Deep learning versus iterative image reconstruction algorithm for head CT in trauma

Purpose To compare the image quality between a deep learning–based image reconstruction algorithm (DLIR) and an adaptive statistical iterative reconstruction algorithm (ASiR-V) in noncontrast trauma head CT. Methods Head CT scans from 94 consecutive trauma patients were included. Images were reconstructed with ASiR-V 50% and the DLIR strengths: low (DLIR-L), medium (DLIR-M), and high (DLIR-H). The image quality was assessed quantitatively and qualitatively and compared between the different reconstruction algorithms. Inter-reader agreement was assessed by weighted kappa. Results DLIR-M and DLIR-H demonstrated lower image noise (p < 0.001 for all pairwise comparisons), higher SNR of up to 82.9% (p < 0.001), and higher CNR of up to 53.3% (p < 0.001) compared to ASiR-V. DLIR-H outperformed other DLIR strengths (p ranging from < 0.001 to 0.016). DLIR-M outperformed DLIR-L (p < 0.001) and ASiR-V (p < 0.001). The distribution of reader scores for DLIR-M and DLIR-H shifted towards higher scores compared to DLIR-L and ASiR-V. There was a tendency towards higher scores with increasing DLIR strengths. There were fewer non-diagnostic CT series for DLIR-M and DLIR-H compared to ASiR-V and DLIR-L. No images were graded as non-diagnostic for DLIR-H regarding intracranial hemorrhage. The inter-reader agreement was fair-good between the second most and the less experienced reader, poor-moderate between the most and the less experienced reader, and poor-fair between the most and the second most experienced reader. Conclusion The image quality of trauma head CT series reconstructed with DLIR outperformed those reconstructed with ASiR-V. In particular, DLIR-M and DLIR-H demonstrated significantly improved image quality and fewer non-diagnostic images. The improvement in qualitative image quality was greater for the second most and the less experienced readers compared to the most experienced reader.

SAT0425 NOVEL COMPUTER-ASSISTED METHODOLOGY FOR QUANTITATIVE ASSESSMENT OF MRI TREATMENT RESPONSES TO APREMILAST IN PATIENTS WITH PSORIATIC ARTHRITIS

