The importance of educational tools and a new software solution for visualizing and quantifying report correction in radiology training.

A novel software, DiffTool, was developed in-house to keep track of changes made by board-certified radiologists to preliminary reports created by residents and evaluate its impact on radiological hands-on training. Before (t0) and after (t2-4) the deployment of the software, 18 residents (median age: 29 years; 33% female) completed a standardized questionnaire on professional training. At t2-4 the participants were also requested to respond to three additional questions to evaluate the software. Responses were recorded via a six-point Likert scale ranging from 1 ("strongly agree") to 6 ("strongly disagree"). Prior to the release of the software, 39% (7/18) of the residents strongly agreed with the statement that they manually tracked changes made by board-certified radiologists to each of their radiological reports while 61% were less inclined to agree with that statement. At t2-4, 61% (11/18) stated that they used DiffTool to track differences. Furthermore, we observed an increase from 33% (6/18) to 44% (8/18) of residents who agreed to the statement "I profit from every corrected report". The DiffTool was well accepted among residents with a regular user base of 72% (13/18), while 78% (14/18) considered it a relevant improvement to their training. The results of this study demonstrate the importance of providing a time-efficient way to analyze changes made to preliminary reports as an additive for professional training.

A deep-learning algorithm to classify skin lesions from mpox virus infection.

Undetected infection and delayed isolation of infected individuals are key factors driving the monkeypox virus (now termed mpox virus or MPXV) outbreak. To enable earlier detection of MPXV infection, we developed an image-based deep convolutional neural network (named MPXV-CNN) for the identification of the characteristic skin lesions caused by MPXV. We assembled a dataset of 139,198 skin lesion images, split into training/validation and testing cohorts, comprising non-MPXV images (n = 138,522) from eight dermatological repositories and MPXV images (n = 676) from the scientific literature, news articles, social media and a prospective cohort of the Stanford University Medical Center (n = 63 images from 12 patients, all male). In the validation and testing cohorts, the sensitivity of the MPXV-CNN was 0.83 and 0.91, the specificity was 0.965 and 0.898 and the area under the curve was 0.967 and 0.966, respectively. In the prospective cohort, the sensitivity was 0.89. The classification performance of the MPXV-CNN was robust across various skin tones and body regions. To facilitate the usage of the algorithm, we developed a web-based app by which the MPXV-CNN can be accessed for patient guidance. The capability of the MPXV-CNN for identifying MPXV lesions has the potential to aid in MPXV outbreak mitigation.

Diagnostic accuracy of coronary computed tomography angiography-derived fractional flow reserve (CT-FFR) in patients before liver transplantation using CT-FFR machine learning algorithm.

OBJECTIVES: Liver transplantation (LT) is associated with high stress on the cardiovascular system. Ruling out coronary artery disease (CAD) is an important part of evaluation for LT. The aim of our study was to assess whether CT-derived fractional flow reserve (CT-FFR) allows for differentiation of hemodynamically significant and non-significant coronary stenosis in patients evaluated for LT. METHODS: In total, 201 patients undergoing LT evaluation were included in the study. The patients received coronary computed tomography angiography (CCTA) to rule out CAD and invasive coronary angiography (ICA) to further evaluate coronary lesions found in CCTA if a significant (≥ 50 % on CCTA) stenosis was suspected. CT-FFR was computed from CCTA datasets using a machine learning-based algorithm and compared to ICA as a standard of reference. Coronary lesions with CT-FFR ≤ 0.80 were defined as hemodynamically significant. RESULTS: In 127 of 201 patients (63%), an obstructive CAD was ruled out by CCTA. In the remaining 74 patients (37%), at least one significant stenosis was suspected in CCTA. Compared to ICA, sensitivity, specificity, PPV, and NPV of the CT-FFR measurements were 71% (49-92%), 90% (82-98%), 67% (45-88%), and 91% (84-99%), respectively. The diagnostic accuracy was 85% (85-86%). In 69% of cases (52 of 75 lesions), additional analysis by CT-FFR correctly excluded the hemodynamic significance of the stenosis. CONCLUSIONS: Machine learning-based CT-FFR seems to be a very promising noninvasive approach for exclusion of hemodynamic significant coronary stenoses in patients undergoing evaluation for LT and could help to reduce the rate of invasive coronary angiography in this high-risk population. KEY POINTS: • Machine learning-based computed tomography-derived fractional flow reserve (CT-FFR) seems to be a very promising noninvasive approach for exclusion of hemodynamic significance of coronary stenoses in patients undergoing evaluation for liver transplantation and could help to reduce the rate of invasive coronary angiography in this high-risk population.

The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): an international, multicenter analysis.

