Validation of a computed tomography diagnostic model for differentiating fibrotic hypersensitivity pneumonitis from idiopathic pulmonary fibrosis.

BACKGROUND: The diagnosis of fibrotic hypersensitivity pneumonitis (fHP) from other interstitial lung diseases, particularly idiopathic pulmonary fibrosis (IPF), is often difficult. This study aimed to examine computed tomography (CT) findings that were useful for differentiating between fHP and IPF and to develop and validate a radiological diagnostic model. METHODS: In this study, 246 patients (fHP, n = 104; IPF, n = 142) from two institutions were included and randomly divided into the test (n = 164) and validation (n = 82) groups (at a 2:1 ratio). Three radiologists evaluated CT findings, such as pulmonary fibrosis, small airway disease, and predominant distribution, and compared them between fHP and IPF using binomial logistic regression and multivariate analysis. A prognostic model was developed from the test group and validated with the validation group. RESULTS: Ground-glass opacity (GGO) with traction bronchiectasis (TB), honeycombing, hypoattenuation area, three-density pattern, diffuse craniocaudal distribution, peribronchovascular opacities in the upper lung, and random distribution were more common in fHP than in IPF. In multivariate analysis, GGO with TB, peribronchovascular opacities in the upper lung, and random distribution were significant features. The area under the curve of the fHP diagnostic model with the three aforementioned CT features was 0.733 (95% confidence interval [CI], 0.655-0.811, p < 0.001) in the test group and 0.630 (95% CI, 0.504-0.755, p < 0.047) in the validation group. CONCLUSION: GGO with TB, peribronchovascular opacities in the upper lung, and random distribution were important CT features for differentiating fHP from IPF.

Idiopathic dendriform pulmonary ossification as the phenotype of interstitial lung abnormalities: CT-pathologic correlation and prevalence.

BACKGROUND AND PURPOSE: Idiopathic dendriform pulmonary ossification (DPO) is mostly asymptomatic, and detected incidentally in lung CT. There have been no reports on the precise CT-pathologic correlation and the prevalence of idiopathic DPO. This study aimed to clarify the histological background and prevalence of idiopathic DPO. MATERIALS AND METHODS: Sixteen patients with histologically confirmed idiopathic DPO (12 men and 4 women; mean age, 38.8 years; range 22-56 years) were identified in a nationwide epidemiological survey. Local HRCT findings of pre-biopsy examinations, such as branching, round, linear structures with or without high attenuation were compared side by side with histological findings. The attenuation of branching, round, and linear structures was classified into three-point levels on bone window images (width, 2500 HU; level, 500 HU). Furthermore, we collected continuous pulmonary CT images of 8111 cases for checking up metastasis from extrathoracic malignancy at a single institution, and evaluated the prevalence of interstitial lung abnormalities (ILAs) and DPO. RESULTS: In all 16 cases, branching (n = 15, 93%), round (n = 5, 31%), or linear (n = 5, 31%) structures were identified, histologically corresponding to dendriform ossification and cicatricial organizing pneumonia (OP)/fibrosis. Histologically, ossification was confirmed in all the 16 patients. However, in two cases, a highly attenuated structure could not be detected on the pre-biopsy CT of the same area. Regarding the prevalence of idiopathic DPO, 283 (3.5%) of 8111 patients had ILAs, of which a total of 26 (0.3% of all cases, 9.2% of ILAs cases) had DPO. CONCLUSION: Idiopathic DPO showed linear or branching structures with or without high attenuation on CT, corresponded to ossification, cicatricial OP/fibrosis. DPO was seen in 9.2% of ILAs cases. Idiopathic DPO is one of pathologic phenotypes of ILAs.

Performance of artificial intelligence-based software for the automatic detection of lung lesions on chest radiographs of patients with suspected lung cancer.

PURPOSE: This study aimed to evaluate the performance of the commercially available artificial intelligence-based software CXR-AID for the automatic detection of pulmonary nodules on the chest radiographs of patients suspected of having lung cancer. MATERIALS AND METHODS: This retrospective study included 399 patients with clinically suspected lung cancer who underwent CT and chest radiography within 1 month between June 2020 and May 2022. The candidate areas on chest radiographs identified by CXR-AID were categorized into target (properly detected areas) and non-target (improperly detected areas) areas. The non-target areas were further divided into non-target normal areas (false positives for normal structures) and non-target abnormal areas. The visibility score, characteristics and location of the nodules, presence of overlapping structures, and background lung score and presence of pulmonary disease were manually evaluated and compared between the nodules detected or undetected by CXR-AID. The probability indices calculated by CXR-AID were compared between the target and non-target areas. RESULTS: Among the 450 nodules detected in 399 patients, 331 nodules detected in 313 patients were visible on chest radiographs during manual evaluation. CXR-AID detected 264 of these 331 nodules with a sensitivity of 0.80. The detection sensitivity increased significantly with the visibility score. No significant correlation was observed between the background lung score and sensitivity. The non-target area per image was 0.85, and the probability index of the non-target area was lower than that of the target area. The non-target normal area per image was 0.24. Larger and more solid nodules exhibited higher sensitivities, while nodules with overlapping structures demonstrated lower detection sensitivities. CONCLUSION: The nodule detection sensitivity of CXR-AID on chest radiographs was 0.80, and the non-target and non-target normal areas per image were 0.85 and 0.24, respectively. Larger, solid nodules without overlapping structures were detected more readily by CXR-AID.

