The Current State of Nuclear Medicine and Nuclear Radiology: Workforce Trends, Training Pathways, and Training Program Websites Publication date: Available online 21 November 2019 Source: Academic Radiology Author(s): Jack H. Ruddell, Adam E.M. Eltorai, Oliver Y. Tang, Johanna A. Suskin, Elizabeth H. Dibble, M. Elizabeth Oates, Don C. Yoo Background Nuclear medicine (NM) is a multidisciplinary field. Its overlap with nuclear radiology (NR) creates unique training considerations, opportunities, and challenges. Various factors impact the workforce, training needs, and training pathways. This state of flux may be perplexing to prospective NM/NR trainees. Purpose To evaluate the state of NM/NR training by assessing the (1) workforce trends and job prospects for NM/NR trainees, (2) NM and NR training pathways, and (3) applicant-accessible online presence of training programs. Methods Workforce trends were analyzed using data collected from the 2017 American College of Radiology Commission on Human Resources Workforce Survey. Information regarding the training pathways leading to board certification(s) for NM and NR physicians were obtained through the American Board of Nuclear Medicine, the American Board of Radiology (ABR), and the Society of Nuclear Medicine and Medical Imaging. Each Accreditation Council for Graduate Medical Education-accredited NM residency or NR fellowship training program's website was reviewed for 20 content items to assess its comprehensiveness for those seeking information regarding eligibility, applications, training curriculum, and program characteristics. Results Number of hires for NM/NR physicians has exceeded the projected number of hires from 2014 to 2017. In the last decade, there has been a greater than 25% decrease in the combined number of traditional NM residencies and NR fellowships (79–58 programs) and a greater than 50% decrease in the combined number of NM and NR trainees (173–82 trainees). In 2017, the ABR redesigned its 16-month pathway leading to specialty certification in diagnostic radiology and subspecialty certification in NR. As of March 24, 2019, there are 36 diagnostic radiology or IR residency programs with 64 trainees participating in this redesigned NR pathway. Of the 93.1% (54/58) of traditional Accreditation Council for Graduate Medical Education-accredited NM and NR training programs having websites in the 2017–2018 academic year, the mean number of online criteria met per program was 7.74 ± 3.2 of 20 (38.7%). Conclusion Recruitment into the traditional NM/NR training pathways has been steadily declining, but there has been a renewed interest with the redesigned ABR 16-month pathway. There is a paucity of online information available to prospective NM/NR applicants. In this rapidly evolving and unique field, it is important to streamline NM/NR training and bolster the information accessible to potential NM/NR applicants as they weigh career options.

Intratumor Heterogeneity Assessed by 18F-FDG PET/CT Predicts Treatment Response and Survival Outcomes in Patients with Hodgkin Lymphoma Publication date: Available online 21 November 2019 Source: Academic Radiology Author(s): Kun-Han Lue, Yi-Feng Wu, Shu-Hsin Liu, Tsung-Cheng Hsieh, Keh-Shih Chuang, Hsin-Hon Lin, Yu-Hung Chen Rationale and Objectives Radiomic analysis of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) images enables the extraction of quantitative information of intratumour heterogeneity. This study investigated whether the baseline 18F-FDG PET/CT radiomics can predict treatment response and survival outcomes in patients with Hodgkin lymphoma (HL). Materials and Methods Thirty-five patients diagnosed with HL who underwent 18F-FDG PET/CT scans before and during chemotherapy were retrospectively enrolled in this investigation. For each patient, we extracted 709 radiomic features from pretreatment PET/CT images. Clinical variables (age, gender, B symptoms, bulky tumor, and disease stage) and radiomic signatures (intensity, texture, and wavelet) were analyzed according to response to therapy, progression-free survival (PFS), and overall survival (OS). Receiver operating characteristic curve, logistic regression, and Cox proportional hazards model were used to examine potential predictive and prognostic factors. Results High-intensity run emphasis (HIR) of PET and run-length nonuniformity (RLNU) of CT extracted from gray-level run-length matrix (GLRM) in high-frequency wavelets were independent predictive factors for the treatment response (odds ratio [OR] = 36.4, p = 0.014; OR = 30.4, p = 0.020). Intensity nonuniformity (INU) of PET and wavelet short run emphasis (SRE) of CT from GLRM and Ann Arbor stage were independently related to PFS (hazard ratio [HR] = 9.29, p = 0.023; HR = 18.40, p = 0.012; HR = 7.46, p = 0.049). Zone-size nonuniformity (ZSNU) of PET from gray-level size zone matrix (GLSZM) was independently associated with OS (HR = 41.02, p = 0.001). Based on these factors, a prognostic stratification model was devised for the risk stratification of patients. The proposed model allowed the identification of four risk groups for PFS and OS (p < 0.001 and p < 0.001). Conclusion HIR_GLRMPET and RLNU_GLRMCT in high-frequency wavelets serve as independent predictive factors for treatment response. ZSNU_GLSZMPET, INU_GLRMPET, and wavelet SRE_GLRMCT serve as independent prognostic factors for survival outcomes. The present study proposes a prognostic stratification model that may be clinically beneficial in guiding risk-adapted treatment strategies for patients with HL.

