Current problems in diagnostic radiology最新文献

Purpose: To compare RECIST 1.1, modified RECIST (mRECIST) and PERCIST for assessment of Peptide Receptor Radionuclide Therapy (PRRT) treatment response in metastatic neuroendocrine tumors.

Materials: In this IRB-approved, HIPAA compliant retrospective study, patients treated with PRRT between July 2019 and Dec 2022 were identified. Inclusion criteria were presence of at least one pre-and one post-treatment imaging (CT, MRI, Ga 68 or Cu64 DOTATATE PET/CT) within one year of the start and end of PRRT respectively. The imaging was reviewed independently by two radiologists using RECIST 1.1, modified RECIST (mRECIST) and PERCIST criteria. Response of first post treatment scan and presence of disease progression during follow-up were recorded along with the date of best response and disease progression. Statistical analysis was performed to determine inter-reader agreement and agreement between the various response criteria using kappa statistics.

Results: Best response by RECIST 1.1 was recorded in 26 patients (PR-7, SD- 13, PD- 6), by mRECIST in 22 patients (PR-7, SD- 10, PD- 5), by PERCIST in 14 patients (PR-4, SD- 3, PD- 7). Inter-reader agreement was highest for PERCIST (weighted kappa 0.921, standard error 0.078 95% CI 0.769 to 1.000) followed by RECIST 1.1 (weighted kappa 0.897, standard error 0.071 95% CI 0.758 to 1.000) and mRECIST (weighted kappa 0.883, standard error 0.079 95% CI 0.727 to 1.000).

Objectives: Acute appendicitis is a common surgical condition which is usually diagnosed on CT in adult patients, though MRI is frequently used as a first-line diagnostic test in pregnant patients due to its lack of ionizing radiation and superior ability to visualize the appendix compared to ultrasound. Interpretation of abdominal MRI exams in pregnant patients with suspected appendicitis is an important skill in clinical practice, but one that is difficult to become proficient at due to its relative infrequence, even in a high-volume practice.

Methods: We created a simulation-based platform built on an online radiology viewing platform (Pacsbin) for training residents and abdominal imaging fellows to interpret pregnant appendicitis MRI exams, which we made publicly available for use by trainees at any institution (forms.office.com/r/FYyq06rw0v). This platform was used to train our 2024-2025 abdominal imaging fellows (N=8), and we collected pre- and post-intervention survey data which included level of confidence (Likert scale,1-5) in approaching these studies.

Results: We discuss and illustrate the content of our case set, including various teaching points we emphasize throughout the exercise. Among our eight body imaging fellows, the level of confidence in approaching pregnant appendicitis MRI studies after the intervention increased from 2.4 ± 0.7 (range 1-3) to 3.6 ± 0.5 (range 3-4; p = 0.01).

Conclusion: Simulation-based training sets such as this have the potential to supplement traditional approaches in radiology education across a broad range of radiology subspecialities and imaging modalities.

Demand for diagnostic imaging services in the United States continues to rise, posing challenges for health systems to maintain efficient scheduling processes. This study documents a quality improvement initiative undertaken at our institution in response to a surge in demand for outpatient imaging during 2022, which led to a notable scheduling backlog. By October 2022, the average scheduling interval, defined as the time from order placement to scheduled examination date, had increased from 2 weeks to 6 weeks. The objective of this initiative was to reduce the scheduling interval from 6 weeks to 10 days by January 2023. Utilizing feedback from schedulers, technologists, and radiologists, several interventions were implemented. The impact of each intervention was monitored with a control chart with weekly appointment delays tracked as a balancing measure. Initially, examination slots were double-booked for a period of 4 weeks to address the backlog, resulting in a reduction of the scheduling interval to 12 days (72 % decrease). Subsequently, examination slot duration was shorted from 20 to 15 min and contrast protocols were standardized across all sites. These adjustments further decreased the interval to 7 days (41 % reduction) over the following 9 weeks. While staffing shift adjustments had no impact on the scheduling interval, the introduction of an extra CT scanner reduced the interval to 3 days (57 % decrease). These interventions resulted in a notable increase in examination volume, from a weekly average of 722 to 860 examinations (19 % increase), approximately an additional $1,612,000 in annual revenue. Importantly, there was no change in the average appointment delay, which remained at 15 min over the study period. These improvements were sustained across the subsequent months and received favorable subjective feedback from staff. While the initiative successfully addressed scheduling inefficiencies across our health system, the rise in examination volumes has led to an increased turnaround time for completed reports. Future directions for enhancing the outpatient scheduling process include expanding online scheduling platforms, implementing systems to assess imaging appropriateness, and developing urgency stratification to prioritize time-sensitive examinations.

