NuCLS: A scalable crowdsourcing approach and dataset for nucleus classification and segmentation in breast cancer

Background

Deep learning enables accurate high-resolution mapping of cells and tissue structures that can serve as the foundation of interpretable machine-learning models for computational pathology. However, generating adequate labels for these structures is a critical barrier, given the time and effort required from pathologists.

Results

This article describes a novel collaborative framework for engaging crowds of medical students and pathologists to produce quality labels for cell nuclei. We used this approach to produce the NuCLS dataset, containing >220,000 annotations of cell nuclei in breast cancers. This builds on prior work labeling tissue regions to produce an integrated tissue region- and cell-level annotation dataset for training that is the largest such resource for multi-scale analysis of breast cancer histology. This article presents data and analysis results for single and multi-rater annotations from both non-experts and pathologists. We present a novel workflow that uses algorithmic suggestions to collect accurate segmentation data without the need for laborious manual tracing of nuclei. Our results indicate that even noisy algorithmic suggestions do not adversely affect pathologist accuracy and can help non-experts improve annotation quality. We also present a new approach for inferring truth from multiple raters and show that non-experts can produce accurate annotations for visually distinctive classes.

Conclusions

This study is the most extensive systematic exploration of the large-scale use of wisdom-of-the-crowd approaches to generate data for computational pathology applications.

Serum KL-6 as predictive and prognostic marker of interstitial lung disease in childhood connective tissue diseases: a pilot study

This study was aimed to evaluate serum KL-6 levels to determine if this marker can be used for diagnosing and assessing severity of interstitial lung disease (ILD) in children with connective tissue disorders. In total, 40 patients [18 patients with juvenile systemic lupus erythematosus (JSLE), 10 patients with juvenile idiopathic arthritis (JIA), 8 patients with juvenile mixed connective tissue disease (JMCTD), 3 patients with juvenile systemic sclerosis (JSSc), and 1 patient with juvenile dermatomyositis (JDM)] and 20 healthy controls were included in this study. Age, sex, and duration of CTD and ILD (if any) were recorded. Blood samples from all the patients and controls were examined by ELISA. 20 of the 40 patients with CTD (50%) had ILD, 12 were mild and 8 were severe as assessed by spirometry. The median serum KL-6 level was 102.7 U/mL (76.1-180.8) in the CTD with severe ILD group, 72.2 U/mL (58.4- 100.5) in the CTD with mild ILD group, 56.7 U/mL (35.8-68.5) in the CTD without ILD group, and 52.3 U/mL (32.8-62.4) in the control group. KL-6 levels were significantly higher in the CTD with ILD (p<0.05), at a cutoff of 63.4 U/ml identified by ROC curve, serum KL-6 showed a sensitivity of 95.2% and specificity of 89.7%. KL-6 is a valuable biomarker for diagnostic purposes and to detect severity in ILD in childhood CTD.

Impact of ultrasonography detected quadriceps calcific tendinopathy on pain and function in patients with primary knee osteoarthritis

Calcific tendinopathy is most commonly seen around the shoulder joint. Only a few cases of quadriceps calcific tendinopathy (QCT) were reported. This study compares pain, function, clinical examination results, and ultrasonographic findings among primary knee osteoarthritis (KOA) patients with or without ultrasonography-detected QCT. A cross-sectional study was conducted on 214 patients with knee OA. Ultrasonography (US) of knee joints was performed according to the EULAR guidelines. Kellgren-Lawrence radiographic grading was used to score OA. Pain and functional status were assessed using the visual analog scale (VAS), the Health Assessment Questionnaire-II (HAQ-II), and the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). QCT was detected in 50 out of 428 knees (11.6%), i.e. in 46 out of 214 patients (21.49%). Most cases of QCT were detected in the following sites: 36 in the vastus lateralis (72%), 10 in the vastus intermedius (20%), and only 4 in the vastus medialis (8%). QCT was found mainly in advanced KOA stages: 44 cases of QCT were found in patients with grade 4 KOA and 6 cases in grade 3 KOA. The presence of QCT showed a statistically significant association (p<0.05) with VAS, HAQ-II, WOMAC subscales, synovitis, and effusion detected by US. In knees with ultrasound-detected QCT, ultrasonographic features of CPPD were found in 31 knees (62%). QCT was found in cases with advanced KOA and mainly with ultrasonographic findings of CPPD disease. QCT could be considered an independent poor prognostic finding regarding pain, functional activity, and response to NSAIDs.

Efficacy and Safety of Musculoskeletal Ultrasound Guided Aspiration and Intra-Lesional Corticosteroids Injection of Ruptured Baker's Cyst: A Retrospective Observational Study

Objective:

The aim of the work was to demonstrate the effectiveness and safety of ultrasonographic guided aspiration performed with corticosteroid injection intra-lesional for ruptured Baker cysts (BCs).

Methods:

Single-center retrospective study that included 42 patients with knee joint disorder associated with ruptured BCs were treated by ultrasonographic guided aspiration of fluid from the cyst and different points from the calf then intra-lesional injection of corticosteroids once or twice, 1 week apart. Follow up were done weekly until complete resolution of symptoms. Visual analog scale (VAS) and Rauschning-Lindgren and Lysholm Knee Scoring Scales (RLC) were used for assessment.

Results:

Clinical parameters (VAS and RLC) improved significantly in all patients at both post injection evaluation visits (1 week and 12 weeks). Ultrasonographic features improved significantly with complete disappearance of free fluid in the calf in 35 (83.3%) cases 1 week after the injection, and in 41 (97.6%) after 12 weeks. As regards BCs only 4 (9.5%) cases showed complete disappearance after 1 week and there was recurrent BCs in 38 (90.5%) cases which required reaspiration. While after 12 weeks, BCs were completely disappeared in 23 (54.8%) cases, most of the relapsed BCs were complex BCs. No side effects were reported in all cases.

Conclusion:

Ultrasonographic guided aspiration followed by injection of corticosteroids intra-lesional is an efficient and safe method for managing ruptured BCs.