We present CERES (Calibrated Early-warning and Risk Estimation System), an automated probabilistic forecasting system for acute food insecurity. CERES generates 90-day ahead probability estimates of IPC Phase 3+ (Crisis), Phase 4+ (Emergency), and Phase 5 (Famine) conditions for 43 high-risk countries globally, updated weekly. The system fuses six data streams, precipitation anomalies (CHIRPS), vegetation indices (MODIS NDVI), conflict events (ACLED), IPC classifications, food consumption scores (WFP), and cereal price indices (FAO/WFP) - through a logistic scoring model with author-specified initial coefficients and parametric input-perturbation intervals (n=2,000 draws). In historical back-validation against four IPC Phase 4-5 events selected for data completeness, CERES assigned TIER-1 classification in all four cases; these are in-sample sanity checks only, not prospective performance claims. All prospective predictions are timestamped, cryptographically identified, and archived for public verification against IPC outcome data at the T+90 horizon. To the author's knowledge, CERES is the first famine early warning system that is simultaneously: (1) probabilistic, (2) open-access, (3) continuously running, (4) machine-readable at prediction level, and (5) committed to public prospective verification of every prediction made.
Jillian E. Beveridge, Madalyn Hague, Meggin Q. Costa
et al.
Background: Knee stability can be conferred passively by ligaments and menisci and actively by the neuromuscular system. We sought to determine the relationship between passive tibiofemoral alignment and dynamic constraint in patients undergoing anterior cruciate ligament (ACL) reconstruction (ACLR) and matched control participants who have been followed for more than a decade. Purpose/Hypothesis: It was hypothesized that (1) anterior tibial position would be greater in the surgical knee compared to the contralateral knee and when compared to knees of control participants, and (2) the surgical limb differences would be greater in the dynamic state during a 1-leg hop-for-distance landing task. Study Design: Controlled laboratory study. Methods: A total of 21 participants were recruited from a recently completed longitudinal clinical trial (NCT00434837): 10 patients who had undergone ACLR 10 to 15 years earlier and 11 matched control participants without knee injury. The 3-dimensional (3D) tibiofemoral position was extracted from each participant's computed tomography images as a measure of passive alignment. Dynamic 3D knee kinematics were recorded using biplane videoradiography during the landing of a 1-leg hop-for-distance activity. Side-to-side differences in knee kinematics between limbs were used as a measure of dynamic constraint. Peak anterior tibial position was the primary outcome measure, and peak anterior tibial position as a function of flexion angle was the secondary outcome measure. Results: The passive tibial position of patients with ACLR was 7.5 ± 2.3 mm more anterior compared to that of uninjured participants and 3.1 ± 1.1 mm more anterior than their contralateral limb ( P < .05). The mean peak dynamic anterior position was not different between surgical and contralateral limbs in ACLR patients ( P = .83). When anterior position was explored as a function of flexion angle, peak anterior tibial position was up to 10.3 mm greater in the ACLR surgical limbs ( P = .01) and 7.5 mm in the contralateral limbs ( P = .001) compared to the limbs of control participants. Conclusion: Passive alignment is abnormal long after ACLR, whereas side-to-side dynamic constraint is largely restored, but with a persistent bias toward greater anterior tibial position that is present bilaterally. Clinical Relevance: Compared with similar studies at earlier postoperative time points, the results at long-term follow-up suggest that ACL graft function deteriorates with time, which can be compensated for to some degree by the neuromuscular system.
Mathilde Labouret, Inès Elhani, Sébastien Cavelot
et al.