Background:Response to treatment in psoriatic arthritis (PsA) can be captured using the OMERACT PsA Magnetic Resonance Imaging Score (PsAMRIS). While reliable and valid, PsAMRIS interpretation requires a trained reader to assess inflammatory lesions such as synovitis and flexor tenosynovitis on a discrete scale ranging from 0 to 3, which might not have sufficient sensitivity to capture early and subtle changes in inflammation in small cohorts.Objectives:To propose a novel computer-assisted imaging quantitative methodology to assess early response to treatment on a continuous scale and compare its results with those of PsAMRIS.Methods:Patients with active PsA in the hand and wrist were treated with apremilast 30 mg twice daily after a 5-day titration period. A total of 29 patients underwent MRI scans at baseline and months 3, 6, and 12. Images were scored for synovitis using the PsAMRIS interpreted by an experienced reader and were read in blinded sequences. Images for 13 patients with involvement of the wrist and metacarpophalangeal (MCP) joints and MRI available at baseline, 3 months, and 6 months were further processed using a novel computer-assisted imaging quantitative methodology. Images were scored concurrently, with the reader blinded to the order of visits. An experienced reader pre-defined regions of interest (ROIs) around the wrist, MCP joints (MCP-2 to MCP-5), and flexor and extensor tendons of the fingers and wrist (as applicable) with adjacent blood vessels and possible artifacts excluded from ROIs. From these ROIs, the normalized volume of inflammation (NormI) was calculated in each joint and tendon. This was done by automatically counting the pixels that were enhanced above the intensity level of a muscle. Each enhanced pixel was given a weight corresponding to the degree of enhancement, allowing differentiation of areas of residual inflammation and high perfusion. This method has been validated, tested, and implemented in the CE/FDA510-cleared software package Dynamika (IAG, Image Analysis Group). PsAMRIS responses were compared with those of the computer-assisted imaging quantitative methodology at baseline, 3 months, and 6 months. A heat map of normalized intensities was produced, highlighting areas of perfusion higher than that of healthy muscle. Changes from baseline were tested for significance using at-test. Patients with non-missing data were included in the final statistical analysis.Results:The generated NormI map highlighted a reduction in wrist inflammation activity after 3 and 6 months of treatment with apremilast. In all cases, a downward trend in inflammatory activity in the wrist and MCP joints was observed at 3 months, indicating a reduction following treatment with apremilast (Figures 1 and 2). Similar improvements were observed in tenosynovitis (Figures 1 and 2).Conclusion:In this pilot assessment, apremilast was associated with improvements in synovitis and tenosynovitis over a period of 6 months using PsAMRIS. Assessment of images using NormI, a methodology allowing quantification of inflammatory activity within a joint or tendon, demonstrated the same trends over 6 months. Further studies are planned to determine the sensitivity of this novel computer-assisted imaging quantitative methodology relative to that of PsAMRIS and whether it could be used to provide early indications of treatment response in small cohorts of patients.Disclosure of Interests:Paul Bird Consultant of: AbbVie, Celgene Corporation, Eli Lilly, Janssen, Novartis, Pfizer – advisor, Speakers bureau: AbbVie, Celgene Corporation, Eli Lilly, Janssen, Novartis, Pfizer, Mikael Boesen Consultant of: AbbVie, AstraZeneca, Eli Lilly, Esaote, Glenmark, Novartis, Pfizer, UCB, Paid instructor for: IAG, Image Analysis Group, AbbVie, Eli Lilly, AstraZeneca, esaote, Glenmark, Novartis, Pfizer, UCB (scientific advisor)., Speakers bureau: Eli Lilly, Esaote, Novartis, Pfizer, UCB, Mark Hinton: None declared, Eser Sanverdi Employee of: Image Analysis Group – employment, Romiesa Hagoug Employee of: Image Analysis Group – employment, Christoper Sabin Employee of: Image Analysis Group – employment, Priscila Nakasato Employee of: Amgen Inc. – employment; Celgene Corporation – employment at the time of study conduct, Benoit Guerette Employee of: Amgen Inc. – employment; Celgene Corporation – employment at the time of study conduct, Olga Kubassova Shareholder of: IAG, Image Analysis Group, Consultant of: Novartis, Takeda, Lilly, Employee of: IAG, Image Analysis Group

Evaluation of the Quadri-Planes Method in Computer-Aided Diagnosis of Breast Lesions by Ultrasonography: Prospective Single-Center Study

Background Computer-aided diagnosis (CAD) is a tool that can help radiologists diagnose breast lesions by ultrasonography. Previous studies have demonstrated that CAD can help reduce the incidence of missed diagnoses by radiologists. However, the optimal method to apply CAD to breast lesions using diagnostic planes has not been assessed. Objective The aim of this study was to compare the performance of radiologists with different levels of experience when using CAD with the quadri-planes method to detect breast tumors. Methods From November 2018 to October 2019, we enrolled patients in the study who had a breast mass as their most prominent symptom. We assigned 2 ultrasound radiologists (with 1 and 5 years of experience, respectively) to read breast ultrasonography images without CAD and then to perform a second reading while applying CAD with the quadri-planes method. We then compared the diagnostic performance of the readers for the 2 readings (without and with CAD). The McNemar test for paired data was used for statistical analysis. Results A total of 331 patients were included in this study (mean age 43.88 years, range 17-70, SD 12.10), including 512 lesions (mean diameter 1.85 centimeters, SD 1.19; range 0.26-9.5); 200/512 (39.1%) were malignant, and 312/512 (60.9%) were benign. For CAD, the area under the receiver operating characteristic curve (AUC) improved significantly from 0.76 (95% CI 0.71-0.79) with the cross-planes method to 0.84 (95% CI 0.80-0.88; P<.001) with the quadri-planes method. For the novice reader, the AUC significantly improved from 0.73 (95% CI 0.69-0.78) for the without-CAD mode to 0.83 (95% CI 0.80-0.87; P<.001) for the combined-CAD mode with the quadri-planes method. For the experienced reader, the AUC improved from 0.85 (95% CI 0.81-0.88) to 0.87 (95% CI 0.84-0.91; P=.15). The kappa indicating consistency between the experienced reader and the novice reader for the combined-CAD mode was 0.63. For the novice reader, the sensitivity significantly improved from 60.0% for the without-CAD mode to 79.0% for the combined-CAD mode (P=.004). The specificity, negative predictive value, positive predictive value, and accuracy improved from 84.9% to 87.8% (P=.53), 76.8% to 86.7% (P=.07), 71.9% to 80.6% (P=.13), and 75.2% to 84.4% (P=.12), respectively. For the experienced reader, the sensitivity improved significantly from 76.0% for the without-CAD mode to 87.0% for the combined-CAD mode (P=.045). The NPV and accuracy moderately improved from 85.8% and 86.3% to 91.0% (P=.27) and 87.0% (P=.84), respectively. The specificity and positive predictive value decreased from 87.4% to 81.3% (P=.25) and from 87.2% to 93.0% (P=.16), respectively. Conclusions S-Detect is a feasible diagnostic tool that can improve the sensitivity, accuracy, and AUC of the quadri-planes method for both novice and experienced readers while also improving the specificity for the novice reader. It demonstrates important application value in the clinical diagnosis of breast cancer. Trial Registration ChiCTR.org.cn 1800019649; http://www.chictr.org.cn/showproj.aspx?proj=33094