Purpose: To determine differentiating CT imaging features of primary ovarian cancers from ovarian metastases of gastrointestinal origin.

Methods: Retrospective study of 50 patients with new ovarian lesions on CT, half were primary ovarian cancers and half gastrointestinal metastases. Two blinded independent readers described tumor characteristics on CT (size, laterality, margin, etc.) and ancillary features (ascites, peritoneal seeding, lymphadenopathy, etc.). Patient age, sex, cancer history, and tumor marker levels for CA-125 and CEA were collected. Wilcoxon test and Pearson's chi-squared test were used for statistical analysis.

Results: 50 patients with mean age of 62.1 years were included. Ovarian metastases were more likely to be cystic/mainly cystic (p=0.013), have smooth margins (p=0.011), and have no/mild enhancement (p<0.001). Primary ovarian lesions were associated with moderate to large volume of ascites (p=0.047) and more commonly seen with lymphadenopathy (p=0.008). Laterality was not significantly different between the two groups. CA-125 level was more commonly elevated in primary ovarian lesions (87% vs 50%, p=0.018), and with much higher values (1076.5 vs 155.1, p=0.013). CEA level was more commonly elevated in metastatic ovarian lesions (83.3% vs 15.4%, p<0.001), and with higher values (72.4 vs 2.1, p<0.001).

Conclusion: Ovarian metastases were more frequently smooth-margined and cystic with little enhancement. Primary ovarian lesions were more commonly associated with lymphadenopathy and larger volume of ascites. Tumor markers CEA and CA-125 were more frequently elevated in metastatic and primary lesions, respectively. Cancer history was the only variable that increased the odds of metastasis and therefore it is important to always correlate with history of cancer.

The Healthcare Quality Improvement Act (HCQIA) of 1986 is a pivotal federal mandate designed to enhance medical care quality through effective professional peer review. Importantly, it offers legal immunity to reviewers under specified conditions and mandates the reporting of adverse actions to the National Practitioner Data Bank (NPDB). This article explores the implementation of peer review processes in hospitals and the potentially severe ramifications of failure to report, using the scenario of a diagnostic radiologist performing high-end vascular interventional procedures, whose performance came under scrutiny, highlighting the intersection of federal and state laws, accreditation standards, hospital policies, and physician professionalism standards and reporting duties.

Problem: An active implant is a medical device that includes a power source and provides diverse therapies to patients. Active implants are a source of risk to patients undergoing magnetic resonance (MR) imaging. Institutions develop workflows to ensure devices are assessed for MR safety and scanned using acceptable acquisition parameters. Low data integrity can result in incorrect assessments and increased patient risk.

Approach and intervention: The rate of data integrity issues and their causes were not known at our institution. Between March 2020 and April 2023, a survey was distributed for each MR implant case recording the information used to assess MR safety of the implanted device. The leading cause of data integrity loss was incorrect vendor manual for the implant. A list of links to implant vendor manual repositories was added to our workflow in December of 2021 with instructions to always find the most recent version of the device manual.

Outcomes: 749 patient records were reviewed by MR safety experts. Data integrity issues, i.e., a lack of complete and/or correct patient and implant information, occurred in 16% of cases and could impact MR safety (assessment or scanning) in 47% of those cases. A missing or incorrect manual was the leading cause of data integrity loss (78%). The incorrect manual problem initially worsened between October 2021 and March 2022 due to increased surveillance leading to more incorrect manuals being detected. The rate improved by August 2022 and remained high through March of 2023. Reducing the difficulty of finding implant vendor manuals by providing a list of links to vendor manual repositories along with guidance to pull the most recent manual version is an effective strategy to improve data integrity in MR safety workflows.

Rationale and objectives: Radiology residents often receive limited feedback on preliminary reports issued during independent call. This study aimed to determine if Large Language Models (LLMs) can supplement traditional feedback by identifying missed diagnoses in radiology residents' preliminary reports.

