-
JMIR AI Mar 2024Many promising artificial intelligence (AI) and computer-aided detection and diagnosis systems have been developed, but few have been successfully integrated into...
The Impact of Expectation Management and Model Transparency on Radiologists' Trust and Utilization of AI Recommendations for Lung Nodule Assessment on Computed Tomography: Simulated Use Study.
BACKGROUND
Many promising artificial intelligence (AI) and computer-aided detection and diagnosis systems have been developed, but few have been successfully integrated into clinical practice. This is partially owing to a lack of user-centered design of AI-based computer-aided detection or diagnosis (AI-CAD) systems.
OBJECTIVE
We aimed to assess the impact of different onboarding tutorials and levels of AI model explainability on radiologists' trust in AI and the use of AI recommendations in lung nodule assessment on computed tomography (CT) scans.
METHODS
In total, 20 radiologists from 7 Dutch medical centers performed lung nodule assessment on CT scans under different conditions in a simulated use study as part of a 2×2 repeated-measures quasi-experimental design. Two types of AI onboarding tutorials (reflective vs informative) and 2 levels of AI output (black box vs explainable) were designed. The radiologists first received an onboarding tutorial that was either informative or reflective. Subsequently, each radiologist assessed 7 CT scans, first without AI recommendations. AI recommendations were shown to the radiologist, and they could adjust their initial assessment. Half of the participants received the recommendations via black box AI output and half received explainable AI output. Mental model and psychological trust were measured before onboarding, after onboarding, and after assessing the 7 CT scans. We recorded whether radiologists changed their assessment on found nodules, malignancy prediction, and follow-up advice for each CT assessment. In addition, we analyzed whether radiologists' trust in their assessments had changed based on the AI recommendations.
RESULTS
Both variations of onboarding tutorials resulted in a significantly improved mental model of the AI-CAD system (informative P=.01 and reflective P=.01). After using AI-CAD, psychological trust significantly decreased for the group with explainable AI output (P=.02). On the basis of the AI recommendations, radiologists changed the number of reported nodules in 27 of 140 assessments, malignancy prediction in 32 of 140 assessments, and follow-up advice in 12 of 140 assessments. The changes were mostly an increased number of reported nodules, a higher estimated probability of malignancy, and earlier follow-up. The radiologists' confidence in their found nodules changed in 82 of 140 assessments, in their estimated probability of malignancy in 50 of 140 assessments, and in their follow-up advice in 28 of 140 assessments. These changes were predominantly increases in confidence. The number of changed assessments and radiologists' confidence did not significantly differ between the groups that received different onboarding tutorials and AI outputs.
CONCLUSIONS
Onboarding tutorials help radiologists gain a better understanding of AI-CAD and facilitate the formation of a correct mental model. If AI explanations do not consistently substantiate the probability of malignancy across patient cases, radiologists' trust in the AI-CAD system can be impaired. Radiologists' confidence in their assessments was improved by using the AI recommendations.
PubMed: 38875574
DOI: 10.2196/52211 -
JMIR AI Jun 2023Ground-glass opacities (GGOs) appearing in computed tomography (CT) scans may indicate potential lung malignancy. Proper management of GGOs based on their features can...
BACKGROUND
Ground-glass opacities (GGOs) appearing in computed tomography (CT) scans may indicate potential lung malignancy. Proper management of GGOs based on their features can prevent the development of lung cancer. Electronic health records are rich sources of information on GGO nodules and their granular features, but most of the valuable information is embedded in unstructured clinical notes.
OBJECTIVE
We aimed to develop, test, and validate a deep learning-based natural language processing (NLP) tool that automatically extracts GGO features to inform the longitudinal trajectory of GGO status from large-scale radiology notes.
METHODS
We developed a bidirectional long short-term memory with a conditional random field-based deep-learning NLP pipeline to extract GGO and granular features of GGO retrospectively from radiology notes of 13,216 lung cancer patients. We evaluated the pipeline with quality assessments and analyzed cohort characterization of the distribution of nodule features longitudinally to assess changes in size and solidity over time.
RESULTS
Our NLP pipeline built on the GGO ontology we developed achieved between 95% and 100% precision, 89% and 100% recall, and 92% and 100% F-scores on different GGO features. We deployed this GGO NLP model to extract and structure comprehensive characteristics of GGOs from 29,496 radiology notes of 4521 lung cancer patients. Longitudinal analysis revealed that size increased in 16.8% (240/1424) of patients, decreased in 14.6% (208/1424), and remained unchanged in 68.5% (976/1424) in their last note compared to the first note. Among 1127 patients who had longitudinal radiology notes of GGO status, 815 (72.3%) were reported to have stable status, and 259 (23%) had increased/progressed status in the subsequent notes.
