Use of a convolutional neural network and quantitative ultrasound for diagnosis of fatty liver

Quantitative ultrasound (QUS) was used to classify rabbits that were induced to have liver disease by placing them on a fatty diet for a defined duration and/or periodically injecting them with CCl₄. The ground truth of the liver state was based on lipid liver percents estimated via the Folch assay and hydroxyproline concentration to quantify fibrosis. Rabbits were scanned ultrasonically in vivo using a SonixOne scanner and an L9-4/38 linear array. Liver fat percentage was classified based on the ultrasonic backscattered radiofrequency (RF) signals from the livers using either QUS or a 1-D convolutional neural network (CNN). Use of QUS parameters with linear regression and canonical correlation analysis demonstrated that the QUS parameters could differentiate between livers with lipid levels above or below 5%. However, the QUS parameters were not sensitive to fibrosis. The CNN was implemented by analyzing raw RF ultrasound signals without using separate reference data. The CNN outputs the classification of liver as either above or below a threshold of 5% fat level in the liver. The CNN outperformed the classification utilizing the QUS parameters combined with a support vector machine in differentiating between low and high lipid liver levels (i.e., accuracies of 74% versus 59% on the testing data). Therefore, although the CNN did not provide a physical interpretation of the tissue properties (e.g., attenuation of the medium or scatterer properties) the CNN had much higher accuracy in predicting fatty liver state and did not require an external reference scan.     

Significant reduction of postoperative pain and opioid analgesics requirement with an Enhanced Recovery After Thoracic Surgery protocol

ObjectiveTo evaluate differences in postoperative pain control and opioids requirement in thoracic surgical patients following implementation of an Enhanced Recovery after Thoracic Surgery protocol with a comprehensive postoperative pain management strategy.Material and MethodsA retrospective analysis of a prospectively maintained database of patients undergoing pulmonary resections by robotic thoracoscopy or thoracotomy from January 1, 2017, to January 31, 2019, was conducted. Multimodal pain management strategy (opioid-sparing analgesics, infiltration of liposomal bupivacaine to intercostal spaces and surgical sites, and elimination of thoracic epidural analgesia use in thoracotomy patients) was implemented as part of Enhanced Recovery after Thoracic Surgery on February 1, 2018. Outcome metrics including patient-reported pain levels, in-hospital and postdischarge opioids use, postoperative complications, and length of stay were compared before and after protocol implementation.ResultsIn total, 310 robotic thoracoscopy and 62 thoracotomy patients met the inclusion criteria. This pain management strategy was associated with significant reduction of postoperative pain in both groups with an overall reduction of postoperative opioids requirement. Median in-hospital opioids use (morphine milligram equivalent per day) was reduced from 30 to 18.36 (P = .009) for the robotic thoracoscopy group and slightly increased from 15.48 to 21.0 (P = .27) in the thoracotomy group. More importantly, median postdischarge opioids prescribed (total morphine milligram equivalent) was significantly reduced from 480.0 to 150.0 (P < .001) and 887.5 to 150.0 (P < .001) for the thoracoscopy and thoracotomy groups, respectively. Similar short-term perioperative outcomes were observed in both groups before and following protocol implementation.ConclusionsImplementation of Enhanced Recovery after Thoracic Surgery allows safe elimination of epidural use, better pain control, and less postoperative opioids use, especially a drastic reduction of postdischarge opioid need, without adversely affecting outcomes.     

Prospective evaluation of rapid antimicrobial susceptibility testing by disk diffusion on Mueller-Hinton rapid-SIR directly on blood cultures

Background

With the worldwide spread of antibiotic resistance, delivering antibiotic susceptibility test (AST) results in a timely manner represents a major challenge. In cases of sepsis, rapid AST may facilitate early optimization of empiric antibiotic therapy. Disc diffusion is a well-standardized AST method, however 16 to 24?h are required to achieve an overall AST profile according to antimicrobial societies.

Evaluating the influence of prostate-specific antigen kinetics on metastasis in men with PSA recurrence after partial gland therapy

Purpose

Although current Delphi Consensus guidelines do not recommend a specific definition of biochemical recurrence after partial gland therapy, these guidelines acknowledge that serial prostate-specific antigen (PSA) tests remain the best marker for monitoring disease after treatment. The purpose of this study was to determine whether PSA velocity at failure per the Phoenix (nadir + 2 ng/mL) definition is associated with metastasis and prostate cancer-specific mortality (PCSM) in a cohort of patients who experienced PSA failure after partial gland therapy.

Differences in surgical resection rate and risk of malignancy in thyroid cytopathology practice between Western and Asian countries: A systematic review and meta-analysis

There is increasing evidence showing that clinicians employ different management strategies in their use of The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC). In this meta-analysis, we investigated the differences in diagnosis frequency, resection rate (RR), and risk of malignancy (ROM) between Western (ie, American and European) and Asian cytopathology practices. We searched PubMed and Web of Science from January 2010 to January 2019. Proportion and 95% CIs were calculated using a random-effect model. We used independent sample t tests to compare frequencies, RR, and ROM between Western and Asian practices. We analyzed a total of 38 studies with 145,066 fine-needle aspirations. Compared with Asian practice, Western series had a significantly lower ROM in most of TBSRTC categories, whereas the RR was not statistically different. Focusing on indeterminate nodules, the RR in Western series was significantly higher (51.3% vs 37.6%; P = .048), whereas the ROM was significantly lower (25.4% vs 41.9%; P = .002) compared with those in Asian series. The addition of Asian cohorts increased ROM for most of diagnostic categories compared with the original TBSRTC. In conclusion, this study demonstrates a difference in Western and Asian thyroid cytology practice, especially regarding the indeterminate categories. Lower RR and higher ROM suggest that Asian clinicians adopt a more conservative approach, whereas immediate diagnostic surgery is favored in Western practice for indeterminate nodules. The addition of Asian series into a meta-analysis of TBSRTC altered ROM for several categories, which should be considered in future revisions of TBSRTC.