies clinically significant features of UIP on CT. Such a method could improve confidence in radiologic assessment of patients with interstitial lung disease, potentially enabling earlier and more precise diagnosis.

A Machine Learning System to Indicate Diagnosis of Idiopathic Pulmonary Fibrosis Non-Invasively in Challenging Cases

Radiologic usual interstitial pneumonia (UIP) patterns and concordant clinical characteristics define a diagnosis of idiopathic pulmonary fibrosis (IPF). However, limited expert access and high inter-clinician variability challenge early and pre-invasive diagnostic sensitivity and differentiation of IPF from other interstitial lung diseases (ILDs). We investigated a machine learning-driven software system, Fibresolve, to indicate IPF diagnosis in a heterogeneous group of 300 patients with interstitial lung disease work-up in a retrospective analysis of previously and prospectively collected registry data from two US clinical sites. Fibresolve analyzed cases at the initial pre-invasive assessment. An Expert Clinical Panel (ECP) and three panels of clinicians with varying experience analyzed the cases for comparison. Ground Truth was defined by separate multi-disciplinary discussion (MDD) with the benefit of surgical pathology results and follow-up. Fibresolve met both pre-specified co-primary endpoints of sensitivity superior to ECP and significantly greater specificity (p = 0.0007) than the non-inferior boundary of 80.0%. In the key subgroup of cases with thin-slice CT and atypical UIP patterns (n = 124), Fibresolve's diagnostic yield was 53.1% [CI: 41.3-64.9] (versus 0% pre-invasive clinician diagnostic yield in this group), and its specificity was 85.9% [CI: 76.7-92.6%]. Overall, Fibresolve was found to increase the sensitivity and diagnostic yield for IPF among cases of patients undergoing ILD work-up. These results demonstrate that in combination with standard clinical assessment, Fibresolve may serve as an adjunct in the diagnosis of IPF in a pre-invasive setting.

Novel 3D-based deep learning for classification of acute exacerbation of idiopathic pulmonary fibrosis using high-resolution CT

PURPOSE

Acute exacerbation of idiopathic pulmonary fibrosis (AE-IPF) is the primary cause of death in patients with IPF, characterised by diffuse, bilateral ground-glass opacification on high-resolution CT (HRCT). This study proposes a three-dimensional (3D)-based deep learning algorithm for classifying AE-IPF using HRCT images.

MATERIALS AND METHODS

A novel 3D-based deep learning algorithm, SlowFast, was developed by applying a database of 306 HRCT scans obtained from two centres. The scans were divided into four separate subsets (training set, n=105; internal validation set, n=26; temporal test set 1, n=79; and geographical test set 2, n=96). The final training data set consisted of 1050 samples with 33 600 images for algorithm training. Algorithm performance was evaluated using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve and weighted κ coefficient.

RESULTS

The accuracy of the algorithm in classifying AE-IPF on the test sets 1 and 2 was 93.9% and 86.5%, respectively. Interobserver agreements between the algorithm and the majority opinion of the radiologists were good (κw=0.90 for test set 1 and κw=0.73 for test set 2, respectively). The ROC accuracy of the algorithm for classifying AE-IPF on the test sets 1 and 2 was 0.96 and 0.92, respectively. The algorithm performance was superior to visual analysis in accurately diagnosing radiological findings. Furthermore, the algorithm's categorisation was a significant predictor of IPF progression.

CONCLUSIONS

The deep learning algorithm provides high auxiliary diagnostic efficiency in patients with AE-IPF and may serve as a useful clinical aid for diagnosis.