CONCLUSIONS
Our deep learning-based NLP pipeline can automatically extract granular GGO features at scale from electronic health records when this information is documented in radiology notes and help inform the natural history of GGO. This will open the way for a new paradigm in lung cancer prevention and early detection.
PubMed: 38875565
DOI: 10.2196/44537 -
Journal of the Korean Society of... May 2024Pleural metastasis is the most common cause of malignant diseases involving the pleura, and characterized by pleural effusion, nodules, and thickening. Pleuroparenchymal...
Pleural metastasis is the most common cause of malignant diseases involving the pleura, and characterized by pleural effusion, nodules, and thickening. Pleuroparenchymal fibroelastosis (PPFE) is a disease characterized by apical pleural thickening and subjacent parenchymal fibrosis. We report a case of a 60-year-old male with lung cancer in the left lower lobe and underlying PPFE combined with left apical pleural metastasis. Initially, asymmetric left apical pleural thickening due to pleural metastasis was mistaken for PPFE. Additionally, we describe the imaging and histopathological findings of PPFE, including MRI findings.
PubMed: 38873385
DOI: 10.3348/jksr.2023.0024 -
Journal of the Korean Society of... May 2024This study investigated whether the respiratory phase during pleural puncture in CT-guided percutaneous transthoracic needle biopsy (PTNB) affects complications.
PURPOSE
This study investigated whether the respiratory phase during pleural puncture in CT-guided percutaneous transthoracic needle biopsy (PTNB) affects complications.
MATERIALS AND METHODS
We conducted a retrospective review of 477 lung biopsy CT scans performed during free breathing. The respiratory phases during pleural puncture were determined based on the table position of the targeted nodule using CT scans obtained during free breathing. We compared the rates of complications among the inspiratory, mid-, and expiratory respiratory phases. Logistic regression analysis was performed to control confounding factors associated with pneumothorax.
RESULTS
Among the 477 procedures, pleural puncture was performed during the expiratory phase in 227 (47.6%), during the mid-phase in 108 (22.6%), and during the inspiratory phase in 142 (29.8%). The incidence of pneumothorax was significantly lower in the expiratory puncture group (40/227, 17.6%; = 0.035) and significantly higher in the mid-phase puncture group (31/108, 28.7%; = 0.048). After controlling for confounding factors, expiratory-phase puncture was found to be an independent protective factor against pneumothorax (odds ratio = 0.571; 95% confidence interval = 0.360-0.906; = 0.017).
CONCLUSION
Our findings suggest that pleural puncture during the expiratory phase may reduce the risk of pneumothorax during image guided PTNB.
PubMed: 38873383
DOI: 10.3348/jksr.2023.0093 -
Respirology Case Reports Jun 2024The differential diagnosis of a lung mass with multiple pulmonary nodules includes metastases of lung cancer, mycobacterial infections, and pulmonary mycosis. Pulmonary...
The differential diagnosis of a lung mass with multiple pulmonary nodules includes metastases of lung cancer, mycobacterial infections, and pulmonary mycosis. Pulmonary cryptococcosis should be recognized, especially in immunocompromised patients.
PubMed: 38872912
DOI: 10.1002/rcr2.1415 -
Canadian Association of Radiologists... Jun 2024Incidental pulmonary nodules (IPN) are common radiologic findings, yet management of IPNs is inconsistent across Canada. This study aims to improve IPN management based... (Review)
Review
Incidental pulmonary nodules (IPN) are common radiologic findings, yet management of IPNs is inconsistent across Canada. This study aims to improve IPN management based on multidisciplinary expert consensus and provides recommendations to overcome patient and system-level barriers. A modified Delphi consensus technique was conducted. Multidisciplinary experts with extensive experience in lung nodule management in Canada were recruited to participate in the panel. A survey was administered in 3 rounds, using a 5-point Likert scale to determine the level of agreement (1 = extremely agree, 5 = extremely disagree). Eleven experts agreed to participate in the panel; 10 completed all 3 rounds. Consensus was achieved for 183/217 (84.3%) statements. Panellists agreed that radiology reports should include a standardized summary of findings and follow-up recommendations for all nodule sizes (ie, <6, 6-8, and >8 mm). There was strong consensus regarding the importance of an automated system for patient follow-up and that leadership support for organizational change at the administrative level is of utmost importance in improving IPN management. There was no consensus on the need for standardized national referral pathways, development of new guidelines, or establishing a uniform picture archiving and communication system. Canadian IPN experts agree that improved IPN management should include standardized radiology reporting of IPNs, standardized and automated follow-up of patients with IPNs, guideline adherence and implementation, and leadership support for organizational change. Future research should focus on the implementation and long-term effectiveness of these recommendations in clinical practice.
