Research on Chest Disease Recognition Based on Deep Hierarchical Learning Algorithm

Chest X-ray has become one of the most common ways in diagnostic radiology exams, and this technology assists expert radiologists with finding the patients at potential risk of cardiopathy and lung diseases. However, it is still a challenge for expert radiologists to assess thousands of cases in a short period so that deep learning methods are introduced to tackle this problem. Since the diseases have correlations with each other and have hierarchical features, the traditional classification scheme could not achieve a good performance. In order to extract the correlation features among the diseases, some GCN-based models are introduced to combine the features extracted from the images to make prediction. This scheme can work well with the high quality of image features, so backbone with high computation cost plays a vital role in this scheme. However, a fast prediction in diagnostic radiology is also needed especially in case of emergency or region with low computation facilities, so we proposed an efficient convolutional neural network with GCN, which is named SGGCN, to meet the need of efficient computation and considerable accuracy. SGGCN used SGNet-101 as backbone, which is built by ShuffleGhost Block (Huang et al., 2021) to extract features with a low computation cost. In order to make sufficient usage of the information in GCN, a new GCN architecture is designed to combine information from different layers together in GCNM module so that we can utilize various hierarchical features and meanwhile make the GCN scheme faster. The experiment on CheXPert datasets illustrated that SGGCN achieves a considerable performance. Compared with GCN and ResNet-101 (He et al., 2015) backbone (test AUC 0.8080, parameters 4.7M and FLOPs 16.0B), the SGGCN achieves 0.7831 (−3.08%) test AUC with parameters 1.2M (−73.73%) and FLOPs 3.1B (−80.82%), where GCN with MobileNet (Sandler and Howard, 2018) backbone achieves 0.7531 (−6.79%) test AUC with parameters 0.5M (−88.46%) and FLOPs 0.66B (−95.88%).

Antibiotic resistance rate of the Methicillin Resistant Staphylococcus aureus isolated from a university affiliated hospital in North Cyprus

Background: Over the past 20 years, studies have indicated that the increasing spread of methicillinresistant Staphylococcus aureus (MRSA) demonstrates the need for adequate information about their epidemiology. This study was conducted in order to investigate the resistance rate of MRSA which were isolated from the Near East University (NEU) Hospital, North Cyprus. Methods: MRSA was isolated and identified by using selective media and the Phoenix BD 100 system (software version 6.01A) was used for antimicrobial susceptibility testing and identification. The antimicrobial susceptibility results were determined according to the Clinical and Laboratory Standarts Institute (CLSI) and the resistance rates of MRSA isolates to antibiotics were examined retrospectively. Results: The highest number of samples were from the departments of chest disease (24%) followed by dermatology (21.3%) and cardiology (18.7%). Out of 75 MRSA strains,; 29.7% from blood, 25.3% from wound, 14.7% from nasal swabs, 10.7% from aspiration fluids, 9.3% from sputum, 6.7% were from urine, 4.0% from IV catheters culture samples. All strains of MRSA were 94.7% sensitive to vancomycin and teicoplanin. Conclusions: The obtained results revealed that preventative measures should be implemented in order to minimize the bacterial resistance to antibiotics. Bangladesh Journal of Medical Science Vol. 21(1) 2022 Page : 101-104

Content Based Medical Image Retrieval for Accurate Disease Diagnosis

Introduction: Content Based Image Retrieval (CBIR) system is an innovative technology to retrieve images from various media types. One of the CBIR applications is Content Based Medical Image Retrieval (CBMIR). The image retrieval system retrieves the most similar images from the historical cases, and such systems can only support the physician's decision to diagnose a disease. To extract the useful features from the query image for linking similar types of images is the major challenge in the CBIR domain. The Convolution Neural Network (CNN) can overcome the drawbacks of traditional algorithms, dependent on the low-level feature extraction technique. Objective: The objective of the study is to develop a CNN model with a minimum number of convolution layers and to get the maximum possible accuracy for the CBMIR system. The minimum number of convolution layers reduces the number of mathematical operations and the time for the model's training. It also reduces the number of training parameters, like weights and bias. Thus, it reduces the memory requirement for the model storage. This work mainly focused on developing an optimized CNN model for the CBMIR system. Such systems can only support the physicians' decision to diagnose a disease from the images and retrieve the relevant cases to help the doctor decide the precise treatment. Methods: The deep learning-based model is proposed in this paper. The experiment is done with several convolution layers and various optimizers to get the maximum accuracy with a minimum number of convolution layers. Thus, the ten-layer CNN model is developed from scratch and used to derive the training and testing images' features and classify the test image. Once the image class is identified, the most relevant images are determined based on the Euclidean distance between the query features and database features of the identified class. Based on this distance, the most relevant images are displayed from the respective class of images. The general dataset CIFAR10, which has 60,000 images of 10 different classes, and the medical dataset IRMA, which has 2508 images of 9 various classes, have been used to analyze the proposed method. The proposed model is also applied for the medical x-ray image dataset of chest disease and compared with the other pre-trained models. Results: The accuracy and the average precision rate are the measurement parameters utilized to compare the proposed model with different machine learning techniques. The accuracy of the proposed model for the CIFAR10 dataset is 93.9%, which is better than the state-of-the-art methods. After the success for the general dataset, the model is also tested for the medical dataset. For the x-ray images of the IRMA dataset, it is 86.53%, which is better than the different pre-trained model results. The model is also tested for the other x-ray dataset, which is utilized to identify chest-related disease. The average precision rate for such a dataset is 97.25%. Also, the proposed model fulfills the major challenge of the semantic gap. The semantic gap of the proposed model for the chest disease dataset is 2.75%, and for the IRMA dataset, it is 13.47%. Also, only ten convolution layers are utilized in the proposed model, which is very small in number compared to the other pre-trained models. Conclusion: The proposed technique shows remarkable improvement in performance metrics over CNN-based state-of-the-art methods. It also offers a significant improvement in performance metrics over different pre-trained models for the two different medical x-ray image datasets.

Content Based Medical Image Retrieval for Accurate Disease Diagnosis

Introduction: Content Based Image Retrieval (CBIR) system is an innovative technology to retrieve images from various media types. One of the CBIR applications is Content Based Medical Image Retrieval (CBMIR). The image retrieval system retrieves the most similar images from the historical cases, and such systems can only support the physician's decision to diagnose a disease. To extract the useful features from the query image for linking similar types of images is the major challenge in the CBIR domain. The Convolution Neural Network (CNN) can overcome the drawbacks of traditional algorithms, dependent on the low-level feature extraction technique. Objective: The objective of the study is to develop a CNN model with a minimum number of convolution layers and to get the maximum possible accuracy for the CBMIR system. The minimum number of convolution layers reduces the number of mathematical operations and the time for the model's training. It also reduces the number of training parameters, like weights and bias. Thus, it reduces the memory requirement for the model storage. This work mainly focused on developing an optimized CNN model for the CBMIR system. Such systems can only support the physicians' decision to diagnose a disease from the images and retrieve the relevant cases to help the doctor decide the precise treatment. Methods: The deep learning-based model is proposed in this paper. The experiment is done with several convolution layers and various optimizers to get the maximum accuracy with a minimum number of convolution layers. Thus, the ten-layer CNN model is developed from scratch and used to derive the training and testing images' features and classify the test image. Once the image class is identified, the most relevant images are determined based on the Euclidean distance between the query features and database features of the identified class. Based on this distance, the most relevant images are displayed from the respective class of images. The general dataset CIFAR10, which has 60,000 images of 10 different classes, and the medical dataset IRMA, which has 2508 images of 9 various classes, have been used to analyze the proposed method. The proposed model is also applied for the medical x-ray image dataset of chest disease and compared with the other pre-trained models. Results: The accuracy and the average precision rate are the measurement parameters utilized to compare the proposed model with different machine learning techniques. The accuracy of the proposed model for the CIFAR10 dataset is 93.9%, which is better than the state-of-the-art methods. After the success for the general dataset, the model is also tested for the medical dataset. For the x-ray images of the IRMA dataset, it is 86.53%, which is better than the different pre-trained model results. The model is also tested for the other x-ray dataset, which is utilized to identify chest-related disease. The average precision rate for such a dataset is 97.25%. Also, the proposed model fulfills the major challenge of the semantic gap. The semantic gap of the proposed model for the chest disease dataset is 2.75%, and for the IRMA dataset, it is 13.47%. Also, only ten convolution layers are utilized in the proposed model, which is very small in number compared to the other pre-trained models. Conclusion: The proposed technique shows remarkable improvement in performance metrics over CNN-based state-of-the-art methods. It also offers a significant improvement in performance metrics over different pre-trained models for the two different medical x-ray image datasets.

Epidemiology and factors of tuberculosis treatment outcome, Bangladesh, 2012-13

Tuberculosis (TB) treatment outcome is an important indicator to improve TB control efforts. We assessed factors associated with unfavorable treatment outcomes among smear-positive pulmonary TB patients reported to the national TB program from January 2012 to December 2013 in Bangladesh. Favorable outcomes were cured and treatment completed with unfavorable outcomes as failed, defaulted, died and lost to follow-up. We retrieved 98,932 patients with outcome data; 65,458 (66%) were male and 7,956 (8%) had unfavorable outcomes (3,737 (47%) died, 1,641 (21%) defaulted, and 1,599 (20%) lost to follow-up). In multivariable analysis, male gender (adjusted odds ratio [aOR] 1.41; 95% confidence interval [CI] 1.34-1.49) and treatment at a chest disease hospital (CDH) (aOR 1.44; 95% CI 1.25-1.66) were risk factors. The association between male gender and unfavorable outcomes may result from the high smoking rates among males in Bangladesh. The association of treatment at a CDH with unfavorable outcomes may occur because complicated cases (e.g., TB with co-infections) are usually treated in a chest hospital in Bangladesh. A case-control study could further confirm and explain these findings.

STUDY OF FINGERPRINT PATTERN IN KASHMIRI POPULATION

Background: Dactylography/Dactyloscopy/Dermatoglyphics is the study of fingerprints as a method of identification.Fingerprint is an easily available,accurate and authentic method of identification.Importance of fingerprints is of immense use in forensic,and criminal application.Nowadays the subject is also developing importance in various other field as well.A Aim:To identify the fingerprint pattern and its relation with gender in kashmiri population. Material and Method: A cross sectional study was done in the government chest disease hospital.The subjects were the staff of the department belonging to various regions and districts of kashmir.The subjects were asked to press their fingers on the stamp pad and then transfered to the paper. Result: Loops were the most common pattern found followed by whorls and arches.Loops was found in 53.8%,whorls in 39.5% and arches in 6.7%.In gender wise distribution a higher percentage of loops was found in females and whorls in males. Conclusion: In the current research work different types of fingerprint patterns were found. Fingerprint is an easily available and effective method of identification of a person. This study will prove helpful to experts in solving criminal cases, identifying missing persons or in case of a disaster.

Impact of Cold Weather on Setup Errors in Radiotherapy

Objective. To investigate the influence of cold weather on setup errors of patients with chest and pelvic disease in radiotherapy. Methods. The image-guided data of the patients were collected from the Radiotherapy Center of Cancer Hospital Affiliated to Guangxi Medical University from October 2020 to February 2021. During this period, the cold weather days were December 15, 16, and 17, 2020, and January 7 and 8, 2021. For body fixation in radiotherapy, an integrated plate and a thermoplastic mold were employed in 18 patients with chest disease, while an integrated plate and a vacuum pad were applied in 19 patients with pelvic disease. All patients underwent cone beam computed tomography (CBCT) scans in the first five treatments and once a week thereafter. The obtained data were registered to the planning CT image to get the setup errors of the patient in the translational direction including X, Y, and Z axes and rotational direction including RX, RY, and RZ. Then, the Mann–Whitney U test was performed. The expansion boundary values of the chest and pelvis were calculated according to the formula M PTV = 2.5 ∑ + 0.7 δ . Results. A total of 286 eligible results of CBCT scans were collected. There were 138 chest CBCT scans, including 26 taken in cold weather and 112 in usual weather, and 148 pelvic CBCT scans, including 33 taken in cold weather and 115 in usual weather. The X-, Y-, and Z-axis translational setup errors of patients with chest disease in the cold weather group were 0.16 (0.06, 0.32) cm, 0.25 (0.17, 0.52) cm, and 0.35 (0.21, 0.47) cm, respectively, and those in the usual weather group were 0.14 (0.08, 0.29) cm, 0.23 (0.13, 0.37) cm, and 0.18 (0.1, 0.35) cm, respectively. The results indicated that there was a statistical difference in the Z-axis translational error between the cold weather group and the usual weather group (U = 935.5; p = 0.005 < 0.05 ), while there was no statistical difference in the rotational error between the two groups. The external boundary values of X, Y, and Z axes in the cold weather group were 0.57 cm, 0.92 cm, and 0.99 cm, respectively, and those in the usual weather group were 0.57 cm, 0.78 cm, and 0.68 cm, respectively. There was no significant difference in the translational and rotational errors of patients with pelvic disease between the cold weather group and the usual weather group ( p < 0.05 ). The external boundary values of X, Y, and Z axes were 0.63 cm, 0.79 cm, and 0.68 cm in the cold weather group and 0.61 cm, 0.79 cm, and 0.61 cm in the usual weather group, respectively. Conclusion. The setup error of patients undergoing radiotherapy with their bodies fixed by an integrated plate and a thermoplastic mold was greater in cold weather than in usual weather, especially in the ventrodorsal direction.

Do Covid-19 patients needing ICU admission have worse 6 months follow up outcomes when compared with hospitalized non-ICU patients? A prospective cohort study

Introduction Studies focus on pathogenesis, clinical manifestations, and complications during the early phase of the coronavirus disease-19 (COVID-19). Long-term outcomes of COVID-19 patients who discharge intensive care unit (ICU) are unclear. Objectives We investigated the effect of COVID-19 on lung structure, pulmonary functional, exercise capacity and quality of life in patients discharge from ICU and medical ward. Methods A prospective single-centre study conducted in PCR confirmed COVID-19 patients who has been discharged from University of Health Sciences, Dr. Suat Seren Chest Disease and Thoracic Surgery Teaching and Research Hospital between 15 January and 5 March 2021. Patients who followed up for more than 48 hours in ICU and more than 72 hours in medical ward were included the study. Computed tomography scores, pulmonary functional tests (PFT), 6-min walking distance and health related quality of life by SF-36 were compared between ICU and medical ward patients at 6 months after discharge. Results Seventy patients were included final analyses and 31 of them discharged from ICU. ICU patients had higher CT scores than non-ICU patients at admission (17 vs 11) and follow up visit (6 vs 0). Two-three of ICU patients had at least one abnormal finding at control CT. Advanced age (OR 1.08, 95% CI 1.02-1.15) and higher CT score at admission (OR 1.13, 95% CI 1.01-1.27) were risk factors for having radiological abnormalities at control CT. Conclusion A number of COVID-19 survivors especially with severe disease could not fully recover after 6 months of hospital discharge.

Challenges in diagnosis and treatment of pneumothorax and giant bullae

Spontaneous pneumothorax is the most common acute chest disease. Often, giant bullae give the impression of the presence of air in the pleural cavity. Inadequate differential diagnosis leads to vain drainage of the pleural cavity, damage to the lung with its collapse and pneumothorax.The aim. Analyze diagnostic and tactical mistakes in patients with pulmonary emphysema, which manifests with giant bullae, and outline the ways to prevent complications.Methods. The analysis of the treatment of 1,636 patients with pulmonary emphysema and its complications undergoing treatment in the thoracic surgical department of the Samara Regional Clinical Hospital named after V.D.Seredavin in the period from 2001 to 2018 is presented.Results. Giant bulla were diagnosed in 35 (2.1%) patients, 16 of them were hospitalized ungently. In 6 patients, the diagnosis of a giant bulla of the lung was correct, and the patients were referred to the thoracic surgical department. In 10 patients, a giant bulla of the lung was regarded as pneumothorax, and pleural drainage was performed before referral to the thoracic surgical department.Conclusion. The correct interpretation of the radiological data and comparison with the clinical picture allows avoiding diagnostic errors and the associated danger and complications.