Use of a radiology tool for the diagnosis of pulmonary fibrosis.

OBJECTIVE: The purpose of this paper was to perform an exploratory reader study to assess the utility of a web-based application in assisting non-chest radiologist in correctly diagnosing the radiographic pattern of pulmonary fibrosis. METHODS: Three non-chest radiologists with 5 to 20 years of experience individually reviewed 3 rounds of randomly chosen chest CT scans (round 1: 100 scans, round 2: 50 scans, round 3: 25 scans) from a list of patients with established diagnosis of pulmonary fibrosis. In round 1, radiologists were asked to directly record their diagnosis for the pattern of fibrosis. In round 2 and 3 they were asked to review for features provided in a web-based application and provide diagnosis based on the most likely predicted diagnosis from the application. There was an approximate 1-month interval and relevant tutorials were provided between each round. Diagnosis accuracy is reported by readers at each round. RESULTS: The overall accuracy increased from 63 % (n = 188/299) in round 1 to 74 % in round 3 (n = 52/70) (p = 0.0265). Difficulty in recognition of mosaic attenuation and homogeneous has led to misdiagnosis. Refining the definition for feature homogeneous increased the diagnosis accuracy of NSIP from 42 % (n = 20/48) in round 2 to 65 % (n = 24/37) in round 3(p = 0.0179). The Fleiss Kappa across readers varied from Round 1 to Round 3 with values 0.36 to 0.42. CONCLUSIONS: Using the web-based application with refined definition for feature homogeneous helps to improve the non-subspecialty radiologist's accuracy in diagnosing different types of fibrosis.

Radiology of fibrosis. Part I: Thoracic organs.

Sustained injury from factors such as hypoxia, infection, or physical damage may provoke improper tissue repair and the anomalous deposition of connective tissue that causes fibrosis. This phenomenon may take place in any organ, ultimately leading to their dysfunction and eventual failure. Tissue fibrosis has also been found to be central in both the process of carcinogenesis and cancer progression. Thus, its prompt diagnosis and regular monitoring is necessary for implementing effective disease-modifying interventions aiming to reduce mortality and improve overall quality of life. While significant research has been conducted on these subjects, a comprehensive understanding of how their relationship manifests through modern imaging techniques remains to be established. This work intends to provide a comprehensive overview of imaging technologies relevant to the detection of fibrosis affecting thoracic organs as well as to explore potential future advancements in this field.

Radiology of fibrosis part II: abdominal organs.

Fibrosis is the aberrant process of connective tissue deposition from abnormal tissue repair in response to sustained tissue injury caused by hypoxia, infection, or physical damage. It can affect almost all organs in the body causing dysfunction and ultimate organ failure. Tissue fibrosis also plays a vital role in carcinogenesis and cancer progression. The early and accurate diagnosis of organ fibrosis along with adequate surveillance are helpful to implement early disease-modifying interventions, important to reduce mortality and improve quality of life. While extensive research has already been carried out on the topic, a thorough understanding of how this relationship reveals itself using modern imaging techniques has yet to be established. This work outlines the ways in which fibrosis shows up in abdominal organs and has listed the most relevant imaging technologies employed for its detection. New imaging technologies and developments are discussed along with their promising applications in the early detection of organ fibrosis.

Radiology of fibrosis part III: genitourinary system.

Fibrosis is a pathological process involving the abnormal deposition of connective tissue, resulting from improper tissue repair in response to sustained injury caused by hypoxia, infection, or physical damage. It can impact any organ, leading to their dysfunction and eventual failure. Additionally, tissue fibrosis plays an important role in carcinogenesis and the progression of cancer.Early and accurate diagnosis of organ fibrosis, coupled with regular surveillance, is essential for timely disease-modifying interventions, ultimately reducing mortality and enhancing quality of life. While extensive research has already been carried out on the topics of aberrant wound healing and fibrogenesis, we lack a thorough understanding of how their relationship reveals itself through modern imaging techniques.This paper focuses on fibrosis of the genito-urinary system, detailing relevant imaging technologies used for its detection and exploring future directions.