Abstract Background Periodic fever, aphthous stomatitis, pharyngitis and cervical adenitis (PFAPA) syndrome is the most common cause of autoinflammatory periodic fever in children. It is generally considered to be a self-limiting condition that resolves spontaneously over time. Objectives To evaluate age and delay to recovery of patients with PFAPA syndrome. Methods We retrospectively reviewed the medical records of patients diagnosed with PFAPA syndrome at the Versailles Hospital (Paris, France) and included in the Juvenile Inflammatory Rheumatism (JIR) cohort between 2016 and February 2023. Recovery was defined as the absence of any febrile PFAPA episode in the past year. Patients with either no reported febrile episode or insufficient information on fever status over the last 12 months were contacted by telephone. Results 209 patients with PFAPA syndrome were included. Overall, 56 (27%) patients experienced resolution of periodic fever, 119 (57%) were still active and 34 (16%) patients were lost to follow-up. Among recovered patients, the median duration of symptoms was 5.43 years (Q1-Q3: 2.97–8.65) and the median age at last febrile episode was 8.34 years (Q1-Q3: 5.44–10.24). Of the 119 patients with persistent fever, 10 patients were initially declared cured but relapsed. Conclusion In patients whose fever resolved, most experienced their last febrile episode before adolescence. The identification of relapses after at least 12 months without a febrile episode raises questions about the definition of recovery.
Pediatrics, Diseases of the musculoskeletal system
Abstract Background Rheumatoid arthritis is a chronic, inflammatory, and symmetrical peripheral polyarthritis often associated with extra-articular manifestations, that end in marked functional impairment. Chemokines, such as monocyte chemotactic protein-1, are not only potential therapeutic targets but also play a crucial role in leukocyte migration within chronic inflammatory diseases. This migration contributes to synovitis and ultimately plays a critical role in the pathogenesis of rheumatoid arthritis. The purpose of this study was to evaluate monocyte chemotactic factor-1 serum levels and its association with RA disease activity score 28. This cross-sectional study included 306 patients aged 18–80 years. Clinical arthritic activity was assessed using swollen joint count, tender joint count, and disease activity score 28, while monocyte chemotactic protein-1, erythrocyte sedimentation rate, or C-reactive protein were used as laboratory biomarkers. Results The mean age of the patients was 53.7 ± 13.6 years, with a female predominance (191/306, 63%). Monocyte chemotactic protein-1correlated with clinical and radiographic parameters of disease activity & progression, whereas C-reactive protein and erythrocyte sedimentation rate correlated with all clinical parameters except tender joint count. Disease activity score 28 monocyte chemotactic protein-1 showed a significant correlation with Disease Activity Score 28 C-reactive protein (r = 0.678) and Disease Activity Score 28 erythrocyte sedimentation rate (r = 0.311) after one year. Disease activity score 28 monocyte chemotactic protein-1 showed a highly significant association with predictive progression (AUC = 0.926). Conclusion The findings of this study suggest that Disease Activity Score 28 and monocyte chemotactic protein-1 may serve as reliable clinical indicators to assess rheumatoid arthritis disease activity and monitor its progression.
Asymptomatic hyperuricemia (AH) and gout are characterized by the presence of elevated uric acid (UA) levels. It is not known whether there are differences between these conditions, beyond the acute attacks of arthritis unique to gout.The aim – to identify differences in the frequency of concomitant diseases, metabolic disorders and dietary habits in patients with gout and asymptomatic hyperuricemia.Material and methods. A single-stage observational case-control study included 202 people: 101 patients each with AH and gout, matched by age and gender. The examination included collection of anamnesis and medical documentation data on the presence of