Performance of Computer-Aided Diagnosis in Ultrasonography for Detection of Breast Lesions Less and More Than 2 cm: Prospective Comparative Study

Background Computer-aided diagnosis (CAD) is used as an aid tool by radiologists on breast lesion diagnosis in ultrasonography. Previous studies demonstrated that CAD can improve the diagnosis performance of radiologists. However, the optimal use of CAD on breast lesions according to size (below or above 2 cm) has not been assessed. Objective The aim of this study was to compare the performance of different radiologists using CAD to detect breast tumors less and more than 2 cm in size. Methods We prospectively enrolled 261 consecutive patients (mean age 43 years; age range 17-70 years), including 398 lesions (148 lesions>2 cm, 79 malignant and 69 benign; 250 lesions≤2 cm, 71 malignant and 179 benign) with breast mass as the prominent symptom. One novice radiologist with 1 year of ultrasonography experience and one experienced radiologist with 5 years of ultrasonography experience were each assigned to read the ultrasonography images without CAD, and then again at a second reading while applying the CAD S-Detect. We then compared the diagnostic performance of the readers in the two readings (without and combined with CAD) with breast imaging. The McNemar test for paired data was used for statistical analysis. Results For the novice reader, the area under the receiver operating characteristic curve (AUC) improved from 0.74 (95% CI 0.67-0.82) from the without-CAD mode to 0.88 (95% CI 0.83-0.93; P<.001) at the combined-CAD mode in lesions≤2 cm. For the experienced reader, the AUC improved from 0.84 (95% CI 0.77-0.90) to 0.90 (95% CI 0.86-0.94; P=.002). In lesions>2 cm, the AUC moderately decreased from 0.81 to 0.80 (novice reader) and from 0.90 to 0.82 (experienced reader). The sensitivity of the novice and experienced reader in lesions≤2 cm improved from 61.97% and 73.23% at the without-CAD mode to 90.14% and 97.18% (both P<.001) at the combined-CAD mode, respectively. Conclusions S-Detect is a feasible diagnostic tool that can improve the sensitivity for both novice and experienced readers, while also improving the negative predictive value and AUC for lesions≤2 cm, demonstrating important application value in the clinical diagnosis of breast cancer. Trial Registration Chinese Clinical Trial Registry ChiCTR1800019649; http://www.chictr.org.cn/showprojen.aspx?proj=33094

Evaluation of the Quadri-Planes Method in Computer-Aided Diagnosis of Breast Lesions by Ultrasonography: Prospective Single-Center Study (Preprint)