OBJECTIVES: AI-based algorithms for medical image analysis showed comparable performance to human image readers. However, in practice, diagnoses are made using multiple imaging modalities alongside other data sources. We determined the importance of this multi-modal information and compared the diagnostic performance of routine breast cancer diagnosis to breast ultrasound interpretations by humans or AI-based algorithms. METHODS: Patients were recruited as part of a multicenter trial (NCT02638935). The trial enrolled 1288 women undergoing routine breast cancer diagnosis (multi-modal imaging, demographic, and clinical information). Three physicians specialized in ultrasound diagnosis performed a second read of all ultrasound images. We used data from 11 of 12 study sites to develop two machine learning (ML) algorithms using unimodal information (ultrasound features generated by the ultrasound experts) to classify breast masses which were validated on the remaining study site. The same ML algorithms were subsequently developed and validated on multi-modal information (clinical and demographic information plus ultrasound features). We assessed performance using area under the curve (AUC). RESULTS: Of 1288 breast masses, 368 (28.6%) were histopathologically malignant. In the external validation set (n = 373), the performance of the two unimodal ultrasound ML algorithms (AUC 0.83 and 0.82) was commensurate with performance of the human ultrasound experts (AUC 0.82 to 0.84; p for all comparisons > 0.05). The multi-modal ultrasound ML algorithms performed significantly better (AUC 0.90 and 0.89) but were statistically inferior to routine breast cancer diagnosis (AUC 0.95, p for all comparisons ≤ 0.05). CONCLUSIONS: The performance of humans and AI-based algorithms improves with multi-modal information. KEY POINTS: • The performance of humans and AI-based algorithms improves with multi-modal information. • Multimodal AI-based algorithms do not necessarily outperform expert humans. • Unimodal AI-based algorithms do not represent optimal performance to classify breast masses.

Contrast of Digital and Health Literacy Between IT and Health Care Specialists Highlights the Importance of Multidisciplinary Teams for Digital Health-A Pilot Study.

PURPOSE: Despite their promises, digital innovations have scarcely translated to technologies used in routine clinical practice, making the identification of barriers to successful implementation a research priority. Low levels of transdisciplinary skills represent such a barrier but so far, this has not been evaluated and compared between information technology (IT) and health care specialists. In this study, we evaluated the level of digital health literacy among IT and health care specialists. MATERIALS AND METHODS: An anonymous questionnaire was distributed to staff at a breast cancer unit and an IT department of two German universities in December 2020. The survey questionnaire consisted of the previously validated eHealth Literacy Assessment Toolkit and additional questions with respect to age, profession, and career stage. Mann-Whitney or Wilcoxon rank-sum tests and two-sample chi-square tests were used for the analysis. RESULTS: The survey was completed by 113 individuals: 70 (61.9%) IT specialists and 43 (38.1%) health care specialists. Health care specialists scored significantly higher on the health-related scales and IT specialists scored significantly higher on the digitally related scales. No single participant identified themselves to have the highest level of literacy on all survey questions (n = 0 of 113; 0%). Only one person (n = 1 of 113; 0.9%) consistently reported a high or the highest level of literacy. CONCLUSION: Although IT and health care specialists showed great literacy in their respective disciplines, only few individuals combined both digital and health care literacy. Multidisciplinary teams and transdisciplinary curricula are crucial to bridge skill gaps between disciplines and to drive the implementation of digital health initiatives.

The role of perfusion effects in monitoring of chemoradiotherapy of rectal carcinoma using diffusion-weighted imaging.

PURPOSE: The aim of this study was to characterize and understand the therapy-induced changes in diffusion parameters in rectal carcinoma under chemoradiotherapy (CRT). The current literature shows conflicting results in this regard. We applied the intravoxel incoherent motion model, which allows for the differentiation between diffusion (D) and perfusion (f) effects, to further elucidate potential underlying causes for these divergent reports. MATERIALS AND METHODS: Eighteen patients with primary rectal carcinoma undergoing preoperative CRT were examined before, during, and after neoadjuvant CRT using diffusion-weighted imaging. Using the intravoxel incoherent motion approach, f and D were extracted and compared with postoperative tumor downstaging and volume. RESULTS: Initial diffusion-derived parameters were within a narrow range (D1 = 0.94 ± 0.12 × 10(-3) mm(2)/s). At follow-up, D rose significantly (D2 = 1.18 ± 0.13 × 10(-3) mm(2)/s; P < 0.0001) and continued to increase significantly after CRT (D3 = 1.24 ± 0.14 × 10(-3) mm(2)/s; P < 0.0001). The perfusion fraction f did not change significantly (f1 = 9.4 ± 2.0%, f2 = 9.4 ± 1.7%, f3 = 9.5 ± 2.7%). Mean volume (V) decreased significantly (V1 = 16,992 ± 13,083 mm(3); V2 = 12,793 ± 8317 mm(3), V3 = 9718 ± 6154 mm(3)). T-downstaging (10:18 patients) showed no significant correlation with diffusion-derived parameters. CONCLUSIONS: Conflicting results in the literature considering apparent diffusion coefficient (ADC) changes in rectal carcinoma under CRT for patients showing T-downstaging are unlikely to be due to perfusion effects. Our data support the view that under effective therapy, an increase in D/ADC can be observed.