cardiovascular diseases, type 2 diabetes mellitus (T2DM), nephrolithiasis; inspection and measurement of anthropometric data. The intake of medications was recorded. A survey was conducted regarding the frequency of consumption of meat, seafood and alcohol. Blood levels of glucose, sUA, alanine aminotransferase (ALT), aspartate aminotransferase (AST), gamma-glutamyltransferase (GGT), alkaline phosphatase (ALP), creatinine, cholesterol, C-reactive protein (CRP), and ESR according to Westergren were determined. GFR was calculated using the CKD-EPI formula. All patients underwent ultrasound examination of the knee joints to determine signs of synovitis and deposition of monosodium urate (MSU) crystals.Result. In patients with gout, arterial hypertension (86 (85.1%) vs 53 (52.4%) patients, respectively; p<0.05), T2DM (12 (11.9%) vs 4 (4.0%) patients, respectively; p<0.05) were detected more often than in patients with AH. In the gout group, there were more patients consuming alcohol ≥1 time per week (p=0.02), while there were no differences in the frequency of consumption of meat and seafood. Among patients with gout, there were more participants with GFR<60 ml/min/1.73 m2. In patients with gout, there was a significant direct correlation between the levels of UA and ALT, creatinine, CRP, and an inverse correlation between serum UA and GFR. Ultrasound of the knee joints showed a significantly more frequent deposition of MSU crystals (46 (45.5%) vs 17 (16.8%) patients, respectively; p<0.05) and the presence of synovitis (37 (36.6%) vs 14 (13.8%) patients, respectively; p<0.05) in the gout group.Conclusions. Despite the apparent commonality of gout and AH, they have a number of differences. In gout, arterial hypertension and T2DM are more often detected. Also, in patients with gout, there is a significant direct correlation between the levels of sUA and ALT, creatinine, CRP, while GFR is inversely correlated with the level of serum sUA. Among patients with AH, such correlations were not found. Gout also predicts a statistically more frequent detection of MSU crystal deposits (45.5% vs 31.1% of patients). The intake of meat and fish products did not differ in both groups.
Jerin Jeevo, Ashel Daphny D’Souza, Bibin Selvin
et al.
Introduction:
Bucket handle meniscus tears (BHMTs) represent a specific pattern of vertical tears wherein the displaced segment of the meniscus lodges into the intercondylar notch. These injuries often present with clinical symptoms including knee pain, intermittent locking, joint instability, swelling, and reduced range of motion. Bucket-handle meniscal tears are frequently observed in conjunction with anterior cruciate ligament (ACL) injuries, with reported incidences varying between 11% and 48%. Meniscus repair aims to alleviate symptoms and restore normal knee joint biomechanics, all while maintaining the integrity of the native meniscus. To the best of our knowledge, this case report is the first to document the fixation of a triple bucket handle tear of the medial meniscus, with clinical results and a 1-year post-operative assessment.
Case Report:
A woman in her early forties presented with a 10-year history of recurrent knee pain, swelling, and mechanical symptoms, worsened by a recent fall. Clinical evaluation revealed signs of ACL deficiency and medial meniscal injury. Imaging confirmed a complex medial meniscus tear and a near-complete ACL tear, with normal knee alignment on radiographs and scanogram. Diagnostic arthroscopy revealed triple BHMT with complete ACL tear. She underwent ACL reconstruction (ACLR) with peroneus longus graft, triple bucket handle meniscus repair with all-inside, inside out and outside in technique, and lateral extra-articular tenodesis.
Conclusion:
Chronic triple bucket-handle meniscal tears present a complex surgical challenge. However, this case highlights that accurate anatomical reduction combined with stable fixation can lead to favorable post-operative outcomes, including improved knee function and enhanced quality of life. In addition, performing meniscal repair alongside ACLR increases the likelihood of successful healing and optimal functional recovery.