BACKGROUND Computer-aided diagnosis (CAD) is a tool that can help radiologists diagnose breast lesions by ultrasonography. Previous studies have demonstrated that CAD can help reduce the incidence of missed diagnoses by radiologists. However, the optimal method to apply CAD to breast lesions using diagnostic planes has not been assessed. OBJECTIVE The aim of this study was to compare the performance of radiologists with different levels of experience when using CAD with the quadri-planes method to detect breast tumors. METHODS From November 2018 to October 2019, we enrolled patients in the study who had a breast mass as their most prominent symptom. We assigned 2 ultrasound radiologists (with 1 and 5 years of experience, respectively) to read breast ultrasonography images without CAD and then to perform a second reading while applying CAD with the quadri-planes method. We then compared the diagnostic performance of the readers for the 2 readings (without and with CAD). The McNemar test for paired data was used for statistical analysis. RESULTS A total of 331 patients were included in this study (mean age 43.88 years, range 17-70, SD 12.10), including 512 lesions (mean diameter 1.85 centimeters, SD 1.19; range 0.26-9.5); 200/512 (39.1%) were malignant, and 312/512 (60.9%) were benign. For CAD, the area under the receiver operating characteristic curve (AUC) improved significantly from 0.76 (95% CI 0.71-0.79) with the cross-planes method to 0.84 (95% CI 0.80-0.88; <i>P</i>&lt;.001) with the quadri-planes method. For the novice reader, the AUC significantly improved from 0.73 (95% CI 0.69-0.78) for the without-CAD mode to 0.83 (95% CI 0.80-0.87; <i>P</i>&lt;.001) for the combined-CAD mode with the quadri-planes method. For the experienced reader, the AUC improved from 0.85 (95% CI 0.81-0.88) to 0.87 (95% CI 0.84-0.91; <i>P</i>=.15). The kappa indicating consistency between the experienced reader and the novice reader for the combined-CAD mode was 0.63. For the novice reader, the sensitivity significantly improved from 60.0% for the without-CAD mode to 79.0% for the combined-CAD mode (<i>P</i>=.004). The specificity, negative predictive value, positive predictive value, and accuracy improved from 84.9% to 87.8% (<i>P</i>=.53), 76.8% to 86.7% (<i>P</i>=.07), 71.9% to 80.6% (<i>P</i>=.13), and 75.2% to 84.4% (<i>P</i>=.12), respectively. For the experienced reader, the sensitivity improved significantly from 76.0% for the without-CAD mode to 87.0% for the combined-CAD mode (<i>P</i>=.045). The NPV and accuracy moderately improved from 85.8% and 86.3% to 91.0% (<i>P</i>=.27) and 87.0% (<i>P</i>=.84), respectively. The specificity and positive predictive value decreased from 87.4% to 81.3% (<i>P</i>=.25) and from 87.2% to 93.0% (<i>P</i>=.16), respectively. CONCLUSIONS S-Detect is a feasible diagnostic tool that can improve the sensitivity, accuracy, and AUC of the quadri-planes method for both novice and experienced readers while also improving the specificity for the novice reader. It demonstrates important application value in the clinical diagnosis of breast cancer. CLINICALTRIAL ChiCTR.org.cn 1800019649; http://www.chictr.org.cn/showproj.aspx?proj=33094

Deutsche Kürzestgeschichte: Erzähltheoretische Analyse ausgewählter „short short stories“ von Kerstin Hensel und Heiner Feldhoff

German Shortest Story: A Narratological Analysis of Chosen „Short Short Stories” by Kerstin Hensel and Heiner Feldhoff Kürzestgeschichte (lit. shortest story), which is the German term for a subcategory of short story, became established as a literary genre in the 20th century. Its condensed content conformed to the hectic pace of life but, in terms of the issues discussed, it was more essential and dedicated to an experienced reader. In this paper, a narratological analysis of selected shortest stories by Heiner Feldhoff and Kerstin Hensel will be conducted. A methodological basis for the analysis is the categories implemented by Gérard Genette. Its aim is to provide an answer to the question whether shortest stories could be, like any other epic texts, subject to a narratological analysis and to what extent the length of a text might influence the findings of such an analysis.