Deep learning to detect left ventricular structural abnormalities in chest X-rays.

BACKGROUND AND AIMS: Early identification of cardiac structural abnormalities indicative of heart failure is crucial to improving patient outcomes. Chest X-rays (CXRs) are routinely conducted on a broad population of patients, presenting an opportunity to build scalable screening tools for structural abnormalities indicative of Stage B or worse heart failure with deep learning methods. In this study, a model was developed to identify severe left ventricular hypertrophy (SLVH) and dilated left ventricle (DLV) using CXRs. METHODS: A total of 71 589 unique CXRs from 24 689 different patients completed within 1 year of echocardiograms were identified. Labels for SLVH, DLV, and a composite label indicating the presence of either were extracted from echocardiograms. A deep learning model was developed and evaluated using area under the receiver operating characteristic curve (AUROC). Performance was additionally validated on 8003 CXRs from an external site and compared against visual assessment by 15 board-certified radiologists. RESULTS: The model yielded an AUROC of 0.79 (0.76-0.81) for SLVH, 0.80 (0.77-0.84) for DLV, and 0.80 (0.78-0.83) for the composite label, with similar performance on an external data set. The model outperformed all 15 individual radiologists for predicting the composite label and achieved a sensitivity of 71% vs. 66% against the consensus vote across all radiologists at a fixed specificity of 73%. CONCLUSIONS: Deep learning analysis of CXRs can accurately detect the presence of certain structural abnormalities and may be useful in early identification of patients with LV hypertrophy and dilation. As a resource to promote further innovation, 71 589 CXRs with adjoining echocardiographic labels have been made publicly available.

Developing radiology diagnostic tools for pulmonary fibrosis using machine learning methods.

BACKGROUND: Accurate and prompt diagnosis of the different patterns for pulmonary fibrosis is essential for patient management. However, accurate diagnosis of the specific pattern is challenging due to overlapping radiographic characteristics. MATERIALS AND METHODS: We conducted a retrospective chart review utilizing two machine learning methods, classification and regression tree and Bayesian additive regression tree, to select the most important radiographic features for diagnosing the three most common fibrosis patterns and created an online diagnostic app for convenient implementation. RESULTS: Four hundred patients (median age of 67 with inter quartile range 58-73; 200 males) were included in the study. Peripheral distribution, homogeneity, lower lobe predominance and mosaic attenuation of fibrosis are the four most important features identified. Bayesian additive regression tree demonstrates better performance than classification and regression tree in diagnosis prediction and provides the predicted probability of each diagnosis with uncertainty intervals for each combination of features. CONCLUSION: The model and app built with Bayesian additive regression tree can be used as an effective tool in assisting radiologists in the diagnostic process of pulmonary fibrosis pattern recognition.

Performance of RAPID noncontrast CT stroke platform in large vessel occlusion and intracranial hemorrhage detection.

Background: Noncontrast CT (NCCT) is used to evaluate for intracerebral hemorrhage (ICH) and ischemia in acute ischemic stroke (AIS). Large vessel occlusions (LVOs) are a major cause of AIS, but challenging to detect on NCCT. Aims: The purpose of this study is to evaluate an AI software called RAPID NCCT Stroke (RAPID, iSchemaView, Menlo Park, CA) for ICH and LVO detection compared to expert readers. Methods: In this IRB approved retrospective, multicenter study, stand-alone performance of the software was assessed based on the consensus of 3 neuroradiologists and sensitivity and specificity were determined. The platform's performance was then compared to interpretation by readers comprised of eight general radiologists (GR) and three neuroradiologists (NR) in detecting ICH and hyperdense vessel sign (HVS) indicating LVO. Results: A total of 244 cases were included. Of the 244, 115 were LVOs and 26 were ICHs. One hundred three cases did not have LVO nor ICH. Stand-alone performance of the software demonstrated sensitivities and specificities of 96.2 and 99.5% for ICH and 63.5 and 95.1% for LVO detection. Compared to all 11 readers and eight GR readers only respectively, the software demonstrated superiority, achieving significantly higher sensitivities (63.5% versus 43.6%, p < 0.0001 and 63.5% versus 40.9%, p = 0.001). Conclusion: The RAPID NCCT Stroke platform demonstrates superior performance to radiologists for detecting LVO from a NCCT. Use of this software platform could lead to earlier LVO detection and expedited transfer of these patients to a thrombectomy capable center.