Orthopedic surgery, Diseases of the musculoskeletal system
Abstract Purpose (1) To figure out a simple and effective indicator that could assist in the assessment of bone mineral density (BMD) based on big data and (2) to verify its predictive value for low BMD among patients with degenerative lumbar scoliosis (DLS). Methods A total of 6,167 participants from the National Health and Nutrition Examination Survey (NHANES) database (2009–2010, 2013–2014, 2017–2018) and 166 patients who were diagnosed with DLS and hospitalized in our center between June 2019 and April 2023 were enrolled in the study. Cases were divided into two groups based on whether the T-score was below − 1. The Osteopenia Index (OI) was defined as the ratio of alkaline phosphatase (ALP) (IU/L) to creatinine (mg/dL). Multivariable logistic regression was performed to identify risk factors, while restricted cubic spline (RCS) analysis was applied to explore the potential non-linear relationship. Patients with DLS from our center were used to validate the diagnostic value of OI through receiver operating characteristic curve (ROC) analysis. Results Participants from NHANES were divided into three subgroups according to the tertiles of OI: subgroup 1 (OI < 68), subgroup 2 (68 ≤ OI < 93), and subgroup 3 (OI ≥ 93). A multivariable logistic regression model adjusted for age, gender, and race revealed that elevated OI was a significant risk factor for osteopenia (subgroup 2 vs. subgroup 1: odds ratio [OR] = 1.473, 95% confidence interval [CI] = 1.173–1.849; subgroup 3 vs. subgroup 1: OR = 2.092, 95% CI = 1.566–2.796). Moreover, the RCS plot showed that the risk of osteopenia gradually increased with the elevation of OI. In patients with DLS, OI showed a significant correlation with lumbar T-score (ρ = − 0.392) and HU value (ρ = − 0.373) (both P < 0.001). ROC analysis revealed that the area under the curve of OI was 0.757, and the cut-off value was set at 124.73 according to the Youden index. A nomogram based on a logistic regression model adjusted for age, gender, and blood urea nitrogen was plotted, with a McFadden R² of 0.212. Conclusion OI correlated significantly with lumbar BMD and HU value. Logistic regression and RCS analysis demonstrated that OI could serve as a simple, economical, and effective screening tool for low lumbar BMD in DLS patients, with its predictive ability further enhanced when adjusted for age and gender.
Orthopedic surgery, Diseases of the musculoskeletal system
Background: While the inclination of the humeral component in reverse total shoulder arthroplasty (rTSA) has been extensively studied, less attention has been given to the parameters of version and torsion. These parameters, which influence outcomes in rTSA, warrant closer examination. This study aims to analyze the designs of humeral stems in rTSA, focusing on their ability to independently adjust inclination (coronal plane), torsion (axial plane), and version (sagittal plane). We hypothesize that while most designs allow for inclination and torsion adjustments, independent version adjustment is rare and may offer unique biomechanical implications.
Purpose: To systematically review currently available rTSA humeral stem designs and assess their capacity for independent adjustment of inclination, torsion, and version based on manufacturer specifications and design features.
Methods: A comprehensive review of commercially available rTSA humeral stem designs was conducted. Humeral stems from various manufacturers were analyzed for their capacity to allow independent adjustment of inclination, torsion, and version. The analysis relied on technical specifications and data provided by manufacturers, supplemented by a critical review of design features.
Results: The review showed that while a few stem designs offer inclination adjustment up to 12.5° via angled liners, there is one implant allowing inclination adjustment within the same stem design, through a modular metaphyseal cup, permitting adjustment from 135° to 155°. Torsion was found to be freely adjustable across all designs, independent of the specific stem configuration. While all systems provide a fixed stem version of 0°, one system offered adjustability of humeral version (0° and 20°) through a modular metaphyseal component.
Conclusions: While torsion can be freely adjusted independent of stem design, the ability to modify inclination is limited to certain systems, mostly relying on angled liners for this purpose. Independent adjustability in the sagittal plane (version) remains rare, with only one system offering this feature through a modular metaphysis. The potential clinical implications of adjustable humeral version in rTSA are yet to be investigated.