Performance of Computer-Aided Diagnosis in Ultrasonography for Detection of Breast Lesions Less and More Than 2 cm: Prospective Comparative Study (Preprint)

BACKGROUND Computer-aided diagnosis (CAD) is used as an aid tool by radiologists on breast lesion diagnosis in ultrasonography. Previous studies demonstrated that CAD can improve the diagnosis performance of radiologists. However, the optimal use of CAD on breast lesions according to size (below or above 2 cm) has not been assessed. OBJECTIVE The aim of this study was to compare the performance of different radiologists using CAD to detect breast tumors less and more than 2 cm in size. METHODS We prospectively enrolled 261 consecutive patients (mean age 43 years; age range 17-70 years), including 398 lesions (148 lesions&gt;2 cm, 79 malignant and 69 benign; 250 lesions≤2 cm, 71 malignant and 179 benign) with breast mass as the prominent symptom. One novice radiologist with 1 year of ultrasonography experience and one experienced radiologist with 5 years of ultrasonography experience were each assigned to read the ultrasonography images without CAD, and then again at a second reading while applying the CAD S-Detect. We then compared the diagnostic performance of the readers in the two readings (without and combined with CAD) with breast imaging. The McNemar test for paired data was used for statistical analysis. RESULTS For the novice reader, the area under the receiver operating characteristic curve (AUC) improved from 0.74 (95% CI 0.67-0.82) from the without-CAD mode to 0.88 (95% CI 0.83-0.93; <i>P</i>&lt;.001) at the combined-CAD mode in lesions≤2 cm. For the experienced reader, the AUC improved from 0.84 (95% CI 0.77-0.90) to 0.90 (95% CI 0.86-0.94; <i>P</i>=.002). In lesions&gt;2 cm, the AUC moderately decreased from 0.81 to 0.80 (novice reader) and from 0.90 to 0.82 (experienced reader). The sensitivity of the novice and experienced reader in lesions≤2 cm improved from 61.97% and 73.23% at the without-CAD mode to 90.14% and 97.18% (both <i>P</i>&lt;.001) at the combined-CAD mode, respectively. CONCLUSIONS S-Detect is a feasible diagnostic tool that can improve the sensitivity for both novice and experienced readers, while also improving the negative predictive value and AUC for lesions≤2 cm, demonstrating important application value in the clinical diagnosis of breast cancer. CLINICALTRIAL Chinese Clinical Trial Registry ChiCTR1800019649; http://www.chictr.org.cn/showprojen.aspx?proj=33094

Artifacts of Recording and Common Errors in Interpretation

This chapter examines the fundamental neurophysiological principles involved in determining electroencephalographic (EEG) artifact and provides general instructions for minimizing the risk of error during clinical interpretation. Examples from EEG recordings are given to illustrate common artifacts that may be challenging to the reader because they mimic epileptiform pattern associated to people with epilepsy. Emerging techniques used to detect and reduce artifact without altering the electrocerebral signal are being developed to limit the contamination. While many artifacts are easy to recognize, more complex waveforms may confuse even the most experienced reader. Constant vigilance and a team effort to minimize artifact will help to ensure a proper interpretation of the EEG for optimal patient care.

FORGETTING THEARS MEMORIAE: OVID,REMEDIA AMORIS579–84

During his encounter with Lethaeus Amor in theRemedia amoris, in which he discusses techniques to forget a former lover, Ovid writes the following:quisquis amas, loca sola nocent: loca sola caveto;quo fugis? in populo tutior esse potes.non tibi secretis (augent secreta furores)est opus; auxilio turba futura tibi est.tristis eris, si solus eris, dominaeque relictaeante oculos facies stabit, ut ipsa, tuos.This passage has been discussed in Hardie's treatment of Lethaeus Amor, and, while he directly addresses Ovid's use oflociin this passage as I shall below, his focus is on the rich intertextuality – textual remembrances – within theRemediarather than the use oflociin thears memoriaeproper. Hardie points out numerous intertexts in theRemedia, using the character of Lethaeus Amor to highlight the paradox of a learned reader of love poetry being unable to forget the poetry he has read, despite this specific oblivion being a precondition for curing oneself of love (as clearly directed atRem. am. 755–66). In this case, theloca solaOvid warns against are ‘topics of solitude’ which ‘conjure up for the experienced reader scenes of erotic despair’, thus calling to mind the lover's own lovelorn state.