Deep Learning-based Fibrosis Extent on Computed Tomography Predicts Outcome of Fibrosing Interstitial Lung Disease Independent of Visually Assessed Computed Tomography Pattern

Rationale: Radiologic pattern has been shown to predict survival in patients with fibrosing interstitial lung disease. The additional prognostic value of fibrosis extent by quantitative computed tomography (CT) is unknown. Objectives: We hypothesized that fibrosis extent provides information beyond visually assessed CT pattern that is useful for outcome prediction. Methods: We performed a retrospective analysis of chest CT, demographics, longitudinal pulmonary function, and transplantation-free survival among participants in the Pulmonary Fibrosis Foundation Patient Registry. CT pattern was classified visually according to the 2018 usual interstitial pneumonia criteria. Extent of fibrosis was objectively quantified using data-driven textural analysis. We used Kaplan-Meier plots and Cox proportional hazards and linear mixed-effects models to evaluate the relationships between CT-derived metrics and outcomes. Results: Visual assessment and quantitative analysis were performed on 979 enrollment CT scans. Linear mixed-effect modeling showed that greater baseline fibrosis extent was significantly associated with the annual rate of decline in forced vital capacity. In multivariable models that included CT pattern and fibrosis extent, quantitative fibrosis extent was strongly associated with transplantation-free survival independent of CT pattern (hazard ratio, 1.04; 95% confidence interval, 1.04-1.05; P < 0.001; C statistic = 0.73). Conclusions: The extent of lung fibrosis by quantitative CT is a strong predictor of physiologic progression and survival, independent of visually assessed CT pattern.

Analysis of Validation Performance of a Machine Learning Classifier in Interstitial Lung Disease Cases Without Definite or Probable Usual Interstitial Pneumonia Pattern on CT Using Clinical and Pathology-Supported Diagnostic Labels

We previously validated Fibresolve, a machine learning classifier system that non-invasively predicts idiopathic pulmonary fibrosis (IPF) diagnosis. The system incorporates an automated deep learning algorithm that analyzes chest computed tomography (CT) imaging to assess for features associated with idiopathic pulmonary fibrosis. Here, we assess performance in assessment of patterns beyond those that are characteristic features of usual interstitial pneumonia (UIP) pattern. The machine learning classifier was previously developed and validated using standard training, validation, and test sets, with clinical plus pathologically determined ground truth. The multi-site 295-patient validation dataset was used for focused subgroup analysis in this investigation to evaluate the classifier's performance range in cases with and without radiologic UIP and probable UIP designations. Radiologic assessment of specific features for UIP including the presence and distribution of reticulation, ground glass, bronchiectasis, and honeycombing was used for assignment of radiologic pattern. Output from the classifier was assessed within various UIP subgroups. The machine learning classifier was able to classify cases not meeting the criteria for UIP or probable UIP as IPF with estimated sensitivity of 56-65% and estimated specificity of 92-94%. Example cases demonstrated non-basilar-predominant as well as ground glass patterns that were indeterminate for UIP by subjective imaging criteria but for which the classifier system was able to correctly identify the case as IPF as confirmed by multidisciplinary discussion generally inclusive of histopathology. The machine learning classifier Fibresolve may be helpful in the diagnosis of IPF in cases without radiological UIP and probable UIP patterns.

A Deep Learning-Based Radiomic Classifier for Usual Interstitial Pneumonia

BACKGROUND

Because chest CT scan has largely supplanted surgical lung biopsy for diagnosing most cases of interstitial lung disease (ILD), tools to standardize CT scan interpretation are urgently needed.

RESEARCH QUESTION

Does a deep learning (DL)-based classifier for usual interstitial pneumonia (UIP) derived using CT scan features accurately discriminate radiologist-determined visual UIP?

STUDY DESIGN AND METHODS

A retrospective cohort study was performed. Chest CT scans acquired in individuals with and without ILD were drawn from a variety of public and private data sources. Using radiologist-determined visual UIP as ground truth, a convolutional neural network was used to learn discrete CT scan features of UIP, with outputs used to predict the likelihood of UIP using a linear support vector machine. Test performance characteristics were assessed in an independent performance cohort and multicenter ILD clinical cohort. Transplant-free survival was compared between UIP classification approaches using the Kaplan-Meier estimator and Cox proportional hazards regression.