Our research is motivated by the urgent global issue of a large population affected by retinal diseases, which are evenly distributed but underserved by specialized medical expertise, particularly in non-urban areas. Our primary objective is to bridge this healthcare gap by developing a comprehensive diagnostic system capable of accurately predicting retinal diseases solely from fundus images. However, we faced significant challenges due to limited, diverse datasets and imbalanced class distributions. To overcome these issues, we have devised innovative strategies. Our research introduces novel approaches, utilizing hybrid models combining deeper Convolutional Neural Networks (CNNs), Transformer encoders, and ensemble architectures sequentially and in parallel to classify retinal fundus images into 20 disease labels. Our overarching goal is to assess these advanced models' potential in practical applications, with a strong focus on enhancing retinal disease diagnosis accuracy across a broader spectrum of conditions. Importantly, our efforts have surpassed baseline model results, with the C-Tran ensemble model emerging as the leader, achieving a remarkable model score of 0.9166, surpassing the baseline score of 0.9. Additionally, experiments with the IEViT model showcased equally promising outcomes with improved computational efficiency. We've also demonstrated the effectiveness of dynamic patch extraction and the integration of domain knowledge in computer vision tasks. In summary, our research strives to contribute significantly to retinal disease diagnosis, addressing the critical need for accessible healthcare solutions in underserved regions while aiming for comprehensive and accurate disease prediction.
Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods are often suboptimal, creating the misconception that effective removal requires large perturbations or powerful adversaries. To bridge the gap, we first formalize the system model for LLM watermark, and characterize two realistic threat models constrained on limited access to the watermark detector. We then analyze how different types of perturbation vary in their attack range, i.e., the number of tokens they can affect with a single edit. We observe that character-level perturbations (e.g., typos, swaps, deletions, homoglyphs) can influence multiple tokens simultaneously by disrupting the tokenization process. We demonstrate that character-level perturbations are significantly more effective for watermark removal under the most restrictive threat model. We further propose guided removal attacks based on the Genetic Algorithm (GA) that uses a reference detector for optimization. Under a practical threat model with limited black-box queries to the watermark detector, our method demonstrates strong removal performance. Experiments confirm the superiority of character-level perturbations and the effectiveness of the GA in removing watermarks under realistic constraints. Additionally, we argue there is an adversarial dilemma when considering potential defenses: any fixed defense can be bypassed by a suitable perturbation strategy. Motivated by this principle, we propose an adaptive compound character-level attack. Experimental results show that this approach can effectively defeat the defenses. Our findings highlight significant vulnerabilities in existing LLM watermark schemes and underline the urgency for the development of new robust mechanisms.
Tomato crop health plays a critical role in ensuring agricultural productivity and food security. Timely and accurate detection of diseases affecting tomato plants is vital for effective disease management. In this study, we propose a deep learning-based approach for Tomato Leaf Disease Detection using two well-established convolutional neural networks (CNNs), namely VGG19 and Inception v3. The experiment is conducted on the Tomato Villages Dataset, encompassing images of both healthy tomato leaves and leaves afflicted by various diseases. The VGG19 model is augmented with fully connected layers, while the Inception v3 model is modified to incorporate a global average pooling layer and a dense classification layer. Both models are trained on the prepared dataset, and their performances are evaluated on a separate test set. This research employs VGG19 and Inception v3 models on the Tomato Villages dataset (4525 images) for tomato leaf disease detection. The models' accuracy of 93.93% with dropout layers demonstrates their usefulness for crop health monitoring. The paper suggests a deep learning-based strategy that includes normalization, resizing, dataset preparation, and unique model architectures. During training, VGG19 and Inception v3 serve as feature extractors, with possible data augmentation and fine-tuning. Metrics like accuracy, precision, recall, and F1 score are obtained through evaluation on a test set and offer important insights into the strengths and shortcomings of the model. The method has the potential for practical use in precision agriculture and could help tomato crops prevent illness early on.
Despite the diversity and volume of brain data acquired and advanced AI-based algorithms to analyze them, brain features are rarely used in clinics for diagnosis and prognosis. Here we argue that the field continues to rely on cohort comparisons to seek biomarkers, despite the well-established degeneracy of brain features. Using a thought experiment (Brain Swap), we show that more data and more powerful algorithms will not be sufficient to identify biomarkers of brain diseases. We argue that instead of comparing patient versus healthy controls using single data type, we should use multimodal (e.g. brain activity, neurotransmitters, neuromodulators, brain imaging) and longitudinal brain data to guide the grouping before defining multidimensional biomarkers for brain diseases.
