Quantifying and leveraging predictive uncertainty for medical image assessment

The interpretation of medical images is a challenging task, often complicated by the presence of artifacts, occlusions, limited contrast and more. Most notable is the case of chest radiography, where there is a high inter-rater variability in the detection and classification of abnormalities. This is largely due to inconclusive evidence in the data or subjective definitions of disease appearance. An additional example is the classification of anatomical views based on 2D Ultrasound images. Often, the anatomical context captured in a frame is not sufficient to recognize the underlying anatomy. Current machine learning solutions for these problems are typically limited to providing probabilistic predictions, relying on the capacity of underlying models to adapt to limited information and the high degree of label noise. In practice, however, this leads to overconfident systems with poor generalization on unseen data. To account for this, we propose a system that learns not only the probabilistic estimate for classification, but also an explicit uncertainty measure which captures the confidence of the system in the predicted output. We argue that this approach is essential to account for the inherent ambiguity characteristic of medical images from different radiologic exams including computed radiography, ultrasonography and magnetic resonance imaging. In our experiments we demonstrate that sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC for various tasks, e.g., by 8% to 0.91 with an expected rejection rate of under 25% for the classification of different abnormalities in chest radiographs. In addition, we show that using uncertainty-driven bootstrapping to filter the training data, one can achieve a significant increase in robustness and accuracy. Finally, we present a multi-reader study showing that the predictive uncertainty is indicative of reader errors.     

Comparison between tension band and cerclage with X-Plate and lag screws in treatment of comminuted patellar fractures

BackgroundComminuted patellar fractures are not rare, and the ideal treatment method remains controversial. The present study was conducted to evaluate effects and compare complications of two different methods used to treat comminuted patellar fractures.MethodsFrom March 2010 to August 2016, 102 cases of 34-C2 or 34-C3 comminuted patellar fractures were treated at our hospital, wherein patients received two different treatments: titanium cable tension band with cerclage method (group A) and intrafragmentary screws with X-shaped plating technique (group B). At follow-ups, articular step-off, range of motion (ROM), Lysholm scores, time of union, and complications were recorded and analyzed. Radiographic and clinical data as well as rate of complications were statistically analyzed.ResultsIn total, 87 patients were included in the final analysis (n = 47 in group A and n = 40 in group B). No significant differences were noted in terms of cost of implant, age, gender, rate of 34-C3 fractures, rate of layered inferior pole fractures, postoperative articular step-off and union time. At 2-year follow-up, average Lysholm scores, ROM and rate of complications were (89.0 ± 4.5), (122°±12°) and (27.7%) in group A and (90.2 ± 3.9), (124°±11°) and (17.5%) in group B, respectively, with no significant differences (p > 0.05). The mean time of surgery in group B was shorter than that in group A with significant difference (p < 0.05).ConclusionsTreatment using the intrafragmentary screws and plate method for amenable comminuted patellar fractures achieved similar complication rate and favorable functional outcomes at the 2-year follow-up, which was comparable to the titanium cable tension band with cerclage method. Thus, the intrafragmentary screws and plate method is effective, safe and convenient for 34-C2/C3 comminuted patellar fractures, especially appropriate for patients with layered fragments.     

Efficacy and safety of cold snare polypectomy for sessile serrated polyps ≥ 10 mm: A systematic review and meta-analysis

BackgroundCold snare polypectomy (CSP) is a promising technique for the removal of sessile serrated polyps (SSPs) ≥ 10 mm. However, the efficacy and safety of this technique remain undetermined.AimsWe aimed to comprehensively evaluate the efficacy and safety of CSP for SSPs ≥ 10 mm.MethodsPubMed, EMBASE, Web of Science and Cochrane Library were searched up to January 2021.ResultsA total of 10 studies consisting of 1727 SSPs (range, 10–40 mm) from 1021 patients were included. The overall rates of technical success, adverse events (AEs) and residual SSPs were 100%, 0.7% and 2.9%, respectively. Subgroup analysis showed that the rates of technical success and AEs were comparable between CSP and cold endoscopic mucosal resection (EMR) (99.9% vs. 100% and 1.3% vs. 0.5%, respectively), between the proximal and distal colon (100% vs. 99.9% and 0.3% vs. 0, respectively), and between polyps of 10–19 mm and ≥20 mm (99.8% vs. 100% and 0.9% vs. 0, respectively). However, subgroup analysis showed that the rate of residual SSPs was slightly lower in CSP compared with cold EMR (1.3% vs. 3.9%), as well as in polyps of 10–19 mm compared with those ≥20 mm (3.1% vs. 4.7%).ConclusionCSP was an effective and safe technique for removing SSPs ≥ 10 mm.     

Longistylin A,a natural stilbene isolated from the leaves of Cajanus cajan,exhibits significant anti-MRSA activity

Longistylin A (LLA) is an abundant stilbene isolated from the leaves of Cajanus cajan (L.) Millsp. However, the antibacterial effect of LLA is not yet understood. Therefore, in this study, a detailed investigation of the antibacterial effect of LLA, particularly against methicillin-resistant Staphylococcus aureus (MRSA), was conducted. In vitro, LLA exhibited strong antibacterial activity against MRSA with a minimum inhibitory concentration (MIC) of 1.56 µg/mL and displayed much more rapid bactericidal activity (3-log decrease in MRSA survival within 8 h) than vancomycin. A membrane-targeting experiment suggested that the antibacterial activity of LLA is associated with perturbation of the bacterial membrane potential and increased membrane permeability. Notably, LLA had relatively weak cytotoxicity to murine macrophages [50% cytotoxic concentration (CC₅₀) = 8.61 ± 0.57 µg/mL]. In vivo, topical treatment of a skin injury with LLA improved wound healing and closure in an MRSA-infected wound healing mouse model. After 3 days treatment, LLA decreased MRSA bacterial counts in the wounded region, reduced the accumulation of immune cells at the injury site, and alleviated induction of the inflammatory cytokines tumour necrosis factor-alpha (180.74 ± 10.78 pg/mL vs. 606.57 ± 68.99 pg/mL) and interleukin-6 (87.25 ± 10.19 pg/mL vs. 280.58 ± 42.27 pg/mL) in serum.