RESULTS

A total of 2,907 chest CT scans were included in the training (n = 1,934), validation (n = 408), and performance (n = 565) data sets. The prevalence of radiologist-determined visual UIP was 12.4% and 37.1% in the performance and ILD clinical cohorts, respectively. The DL-based UIP classifier predicted visual UIP in the performance cohort with sensitivity and specificity of 93% and 86%, respectively, and in the multicenter ILD clinical cohort with 81% and 77%, respectively. DL-based and visual UIP classification similarly discriminated survival, and outcomes were consistent among cases with positive DL-based UIP classification irrespective of visual classification.

INTERPRETATION

A DL-based classifier for UIP demonstrated good test performance across a wide range of UIP prevalence and similarly discriminated survival when compared with radiologist-determined UIP. This automated tool could efficiently screen for UIP in patients undergoing chest CT scan and identify a high-risk phenotype among those with known ILD.

[The contribution of artificial intelligence (AI) subsequent to the processing of thoracic imaging]

The contribution of artificial intelligence (AI) to medical imaging is currently the object of widespread experimentation. The development of deep learning (DL) methods, particularly convolution neural networks (CNNs), has led to performance gains often superior to those achieved by conventional methods such as machine learning. Radiomics is an approach aimed at extracting quantitative data not accessible to the human eye from images expressing a disease. The data subsequently feed machine learning models and produce diagnostic or prognostic probabilities. As for the multiple applications of AI methods in thoracic imaging, they are undergoing evaluation. Chest radiography is a practically ideal field for the development of DL algorithms able to automatically interpret X-rays. Current algorithms can detect up to 14 different abnormalities present either in isolation or in combination. Chest CT is another area offering numerous AI applications. Various algorithms have been specifically formed and validated for the detection and characterization of pulmonary nodules and pulmonary embolism, as well as segmentation and quantitative analysis of the extent of diffuse lung diseases (emphysema, infectious pneumonias, interstitial lung disease). In addition, the analysis of medical images can be associated with clinical, biological, and functional data (multi-omics analysis), the objective being to construct predictive approaches regarding disease prognosis and response to treatment.

A Novel Automatic Algorithm to Support Lung Ultrasound Non-Expert Physicians in Interstitial Pneumonia Evaluation: A Single-Center Study

INTRODUCTION

Lung ultrasound (LUS) is widely used in clinical practice for identifying interstitial lung diseases (ILDs) and assessing their progression. Although high-resolution computed tomography (HRCT) remains the gold standard for evaluating the severity of ILDs, LUS can be performed as a screening method or as a follow-up tool post-HRCT. Minimum training is needed to better identify typical lesions, and the integration of innovative artificial intelligence (AI) automatic algorithms may enhance diagnostic efficiency.

AIM

This study aims to assess the effectiveness of a novel AI algorithm in automatic ILD recognition and scoring in comparison to an expert LUS sonographer. The "SensUS Lung" device, equipped with an automatic algorithm, was employed for the automatic recognition of the typical ILD patterns and to calculate an index grading of the interstitial involvement.

METHODS

We selected 33 Caucasian patients in follow-up for ILDs exhibiting typical HRCT patterns (honeycombing, ground glass, fibrosis). An expert physician evaluated all patients with LUS on twelve segments (six per side). Next, blinded to the previous evaluation, an untrained operator, a non-expert in LUS, performed the exam with the SensUS device equipped with the automatic algorithm ("SensUS Lung") using the same protocol. Pulmonary functional tests (PFT) and DLCO were conducted for all patients, categorizing them as having reduced or preserved DLCO. The SensUS device indicated different grades of interstitial involvement named Lung Staging that were scored from 0 (absent) to 4 (peak), which was compared to the Lung Ultrasound Score (LUS score) by dividing it by the number of segments evaluated. Statistical analyses were done with Wilcoxon tests for paired values or Mann-Whitney for unpaired samples, and correlations were performed using Spearman analysis; p < 0.05 was considered significant.