Michael Schirmer, Lukas Kampik, Johannes D. Pallua
Recent developments in digital health technologies are overwhelming, and their use in routine work is still difficult to anticipate. This narrative review summarizes the concept of consecutive cohorts in the literature, together with local research experiences in consecutive rheumatic outpatients. Digital health techniques have to reflect the clinicians’ needs, support real-life care of patients, and allow for the specific assessment of quality parameters fulfilling the Donabedian aspect of qualified health care, using quality indicators to improve health care and research. Rapidly growing observational cohorts will perform best to provide follow-up data as the basis for further development of healthcare approaches for rheumatic patients. The challenges of a selection bias, patients with limited disease expression, and chances of early detection of patients with rare diseases are addressed. For research purposes, sequential analyses with growing cohort size, comparative cross-sectional studies with sequential hypothesis testing and other prognostic, diagnostic, and therapeutic aspects of patient management can be performed. With the support of new technologies, young clinicians can easily approach such clinical topics, and learn about clinical data analyses. The use of quality standards as proposed in international recommendations for diagnostic issues and classification criteria, management recommendations, monitoring, and training issues can be supported by digital technologies. In conclusion, collaborative projects allow detailed clinical analyses of large cohorts, but local initiatives can prepare these co-operations, provide first local logistics and research experiences, and teach clinicians how to perform clinical research. Digital health technologies will strongly support these local initiatives.
María Varela-García, Carlos Torrijos-Pulpón, Laura Pino-López
et al.
Abstract Purpose Legg Calve Perthes disease (LCPD) is a paediatric hip disorder caused by ischemia of the femoral epiphysis, causing femoral head deformity when untreated. This study aims to determine if previously validated pelvic obliquity radiographic parameters, used for assessing acetabular retroversion in developmental dysplasia of the hip, are applicable to patients with LCPD and its prognostic value. Method A retrospective study of patients with Legg Calve Perthes disease was carried out, analysing 4 pelvic parameters: Ilioischial Angle, Obturator Index, Sharp’s Angle and Acetabular Depth-Width Ratio (ADR). The differences between healthy and affected hips were studied, and subsequently, it was assessed whether these parameters have prognostic value in the disease outcome. Results Statistically significant differences have been obtained in the ilioischial angle, obturator index and ADR, between the affected and healthy hip. However, only the Acetabular Depth-Width Ratio showed predictive value for the disease outcome. Conclusion Although this study revealed differences in pelvic parameters between healthy and diseased hips, with only the ADR showing statistical significance in the disease's evolution and prognosis, further studies with larger sample sizes are necessary.
Yumeng Yang, Ashley Gilliam, Ethan B Ludmir
et al.
Clinical trials are pivotal in medical research, and NLP can enhance their success, with application in recruitment. This study aims to evaluate the generalizability of eligibility classification across a broad spectrum of clinical trials. Starting with phase 3 cancer trials, annotated with seven eligibility exclusions, then to determine how well models can generalize to non-cancer and non-phase 3 trials. To assess this, we have compiled eligibility criteria data for five types of trials: (1) additional phase 3 cancer trials, (2) phase 1 and 2 cancer trials, (3) heart disease trials, (4) type 2 diabetes trials, and (5) observational trials for any disease, comprising 2,490 annotated eligibility criteria across seven exclusion types. Our results show that models trained on the extensive cancer dataset can effectively handle criteria commonly found in non-cancer trials, such as autoimmune diseases. However, they struggle with criteria disproportionately prevalent in cancer trials, like prior malignancy. We also experiment with few-shot learning, demonstrating that a limited number of disease-specific examples can partially overcome this performance gap. We are releasing this new dataset of annotated eligibility statements to promote the development of cross-disease generalization in clinical trial classification.
