Publications by authors named "Akinori Hata"
This retrospective study developed an automated algorithm for 3D segmentation of adipose tissue and paravertebral muscle on chest CT using artificial intelligence (AI) and assessed its feasibility. The study included patients from the Boston Lung Cancer Study (2000-2011). For adipose tissue quantification, 77 patients were included, while 245 were used for muscle quantification.
View Article and Find Full Text PDFPurpose: To compare the variability of quantitative values from lung adenocarcinoma CT images independently assessed by 2 radiologists and AI-based software under different display conditions, and to identify predictors of pathological lymph node metastasis (LNM), disease-free survival (DFS), and overall survival (OS).
Methods: Preoperative CT images of 307 patients were displayed under 4 conditions: lung-1, lung-2, mediastinum-1, and mediastinum-2. Two radiologists (R1, R2) measured total diameter (tD) and the longest solid diameter (sD) under each condition.
Topic Importance: As interstitial lung abnormalities (ILAs) are increasingly recognized on imaging and in clinical practice, identification and appropriate management are critical. We propose an algorithmic approach to the identification and management of patients with ILAs.
Review Findings: The radiologist initially identifies chest CT scan findings suggestive of an ILA pattern and excludes findings that are not consistent with ILAs.
Article Synopsis
- - The study aimed to create a CT-based deep learning model for distinguishing low-risk and high-risk thymoma, comparing its performance with that of radiologists.
- - A total of 159 patients were analyzed using a fine-tuned VGG16 model with various data augmentations, resulting in a DL accuracy of 71.3%.
- - While the DL model improved diagnostic accuracy for radiologists, the overall performance, gauged by the area under the curve (AUC), showed no significant differences with or without the model.
Article Synopsis
- Researchers are developing automated models using machine learning to predict interstitial lung abnormalities (ILAs) in CT scans, as current methods rely heavily on manual assessments, which can be less efficient.
- The study analyzed 1,382 CT scans from the Boston Lung Cancer Study, with radiologists serving as a reference point to identify ILAs; the scans were categorized into three groups: ILA present, indeterminate, and no ILA.
- Various machine learning classifiers were tested for accuracy, revealing that certain models performed better in identifying ILAs, highlighting the potential for automated methods to improve clinical decision-making in lung health.
Article Synopsis
- The study aimed to compare the effectiveness of two types of CT scanning technologies: photon-counting detector computed tomography (PCD-CT) and energy-integrating detector computed tomography (EID-CT) in detecting nodules and airways in human lungs.
- Twenty cadaveric lungs were examined, utilizing various settings for PCD-CT and standard settings for EID-CT, followed by histological evaluation after staining.
- Results showed that PCD-CT, particularly in the ultra-high-resolution mode, outperformed EID-CT in visualizing both nodules and airways, with significant differences in detection capabilities highlighted in the scores and sizes of detected structures.
To investigate the effect of heart rate and virtual monoenergetic image (VMI) on coronary stent imaging in dual-source photon-counting detector computed tomography (PCD-CT). A dynamic cardiac phantom was used to vary the heart rate at 50 beats per minute (bpm), 70 bpm, and 90 bpm. Five types of stents (4.
View Article and Find Full Text PDFWe examined the association between texture features using three-dimensional (3D) io-dine density histogram on delayed phase of dual-energy CT (DECT) and expression of programmed death-ligand 1 (PD-L1) using immunostaining methods in non-small cell lung cancer. Consecutive 37 patients were scanned by DECT. Unenhanced and enhanced (3 min delay) images were obtained.
View Article and Find Full Text PDFObjectives: To investigate the association of lung signal intensity changes during forced breathing using dynamic digital radiography (DDR) with pulmonary function and disease severity in patients with chronic obstructive pulmonary disease (COPD).
Methods: This retrospective study included 46 healthy subjects and 33 COPD patients who underwent posteroanterior chest DDR examination. We collected raw signal intensity and gray-scale image data.
Article Synopsis
- The study aimed to explore how interstitial lung abnormalities (ILAs) affect mortality in patients with esophageal cancer, focusing on overall survival and causes of death.
- Conducted from 2011 to 2015, the research evaluated 478 esophageal cancer patients, categorizing their ILAs based on CT scans and analyzing survival rates with various statistical models.
- Results indicated that patients with ILAs had a significantly shorter overall survival, particularly those with subpleural fibrotic ILAs, and a higher prevalence of death from pneumonia or respiratory failure compared to those without ILAs.
Background: Novel biomarkers (BMs) are urgently needed for bronchial asthma (BA) with various phenotypes and endotypes.
Objective: We sought to identify novel BMs reflecting tissue pathology from serum extracellular vesicles (EVs).
Methods: We performed data-independent acquisition of serum EVs from 4 healthy controls, 4 noneosinophilic asthma (NEA) patients, and 4 eosinophilic asthma (EA) patients to identify novel BMs for BA.
Purpose: To predict solid and micropapillary components in lung invasive adenocarcinoma using radiomic analyses based on high-spatial-resolution CT (HSR-CT).
Materials And Methods: For this retrospective study, 64 patients with lung invasive adenocarcinoma were enrolled. All patients were scanned by HSR-CT with 1024 matrix.
Article Synopsis
- The study aimed to explore how common interstitial lung abnormalities (ILAs) are in individuals with rheumatoid arthritis (RA) compared to those without, and how these conditions affect mortality.
- Researchers analyzed data from a cohort of current and former smokers, using chest scans to identify and classify ILAs while considering the impact of various lifestyle factors and genetics.
- Results showed that RA patients had a significantly higher prevalence of ILAs (16.9%) compared to non-RA individuals (5.0%), with RA patients who had ILAs experiencing a threefold increase in all-cause mortality, highlighting the need for better screening and management.
Article Synopsis
- A study involving 42 patients analyzed the effectiveness of dual-energy CT in differentiating between thymic epithelial tumors, specifically low-risk and high-risk thymomas, and thymic carcinoma.
- The research utilized 3D iodine density histogram texture analysis, measuring various factors like iodine effect and extracellular volume fraction (ECV) to predict tumor types and assess correlations with tissue fibrosis.
- Results indicated that an ECV greater than 21.47% could predict thymic carcinoma, while an iodine effect of 1.31 mg/cc or lower could distinguish high-risk thymoma, both showing notable diagnostic performance.
Pulmonary fibrosis is recognized as occurring in association with a wide and increasing array of conditions, and it presents with a spectrum of chest CT appearances. Idiopathic pulmonary fibrosis (IPF), which corresponds histologically with usual interstitial pneumonia and represents the most common idiopathic interstitial pneumonia, is a chronic progressive fibrotic interstitial lung disease (ILD) of unknown cause. Progressive pulmonary fibrosis (PPF) describes the radiologic development of pulmonary fibrosis in patients with ILD of a known or unknown cause other than IPF.
View Article and Find Full Text PDFArticle Synopsis
- Immune checkpoint inhibitors (ICI) are used to treat advanced nonsmall cell lung cancer (NSCLC) but can lead to immune-related adverse events, including thyroiditis.
- The study examined 534 NSCLC patients and found that 9.4% showed imaging signs of thyroiditis, particularly on chest CT and PET/CT scans, with symptoms typically starting about 9.5 weeks after treatment began.
- Effective management, such as hormone replacement, was more common in patients with both clinical and imaging diagnoses of thyroiditis, highlighting the importance of recognizing these imaging findings in clinical practice.
Article Synopsis
- - The study aimed to evaluate the connection between projected lung area (PLA), demographic data, pulmonary function, and severity of COPD, while also creating longitudinal PLA curves using automated methods.
- - Researchers compared healthy volunteers and COPD patients, finding that severe COPD patients exhibited larger PLA and distinct differences in related metrics when compared to normal subjects.
- - Results indicated that PLA correlated with forced expiratory volume and vital capacity measures, highlighting pulmonary function variations between healthy individuals and those with COPD.
(ILA) is defined as an interstitial change detected incidentally on CT images. It is seen in 4%-9% of smokers and 2%-7% of nonsmokers. ILA has a tendency to progress with time and is associated with respiratory symptoms, decreased exercise capability, reduced pulmonary function, and increased mortality.
View Article and Find Full Text PDFArticle Synopsis
- Interstitial lung abnormalities (ILA) on CT scans are linked to poor lung function and higher mortality, but it’s unclear if incidental interstitial lung disease (ILD) contributes to these issues.
- In a study, 239 out of 4,361 participants were found to have suspected ILD, which correlated with worse health outcomes such as decreased exercise tolerance and higher mortality rates compared to those with ILA only.
- Key risk factors for suspected ILD included being self-identified as Black and having a significant smoking history.
Article Synopsis
- A study compared radiologists' performance in diagnosing lung nodules/masses with and without the aid of deep learning (DL) computer-aided diagnosis (CAD).
- A total of 101 cases were analyzed, grouping 15 radiologists by experience level (L, M, and H) and assessing their ability to identify characteristics of the nodules and diagnose malignancy.
- Results showed that radiologists with less than 5 years of experience benefited significantly from CAD, leading to improved accuracy and consistency in diagnoses without increasing assessment time.
Background: Interstitial lung abnormalities (ILA) are radiologic findings that may progress to idiopathic pulmonary fibrosis (IPF). Blood gene expression profiles can predict IPF mortality, but whether these same genes associate with ILA and ILA outcomes is unknown. This study evaluated if a previously described blood gene expression profile associated with IPF mortality is associated with ILA and all-cause mortality.
View Article and Find Full Text PDF