RESULTS

Lung Staging was non-inferior to LUS score in identifying the risk of ILDs (median SensUS 1 [0-2] vs. LUS 0.67 [0.25-1.54]; p = 0.84). Furthermore, the grade of interstitial pulmonary involvement detected with the SensUS device is directly related to the LUS score (r = 0.607, p = 0.002). Lung Staging values were inversely correlated with forced expiratory volume at first second (FEV1%, r = -0.40, p = 0.027), forced vital capacity (FVC%, r = -0.39, p = 0.03) and forced expiratory flow (FEF) at 25th percentile (FEF25%, r = -0.39, p = 0.02) while results directly correlated with FEF25-75% (r = 0.45, p = 0.04) and FEF75% (r = 0.43, p = 0.01). Finally, in patients with reduced DLCO, the Lung Staging was significantly higher, overlapping the LUS (reduced median 1 [1-2] vs. preserved 0 [0-1], p = 0.001), and overlapping the LUS (reduced median 18 [4-20] vs. preserved 5.5 [2-9], p = 0.035).

CONCLUSIONS

Our data suggest that the considered AI automatic algorithm may assist non-expert physicians in LUS, resulting in non-inferior-to-expert LUS despite a tendency to overestimate ILD lesions. Therefore, the AI algorithm has the potential to support physicians, particularly non-expert LUS sonographers, in daily clinical practice to monitor patients with ILDs. The adopted device is user-friendly, offering a fully automatic real-time analysis. However, it needs proper training in basic skills.

Drug-induced interstitial lung disease: a narrative review of a clinical conundrum

INTRODUCTION

Drug-induced interstitial lung disease (DI-ILD) is increasing in incidence, due to the use of many new drugs across a broad range of cancers and chronic inflammatory diseases. The presentation and onset of DI-ILD are variable even for the same drug across different individuals. Clinical suspicion is essential for identifying these conditions, with timely drug cessation an important determinant of outcomes.

AREAS COVERED

This review provides a comprehensive and up-to-date summary of epidemiology, risk factors, pathogenesis, diagnosis, treatment, and prognosis of DI-ILD. Relevant research articles from PubMed and Medline searches up to September 2023 were screened and summarized. Specific drugs including immune checkpoint inhibitors, CAR-T cell therapy, methotrexate, and amiodarone are discussed in detail. The potential role of pharmacogenomic profiling for lung toxicity risk is considered.

EXPERT OPINION

DI-ILD is likely to be an increasingly important contributor to respiratory disability in the community. These conditions can negatively impact quality of life and patient longevity, due to associated respiratory compromise as well as cessation of evidence-based therapy for the underlying disease. This clinical conundrum is relevant to all areas of medicine, necessitating increased understanding and greater vigilance for drug-related lung toxicity.

Pulmonary fibrosis: from pathogenesis to clinical decision-making

Pulmonary fibrosis (PF) encompasses a spectrum of chronic lung diseases that progressively impact the interstitium, resulting in compromised gas exchange, breathlessness, diminished quality of life (QoL), and ultimately respiratory failure and mortality. Various diseases can cause PF, with their underlying causes primarily affecting the lung interstitium, leading to their referral as interstitial lung diseases (ILDs). The current understanding is that PF arises from abnormal wound healing processes triggered by various factors specific to each disease, leading to excessive inflammation and fibrosis. While significant progress has been made in understanding the molecular mechanisms of PF, its pathogenesis remains elusive. This review provides an in-depth exploration of the latest insights into PF pathophysiology, diagnosis, treatment, and future perspectives.