PubMed: 38869196
DOI: 10.1177/08465371241257910 -
Respiratory Medicine Case Reports 2024The advancement of molecular pathology techniques has led to the discovery of rare mutations for targeted therapy in lung cancer. Additionally, a substantial body of...
The advancement of molecular pathology techniques has led to the discovery of rare mutations for targeted therapy in lung cancer. Additionally, a substantial body of evidence indicates a connection between the development of lung cancer and genetic variations in the EGFR gene. Here, we present a case report of a patient with multifocal lung adenocarcinoma who possessed a rare germline mutation, R776H. An investigation into the family history of the patient exposed the notable incidence of lung adenocarcinoma, indicating a plausible genetic vulnerability to the ailment. To be specific, the patient's older brother and sister both suffered from lung cancer, which underlines the hereditary predisposition. Furthermore, it should be noted that the patient's daughter has inherited the germline mutation and also presented with multiple lung ground-glass nodules, emphasizing the clinical importance of this genetic variation. Following the lobectomy, the patient received treatment with almonertinib, a third-generation tyrosine kinase inhibitor (TKI), and at the latest follow-up, the patient has achieved partial remission. This case highlights the significance of taking into account germline possibilities when multiple lesions carry the same mutation. It stresses the importance of acquiring a comprehensive family history and performing genetic testing on leukocytes. Moreover, for the infrequent R776H mutation, third generation EGFR-TKIs may be a viable option.
PubMed: 38868164
DOI: 10.1016/j.rmcr.2024.102051 -
BMC Medical Imaging Jun 2024This study developed and validated a nomogram utilizing clinical and multi-slice spiral computed tomography (MSCT) features for the preoperative prediction of Ki-67...
Nomogram for the preoperative prediction of Ki-67 expression and prognosis in stage IA lung adenocarcinoma based on clinical and multi-slice spiral computed tomography features.
OBJECTIVE
This study developed and validated a nomogram utilizing clinical and multi-slice spiral computed tomography (MSCT) features for the preoperative prediction of Ki-67 expression in stage IA lung adenocarcinoma. Additionally, we assessed the predictive accuracy of Ki-67 expression levels, as determined by our model, in estimating the prognosis of stage IA lung adenocarcinoma.
MATERIALS AND METHODS
We retrospectively analyzed data from 395 patients with pathologically confirmed stage IA lung adenocarcinoma. A total of 322 patients were divided into training and internal validation groups at a 6:4 ratio, whereas the remaining 73 patients composed the external validation group. According to the pathological results, the patients were classified into high and low Ki-67 labeling index (LI) groups. Clinical and CT features were subjected to statistical analysis. The training group was used to construct a predictive model through logistic regression and to formulate a nomogram. The nomogram's predictive ability and goodness-of-fit were assessed. Internal and external validations were performed, and clinical utility was evaluated. Finally, the recurrence-free survival (RFS) rates were compared.
RESULTS
In the training group, sex, age, tumor density type, tumor-lung interface, lobulation, spiculation, pleural indentation, and maximum nodule diameter differed significantly between patients with high and low Ki-67 LI. Multivariate logistic regression analysis revealed that sex, tumor density, and maximum nodule diameter were significantly associated with high Ki-67 expression in stage IA lung adenocarcinoma. The calibration curves closely resembled the standard curves, indicating the excellent discrimination and accuracy of the model. Decision curve analysis revealed favorable clinical utility. Patients with a nomogram-predicted high Ki-67 LI exhibited worse RFS.
CONCLUSION
The nomogram utilizing clinical and CT features for the preoperative prediction of Ki-67 expression in stage IA lung adenocarcinoma demonstrated excellent performance, clinical utility, and prognostic significance, suggesting that this nomogram is a noninvasive personalized approach for the preoperative prediction of Ki-67 expression.
