Comparison of the Discrimination Performance of AI Scoring and the Brixia Score in Predicting COVID-19 Severity on Chest X-Ray Imaging: Diagnostic Accuracy Study.

BACKGROUND: The artificial intelligence (AI) analysis of chest x-rays can increase the precision of binary COVID-19 diagnosis. However, it is unknown if AI-based chest x-rays can predict who will develop severe COVID-19, especially in low- and middle-income countries. OBJECTIVE: The study aims to compare the performance of human radiologist Brixia scores versus 2 AI scoring systems in predicting the severity of COVID-19 pneumonia. METHODS: We performed a cross-sectional study of 300 patients suspected with and with confirmed COVID-19 infection in Jakarta, Indonesia. A total of 2 AI scores were generated using CAD4COVID x-ray software. RESULTS: The AI probability score had slightly lower discrimination (area under the curve [AUC] 0.787, 95% CI 0.722-0.852). The AI score for the affected lung area (AUC 0.857, 95% CI 0.809-0.905) was almost as good as the human Brixia score (AUC 0.863, 95% CI 0.818-0.908). CONCLUSIONS: The AI score for the affected lung area and the human radiologist Brixia score had similar and good discrimination performance in predicting COVID-19 severity. Our study demonstrated that using AI-based diagnostic tools is possible, even in low-resource settings. However, before it is widely adopted in daily practice, more studies with a larger scale and that are prospective in nature are needed to confirm our findings.

Clinical presentation, management, and outcome of suspected central nervous system infections in Indonesia: a prospective cohort study.

BACKGROUND: Little is known about the etiology, clinical presentation, management, and outcome of central nervous system (CNS) infections in Indonesia, a country with a high burden of infectious diseases and a rising prevalence of HIV. METHODS: We included adult patients with suspected CNS infections at two referral hospitals in a prospective cohort between April 2019 and December 2021. Clinical, laboratory, and radiological assessments were standardized. We recorded initial and final diagnoses, treatments, and outcomes during 6 months of follow-up. RESULTS: Of 1051 patients screened, 793 were diagnosed with a CNS infection. Patients (median age 33 years, 62% male, 38% HIV-infected) presented a median of 14 days (IQR 7-30) after symptom onset, often with altered consciousness (63%), motor deficits (73%), and seizures (21%). Among HIV-uninfected patients, CNS tuberculosis (TB) was most common (60%), while viral (8%) and bacterial (4%) disease were uncommon. Among HIV-infected patients, cerebral toxoplasmosis (41%) was most common, followed by CNS TB (19%), neurosyphilis (15%), and cryptococcal meningitis (10%). A microbiologically confirmed diagnosis was achieved in 25% of cases, and initial diagnoses were revised in 46% of cases. In-hospital mortality was 30%, and at six months, 45% of patients had died, and 12% suffered from severe disability. Six-month mortality was associated with older age, HIV, and severe clinical, radiological and CSF markers at presentation. CONCLUSION: CNS infections in Indonesia are characterized by late presentation, severe disease, frequent HIV coinfection, low microbiological confirmation and high mortality. These findings highlight the need for earlier disease recognition, faster and more accurate diagnosis, and optimized treatment, coupled with wider efforts to improve the uptake of HIV services.

Derivation and validation of novel integrated inpatient mortality prediction score for COVID-19 (IMPACT) using clinical, laboratory, and AI-processed radiological parameter upon admission: a multicentre study.