The potential role of artificial intelligence in the clinical practice of interstitial lung disease

Artificial intelligence (AI) is being widely applied in the field of medicine, in areas such as drug discovery, diagnostic support, and assistance with medical practice. Among these, medical imaging is an area where AI is expected to make a significant contribution. In Japan, as of November 2022, 23 AI medical devices have received regulatory approval; all these devices are related to image analysis. In interstitial lung diseases, technologies have been developed that use AI to analyze high-resolution computed tomography and pathological images, and gene expression patterns in tissue taken from transbronchial lung biopsies to assist in the diagnosis of idiopathic pulmonary fibrosis. Some of these technologies are already being used in clinical practice in the United States. AI is expected to reduce the burden on physicians, improve reproducibility, and advance personalized medicine. Obtaining sufficient data for diseases with a small number of patients is difficult. Additionally, certain issues must be addressed in order for AI to be applied in healthcare. These issues include taking responsibility for the AI results output, updating software after the launch of technology, and adapting to new imaging technologies. Establishing research infrastructures such as large-scale databases and common platforms is important for the development of AI technology: their use requires an understanding of the characteristics and limitations of the systems. CLINICAL TRIAL REGISTRATION: Not applicable.

Development and validation of a CT-based deep learning algorithm to augment non-invasive diagnosis of idiopathic pulmonary fibrosis

RATIONALE

Non-invasive diagnosis of idiopathic pulmonary fibrosis (IPF) involves identification of usual interstitial pneumonia (UIP) pattern by computed tomography (CT) and exclusion of other known etiologies of interstitial lung disease (ILD). However, uncertainty in identification of radiologic UIP pattern leads to the continued need for invasive surgical biopsy. We thus developed and validated a machine learning algorithm using CT scans alone to augment non-invasive diagnosis of IPF.

METHODS

The primary algorithm was a deep learning convolutional neural network (CNN) with model inputs of CT images only. The algorithm was trained to predict IPF among cases of ILD, with reference standard of multidisciplinary discussion (MDD) consensus diagnosis. The algorithm was trained using a multi-center dataset of more than 2000 cases of ILD. A US-based multi-site cohort (n = 295) was used for algorithm tuning, and external validation was performed with a separate dataset (n = 295) from European and South American sources.

RESULTS

In the tuning set, the model achieved an area under the receiver operating characteristic curve (AUC) of 0.87 (CI: 0.83-0.92) in differentiating IPF from other ILDs. Sensitivity and specificity were 0.67 (0.57-0.76) and 0.90 (0.83-0.95), respectively. By contrast, pre-recorded assessment prior to MDD diagnosis had sensitivity of 0.31 (0.23-0.42) and specificity of 0.92 (0.87-0.95). In the external test set, c-statistic was also 0.87 (0.83-0.91). Model performance was consistent across a variety of CT scanner manufacturers and slice thickness.

CONCLUSION

The presented deep learning algorithm demonstrated consistent performance in identifying IPF among cases of ILD using CT images alone and suggests generalization across CT manufacturers.

Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software

Background

Improvement in recognition and referral of pulmonary fibrosis (PF) is vital to improving patient outcomes within interstitial lung disease. We determined the performance metrics and processing time of an artificial intelligence triage and notification software, ScreenDx-LungFibrosis™, developed to improve detection of PF.

Methods

ScreenDx-LungFibrosis™ was applied to chest computed tomography (CT) scans from multisource data. Device output (+/- PF) was compared to clinical diagnosis (+/- PF), and diagnostic performance was evaluated. Primary endpoints included device sensitivity and specificity > 80% and processing time < 4.5 min.

Results

Of 3,018 patients included, PF was present in 22.9%. ScreenDx-LungFibrosis™ detected PF with a sensitivity and specificity of 91.3% (95% confidence interval (CI): 89.0-93.3%) and 95.1% (95% CI: 94.2-96.0%), respectively. Mean processing time was 27.6 s (95% CI: 26.0 - 29.1 s).

Conclusions

ScreenDx-LungFibrosis™ accurately and reliably identified PF with a rapid per-case processing time, underscoring its potential for transformative improvement in PF outcomes when routinely applied to chest CTs.