Topics: Humans; Ki-67 Antigen; Nomograms; Male; Female; Middle Aged; Retrospective Studies; Lung Neoplasms; Adenocarcinoma of Lung; Prognosis; Aged; Neoplasm Staging; Tomography, Spiral Computed; Adult
PubMed: 38867154
DOI: 10.1186/s12880-024-01305-5 -
Journal of Infection in Developing... May 2024Mycobacterium canariasense is a relatively rare and rapidly growing nontuberculous mycobacterium (NTM) infection.
INTRODUCTION
Mycobacterium canariasense is a relatively rare and rapidly growing nontuberculous mycobacterium (NTM) infection.
CASE REPORT
This case report describes a 36-year-old man with a Canariasense infection in the lung with solitary cavitation nodules located subpleural on CT scan, for which the final diagnosis was made by metagenomic next-generation sequencing (mNGS) of bronchoalveolar lavage fluid (BALF-mNGS). It was successfully treated with levofloxacin and amikacin.
CONCLUSIONS
This experience is instructive because clinical diagnostic and CT imaging characteristics and treatment strategy guidelines for pulmonary infections caused by M. canariasense have not yet been established.
Topics: Humans; Male; Adult; Mycobacterium Infections, Nontuberculous; Anti-Bacterial Agents; Tomography, X-Ray Computed; Bronchoalveolar Lavage Fluid; Lung; Levofloxacin; Amikacin; Nontuberculous Mycobacteria; High-Throughput Nucleotide Sequencing; Treatment Outcome
PubMed: 38865393
DOI: 10.3855/jidc.18535 -
Cancer Medicine Jun 2024The genomic and molecular ecology involved in the stepwise continuum progression of lung adenocarcinoma (LUAD) from adenocarcinoma in situ (AIS) to minimally invasive...
Integrated whole-exome and bulk transcriptome sequencing delineates the dynamic evolution from preneoplasia to invasive lung adenocarcinoma featured with ground-glass nodules.
OBJECTIVE
The genomic and molecular ecology involved in the stepwise continuum progression of lung adenocarcinoma (LUAD) from adenocarcinoma in situ (AIS) to minimally invasive adenocarcinoma (MIA) and subsequent invasive adenocarcinoma (IAC) remains unclear and requires further elucidation. We aimed to characterize gene mutations and expression landscapes, and explore the association between differentially expressed genes (DEGs) and significantly mutated genes (SMGs) during the dynamic evolution from AIS to IAC.
METHODS
Thirty-five patients with ground-glass nodules (GGNs) lung adenocarcinomas were enrolled. Whole-exome sequencing (WES) and transcriptome sequencing (RNA-Seq) were conducted on all patients, encompassing both tumor samples and corresponding noncancerous tissues. Data obtained from WES and RNA-Seq were subsequently analyzed.
RESULTS
The findings from WES delineated that the predominant mutations were observed in EGFR (49%) and ANKRD36C (17%). SMGs, including EGFR and RBM10, were associated with the dynamic evolution from AIS to IAC. Meanwhile, DEGs, including GPR143, CCR9, ADAMTS16, and others were associated with the entire process of invasive LUAD. We found that the signaling pathways related to cell migration and invasion were upregulated, and the signaling pathways of angiogenesis were downregulated across the pathological stages. Furthermore, we found that the messenger RNA (mRNA) levels of FAM83A, MAL2, DEPTOR, and others were significantly correlated with CNVs. Gene set enrichment analysis (GSEA) showed that heme metabolism and cholesterol homeostasis pathways were significantly upregulated in patients with EGFR/RBM10 co-mutations, and these patients may have poorer overall survival than those with EGFR mutations. Based on the six calculation methods for the immune infiltration score, NK/CD8 T cells decreased, and Treg/B cells increased with the progression of early LUAD.
CONCLUSIONS
Our findings offer valuable insights into the unique genomic and molecular features of LUAD, facilitating the identification and advancement of precision medicine strategies targeting the invasive progression of LUAD from AIS to IAC.
Topics: Humans; Exome Sequencing; Adenocarcinoma of Lung; Lung Neoplasms; Male; Female; Mutation; Middle Aged; Aged; Neoplasm Invasiveness; Disease Progression; Gene Expression Regulation, Neoplastic; Transcriptome; Gene Expression Profiling; Adenocarcinoma in Situ; Precancerous Conditions; Biomarkers, Tumor
PubMed: 38864483
DOI: 10.1002/cam4.7383