Image classification usually requires connectivity and access to the cloud which is often limited in many parts of the world, including hard to reach rural areas. TinyML aims to solve this problem by hosting AI assistants on constrained devices, eliminating connectivity issues by processing data within the device itself, without internet or cloud access. This pilot study explores the use of tinyML to provide healthcare support with low spec devices in low connectivity environments, focusing on diagnosis of skin diseases and the ethical use of AI assistants in a healthcare setting. To investigate this, 10,000 images of skin lesions were used to train a model for classifying visually detectable diseases (VDDs). The model weights were then offloaded to a Raspberry Pi with a webcam attached, to be used for the classification of skin lesions without internet access. It was found that the developed prototype achieved a test accuracy of 78% and a test loss of 1.08.
Effective epidemic forecasting is critical for public health strategies and efficient medical resource allocation, especially in the face of rapidly spreading infectious diseases. However, existing deep-learning methods often overlook the dynamic nature of epidemics and fail to account for the specific mechanisms of disease transmission. In response to these challenges, we introduce an innovative end-to-end framework called Epidemiology-Aware Neural ODE with Continuous Disease Transmission Graph (EARTH) in this paper. To learn continuous and regional disease transmission patterns, we first propose EANO, which seamlessly integrates the neural ODE approach with the epidemic mechanism, considering the complex spatial spread process during epidemic evolution. Additionally, we introduce GLTG to model global infection trends and leverage these signals to guide local transmission dynamically. To accommodate both the global coherence of epidemic trends and the local nuances of epidemic transmission patterns, we build a cross-attention approach to fuse the most meaningful information for forecasting. Through the smooth synergy of both components, EARTH offers a more robust and flexible approach to understanding and predicting the spread of infectious diseases. Extensive experiments show EARTH superior performance in forecasting real-world epidemics compared to state-of-the-art methods. The code will be available at https://github.com/Emory-Melody/EpiLearn.
This paper studies Clinical Intelligent Decision Support Systems (CIDSSs) for lung cancer segmentation, which are based on deep neural nets. A new interactive CIDSS is proposed and compared with previous approaches. Addition-ally, the purpose uncertainty problem in building interactive systems is discussed, and criteria for measuring both quality and amount of user feedback are proposed. In order to automate system evaluation, a new algorithm was used to simulate expert feedback. The proposed interactive CIDSS outperforms previous approaches (both interactive and noninteractive) on the task of lung lesion segmentation. This ap-proach looks promising both in terms of quality and expert user experience. At the same time, this paper discusses a bunch of possible modifications that can be done to improve both evaluation criteria and proposed CIDSS in future works.
Calcium pyrophosphate deposition disease is known as crowned dens syndrome or peripheral arthritis, especially of knees, hips and shoulders. The disease course is asymptomatic, with acute or chronic disease activity related to osteoarthritis, especially in the elderly. Other risk factors are joint injury, osteoarthritis and metabolic conditions such as primary hyperparathyroidism, hemochromatosis, hypophosphatasia and hypomagnesemia. Genetic background should be considered before the age of 55 years. Only recently was the value of signs and symptoms weighted, allowing the introduction of classification criteria. Biomarkers include compensated polarized light microscopy findings, laboratory values and imaging. Imaging evidence refers to calcification of the fibrocartilage or hyaline cartilage. Chondrocalcinosis defined as such cartilage calcification is most commonly due to calcium pyrophosphate deposition disease. Calcification of the synovial membrane, joint capsule, or tendon should not be scored. Ultrasonography detects calcium pyrophosphate deposits with more than 80% sensitivity rates, which is superior to conventional radiography. In the future, dual-energy computerized tomography and Raman spectroscopy are promising new techniques to assess disease activity. Currently, the primary therapeutic goal is controlling inflammatory reactions and preventing further episodes. However, only hydroxychloroquine and magnesium carbonate have shown some efficacy and reduction of pain intensity so far. As patients report more significant unmet treatment needs than patients with gout, education is an essential issue of care. The new classification criteria will allow the validation of standardized outcome parameters with the definition of remission and low disease activity for developing treat-to-target strategies to perform well-designed interventional trials evaluating new treatment options and strategies.