Limited studies explore the use of AI for COVID-19 prognostication. This study investigates the relationship between AI-aided radiographic parameters, clinical and laboratory data, and mortality in hospitalized COVID-19 patients. We conducted a multicentre retrospective study. The derivation and validation cohort comprised of 512 and 137 confirmed COVID-19 patients, respectively. Variable selection for constructing an in-hospital mortality scoring model was performed using the least absolute shrinkage and selection operator, followed by logistic regression. The accuracy of the scoring model was assessed using the area under the receiver operating characteristic curve. The final model included eight variables: anosmia (OR: 0.280; 95%CI 0.095-0.826), dyspnoea (OR: 1.684; 95%CI 1.049-2.705), loss of consciousness (OR: 4.593; 95%CI 1.702-12.396), mean arterial pressure (OR: 0.928; 95%CI 0.900-0.957), peripheral oxygen saturation (OR: 0.981; 95%CI 0.967-0.996), neutrophil % (OR: 1.034; 95%CI 1.013-1.055), serum urea (OR: 1.018; 95%CI 1.010-1.026), affected lung area score (OR: 1.026; 95%CI 1.014-1.038). The Integrated Inpatient Mortality Prediction Score for COVID-19 (IMPACT) demonstrated a predictive value of 0.815 (95% CI 0.774-0.856) in the derivation cohort. Internal validation resulted in an AUROC of 0.770 (95% CI 0.661-0.879). Our study provides valuable evidence of the real-world application of AI in clinical settings. However, it is imperative to conduct prospective validation of our findings, preferably utilizing a control group and extending the application to broader populations.

The relationship of vascular endothelial growth factor and osteopontin expression with 3-year progression-free survival of locally advanced nasopharyngeal cancer patients treated with platinum-based chemoradiation.

Introduction: The incidence of nasopharyngeal cancer (NPC) is high, with new cases accounting for 5.2% of all malignancies in Indonesia. Most cases are detected at an advanced stage, and recurrences are common. Vascular endothelial growth factor (VEGF) and osteopontin (OPN) are important markers in tumorigenesis that serve as prognostic predictors. This study aims to determine the correlation of VEGF and OPN expression with 3-year progression-free survival (PFS). Material and methods: This retrospective cohort study analyzed 155 patients with locally advanced NPC. Data were obtained from medical records between 2015 and 2017. The locally advanced sample of this disease that met the inclusion criteria was stained with H&E before being prepared in a paraffin block. Furthermore, the immunohistochemistry staining results for VEGF and OPN were observed with ImageJ 1.50i and calculated semi-quantitatively using the histoscore. Results: The 3-year PFS obtained was 39%, with a median of 23 months. Vascular endothelial growth factor expression was detected in 113 of 155 samples (72.9%), while positive OPN expression was discovered in 99 of 155 samples (63.8%). There was a correlation between VEGF (p = 0.747) and OPN expression (p = 0.584) and 3-year PFS. Positive VEGF and OPN expression in the subgroup of patients with stage IVB and N3 tumors was related to improved 3-year PFS (p < 0.05). This was similar to the positive VEGF expression in the subgroup of patients receiving neoadjuvant chemotherapy (p < 0.05). Conclusions: Vascular endothelial growth factor and OPN remained potential prognostic predictors in NPC. Patients with positive VEGF and OPN expression in N3, IVB, and neoadjuvant treatment had significantly improved 3-year PFS.

A case of aseptic bilateral cavernous sinus thrombosis following a recent inactivated SARS-CoV-2 vaccination.

This case report aims to describe the first report of bilateral aseptic cavernous sinus thrombosis (CST) with a recent history of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccination. A 50-year-old woman presented with bilateral proptosis, decreased vision, and ophthalmoplegia 16 days following CoronaVac® vaccine. The visual acuity of the left eye was 20/150, while the right eye was no light perception with a hyperemic optic nerve head. She had a history of hyperthyroidism and currently on warfarin consumption. Laboratory results depicted elevated free T4, free T3, international normalized ratio, and low protein S and C. Magnetic resonance imaging showed bilateral CST, and high-dose methylprednisolone along with fondaparinux was given. The symptoms were significantly resolved, with the visual acuity of the left eye being improved to 20/20 but not the right eye. Bilateral CST has not been previously reported following inactivated SARS-CoV-2 vaccination. The underlying systemic conditions should be taken into consideration for the possibility of the inactivated SARS-CoV-2 vaccine-related event.

Diffusion magnetic resonance imaging of normal-appearing white matter in multiple sclerosis: correlation with brain volume and clinical disability.

