Search results

Lung cancer is the leading cause of death worldwide. Physical and chemical agents such as tobacco smoke are the leading cause of various lung cancers. The intrinsic heterogeneity of normal lung tissue may be affected in different ways, giving rise to different types of lung cancers classified as either small‐cell lung cancer (SCLC) or non‐small cell lung cancer (NSCLC). Adenocarcinoma, a NSCLC, accounts for 40 percent of all lung cancer cases and the incidence is increasing worldwide, especially among women. The survival rate and prognosis is poorest for adenocarcinoma. Therefore, diagnosis at the earliest stage (Stage I, localized) is critical for increasing survival rates of those suffering from lung cancer. However, many factors affect early diagnosis including the variable natural growth of tumors plus technological and human factors associated with manipulation of tissue samples and interpretation of results. This article reviews potential problems associated with diagnosing lung cancer and considers future directions of diagnostic technology.

The purpose of this paper is to show an efficient method for the detection of signs of early lung cancer. Various image processing algorithms are presented for different types of lesions, and a scheme is proposed for the combination of results.

A computer aided detection (CAD) scheme was developed for detection of lung cancer. It enables different lesion enhancer algorithms, sensitive to specific lesion subtypes, to be used simultaneously. Three image processing algorithms are presented for the detection of small nodules, large ones, and infiltrated areas. The outputs are merged, the false detection rate is reduced with four separated support vector machine (SVM) classifiers. The classifier input comes from a feature selection algorithm selecting from various textural and geometric features. A total of 761 images were used for testing, including the database of the Japanese Society of Radiological Technology (JSRT).

The fusion of algorithms reduced false positives on average by 0.6 per image, while the sensitivity remained 80 per cent. On the JSRT database the system managed to find 60.2 per cent of lesions at an average of 2.0 false positives per image. The effect of using different result evaluation criteria was tested and a difference as high as 4 percentage points in sensitivity was measured. The system was compared to other published methods.

The study described in the paper proves the usefulness of lesion enhancement decomposition, while proposing a scheme for the fusion of algorithms. Furthermore, a new algorithm is introduced for the detection of infiltrated areas, possible signs of lung cancer, neglected by previous solutions.

The purpose of this study is to investigate and demonstrate the advancements achieved in the field of chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Typical convolutional neural networks (CNNs) are unable to capture both local and global contextual information effectively and apply a uniform operation to all pixels in an image. To address this, we propose an innovative approach that integrates a dynamic convolution operation at the encoder stage, improving image encoding quality and disease detection. In addition, a decoder based on the gated recurrent unit (GRU) is used for language modeling, and an attention network is incorporated to enhance consistency. This novel combination allows for improved feature extraction, mimicking the expertise of radiologists by selectively focusing on important areas and producing coherent captions with valuable clinical information.

In this study, we have presented a new report generation approach that utilizes dynamic convolution applied Resnet-101 (DyCNN) as an encoder (Verelst and Tuytelaars, 2019) and GRU as a decoder (Dey and Salemt, 2017; Pan et al., 2020), along with an attention network (see Figure 1). This integration innovatively extends the capabilities of image encoding and sequential caption generation, representing a shift from conventional CNN architectures. With its ability to dynamically adapt receptive fields, the DyCNN excels at capturing features of varying scales within the CXR images. This dynamic adaptability significantly enhances the granularity of feature extraction, enabling precise representation of localized abnormalities and structural intricacies. By incorporating this flexibility into the encoding process, our model can distil meaningful and contextually rich features from the radiographic data. While the attention mechanism enables the model to selectively focus on different regions of the image during caption generation. The attention mechanism enhances the report generation process by allowing the model to assign different importance weights to different regions of the image, mimicking human perception. In parallel, the GRU-based decoder adds a critical dimension to the process by ensuring a smooth, sequential generation of captions.

The findings of this study highlight the significant advancements achieved in chest X-ray image captioning through the utilization of dynamic convolutional encoder–decoder networks (DyCNN). Experiments conducted using the IU-Chest X-ray datasets showed that the proposed model outperformed other state-of-the-art approaches. The model achieved notable scores, including a BLEU_1 score of 0.591, a BLEU_2 score of 0.347, a BLEU_3 score of 0.277 and a BLEU_4 score of 0.155. These results highlight the efficiency and efficacy of the model in producing precise radiology reports, enhancing image interpretation and clinical decision-making.

This work is the first of its kind, which employs DyCNN as an encoder to extract features from CXR images. In addition, GRU as the decoder for language modeling was utilized and the attention mechanisms into the model architecture were incorporated.

The cardiomegaly can be determined by the cardiothoracic ratio (CTR) which can be measured in a chest x-ray image. It is calculated based on a relationship between a size of heart and a transverse dimension of chest. The cardiomegaly is identified when the ratio is larger than a cut-off threshold. This paper aims to propose a solution to calculate the ratio for classifying the cardiomegaly in chest x-ray images.

The proposed method begins with constructing lung and heart segmentation models based on U-Net architecture using the publicly available datasets with the groundtruth of heart and lung masks. The ratio is then calculated using the sizes of segmented lung and heart areas. In addition, Progressive Growing of GANs (PGAN) is adopted here for constructing the new dataset containing chest x-ray images of three classes including male normal, female normal and cardiomegaly classes. This dataset is then used for evaluating the proposed solution. Also, the proposed solution is used to evaluate the quality of chest x-ray images generated from PGAN.

In the experiments, the trained models are applied to segment regions of heart and lung in chest x-ray images on the self-collected dataset. The calculated CTR values are compared with the values that are manually measured by human experts. The average error is 3.08%. Then, the models are also applied to segment regions of heart and lung for the CTR calculation, on the dataset computed by PGAN. Then, the cardiomegaly is determined using various attempts of different cut-off threshold values. With the standard cut-off at 0.50, the proposed method achieves 94.61% accuracy, 88.31% sensitivity and 94.20% specificity.

The proposed solution is demonstrated to be robust across unseen datasets for the segmentation, CTR calculation and cardiomegaly classification, including the dataset generated from PGAN. The cut-off value can be adjusted to be lower than 0.50 for increasing the sensitivity. For example, the sensitivity of 97.04% can be achieved at the cut-off of 0.45. However, the specificity is decreased from 94.20% to 79.78%.

The purpose of this paper is to study the efficacy of a district tuberculosis (TB) co-ordinating team on health service performance for suspected TB patients in a district hospital in northeastern Thailand.

A comparison study of pre- and post-evaluations of TB system improvement was conducted in a district hospital in northeastern Thailand between October 2016 and June 2017. Data collection reviewed the record of suspected TB cases reported in the district hospital in the past nine months as a base line for describing the health service performance in term of received investigation for TB diagnosis. Participants from a TB clinic, district health office and health center set up a TB co-ordinating team to explore situations and systematic gaps. The TB co-ordinating team gave recommendations of health service performance for suspected TB patients over a nine-month period. Records of suspected TB cases health service performance were collected nine months after intervention. Data analysis by descriptive statistics and to test the effect of intervention was performed.

The records from 324 and 379 suspected TB cases reported in the hospital from the 9 months preceding and 9 months, respectively, after intervention were reviewed. A TB co-ordinating team was set up to improve the system and health service performance in terms of investigation for TB diagnosis. The results revealed that health service performance in terms of complete microscopy and investigation in both chest radiography and microscopy increased after intervention. When comparing between pre- and post-intervention, suspected cases received both chest radiography and microscopy in 176 cases and 283 cases, respectively (p-value=0.001). There were 27 cases diagnosed for smear positive TB in pre-intervention and 51 cases diagnosed in post-intervention (p-value=0.011). There were 21 cases pre- and 36 cases post-intervention that had referral documents from health center with no statistically significant difference.

The TB co-ordinating team had the role to improve health service performance for suspected TB cases to enroll in investigation process for increase TB diagnosis in district hospital.

Few case studies in the literature report on adult patients with intentional foreign body ingestion. Prisoners deliberately ingest foreign bodies, such as cylindrical alkaline batteries and razor blades, to achieve hospitalization or commit suicide. The purpose of this paper is to present a case of deliberate ingestion of batteries and razor blades by an inmate.

The authors present a case of an incarcerated man in Greece, who intentionally ingested three cylindrical alkaline batteries and three razor blades wrapped in aluminum foil.

The patient was treated conservatively with serial radiographs and was subsequently discharged without complication. This paper discusses the complications and examine the current guidelines available.

To best of authors’ knowledge, this is the first report of a simultaneous ingestion of batteries and razor blades.

This intensified case finding study aimed to evaluate the prevalence of tuberculosis (TB) disease among people with HIV entering the largest prison in Malaysia.

The study was conducted in Kajang prison, starting in July 2013 in the men’s prison and June 2015 in the women’s prison. Individuals tested positive for HIV infection, during the mandatory HIV testing at the prison entry, were consecutively recruited over five months at each prison. Consented participants were interviewed using a structured questionnaire and asked to submit two sputum samples that were assessed using GeneXpert MTB/RIF (Xpert) and culture, irrespective of clinical presentation. Factors associated with active TB (defined as a positive result on either Xpert or culture) were assessed using regression analyses.

Overall, 214 incarcerated people with HIV were recruited. Most were men (84.6%), Malaysians (84.1%) and people who inject drugs (67.8%). The mean age was 37.5 (SD 8.2) years, and median CD4 lymphocyte count was 376 cells/mL (IQR 232–526). Overall, 27 (12.6%) TB cases were identified, which was independently associated with scores of five or more on the World Health Organization clinical scoring system for prisons (ARR 2.90 [95% CI 1.48–5.68]).

Limited data exists about the prevalence of TB disease at prison entry, globally and none from Malaysia. The reported high prevalence of TB disease in the study adds an important and highly needed information to design comprehensive TB control programmes in prisons.

The COVID-19 pandemic has led to a huge loss of human life worldwide and presents an unprecedented challenge to public health, food systems and the world of work. Tens of millions of people are at risk of falling into extreme poverty due to loss of their carriers. Mainly, the people who work in public places are impacted due to this decease. The frontline warriors such as doctors, health workers, sweepers and policemen showed their effort to reduce the spreading of the virus. In this paper gives the detailed view of how the corona virus evaluated and how it spread from one person to another person and how we prevent this virus. The purpose of the paper, detailed about the diagnosis of the virus in the human body. There are some tests associated to know the presence of virus in our body; these are nose test, chest scan and CT scan of lungs.

Molecular analysis methods such as antibody or enzyme tests are used to assess whether the infection is present. The most common lancing techniques include using a cotton swab is in the back of the neck. Then hands over the sample to the doctor for examination. Polymerase chain reaction (PCR) is performed on the sample. This test screens for viral DNA. A CO19 PCR test can detect unique SARS-2 gene products. If one of these genes is ignored, it will return as an invalid result This test is useful only for patients who are already suffering from COVID-19. You cannot know if anyone has the infection, and they cannot say for sure whether they ever did. Serological tests are particularly useful for detecting cases of infection with mild or no symptom.

In this paper, the different tests provided to diagnosis the virus and the prevention measures to be taken to prevent the virus from spreading from one person to another are explained.

This work presents the original contribution and information of the COVID-19 pandemic.

The purpose of this paper is to provide a consolidated reference for the acute management of selected iatrogenic procedural injuries occurring in the emergency department (ED).

A literature search was performed utilizing PubMed, Scopus, Web of Science and Google Scholar for studies through March of 2017 investigating search terms “iatrogenic procedure complications,” “error management” and “procedure complications,” in addition to the search terms reflecting case reports involving the eight below listed procedure complications.

This may be particularly helpful to academic faculty who supervise physicians in training who present a higher risk to cause such injuries.

Emergent procedures performed in the ED present a higher risk for iatrogenic injury than in more controlled settings. Many physicians are taught error-avoidance rather than how to handle errors when learning procedures. There is currently very limited literature on the error management of iatrogenic procedure complications in the ED.