Liver Transplant for Nonhepatocellular Malignancies: A Review for Radiologists.

Although liver transplant is traditionally only performed for hepatocellular carcinoma (HCC), the last decade has seen a resurgence in its use for non-HCC malignancies, likely due to improvements in neoadjuvant treatment regimens and the establishment of well-defined eligibility criteria. Given promising survival results, patients with perihilar cholangiocarcinoma, neuroendocrine liver metastases, and hepatic hemangioendothelioma are eligible to receive Model for End-Stage Liver Disease (MELD) exception points for tumors that meet well-defined criteria. Patients with additional tumors such as colorectal cancer liver metastases, intrahepatic cholangiocarcinoma, and hepatocellular cholangiocarcinoma may undergo transplant at specialized centers with well-defined protocols, although these patients are not yet eligible for MELD exception. Transplant eligibility criteria commonly incorporate imaging findings; however, because of the relatively novel and evolving nature of liver transplant for non-HCC malignancies, radiologists may be unaware of relevant criteria or the implications of their imaging interpretations. Knowledge of the allocation process, previous studies, and liver transplant selection criteria facilitates radiologists' active participation in multidisciplinary discussion, leading to better and more equitable care for transplant candidates with non-HCC malignancy. This review provides an overview of transplant allocation and selection criteria in patients with non-HCC malignancy, with an emphasis on imaging features and the role of the radiologist.

MR Angiography Series: Fundamentals of Non-Contrast-enhanced MR Angiography.

Unlike CT angiography, which requires the use of contrast medium, MR angiography (MRA) can be performed without the use of contrast agents. This subfield of MRA is referred to as non-contrast-enhanced MRA (NC-MRA). While NC-MRA can be performed in many patients, it is especially useful in the imaging of pediatric and pregnant patients, as well as in patients with renal impairment. NC-MRA can also provide unique functional and hemodynamic information that is not obtainable with CT angiography or contrast-enhanced MRA. This module gives an overview of the predominant NC-MRA techniques that are currently available on modern clinical MRI systems, while also discussing some new and emerging topics in the field. This module is the second in a series created on behalf of the Society for Magnetic Resonance Angiography (SMRA), a group of researchers and clinicians who are passionate about the benefits of MRA but understand its challenges. The full digital presentation is available online. ©RSNA, 2021.

Diffuse Peripheral Zone T2 Hypointensity: When to Worry About Prostate Cancer.

OBJECTIVE: Evaluate the accuracy of an obscured surgical capsule (OSC) for detecting diffuse prostate cancer (PCa) in the setting of diffusely T2 hypointense peripheral zones (PZs) on prostate magnetic resonance imaging. METHODS: Axial T2-weighted sequences of prostate magnetic resonance imaging performed on July 1, 2015, to August 1, 2017, were blindly assessed for diffusely T2 hypointense PZs, OSC, and focal diffusion abnormalities by 2 radiologists. Diffuse PCa was defined by the presence of bilateral PCa on at least 4 contiguous biopsy cores involving 2/3 levels. Interobserver agreement and multivariate analysis were performed. RESULTS: Seven (10%) of 70 patients had diffuse PCa. There was weak interreader agreement for OSC (κ coefficient = 0.58). Obscured surgical capsule was 57% sensitive and 89% specific for the presence of diffuse PCa and was associated with it (odds ratio, 17.6; P = 0.0008). Multivariate logistic regression demonstrated that OSC was the only significant predictor for the presence of diffuse PCa. CONCLUSION: Obscured surgical capsule is a strong independent predictor for diffuse PCa in T2 hypointense PZs.