Precision medicine advances in idiopathic pulmonary fibrosis

Idiopathic pulmonary fibrosis (IPF) is a highly heterogeneous, unpredictable and ultimately lethal chronic lung disease. Over the last decade, two anti-fibrotic agents have been shown to slow disease progression, however, both drugs are administered uniformly with minimal consideration of disease severity and inter-individual molecular, genetic, and genomic differences. Advances in biological understanding of disease endotyping and the emergence of precision medicine have shown that "a one-size-fits-all approach" to the management of chronic lung diseases is no longer appropriate. While precision medicine approaches have revolutionized the management of other diseases such as lung cancer and asthma, the implementation of precision medicine in IPF clinical practice remains an unmet need despite several reports demonstrating a large number of diagnostic, prognostic and theragnostic biomarker candidates in IPF. This review article aims to summarize our current knowledge of precision medicine in IPF and highlight barriers to translate these research findings into clinical practice.

Role of the internet of medical things in care for patients with interstitial lung disease

PURPOSE OF REVIEW

Online technologies play an increasing role in facilitating care for patients with interstitial lung disease (ILD). In this review, we will give an overview of different applications of the internet of medical things (IoMT) for patients with ILD.

RECENT FINDINGS

Various applications of the IoMT, including teleconsultations, virtual MDTs, digital information, and online peer support, are now used in daily care of patients with ILD. Several studies showed that other IoMT applications, such as online home monitoring and telerehabilitation, seem feasible and reliable, but widespread implementation in clinical practice is lacking. The use of artificial intelligence algorithms and online data clouds in ILD is still in its infancy, but has the potential to improve remote, outpatient clinic, and in-hospital care processes. Further studies in large real-world cohorts to confirm and clinically validate results from previous studies are needed.

SUMMARY

We believe that in the near future innovative technologies, facilitated by the IoMT, will further enhance individually targeted treatment for patients with ILD by interlinking and combining data from various sources.

Exploring computer-based imaging analysis in interstitial lung disease: opportunities and challenges

The advent of quantitative computed tomography (QCT) and artificial intelligence (AI) using high-resolution computed tomography data has revolutionised the way interstitial diseases are studied. These quantitative methods provide more accurate and precise results compared to prior semiquantitative methods, which were limited by human error such as interobserver disagreement or low reproducibility. The integration of QCT and AI and the development of digital biomarkers has facilitated not only diagnosis but also prognostication and prediction of disease behaviour, not just in idiopathic pulmonary fibrosis in which they were initially studied, but also in other fibrotic lung diseases. These tools provide reproducible, objective prognostic information which may facilitate clinical decision-making. However, despite the benefits of QCT and AI, there are still obstacles that need to be addressed. Important issues include optimal data management, data sharing and maintenance of data privacy. In addition, the development of explainable AI will be essential to develop trust within the medical community and facilitate implementation in routine clinical practice.

A fully automated micro‑CT deep learning approach for precision preclinical investigation of lung fibrosis progression and response to therapy

Micro-computed tomography (µCT)-based imaging plays a key role in monitoring disease progression and response to candidate drugs in various animal models of human disease, but manual image processing is still highly time-consuming and prone to operator bias. Focusing on an established mouse model of bleomycin (BLM)-induced lung fibrosis we document, here, the ability of a fully automated deep-learning (DL)-based model to improve and speed-up lung segmentation and the precise measurement of morphological and functional biomarkers in both the whole lung and in individual lobes. µCT-DL whose results were overall highly consistent with those of more conventional, especially histological, analyses, allowed to cut down by approximately 45-fold the time required to analyze the entire dataset and to longitudinally follow fibrosis evolution and response to the human-use-approved drug Nintedanib, using both inspiratory and expiratory μCT. Particularly significant advantages of this µCT-DL approach, are: (i) its reduced experimental variability, due to the fact that each animal acts as its own control and the measured, operator bias-free biomarkers can be quantitatively compared across experiments; (ii) its ability to monitor longitudinally the spatial distribution of fibrotic lesions, thus eliminating potential confounding effects associated with the more severe fibrosis observed in the apical region of the left lung and the compensatory effects taking place in the right lung; (iii) the animal sparing afforded by its non-invasive nature and high reliability; and (iv) the fact that it can be integrated into different drug discovery pipelines with a substantial increase in both the speed and robustness of the evaluation of new candidate drugs. The µCT-DL approach thus lends itself as a powerful new tool for the precision preclinical monitoring of BLM-induced lung fibrosis and other disease models as well. Its ease of operation and use of standard imaging instrumentation make it easily transferable to other laboratories and to other experimental settings, including clinical diagnostic applications.