ACGME Case Log Values Correlate with Performance on ABR Core Exam Publication date: Available online 21 November 2019 Source: Academic Radiology Author(s): Charles M Maxfield

Artificial Intelligence, Radiology, and Tuberculosis: A Review Publication date: Available online 20 November 2019 Source: Academic Radiology Author(s): Sagar Kulkarni, Saurabh Jha Tuberculosis is a leading cause of death from infectious disease worldwide, and is an epidemic in many developing nations. Countries where the disease is common also tend to have poor access to medical care, including diagnostic tests. Recent advancements in artificial intelligence may help to bridge this gap. In this article, we review the applications of artificial intelligence in the diagnosis of tuberculosis using chest radiography, covering simple computer-aided diagnosis systems to more advanced deep learning algorithms. In so doing, we will demonstrate an area where artificial intelligence could make a substantial contribution to global health through improved diagnosis in the future.

Artificial Intelligence in Radiology––The State of the Future Publication date: Available online 18 November 2019 Source: Academic Radiology Author(s): Saurabh Jha, Tessa Cook

The Economics of Automation Publication date: Available online 18 November 2019 Source: Academic Radiology Author(s): Saurabh Jha

Automation and Radiology—Part 1 Publication date: Available online 16 November 2019 Source: Academic Radiology Author(s): Saurabh Jha

Automation and Radiology—Part 2 Publication date: Available online 16 November 2019 Source: Academic Radiology Author(s): Saurabh Jha

Value of Triage by Artificial Intelligence Publication date: Available online 16 November 2019 Source: Academic Radiology Author(s): Saurabh Jha

The Effect of Visual Hindsight Bias on Radiologist Perception Publication date: Available online 15 November 2019 Source: Academic Radiology Author(s): Jacky Chen, Stephen Littlefair, Roger Bourne, Warren M. Reed Rationale and Objectives To measure the effect of visual hindsight bias on radiologists’ perception during chest radiograph pulmonary nodule detection. Materials and Methods This was a prospective multi-observer study to assess the effect of hindsight bias on radiologists’ perception. Sixteen radiologists were asked to interpret 15 postero-anterior chest images containing a solitary lung nodule each consisting of 25 incremental levels of blur. Participants were requested initially to detect the nodule by reducing the blur of the images (foresight). They were then asked to increase the blur until the identified nodule was undetectable (hindsight). Participants then repeated the experiment, after being informed of the potential effects of hindsight bias and asked to counteract these effects. Participants were divided into two groups (experienced and less experienced) and the nodules were given different conspicuity ratings to determine the effect of expertise and task difficulty. Eye tracking technology was also utilised to capture visual search. Results Wilcoxon analysis demonstrated significant differences between foresight and hindsight values of the radiologists (p = 0.02). However, after being informed of hindsight bias, these differences were no longer significant (p = 0.97). Friedman analysis also determined overall significance in the hindsight ratios between nodule conspicuities for both phases (phase 1: p = 0.02; phase 2: p = 0.02). There was no significance difference between the experienced and less experienced groups. Conclusion This study demonstrated that radiologists exhibit hindsight bias but appeared to be able to compensate for this phenomenon once its effects were considered. Also, visual hindsight bias appears to be affected by task difficulty with a greater effect occurring with less conspicuous nodules.