Precisely segmented lung fields restrict the region-of-interest from which radiological patterns are searched, and is thus an indispensable prerequisite step in any chest radiographic CADx system. Recently, a number of deep learning-based approaches have been proposed to implement this step. However, deep learning has its own limitations and cannot be used in resource-constrained settings. Medical systems generally have limited RAM, computational power, storage, and no GPUs. They are thus not always suited for running deep learning-based models. Shallow learning-based models with appropriately selected features give comparable performance but with modest resources. The present paper thus proposes a shallow learning-based method that makes use of 40 radiomic features to segment lung fields from chest radiographs. A distance regularized level set evolution (DRLSE) method along with other post-processing steps are used to refine its output. The proposed method is trained and tested using publicly available JSRT dataset. The testing results indicate that the performance of the proposed method is comparable to the state-of-the-art deep learning-based lung field segmentation (LFS) methods and better than other LFS methods.
Dataset ; Learning ; Lung ; Methods ; Radiography, Thoracic ; Running ; Thorax

INTRODUCTIONRheumatoid arthritis (RA) patients taking disease-modifying antirheumatic drugs (DMARDs) may experience treatment failure due to adverse effects or a lack of efficacy/resistance. The purpose of this study was to evaluate the prescription patterns, the incidence and reasons for failure, and the time to treatment failure of DMARDs in RA patients.

METHODSThe medical records of patients visiting the Rheumatology Clinic were scrutinised retrospectively in order to extract the relevant data, including demographics, clinical and laboratory investigations and drug usage, for analysis.

RESULTSMore than 60% of the 474 eligible patients were started on a combination of DMARDs. Hydroxychloroquine (HCQ) (79.7%) and methotrexate (MTX) (55.6%) were the most common DMARDs prescribed initially. There was a significant difference in survival times among the various treatment groups (p ≤ 0.001). Adverse effect was the main reason for treatment failure of sulfasalazine (SSZ) (88.9%) and MTX (75%), while addition or substitution DMARDs was more common for those taking HCQ (72.2%). Adverse event was reported as the most significant predictor of treatment failure. The most commonly reported adverse effects were bone marrow suppression and hepatotoxicity.

CONCLUSIONA combination of DMARDs was used to initiate therapy in more than 60% of RA patients, with HCQ and MTX being prescribed most frequently. Adverse effects accounted mainly for treatment failures with MTX and SSZ, while lack of efficacy was responsible for major treatment failures with HCQ.

Adult ; Antirheumatic Agents ; adverse effects ; therapeutic use ; Arthritis, Rheumatoid ; drug therapy ; Drug Therapy, Combination ; Female ; Humans ; Kaplan-Meier Estimate ; Male ; Middle Aged ; Retrospective Studies ; Treatment Failure