Zero Echo Time Magnetic Resonance Imaging; Techniques and Clinical Utility in Musculoskeletal System.

Zero echo time (ZTE) sequence is recent advanced magnetic resonance technique that utilizes ultrafast readouts to capture signals from short-T2 tissues. This sequence enables T2- and T2* weighted imaging of tissues with short intrinsic relaxation times by using an extremely short TE, and are increasingly used in the musculoskeletal system. We review the imaging physics of these sequences, practical limitations, and image reconstruction, and then discuss the clinical utilities in various disorders of the musculoskeletal system. ZTE can be readily incorporated into the clinical workflow, and is a promising technique to avoid unnecessary radiation exposure, cost, and time-consuming by computed tomography in some cases. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 1.

Stepwise diagnostic algorithm for high-attenuation pulmonary abnormalities on CT.

High-attenuation pulmonary abnormalities are commonly seen on CT. These findings are increasingly encountered with the growing number of CT examinations and the wide availability of thin-slice images. The abnormalities include benign lesions, such as infectious granulomatous diseases and metabolic diseases, and malignant tumors, such as lung cancers and metastatic tumors. Due to the wide spectrum of diseases, the proper diagnosis of high-attenuation abnormalities can be challenging. The assessment of these abnormal findings requires scrutiny, and the treatment is imperative. Our proposed stepwise diagnostic algorithm consists of five steps. Step 1: Establish the presence or absence of metallic artifacts. Step 2: Identify associated nodular or mass-like soft tissue components. Step 3: Establish the presence of solitary or multiple lesions if identified in Step 2. Step 4: Ascertain the predominant distribution in the upper or lower lungs if not identified in Step 2. Step 5: Identify the morphological pattern, such as linear, consolidation, nodular, or micronodular if not identified in Step 4. These five steps to diagnosing high-attenuation abnormalities subdivide the lesions into nine categories. This stepwise radiologic diagnostic approach could help to narrow the differential diagnosis for various pulmonary high-attenuation abnormalities and to achieve a precise diagnosis.Critical relevance statement Our proposed stepwise diagnostic algorithm for high-attenuation pulmonary abnormalities may help to recognize a variety of those high-attenuation findings, to determine whether the associated diseases require further investigation, and to guide appropriate patient management. Key points • To provide a stepwise diagnostic approach to high-attenuation pulmonary abnormalities.• To familiarize radiologists with the varying cause of high-attenuation pulmonary abnormalities.• To recognize which high-attenuation abnormalities require scrutiny and prompt treatment.

Deep learning-based automatic detection for pulmonary nodules on chest radiographs: The relationship with background lung condition, nodule characteristics, and location.

PURPOSE: Computer-aided diagnosis (CAD), which assists in the interpretation of chest radiographs, is becoming common. However, few studies have evaluated the benefits and pitfalls of CAD in the real world. This study aimed to evaluate the independent performance of commercially available deep learning-based automatic detection (DLAD) software, EIRL Chest X-ray Lung Nodule, in a cohort that included patients with background pulmonary abnormalities often encountered in clinical situations. METHODS: Patients with clinically suspected lung cancer for whom chest radiography was performed within a month before or after CT scan between June 2020 and May 2022 in our institution were enrolled. The reference standard was created using a bounding box annotated by two radiologists with reference to the CT. The visibility score, characteristics, location of the pulmonary nodules, presence of overlapping structures or pulmonary disease, and background lung score were manually determined. RESULTS: We included 388 patients. The DLAD software detected 222 of the 322 nodules visible on manual evaluation, with a sensitivity of 0.689 and a false-positive rate of 0.168. The detectability of the DLAD software was significantly lower for small and subsolid and nodules with overlapping structures. The visibility score and sensitivity of detection by the DLAD software were positively correlated. The relationship between the background lung score and detection by the DLAD software was unclear. CONCLUSION: The standalone performance of DLAD in detecting pulmonary nodules exhibited a sensitivity of 0.689 and a false-positive rate of 0.168. Understanding the characteristics of DLAD is crucial when interpreting chest radiographs with the assistance of the DLAD.

