This retrospective study evaluated a commercial deep learning (DL) software for chest radiographs and explored its performance in different scenarios. A total of 477 patients (284 male, 193 female, mean age 61.4 (44.7–78.1) years) were included. For the reference standard, two radiologists performed independent readings on seven diseases, thus reporting 226 findings in 167 patients. An autonomous DL reading was performed separately and evaluated against the gold standard regarding accuracy, sensitivity and specificity using ROC analysis. The overall average AUC was 0.84 (95%-CI 0.76–0.92) with an optimized DL sensitivity of 85% and specificity of 75.4%. The best results were seen in pleural effusion with an AUC of 0.92 (0.885–0.955) and sensitivity and specificity of each 86.4%. The data also showed a significant influence of sex, age, and comorbidity on the level of agreement between gold standard and DL reading. About 40% of cases could be ruled out correctly when screening for only one specific disease with a sensitivity above 95% in the exploratory analysis. For the combined reading of all abnormalities at once, only marginal workload reduction could be achieved due to insufficient specificity. DL applications like this one bear the prospect of autonomous comprehensive reporting on chest radiographs but for now require human supervision. Radiologists need to consider possible bias in certain patient groups, e.g., elderly and women. By adjusting their threshold values, commercial DL applications could already be deployed for a variety of tasks, e.g., ruling out certain conditions in screening scenarios and offering high potential for workload reduction.

The purpose of this study was to explore the effects of the integration of machine learning into daily radiological diagnostics, using the example of the machine learning software mdbrain^® (Mediaire GmbH, Germany) in the diagnostic MRI workflow of patients with multiple sclerosis at the University Medicine Greifswald. The data were assessed through expert interviews, a comparison of analysis times with and without the machine learning software, as well as a process analysis of MRI workflows. Our results indicate a reduction in the screen-reading workload, improved decision-making regarding contrast administration, an optimized workflow, reduced examination times, and facilitated report communication with colleagues and patients. Our results call for a broader and quantitative analysis.

An aneurysmal fibrous histiocytoma is a rare cutaneous soft-tissue tumour which accounts for approximately 0.06% of all dermatopathologies. Metastasis is exceedingly uncommon, to the point that there have only been eight reported cases in the scientific literature. We present the case of a 25-year-old male with a primary aneurysmal fibrous histiocytoma located in the nuchal region which exhibited rapid growth and abrupt ulceration over a short time span and showed signs of locoregional aggressive infiltration. A subsequent histopathological analysis confirmed the presence of diffuse solid and cystic pulmonary metastases. Further genetic sequencing verified LAMTOR1-PRKCD fusion. This case report seeks to review the existing literature on aneurysmal fibrous histiocytoma, discuss the challenges of differential diagnosis and propose standardised diagnostic criteria.

Thermal ablation offers a minimally invasive alternative in the treatment of hepatic tumours. Several types of ablation are utilised with different methods and indications. However, to this day, ablation size remains limited due to the formation of a central non-conductive boundary layer. In thermal ablation, this boundary layer is formed by carbonisation. Our goal was to prevent or delay carbonisation, and subsequently increase ablation size. We used bovine liver to compare ablation diameter and volume, created by a stand-alone laser applicator, with those created when utilising a spacer between laser applicator and hepatic tissue. Two spacer variants were developed: one with a closed circulation of cooling fluid and one with an open circulation into hepatic tissue. We found that the presence of a spacer significantly increased ablation volume up to 75.3 cm³, an increase of a factor of 3.19 (closed spacer) and 3.02 (open spacer) when compared to the stand-alone applicator. Statistical significance between spacer variants was also present, with the closed spacer producing a significantly larger ablation volume (p < 0.001, M_Diff = 3.053, 95% CI[1.612, 4.493]) and diameter (p < 0.001, M_Diff = 4.467, 95% CI[2.648, 6.285]) than the open spacer. We conclude that the presence of a spacer has the potential to increase ablation size.

Wir sind das Forum Junge Radiologie (FJR) in der Deutschen Röntgengesellschaft (DRG). Mit mehr als 3800 Mitgliedern sind wir die größte Mitgliedergruppe innerhalb der DRG. Auf den Seiten dieser neuen Rubrik erwarten die Leserinnen und Leser spannende und aktuelle Themen rund um die radiologische Weiterbildung. Article published online: 24 January 2025 © 2025. Thieme. All rights reserved. Georg Thieme Verlag KG Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany