Impact of retraining a deep learning algorithm for improving guideline-compliant aortic diameter measurements on non-gated chest CT

PURPOSE/OBJECTIVE

Reliable detection of thoracic aortic dilatation (TAD) is mandatory in clinical routine. For ECG-gated CT angiography, automated deep learning (DL) algorithms are established for diameter measurements according to current guidelines. For non-ECG gated CT (contrast enhanced (CE) and non-CE), however, only a few reports are available. In these reports, classification as TAD is frequently unreliable with variable result quality depending on anatomic location with the aortic root presenting with the worst results. Therefore, this study aimed to explore the impact of re-training on a previously evaluated DL tool for aortic measurements in a cohort of non-ECG gated exams.

METHODS & MATERIALS

A cohort of 995 patients (68 ± 12 years) with CE (n = 392) and non-CE (n = 603) chest CT exams was selected which were classified as TAD by the initial DL tool. The re-trained version featured improved robustness of centerline fitting and cross-sectional plane placement. All cases were processed by the re-trained DL tool version. DL results were evaluated by a radiologist regarding plane placement and diameter measurements. Measurements were classified as correctly measured diameters at each location whereas false measurements consisted of over-/under-estimation of diameters.

RESULTS

We evaluated 8948 measurements in 995 exams. The re-trained version performed 8539/8948 (95.5%) of diameter measurements correctly. 3765/8948 (42.1%) of measurements were correct in both versions, initial and re-trained DL tool (best: distal arch 655/995 (66%), worst: Aortic sinus (AS) 221/995 (22%)). In contrast, 4456/8948 (49.8%) measurements were correctly measured only by the re-trained version, in particular at the aortic root (AS: 564/995 (57%), sinotubular junction: 697/995 (70%)). In addition, the re-trained version performed 318 (3.6%) measurements which were not available previously. A total of 228 (2.5%) cases showed false measurements because of tilted planes and 181 (2.0%) over-/under-segmentations with a focus at AS (n = 137 (14%) and n = 73 (7%), respectively).

CONCLUSION

Re-training of the DL tool improved diameter assessment, resulting in a total of 95.5% correct measurements. Our data suggests that the re-trained DL tool can be applied even in non-ECG-gated chest CT including both, CE and non-CE exams.

TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images

Purpose

To present a deep learning segmentation model that can automatically and robustly segment all major anatomic structures on body CT images.

Materials and Methods

In this retrospective study, 1204 CT examinations (from 2012, 2016, and 2020) were used to segment 104 anatomic structures (27 organs, 59 bones, 10 muscles, and eight vessels) relevant for use cases such as organ volumetry, disease characterization, and surgical or radiation therapy planning. The CT images were randomly sampled from routine clinical studies and thus represent a real-world dataset (different ages, abnormalities, scanners, body parts, sequences, and sites). The authors trained an nnU-Net segmentation algorithm on this dataset and calculated Dice similarity coefficients to evaluate the model's performance. The trained algorithm was applied to a second dataset of 4004 whole-body CT examinations to investigate age-dependent volume and attenuation changes.

Results

The proposed model showed a high Dice score (0.943) on the test set, which included a wide range of clinical data with major abnormalities. The model significantly outperformed another publicly available segmentation model on a separate dataset (Dice score, 0.932 vs 0.871; P < .001). The aging study demonstrated significant correlations between age and volume and mean attenuation for a variety of organ groups (eg, age and aortic volume [rs = 0.64; P < .001]; age and mean attenuation of the autochthonous dorsal musculature [rs = -0.74; P < .001]).

Conclusion

The developed model enables robust and accurate segmentation of 104 anatomic structures. The annotated dataset (https://doi.org/10.5281/zenodo.6802613) and toolkit (https://www.github.com/wasserth/TotalSegmentator) are publicly available.Keywords: CT, Segmentation, Neural Networks Supplemental material is available for this article. © RSNA, 2023See also commentary by Sebro and Mongan in this issue.

Pulmonary transit time of cardiovascular magnetic resonance perfusion scans for quantification of cardiopulmonary haemodynamics

AIMS

Pulmonary transit time (PTT) is the time blood takes to pass from the right ventricle to the left ventricle via pulmonary circulation. We aimed to quantify PTT in routine cardiovascular magnetic resonance imaging perfusion sequences. PTT may help in the diagnostic assessment and characterization of patients with unclear dyspnoea or heart failure (HF).

METHODS AND RESULTS

We evaluated routine stress perfusion cardiovascular magnetic resonance scans in 352 patients, including an assessment of PTT. Eighty-six of these patients also had simultaneous quantification of N-terminal pro-brain natriuretic peptide (NTproBNP). NT-proBNP is an established blood biomarker for quantifying ventricular filling pressure in patients with presumed HF. Manually assessed PTT demonstrated low inter-rater variability with a correlation between raters >0.98. PTT was obtained automatically and correctly in 266 patients using artificial intelligence. The median PTT of 182 patients with both left and right ventricular ejection fraction >50% amounted to 6.8 s (Pulmonary transit time: 5.9-7.9 s). PTT was significantly higher in patients with reduced left ventricular ejection fraction (<40%; P < 0.001) and right ventricular ejection fraction (<40%; P < 0.0001). The area under the receiver operating characteristics curve (AUC) of PTT for exclusion of HF (NT-proBNP <125 ng/L) was 0.73 (P < 0.001) with a specificity of 77% and sensitivity of 70%. The AUC of PTT for the inclusion of HF (NT-proBNP >600 ng/L) was 0.70 (P < 0.001) with a specificity of 78% and sensitivity of 61%.

CONCLUSION

PTT as an easily, even automatically obtainable and robust non-invasive biomarker of haemodynamics might help in the evaluation of patients with dyspnoea and HF.

Performance of a deep learning tool to detect missed aortic dilatation in a large chest CT cohort

Purpose

Thoracic aortic (TA) dilatation (TAD) is a risk factor for acute aortic syndrome and must therefore be reported in every CT report. However, the complex anatomy of the thoracic aorta impedes TAD detection. We investigated the performance of a deep learning (DL) prototype as a secondary reading tool built to measure TA diameters in a large-scale cohort.

Material and methods

Consecutive contrast-enhanced (CE) and non-CE chest CT exams with “normal” TA diameters according to their radiology reports were included. The DL-prototype (AIRad, Siemens Healthineers, Germany) measured the TA at nine locations according to AHA guidelines. Dilatation was defined as &gt;45 mm at aortic sinus, sinotubular junction (STJ), ascending aorta (AA) and proximal arch and &gt;40 mm from mid arch to abdominal aorta. A cardiovascular radiologist reviewed all cases with TAD according to AIRad. Multivariable logistic regression (MLR) was used to identify factors (demographics and scan parameters) associated with TAD classification by AIRad.

Results

18,243 CT scans (45.7% female) were successfully analyzed by AIRad. Mean age was 62.3 ± 15.9 years and 12,092 (66.3%) were CE scans. AIRad confirmed normal diameters in 17,239 exams (94.5%) and reported TAD in 1,004/18,243 exams (5.5%). Review confirmed TAD classification in 452/1,004 exams (45.0%, 2.5% total), 552 cases were false-positive but identification was easily possible using visual outputs by AIRad. MLR revealed that the following factors were significantly associated with correct TAD classification by AIRad: TAD reported at AA [odds ratio (OR): 1.12, p &lt; 0.001] and STJ (OR: 1.09, p = 0.002), TAD found at &gt;1 location (OR: 1.42, p = 0.008), in CE exams (OR: 2.1–3.1, p &lt; 0.05), men (OR: 2.4, p = 0.003) and patients presenting with higher BMI (OR: 1.05, p = 0.01). Overall, 17,691/18,243 (97.0%) exams were correctly classified.

Conclusions

AIRad correctly assessed the presence or absence of TAD in 17,691 exams (97%), including 452 cases with previously missed TAD independent from contrast protocol. These findings suggest its usefulness as a secondary reading tool by improving report quality and efficiency.

Quantifying the Effects of Structured Reporting on Report Turnaround Times and Proofreading Workload in Neuroradiology

RATIONALE AND OBJECTIVES

To assess the effects of a change from free text reporting to structured reporting on resident reports, the proofreading workload and report turnaround times in the neuroradiology daily routine.

MATERIALS AND METHODS

Our neuroradiology section introduced structured reporting templates in July 2019. Reports dictated by residents during dayshifts from January 2019 to March 2020 were retrospectively assessed using quantitative parameters from report comparison. Through automatic analysis of text-string differences between report states (i.e. draft, preliminary and final report), Jaccard similarities and edit distances of reports following read-out sessions as well as after report sign-off were calculated. Furthermore, turnaround times until preliminary and final report availability to clinicians were investigated. Parameters were visualized as trending line graphs and statistically compared between reporting standards.

RESULTS

Three thousand five hundred thirty-eight reports were included into analysis. Mean Jaccard similarity of resident drafts and staff-reviewed final reports increased from 0.53 ± 0.37 to 0.79 ± 0.22 after the introduction of structured reporting (p < .001). Both mean overall edits on draft reports by residents following read-out sessions (0.30 ± 0.45 vs. 0.09 ± 0.29; p < .001) and by staff radiologists during report sign-off (0.17 ± 0.28 vs. 0.12 ± 0.23, p < .001) decreased. With structured reporting, mean turnaround time until preliminary report availability to clinicians decreased by 20.7 minutes (246.9 ± 207.0 vs. 226.2 ± 224.9; p < .001). Similarly, final reports were available 35.0 minutes faster on average (558.05 ± 15.1 vs. 523.0 ± 497.3; p = .002).

CONCLUSION

Structured reporting is beneficial in the neuroradiology daily routine, as resident drafts require fewer edits in the report review process. This reduction in proofreading workload is likely responsible for lower report turnaround times.

Atri-U: assisted image analysis in routine cardiovascular magnetic resonance volumetry of the left atrium

BACKGROUND

Artificial intelligence can assist in cardiac image interpretation. Here, we achieved a substantial reduction in time required to read a cardiovascular magnetic resonance (CMR) study to estimate left atrial volume without compromising accuracy or reliability. Rather than deploying a fully automatic black-box, we propose to incorporate the automated LA volumetry into a human-centric interactive image-analysis process.

METHODS AND RESULTS

Atri-U, an automated data analysis pipeline for long-axis cardiac cine images, computes the atrial volume by: (i) detecting the end-systolic frame, (ii) outlining the endocardial borders of the LA, (iii) localizing the mitral annular hinge points and constructing the longitudinal atrial diameters, equivalent to the usual workup done by clinicians. In every step human interaction is possible, such that the results provided by the algorithm can be accepted, corrected, or re-done from scratch. Atri-U was trained and evaluated retrospectively on a sample of 300 patients and then applied to a consecutive clinical sample of 150 patients with various heart conditions. The agreement of the indexed LA volume between Atri-U and two experts was similar to the inter-rater agreement between clinicians (average overestimation of 0.8 mL/m2 with upper and lower limits of agreement of - 7.5 and 5.8 mL/m2, respectively). An expert cardiologist blinded to the origin of the annotations rated the outputs produced by Atri-U as acceptable in 97% of cases for step (i), 94% for step (ii) and 95% for step (iii), which was slightly lower than the acceptance rate of the outputs produced by a human expert radiologist in the same cases (92%, 100% and 100%, respectively). The assistance of Atri-U lead to an expected reduction in reading time of 66%-from 105 to 34 s, in our in-house clinical setting.

CONCLUSIONS

Our proposal enables automated calculation of the maximum LA volume approaching human accuracy and precision. The optional user interaction is possible at each processing step. As such, the assisted process sped up the routine CMR workflow by providing accurate, precise, and validated measurement results.

Fully automated guideline-compliant diameter measurements of the thoracic aorta on ECG-gated CT angiography using deep learning

Background

Manually performed diameter measurements on ECG-gated CT-angiography (CTA) represent the gold standard for diagnosis of thoracic aortic dilatation. However, they are time-consuming and show high inter-reader variability. Therefore, we aimed to evaluate the accuracy of measurements of a deep learning-(DL)-algorithm in comparison to those of radiologists and evaluated measurement times (MT).

Methods

We retrospectively analyzed 405 ECG-gated CTA exams of 371 consecutive patients with suspected aortic dilatation between May 2010 and June 2019. The DL-algorithm prototype detected aortic landmarks (deep reinforcement learning) and segmented the lumen of the thoracic aorta (multi-layer convolutional neural network). It performed measurements according to AHA-guidelines and created visual outputs. Manual measurements were performed by radiologists using centerline technique. Human performance variability (HPV), MT and DL-performance were analyzed in a research setting using a linear mixed model based on 21 randomly selected, repeatedly measured cases. DL-algorithm results were then evaluated in a clinical setting using matched differences. If the differences were within 5 mm for all locations, the cases was regarded as coherent; if there was a discrepancy >5 mm at least at one location (incl. missing values), the case was completely reviewed.

Results

HPV ranged up to ±3.4 mm in repeated measurements under research conditions. In the clinical setting, 2,778/3,192 (87.0%) of DL-algorithm's measurements were coherent. Mean differences of paired measurements between DL-algorithm and radiologists at aortic sinus and ascending aorta were -0.45±5.52 and -0.02±3.36 mm. Detailed analysis revealed that measurements at the aortic root were over-/underestimated due to a tilted measurement plane. In total, calculated time saved by DL-algorithm was 3:10 minutes/case.

Conclusions

The DL-algorithm provided coherent results to radiologists at almost 90% of measurement locations, while the majority of discrepent cases were located at the aortic root. In summary, the DL-algorithm assisted radiologists in performing AHA-compliant measurements by saving 50% of time per case.

AI-based detection and classification of distal radius fractures using low-effort data labeling: evaluation of applicability and effect of training set size

Objectives

To evaluate the performance of a deep convolutional neural network (DCNN) in detecting and classifying distal radius fractures, metal, and cast on radiographs using labels based on radiology reports. The secondary aim was to evaluate the effect of the training set size on the algorithm’s performance.

Methods

A total of 15,775 frontal and lateral radiographs, corresponding radiology reports, and a ResNet18 DCNN were used. Fracture detection and classification models were developed per view and merged. Incrementally sized subsets served to evaluate effects of the training set size. Two musculoskeletal radiologists set the standard of reference on radiographs (test set A). A subset (B) was rated by three radiology residents. For a per-study-based comparison with the radiology residents, the results of the best models were merged. Statistics used were ROC and AUC, Youden’s J statistic (J), and Spearman’s correlation coefficient (ρ).

Results

The models’ AUC/J on (A) for metal and cast were 0.99/0.98 and 1.0/1.0. The models’ and residents’ AUC/J on (B) were similar on fracture (0.98/0.91; 0.98/0.92) and multiple fragments (0.85/0.58; 0.91/0.70). Training set size and AUC correlated on metal (ρ = 0.740), cast (ρ = 0.722), fracture (frontal ρ = 0.947, lateral ρ = 0.946), multiple fragments (frontal ρ = 0.856), and fragment displacement (frontal ρ = 0.595).

Conclusions

The models trained on a DCNN with report-based labels to detect distal radius fractures on radiographs are suitable to aid as a secondary reading tool; models for fracture classification are not ready for clinical use. Bigger training sets lead to better models in all categories except joint affection.

Key Points

• Detection of metal and cast on radiographs is excellent using AI and labels extracted from radiology reports.

• Automatic detection of distal radius fractures on radiographs is feasible and the performance approximates radiology residents.

• Automatic classification of the type of distal radius fracture varies in accuracy and is inferior for joint involvement and fragment displacement.

Quantifying Radiology Resident Fatigue: Analysis of Preliminary Reports

Background Workloads in radiology departments have constantly increased over the past decades. The resulting radiologist fatigue is considered a rising problem that affects diagnostic accuracy. Purpose To investigate whether data mining of quantitative parameters from the report proofreading process can reveal daytime and shift-dependent trends in report similarity as a surrogate marker for resident fatigue. Materials and Methods Data from 117 402 radiology reports written by residents between September 2017 and March 2020 were extracted from a report comparison tool and retrospectively analyzed. Through calculation of the Jaccard similarity coefficient between residents' preliminary and staff-reviewed final reports, the amount of edits performed by staff radiologists during proofreading was quantified on a scale of 0 to 1 (1: perfect similarity, no edits). Following aggregation per weekday and shift, data were statistically analyzed by using simple linear regression or one-way analysis of variance (significance level, P < .05) to determine relationships between report similarity and time of day and/or weekday reports were dictated. Results Decreasing report similarity with increasing work hours was observed for day shifts (r = -0.93 [95% CI: -0.73, -0.98]; P < .001) and weekend shifts (r = -0.72 [95% CI: -0.31, -0.91]; P = .004). For day shifts, negative linear correlation was strongest on Fridays (r = -0.95 [95% CI: -0.80, -0.99]; P < .001), with a 16% lower mean report similarity at the end of shifts (0.85 ± 0.24 at 8 am vs 0.69 ± 0.32 at 5 pm). Furthermore, mean similarity of reports dictated on Fridays (0.79 ± 0.35) was lower than that on all other weekdays (range, 0.84 ± 0.30 to 0.86 ± 0.27; P < .001). For late shifts, report similarity showed a negative correlation with the course of workweeks, showing a continuous decrease from Monday to Friday (r = -0.98 [95% CI: -0.70, -0.99]; P = .007). Temporary increases in report similarity were observed after lunch breaks (day and weekend shifts) and with the arrival of a rested resident during overlapping on-call shifts. Conclusion Decreases in report similarity over the course of workdays and workweeks suggest aggravating effects of fatigue on residents' report writing performances. Periodic breaks within shifts potentially foster recovery. © RSNA, 2021.

Assessment of a Deep Learning Algorithm for the Detection of Rib Fractures on Whole-Body Trauma Computed Tomography

Objective

To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT.

Materials and Methods

We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455).

Results

All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement.

Conclusion

We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

Revealing the most common reporting errors through data mining of the report proofreading process

Objectives

To investigate the most common errors in residents’ preliminary reports, if structured reporting impacts error types and frequencies, and to identify possible implications for resident education and patient safety.

Material and methods

Changes in report content were tracked by a report comparison tool on a word level and extracted for 78,625 radiology reports dictated from September 2017 to December 2018 in our department. Following data aggregation according to word stems and stratification by subspecialty (e.g., neuroradiology) and imaging modality, frequencies of additions/deletions were analyzed for findings and impression report section separately and compared between subgroups.

Results

Overall modifications per report averaged 4.1 words, with demonstrably higher amounts of changes for cross-sectional imaging (CT: 6.4; MRI: 6.7) than non-cross-sectional imaging (radiographs: 0.2; ultrasound: 2.8). The four most frequently changed words (right, left, one, and none) remained almost similar among all subgroups (range: 0.072–0.117 per report; once every 9–14 reports). Albeit representing only 0.02% of analyzed words, they accounted for up to 9.7% of all observed changes. Subspecialties solely using structured reporting had substantially lower change ratios in the findings report section (mean: 0.2 per report) compared with prose-style reporting subspecialties (mean: 2.0). Relative frequencies of the most changed words remained unchanged.

Conclusion

Residents’ most common reporting errors in all subspecialties and modalities are laterality discriminator confusions (left/right) and unnoticed descriptor misregistration by speech recognition (one/none). Structured reporting reduces overall error rates, but does not affect occurrence of the most common errors. Increased error awareness and measures improving report correctness and ensuring patient safety are required.

Key Points

• The two most common reporting errors in residents’ preliminary reports are laterality discriminator confusions (left/right) and unnoticed descriptor misregistration by speech recognition (one/none).

• Structured reporting reduces the overall the error frequency in the findings report section by a factor of 10 (structured reporting: mean 0.2 per report; prose-style reporting: 2.0) but does not affect the occurrence of the two major errors.

• Staff radiologist review behavior noticeably differs between radiology subspecialties.

Electronic supplementary material

The online version of this article (10.1007/s00330-020-07306-6) contains supplementary material, which is available to authorized users.

Development and clinical implementation of tailored image analysis tools for COVID-19 in the midst of the pandemic: The synergetic effect of an open, clinically embedded software development platform and machine learning

Purpose

During the emerging COVID-19 pandemic, radiology departments faced a substantial increase in chest CT admissions coupled with the novel demand for quantification of pulmonary opacities. This article describes how our clinic implemented an automated software solution for this purpose into an established software platform in 10 days. The underlying hypothesis was that modern academic centers in radiology are capable of developing and implementing such tools by their own efforts and fast enough to meet the rapidly increasing clinical needs in the wake of a pandemic.

Method

Deep convolutional neural network algorithms for lung segmentation and opacity quantification on chest CTs were trained using semi-automatically and manually created ground-truth (N_total = 172). The performance of the in-house method was compared to an externally developed algorithm on a separate test subset (N = 66).

Results

The final algorithm was available at day 10 and achieved human-like performance (Dice coefficient = 0.97). For opacity quantification, a slight underestimation was seen both for the in-house (1.8 %) and for the external algorithm (0.9 %). In contrast to the external reference, the underestimation for the in-house algorithm showed no dependency on total opacity load, making it more suitable for follow-up.

Conclusions

The combination of machine learning and a clinically embedded software development platform enabled time-efficient development, instant deployment, and rapid adoption in clinical routine. The algorithm for fully automated lung segmentation and opacity quantification that we developed in the midst of the COVID-19 pandemic was ready for clinical use within just 10 days and achieved human-level performance even in complex cases.

Quantitative enhancement thresholds and machine learning algorithms for the evaluation of renal lesions using single-phase split-filter dual-energy CT

PURPOSE

To establish thresholds for contrast enhancement-based attenuation (CM) and iodine concentration (IOD) for the quantitative evaluation of enhancement in renal lesions on single-phase split-filter dual-energy CT (tbDECT) and combine measurements in a machine learning algorithm to potentially improve performance.

MATERIAL

126 patients with incidental renal cysts (both hypo- and hyperdense cysts) or high suspicion for renal cell carcinoma (312 total lesions) undergoing abdominal, portal venous phase tbDECT were initially included in this retrospective study. Gold standard was pathological confirmation or follow-up imaging (MRI or multiphasic CT). CM, IOD, and ROI size were recorded. Thresholds for CM and IOD were identified using Youden-Index of the empirical ROC curves. Decision tree (DTC) and random forest classifier (RFC) were trained. Sensitivities, specificities, and AUCs were compared using McNemar and DeLong test.

RESULTS

The final study cohort comprised 40 enhancing and 113 non-enhancing renal lesions. Optimal thresholds for quantitative iodine measurements and contrast enhancement-based attenuation were 1.0 ± 0.0 mg/ml and 23.6 ± 0.3 HU, respectively. Single DECT parameters (IOD, CM) showed similar overall performance with an AUC of 0.894 and 0.858 (p = 0.541) (sensitivity 90 and 80%, specificity 88 and 92%, respectively). While overall performance for the DTC (AUC 0.944) was higher than RFC (AUC 0.886), this difference (p = 0.409) and comparison to CM (p = 0.243) and IOD (p = 0.353) was not statistically significant.

CONCLUSIONS

Enhancement in incidental renal lesions on single-phase tbDECT can be classified with up to 87.5% sensitivity and 94.6% specificity. Algorithms combining DECT parameters did not increase overall performance.

Centralized expert HRCT Reading in suspected idiopathic pulmonary fibrosis: Experience from an Eurasian teleradiology program

PURPOSE

To share experience from a large, ongoing expert reading teleradiology program in Europe and Asia aiming at supporting referring centers to interpret high-resolution computed tomography (HRCT) with respect to presence of Usual Interstitial Pneumonia (UIP)-pattern in patients with suspected Idiopathic Pulmonary Fibrosis (IPF).

METHOD

We analyzed data from 01/2014 to 05/2019, including HRCTs from 239 medical centers in 12 European and Asian countries that were transmitted to our Picture Archiving and Communication System (PACS) via a secured internet connection. Structured reports were generated in consensus by a radiologist with over 20 years of experience in thoracic imaging and a pulmonologist with specific expertise in interstitial lung disease according to current guidelines on IPF. Reports were sent to referring physicians. We evaluated patient characteristics, technical issues, report turnaround times and frequency of diagnoses. We also conducted a survey to collect feedback from referring physicians.

RESULTS

HRCT image data from 703 patients were transmitted (53.5% male). Mean age was 63.7 years (SD:17). In 35.1% of all cases diagnosis was "UIP"/"Typical UIP". The mean report turnaround time was 1.7 days (SD:2.9). Data transmission errors occurred in 7.1%. Overall satisfaction rate among referring physicians was high (8.4 out of 10; SD:3.2).

CONCLUSIONS

This Eurasian teleradiology program demonstrates the feasibility of cross-border teleradiology for the provision of state-of-the-art reporting despite heterogeneity of referring medical centers and challenges like data transmission errors and language barriers. We also point out important factors for success like the usage of structured reporting templates.

Artificial Intelligence in Musculoskeletal Imaging: Review of Current Literature, Challenges, and Trends

Artificial intelligence (AI) has gained major attention with a rapid increase in the number of published articles, mostly recently. This review provides a general understanding of how AI can or will be useful to the musculoskeletal radiologist. After a brief technical background on AI, machine learning, and deep learning, we illustrate, through examples from the musculoskeletal literature, potential AI applications in the various steps of the radiologist's workflow, from managing the request to communication of results. The implementation of AI solutions does not go without challenges and limitations. These are also discussed, as well as the trends and perspectives.

How to use… urine dipsticks

'Urine dipstick', the commonly used point-of-care test, is an extremely sensitive investigation. Results of this test affected by numerous factors, if not meticulously linked with detailed history and examination, can lead a well-meaning clinician down the wrong clinical pathway. The aim of this article is to provide an overview of this every day test, touching on the physiological and technological basis initially, but mainly focusing on common questions like when to request the dipstick test, the correlation of dipstick results with urine specimen collected by different method and complexities of interpretation of dipstick results in everyday clinical scenarios.

Whistles and wheezes: don't miss diseases

Upper airway obstruction (UAO) in infants and children has a broad spectrum of presentations including benign self-resolving conditions, from mild croup, to critical life-threatening conditions which, though uncommon now, require prompt recognition and effective multidisciplinary collaborative management to achieve a good outcome. The aim of this article is to highlight the diagnostic and management difficulties in acute UAO in paediatric patients and encourage a problem-solving approach.

Regulation of protein synthesis in mammary glands of lactating dairy cows by starch and amino acids

The objective of this study was to evaluate local molecular adaptations proposed to regulate protein synthesis in the mammary glands. It was hypothesized that AA and energy-yielding substrates independently regulate AA metabolism and protein synthesis in mammary glands by a combination of systemic and local mechanisms. Six primiparous mid-lactation Holstein cows with ruminal cannulas were randomly assigned to 4 treatment sequences in a replicated incomplete 4 x 4 Latin square design experiment. Treatments were abomasal infusions of casein and starch in a 2 x 2 factorial arrangement. All animals received the same basal diet (17.6% crude protein and 6.61 MJ of net energy for lactation/kg of DM) throughout the study. Cows were restricted to 70% of ad libitum intake and abomasally infused for 36 h with water, casein (0.86 kg/d), starch (2 kg/d), or a combination (2 kg/d starch+0.86 kg/d casein) using peristaltic pumps. Milk yields and composition were assessed throughout the study. Arterial and venous plasma samples were collected every 20 min during the last 8h of infusion to assess mammary uptake. Mammary biopsy samples were collected at the end of each infusion and assessed for the phosphorylation state of selected intracellular signaling molecules that regulate protein synthesis. Animals infused with casein had increased arterial concentrations of AA, increased mammary extraction of AA from plasma, either no change or a trend for reduced mammary AA clearance rates, and no change in milk protein yield. Animals infused with starch had increased milk and milk protein yields, increased mammary plasma flow, reduced arterial concentrations of AA, and increased mammary clearance rates and net uptake of some AA. Infusions of starch increased plasma concentrations of glucose, insulin, and insulin-like growth factor-I. Starch infusions increased phosphorylation of ribosomal protein S6 and endothelial nitric oxide synthase, consistent with changes in milk protein yields and plasma flow, respectively. Phosphorylation of the mammalian target of rapamycin was increased in response to starch only when casein was also infused. Thus, cell signaling molecules involved in the regulation of protein synthesis differentially responded to these nutritional stimuli. The hypothesized independent effects of casein and starch on animal metabolism and cell signaling were not observed, presumably because of the lack of a milk protein response to infused casein.

An unusual cause of interference in a salicylate assay caused by mitochondrial acetoacetyl-CoA thiolase deficiency

Mitochondrial acetoacetyl-CoA thiolase deficiency (or beta-ketothiolase deficiency) is a rare metabolic disorder characterized by acute episodes of severe acidosis and ketosis. A case is presented of an 18-month-old boy who presented with vomiting and diarrhoea and was found to be markedly acidotic. When the acidosis persisted despite saline fluid boluses and bicarbonate correction, further investigations were undertaken. Routine biochemical investigation revealed detectable salicylate concentrations despite the parents denying its administration, which initially caused some diagnostic confusion. The results of urine organic acid analysis, however, confirmed that the diagnosis of mitochondrial acetoacetyl-CoA thiolase deficiency. The high concentrations of acetoacetate present in the patient's sample resulted in a false-positive reaction in the Trinder assay for salicylate.

A Fatal Neonatal Presentation of Medium-chain Acyl Coenzyme a Dehydrogenase Deficiency

Medium-chain acyl coenzyme A dehydrogenase (MCAD) deficiency is the most common of the inborn errors of mitochondrial fatty acid β-oxidation. A male infant was born at 39 weeks of gestation following an uneventful pregnancy. He was discharged at age 28 h after a normal first-day check, but was subsequently re-admitted and died aged 44 h. Post-mortem blood and bile spot carnitine analysis revealed a profile consistent with MCAD deficiency. MCAD genotyping revealed 985 A to G (K329E) homozygosity. This is the first confirmed case of neonatal death due to MCAD deficiency in the UK.

What is a meant when a laparoscopic surgical procedure is described as “safe”?

BACKGROUND

The literature on laparoscopic surgery contains many studies concluding that a procedure is "safe." This study aimed to review systematically articles from the past 10 years that judged a laparoscopic technique for colon resection and anastomosis to be "safe."

METHODS

The authors searched the Medline database from January 1995 to August 2005 using the search terms "laparoscopic," "colon," and "safe," selecting studies of laparoscopic colon resection or laparoscopic techniques of colonic anastomosis. They calculated exact 95% confidence intervals around estimates of the risk for death reported in the studies to determine the upper limit of the possible risk for death in a study reporting no deaths.

RESULTS

Of 135 studies matching the search criteria, 41 (30%) described operations involving laparoscopic colonic resection or anastomosis. These studies enrolled a mean number of 233 subjects. There were 26 retrospective studies, 12 prospective studies, 2 randomized control trials, and 1 case report. The estimated upper 95% confidence limits for studies reporting mortality ranged from 1.66% to 97.5%. Of the studies that reported mortality and concluded that laparoscopic colon surgery is "safe," 77.8% could not exclude a mortality rate higher than 5%.

CONCLUSION

Many studies concluding that laparoscopic colon surgery is "safe" could not exclude a high risk of operative mortality. The term "safe" is not a useful descriptor of the relative safety of laparoscopic surgical procedures, and statements about the safety of a surgical procedure should be justified with precise estimates and confidence intervals of the risk for adverse events.

A laparoscopic duodenojejunostomy for a duodenal obstruction from lymphoma

A patient with lymphoma in one-third of the duodenum causing a duodenal obstruction is described. The patient had a partial response with chemotherapy, but still was obstructed and unable to eat. He was losing weight, and chemotherapy had to be stopped. A gastrostomy tube was inserted for drainage because the stomach was quite distended. A jejunostomy tube was passed through the gastrostomy tube for feeding, but the patient did not tolerate the feeding. A laparoscopic bypass of the duodenumduodenal obstruction (from duodenum to jejunum) for this patient is shown on a video. The patient did very well after this bypass was provided. He was able to tolerate an oral diet on postoperative day 2, and on postoperative day 4, he was discharged home. He has since resumed chemotherapy, and is doing well, at this writing, 2 months after surgery. Electronic supplementary material is available for this article at http://dx.doi.org/10.1007/s00464-005-0874-2.

Acceleromyography vs. electromyography: an ipsilateral comparison of the indirectly evoked neuromuscular response to train-of-four stimulation

BACKGROUND

There is a considerable body of evidence which suggests that data obtained using acceleromyography (AMG) cannot be used interchangeably with observations obtained by mechanomyographic (MMG) or electromyograhic (EMG) methods. All previous such studies evaluated the responses from contralateral limbs. This investigation was undertaken to determine if these previously described differences were in part a function of observing the responses from opposing limbs.

METHODS

We compared the ipsilateral EMG and AMG response to an ED(95) bolus of atracurium in 50 subjects. In half of the individuals the thumb was free to move freely; in half, a small elastic preload was applied to the thumb. Train-of-four (TOF) recovery was followed until a TOF ratio >0.90 was recorded by both monitors. Acceleromyography vs. EMG differences and the resultant 95% confidence limits for twitch height (T1) and the TOF ratio were determined.

RESULTS

When the AMG TOF value had recovered to a value of 0.72 +/- 0.03; the simultaneously evoked EMG value averaged only 0.59 +/- 0.08. This difference was statistically significant (P < 0.001). Although the mean difference AMG vs. EMG was little more than 0.10, differences in an individual might be twice that amount. When the AMG TOF value had recovered to 0.90, the simultaneously evoked EMG value averaged 0.85. Again the 95% confidence limits for individual observations was very wide. With EMG, once the TOF ratio returns to a value of 0.70, T1 has returned to 95% of control. In contrast with AMG, return of T1 -95% of control requires a TOF ratio of almost 0.90. Addition of an elastic preload to the thumb decreased control TOF variability without effecting the relationship between twitch height and the TOF ratio.

CONCLUSION

Acceleromyographic TOF values tend to overestimate the extent of EMG recovery. Acceleromyographic TOF values <0.90 are indicative of incomplete neuromuscular recovery.

High fat diet increases the weight of rat ventral prostate

BACKGROUND

Understanding the mechanisms by which diet influences the prostate may eventually lead to novel approaches for preventing prostate cancer. The objective of this research is to examine the impact of dietary fat, vitamin D, and genistein on prostate weight, serum and intraprostatic androgen levels, and the expression of several androgen-response genes.

METHODS

Sprague-Dawley rats were fed, beginning at 21 days of age, for 1 or 3 months of experimental diets with high saturated fat (32.2% calories from fat), low saturated fat (3.6% calories from fat), genistein plus (20 mg/kg), genistein deficient, vitamin D surplus (4,000 U/kg), or vitamin D deficient. The body weight, food intake, the weights of the ventral prostate and dorsolateral prostate, and the levels of testosterone and dihydrotestosterone (DHT) in the serum and in the prostate were determined. The expression of androgen-response genes was characterized by Northern blot analysis.

RESULTS

The pilot experiments showed that high dietary fat appeared to consistently increase the weight of the ventral prostate, while vitamin D or genistein did not have a consistent effect on prostate weight. Further analysis confirmed that the ventral prostate is 15% (P < 0.001) heavier in the rat on a high fat diet as compared to a low fat diet. Dietary fat had no significant influence on the levels of serum and intraprostatic androgens and the expression of androgen-response genes.

CONCLUSIONS

Our results suggested that the ventral prostate weight of the rat is increased without affecting the androgen axis by feeding the animals with high fat diet beginning at 21 days of age. This observation is potentially important since epidemiological data suggest that saturated fat consumption is a major risk factor associated with prostate cancer incidence rate.

Farnesyl diphosphate synthase is abundantly expressed and regulated by androgen in rat prostatic epithelial cells

Farnesyl diphosphate synthase (FPPS) has been identified as an androgen-response gene in the rat ventral prostate using a highly sensitive PCR-based cDNA subtraction technique. FPPS is an essential enzyme that catalyzes the synthesis of farnesyl diphosphate (FPP), which is required for cholesterol biosynthesis as well as protein prenylation. We have characterized the expression of FPPS in the rat prostate in response to androgen manipulation. Northern blot analysis showed that castration induced a 10-fold down-regulation of FPPS mRNA within 24 h in the ventral prostate and androgen replacement up-regulated FPPS mRNA rapidly in the regressed ventral prostate of a castrated rat. The expression of FPPS was also regulated by androgen in the lateral and dorsal prostate, indicating that FPPS is important to androgen action in all three lobes of the prostate. Western blot analysis showed that FPPS protein level was also regulated by androgen in the prostate. Northern blot analysis of tissue specificity indicated that FPPS was most abundantly expressed in the ventral prostate of a mature rat and was responsive to androgen manipulation in the prostate and seminal vesicles, but not in other tissues. In situ hybridization study showed that FPPS mRNA was localized to the prostatic epithelium. Interestingly, the expression of FPPS was elevated in Dunning rat prostate tumor cell lines. The above findings suggest that FPPS has the potential to play an important role in androgen action and prostate cancer progression.

Androgen regulation of the largest subunit of RNA polymerase II in the rat ventral prostate

One of the dramatic changes in the prostate during androgen manipulation is the alteration in cellular content of total RNA - the amount of total RNA in each cell. The abundance of cellular total RNA correlates with the RNA polymerase (RNAP) activity in the prostate. One possible mechanism of androgen regulation of RNAP activity involves the regulation of RNAP expression. Western blot analysis showed that the largest subunit of the RNAP II, an essential component of the transcriptional machinery for mRNA, is indeed regulated by androgens. Castration down-regulates the protein level of RNAP II, whereas androgen replacement up-regulates the protein. However, androgen manipulation does not have consistent effects on the phosphorylation of the C-terminal domain (CTD) of the RNAP II. Androgen regulation of the RNAP II protein expression was also observed in the seminal vesicles but not in the thymus and liver, indicating that androgen regulation of RNAP II protein expression appears to be limited to the male sex accessory organs. These observations suggest that RNAP II plays an essential role in androgen action in male sex accessory organs.

Infantile Salmonella meningitis associated with gecko-keeping

A serotype found mainly in reptiles was isolated from cerebrospinal fluid from a 2 month old baby with meningitis. A related salmonella was isolated from gecko faeces from the floor of the tank in the baby's home, suggesting a possible source of infection, and indicating the need for hygienic precautions in homes where reptiles are kept as pets.