Cooperative AI training for cardiothoracic segmentation in computed tomography: An iterative multi-center annotation approach.

PURPOSE: Radiological reporting is transitioning to quantitative analysis, requiring large-scale multi-center validation of biomarkers. A major prerequisite and bottleneck for this task is the voxelwise annotation of image data, which is time-consuming for large cohorts. In this study, we propose an iterative training workflow to support and facilitate such segmentation tasks, specifically for high-resolution thoracic CT data. METHODS: Our study included 132 thoracic CT scans from clinical practice, annotated by 13 radiologists. In three iterative training experiments, we aimed to improve and accelerate segmentation of the heart and mediastinum. Each experiment started with manual segmentation of 5-25 CT scans, which served as training data for a nnU-Net. Further iterations incorporated AI pre-segmentation and human correction to improve accuracy, accelerate the annotation process, and reduce human involvement over time. RESULTS: Results showed consistent improvement in AI model quality with each iteration. Resampled datasets improved the Dice similarity coefficients for both the heart (DCS 0.91 [0.88; 0.92]) and the mediastinum (DCS 0.95 [0.94; 0.95]). Our AI models reduced human interaction time by 50 % for heart and 70 % for mediastinum segmentation in the most potent iteration. A model trained on only five datasets achieved satisfactory results (DCS > 0.90). CONCLUSIONS: The iterative training workflow provides an efficient method for training AI-based segmentation models in multi-center studies, improving accuracy over time and simultaneously reducing human intervention. Future work will explore the use of fewer initial datasets and additional pre-processing methods to enhance model quality.

Pericardial Effusion Predicts Clinical Outcomes in Patients with COVID-19: A Nationwide Multicenter Study.

RATIONALE AND OBJECTIVES: The prognostic role of pericardial effusion (PE) in Covid 19 is unclear. The aim of the present study was to estimate the prognostic role of PE in patients with Covid 19 in a large multicentre setting. MATERIALS AND METHODS: This retrospective study is a part of the German multicenter project RACOON (Radiological Cooperative Network of the Covid 19 pandemic). The acquired sample comprises 1197 patients, 363 (30.3%) women and 834 (69.7%) men. In every case, chest computed tomography was analyzed for PE. Data about 30-day mortality, need for mechanical ventilation and need for intensive care unit (ICU) admission were collected. Data were evaluated by means of descriptive statistics. Group differences were calculated with Mann-Whitney test and Fisher exact test. Uni-and multivariable regression analyses were performed. RESULTS: Overall, 46.4% of the patients were admitted to ICU, mechanical lung ventilation was performed in 26.6% and 30-day mortality was 24%. PE was identified in 159 patients (13.3%). The presence of PE was associated with 30-day mortality: HR= 1.54, CI 95% (1.05; 2.23), p = 0.02 (univariable analysis), and HR= 1.60, CI 95% (1.03; 2.48), p = 0.03 (multivariable analysis). Furthermore, density of PE was associated with the need for intubation (OR=1.02, CI 95% (1.003; 1.05), p = 0.03) and the need for ICU admission (OR=1.03, CI 95% (1.005; 1.05), p = 0.01) in univariable regression analysis. The presence of PE was associated with 30-day mortality in male patients, HR= 1.56, CI 95%(1.01-2.43), p = 0.04 (multivariable analysis). In female patients, none of PE values predicted clinical outcomes. CONCLUSION: The prevalence of PE in Covid 19 is 13.3%. PE is an independent predictor of 30-day mortality in male patients with Covid 19. In female patients, PE plays no predictive role.

Potential of spiral breast computed tomography to increase patient comfort compared to DM.

PURPOSE: To intra-individually compare patient comfort of spiral breast computed tomography (SBCT) versus digital mammography (DM). METHOD: This prospective IRB approved study included 79 patients undergoing both SBCT and DM for the assessment of BI-RADS 4 - 6 lesions. Following SBCT and DM patients answered a standardized questionnaire regarding "Overall patient comfort" and "Pain" on a 5-point Likert Scale. On the same Likert Scale, experienced radiologic technicians rated the workflow of the SBCT regarding patients' "Mobility", ease of patient "Positioning", patients' adherence to the examination ("Compliance") and expected image quality. Visibility of fibroglandular tissue in SBCT was independently rated by two breast radiologists on a 10-point Likert Scale. Subgroups stratified by menopausal status and body mass index (BMI) were analyzed. RESULTS: Patients reported significantly lower pain during SBCT (4.73 ± 0.57) compared to DM (4.09 ± 0.90; P < 0.01). This effect was independent from BMI. However, pain reduction by SBCT was most pronounced in premenopausal (SBCT vs. DM: 4.79 ± 0.50 vs. 3.89 ± 0.99) compared to postmenopausal patients (4.71 ± 0.77 vs. 4.20 ± 0.89). Overall patient comfort in premenopausal patients tended to be higher in SBCT compared to DM (P = 0.08). Radiologic technicians rated the SBCT procedure generally as positive (average: 4.62 ± 0.56). Coverage of fibroglandular tissue in SBCT was generally high (9.82 ± 0.43) and interrater agreement was good (κ = 0.77). CONCLUSIONS: Patients experience less pain during spiral breast computed tomography compared to DM, especially in premenopausal women. Imaging is feasible at a high level of anatomical breast coverage and without problems with the clinical workflow.

Fumarate hydratase (FH) deficiency in uterine leiomyomas: recognition by histological features versus blind immunoscreening.

Hereditary leiomyomatosis and renal cell carcinoma (HLRCC) syndrome is a rare autosomal dominant disease caused by germline mutations in the fumarate hydratase (FH) gene. Affected individuals develop cutaneous and uterine leiomyomas and aggressive RCC. To date, only few publications described the frequency and morphology of FH-deficient uterine leiomyomas. We reviewed 22 cases collected over 8 years from routine and consultation files based on distinctive histological features. In addition, we screened 580 consecutive uterine leiomyomas from 484 patients, 23 extra-uterine and 8 uterine leiomyosarcomas, and 6 leiomyomas with bizarre nuclei for FH loss using immunohistochemistry (IHC) on tissue microarrays (TMAs). All 22 FH-deficient cases were suspected on H&E sections and confirmed by FH IHC. Patients' ages ranged from 25 to 70 years (median 36). Seventeen patients had multiple nodules (2-14) measuring up to 11.8 cm. None of the patients had stigmata or family history of the HLRCC syndrome. Histologically, all FH-deficient tumors showed consistent and reproducible features as reported previously. FH loss was detected in 2/534 evaluable leiomyomas (0.4%), but in none of leiomyosarcomas. Two of six leiomyomas with bizarre nuclei were FH-deficient. FH-deficient uterine leiomyomas are rare in routine material (= 0.4%). They can be reliably identified or suspected by consistent morphological features. Our data showed predictive morphology to be superior to blind IHC screening for detecting them. The relationship of FH-deficient uterine smooth muscle tumors to the HLRCC syndrome needs further clarification.