Role of Peer Support in Posttraumatic Growth Among Adolescent and Young Adult Cancer Patients and Survivors.

Purpose: Adolescents and young adults (AYA) who undergo cancer treatment sometimes report posttraumatic growth (PTG). Although the importance of peer support has been suggested, its association with PTG, especially its five distinct domains, needs to be investigated further in AYA cancer survivors. The present study examined the role of demographics and peer support in PTG among AYA cancer patients and survivors. Methods: The present, multicenter, cross-sectional, web-based study enrolled AYA cancer patients and survivors (median age: 28 years). Of 549 AYA patients recruited, 212 from 11 cancer centers and 12 cancer patient communities agreed to participate by completing a self-reported measure of PTG (Extended Version of the Posttraumatic Growth Inventory-Japanese) and providing information about their diagnosis, treatment, peer support (affiliation with an AYA patient community or friendship with other AYA patients), and social status. Multiple regression analysis was used to identify significant correlations overall and in the five PTG domains. Results: PTG was positively associated with male sex, having a confidant, and friendship with other AYA patients, and negatively associated with cranial radiation. Friendship with other AYA patients was positively associated with four of the five PTG subscales. For the five subscale scores, "cranial radiation" was negatively associated with "relating to others"; "belonging to a religion" was positively associated with "spiritual change"; and "having a confidant" was positively associated with "relating to others" and "new possibility." Conclusion: "Having a confidant" and "friendship with other AYA patients" were positively associated with PTG. Psychosocial interventions mobilizing peer support may contribute to promoting PTG in AYA patients. UMIN000035439.

The effect of deep convolutional neural networks on radiologists' performance in the detection of hip fractures on digital pelvic radiographs.

PURPOSE: The purpose of our study is to develop deep convolutional neural network (DCNN) for detecting hip fractures using CT and MRI as a gold standard, and to evaluate the diagnostic performance of 7 readers with and without DCNN. METHODS: The study population consisted of 327 patients who underwent pelvic CT or MRI and were diagnosed with proximal femoral fractures. All radiographs were manually checked and annotated by radiologists referring to CT and MRI for selecting ROI. At first, a DCNN with the GoogLeNet model was trained by 302 cases. The remaining 25 cases and 25 control subjects were used for the observer performance study and for the testing of DCNN. Seven readers took part in this study. A continuous rating scale was used to record each observer's confidence level. Subsequently, each observer interpreted with the DCNN outputs and rated them again. The area under the curve (AUC) was used to compare the fracture detection. RESULTS: The average AUC of the 7 readers was 0.832. The AUC of DCNN alone was 0.905. The average AUC of the 7 readers with DCNN outputs was 0.876. The AUC of readers with DCNN output were higher than those without(p < 0.05). The AUC of the 2 experienced readers with DCNN output exceeded the AUC of DCNN alone. CONCLUSION: For detecting the hip fractures on radiographs, DCNN developed using CT and MRI as a gold standard by radiologists improved the diagnostic performance including the experienced readers.

CT temporal subtraction method for detection of sclerotic bone metastasis in the thoracolumbar spine.

PURPOSE: To assess the effectiveness of a CT temporal subtraction (TS) method on radiologists' performance in sclerotic metastasis detection in the thoracolumbar spine. MATERIALS AND METHODS: 20 pairs (current and previous CTs) of standard-dose CT and their TS images in patients with sclerotic bone metastasis and 20 pairs (current and previous CTs) of those in patients without bone metastasis were used for an observer performance study. A total of 135 lesions were identified as the reference standard of actionable lesions (sclerotic metastasis newly appeared or increased in size or in attenuation). 4 attending radiologists and 4 radiology residents participated in this observer study. Ratings and locations of "lesions" determined by the observers were utilized for assessing the statistical significance of differences between radiologists' performances without and with the CT-TS images in JAFROC analysis. The statistical significance of differences in the reviewing time was determined by a two-tailed paired t-test. RESULTS: The average figure-of-merit (FOM) values for all but one radiologist increased to a statistically significant degree, from 0.856 without the CT-TS images to 0.884 with the images (P = .037). The average sensitivity for detecting the actionable lesions was improved from 60.7 % to 72.5% at a false-positive rate of 0.15 per case by use of the CT-TS images. The average reading time with CT-TS images was significantly shorter than that without (150.6 s vs. 166.5 s, P = .004). CONCLUSION: The use of CT-TS would improve the observer performance for the detection of the sclerotic bone metastasis in the thoracolumbar spine.