Interpretable deep learning survival predictive tool for small cell lung cancer

Background

Small cell lung cancer (SCLC) is an aggressive and almost universally lethal neoplasm. There is no accurate predictive method for its prognosis. Artificial intelligence deep learning may bring new hope.

Methods

By searching the Surveillance, Epidemiology, and End Results database (SEER), 21,093 patients' clinical data were eventually included. Data were then divided into two groups (train dataset/test dataset). The train dataset (diagnosed in 2010-2014, N = 17,296) was utilized to conduct a deep learning survival model, validated by itself and the test dataset (diagnosed in 2015, N = 3,797) in parallel. According to clinical experience, age, sex, tumor site, T, N, M stage (7th American Joint Committee on Cancer TNM stage), tumor size, surgery, chemotherapy, radiotherapy, and history of malignancy were chosen as predictive clinical features. The C-index was the main indicator to evaluate model performance.

Results

The predictive model had a 0.7181 C-index (95% confidence intervals, CIs, 0.7174-0.7187) in the train dataset and a 0.7208 C-index (95% CIs, 0.7202-0.7215) in the test dataset. These indicated that it had a reliable predictive value on OS for SCLC, so it was then packaged as a Windows software which is free for doctors, researchers, and patients to use.

Conclusion

The interpretable deep learning survival predictive tool for small cell lung cancer developed by this study had a reliable predictive value on their overall survival. More biomarkers may help improve the prognostic predictive performance of small cell lung cancer.

Novel diagnostic techniques in interstitial lung disease

Research into novel diagnostic techniques and targeted therapeutics in interstitial lung disease (ILD) is moving the field toward increased precision and improved patient outcomes. An array of molecular techniques, machine learning approaches and other innovative methods including electronic nose technology and endobronchial optical coherence tomography are promising tools with potential to increase diagnostic accuracy. This review provides a comprehensive overview of the current evidence regarding evolving diagnostic methods in ILD and to consider their future role in routine clinical care.

Quantitative computed tomography and machine learning: recent data in fibrotic interstitial lung disease and potential role in pulmonary sarcoidosis

PURPOSE OF REVIEW

The aim of this study was to summarize quantitative computed tomography (CT) and machine learning data in fibrotic lung disease and to explore the potential application of these technologies in pulmonary sarcoidosis.

RECENT FINDINGS

Recent data in the use of quantitative CT in fibrotic interstitial lung disease (ILD) are covered. Machine learning includes deep learning, a branch of machine learning particularly suited to medical imaging analysis. Deep learning imaging biomarker research in ILD is currently undergoing accelerated development, driven by technological advances in image processing and analysis. Fundamental concepts and goals related to deep learning imaging research in ILD are discussed. Recent work highlighted in this review has been performed in patients with idiopathic pulmonary fibrosis (IPF). Quantitative CT and deep learning have not been applied to pulmonary sarcoidosis, although there are recent deep learning data in cardiac sarcoidosis.

SUMMARY

Pulmonary sarcoidosis presents unsolved problems for which quantitative CT and deep learning may provide unique solutions: in particular, the exploration of the long-standing question of whether sarcoidosis should be viewed as a single disease or as an umbrella term for disorders that might usefully be considered as separate diseases.