Materials & methods: A randomly selected subset of 500 (250 train/250 validation) paired preliminary and final reports between 12/17/2022 and 5/22/2023 were extracted and de-identified from our institutional database. The prompts and report text were input into the GPT-4 language model via the GPT-4 API (gpt-4-0314 model version). Iterative prompt tuning was used on a subset of the training/validation sets to direct the model to identify important findings in the final report that were absent in preliminary reports. For testing, a subset of 10 reports with confirmed diagnostic errors were randomly selected. Fourteen residents with on-call experience assessed the LLM-generated discrepancies and completed a survey on their experience using a 5-point Likert scale.

Results: The model identified 24 unique missed diagnoses across 10 test reports with i% model prediction accuracy as rated by 14 residents. Five additional diagnoses were identified by users, resulting in a model sensitivity of 79.2 %. Post-evaluation surveys showed a mean satisfaction rating of 3.50 and perceived accuracy rating of 3.64 out of 5 for LLM-generated feedback. Most respondents (71.4 %) favored a combination of LLM-generated and traditional feedback.

Conclusion: This pilot study on the use of LLM-generated feedback for radiology resident preliminary reports demonstrated notable accuracy in identifying missed diagnoses and was positively received, highlighting LLMs' potential role in supplementing conventional feedback methods.

Objective: In January 2016, we created an Instagram page for radiology education. Numerous publications in different fields have reported that Instagram "reels," introduced in 2020 as a short-form video feature, are more popular than image posts. These findings and our familiarity with Instagram prompted us to analyze our own data to better understand how image posts compared with reels when used in the context of radiology education.

Materials and methods: For each post category, metric values were extracted from the Instagram platform and analyzed as continuous variables, reported as medians with interquartile ranges (IQR). Metrics were compared between image categories using the Kruskal-Wallis test, with resulting p-values adjusted for multiple comparisons using the Bonferroni correction. Corrected p-values of less than 0.05 were considered statistically significant.

Results: We included 128 images and 96 reels in the analysis. Images generally reached a larger audience, with a median of 18,745 [IQR: 13,478-27,243] impressions vs. 11,972 [IQR: 9,310.0-13,844.5] for reels (p < 0.01). Images also tended to be shared more frequently (median 19 vs. 20, p < 0.01), liked more often (median 480 vs. 296, p < 0.01), and saved more by users (median 138 vs. 84, p < 0.01) than reels, respectively. Both images and reels received a similar number of comments, with a median of 3 comments for both (p > 0.99). We also explored the performance differences of image post subcategories. Within images, our "You Make the Call!" (YMTC) questions (n = 23) displayed higher performance metrics across the board than the three other types of image posts combined (n = 105). When compared, the median number of impressions for YMTC images was 36,735 [IQR: 31,343-40,742] vs. 15,992 [IQR:12,774-21,873] for other types of images (p < 0.01). YMTC images were shared more often (median 25 vs. 17, p < 0.01), received more likes (median 809 vs. 445, p < 0.01) and saves (median 206 vs. 119, p < 0.01) than non-YMTC images, respectively. User engagement showed slightly different trends with YMTC reels being the most liked, while quiz reels receiving the most comments and talking clips being the most saved.

Conclusion: Our findings on the use of Instagram in radiology education suggest that static images perform much better than reels. Consequently, we recommend to radiology educators seeking to establish an Instagram presence that using static image posts is an appropriate approach for reaching a radiology audience, particularly with image posts that engage an audience with participatory opportunities such as answering quiz-like questions aimed at making a diagnosis.

Novel strategies are needed to improve low rates of lung cancer screening (LCS) in the US. Seeking to determine hospitalists' perspectives on leveraging hospitalizations to identify patients eligible for LCS, we performed qualitative interviews with eight hospitalists from two hospitals within a large integrated healthcare system. The interviews used semi-structured questions to assess (1) knowledge and practice of general screening and LCS guidelines from the United States Preventive Services Task Force (USPSTF), (2) identification of smoking history, and (3) hospitalists' views on how data obtained during hospitalization may be utilized to improve general screening and LCS post hospitalization. We ultimately reached the conclusion that hospitalists would support a dedicated program to identify hospitalized patients eligible for LCS and facilitate testing after discharge. Efforts to identify patients and arrange subsequent screening should be performed by team members outside the inpatient team.