Background: Diffusion magnetic resonance imaging (MRI) abnormalities in multiple sclerosis (MS) are not limited to lesions, but have also been observed in the white matter that appears normal on conventional MRI sequences, known as normal-appearing white matter (NAWM). There is evidence of microstructural processes occurring in the NAWM. Objective: To assess the correlation between NAWM apparent diffusion coefficient (ADC) and fractional anisotropy (FA) with brain volume and clinical disability in MS. Methods: Brain MRI from 33 MS patients were included. ADC and FA measurements of the genu, body, and splenium of corpus callosum (CC) were done. ADC and FA values were analyzed to measure their correlation with brain volume from MR volumetry and clinical disability represented by Expanded Disability Status Scale (EDSS). Results: The mean ADC of CC NAWM was .93 ×10-3 mm2/s (±.13 SD), and the mean FA .72 (±.12 SD). ADC and FA of CC NAWM were significantly correlated with the ratio of brain volume to intracranial volume (R = -0,70 and 0,78 respectively), and with EDSS (R = .52 and -.59 respectively). Conclusion: There were significant correlations between ADC and FA of NAWM with brain volume and EDSS of MS patients. Further longitudinal studies were needed to evaluate the potential of diffusion MRI in the evaluation of MS.

Difficulties in Diagnosis Acute Necrotizing Encephalopathy of Childhood: A Case Report.

Acute necrotizing encephalopathy of childhood (ANEC) is a rare condition of encephalopathy which commonly occurs in healthy children. This case report will discuss the diagnostic approach in a female child, three years old, with neurologic deficits. The diagnostic approach of ANEC consists of clinical manifestation, laboratory examination, cerebrospinal fluid (CSF) analysis, and neuroimaging interpretation. The patient had high liver enzyme, normal CSF analysis with appearances of edema, hemorrhage and necrosis in serial brain magnetic resonance imaging (MRI).

Automated selection of mid-height intervertebral disc slice in traverse lumbar spine MRI using a combination of deep learning feature and machine learning classifier.

Abnormalities and defects that can cause lumbar spinal stenosis often occur in the Intervertebral Disc (IVD) of the patient's lumbar spine. Their automatic detection and classification require an application of an image analysis algorithm on suitable images, such as mid-sagittal images or traverse mid-height intervertebral disc slices, as inputs. Hence the process of selecting and separating these images from other medical images in the patient's set of scans is necessary. However, the technological progress in making this process automated is still lagging behind other areas in medical image classification research. In this paper, we report the result of our investigation on the suitability and performance of different approaches of machine learning to automatically select the best traverse plane that cuts closest to the half-height of an IVD from a database of lumbar spine MRI images. This study considers images features extracted using eleven different pre-trained Deep Convolution Neural Network (DCNN) models. We investigate the effectiveness of three dimensionality-reduction techniques and three feature-selection techniques on the classification performance. We also investigate the performance of five different Machine Learning (ML) algorithms and three Fully Connected (FC) neural network learning optimizers which are used to train an image classifier with hyperparameter optimization using a wide range of hyperparameter options and values. The different combinations of methods are tested on a publicly available lumbar spine MRI dataset consisting of MRI studies of 515 patients with symptomatic back pain. Our experiment shows that applying the Support Vector Machine algorithm with a short Gaussian kernel on full-length image features extracted using a pre-trained DenseNet201 model is the best approach to use. This approach gives the minimum per-class classification performance of around 0.88 when measured using the precision and recall metrics. The median performance measured using the precision metric ranges from 0.95 to 0.99 whereas that using the recall metric ranges from 0.93 to 1.0. When only considering the L3/L4, L4/L5, and L5/S1 classes, the minimum F1-Scores range between 0.93 to 0.95, whereas the median F1-Scores range between 0.97 to 0.99.

Automated measurement of anteroposterior diameter and foraminal widths in MRI images for lumbar spinal stenosis diagnosis.

Lumbar Spinal Stenosis causes low back pain through pressures exerted on the spinal nerves. This can be verified by measuring the anteroposterior diameter and foraminal widths of the patient's lumbar spine. Our goal is to develop a novel strategy for assessing the extent of Lumbar Spinal Stenosis by automatically calculating these distances from the patient's lumbar spine MRI. Our method starts with a semantic segmentation of T1- and T2-weighted composite axial MRI images using SegNet that partitions the image into six regions of interest. They consist of three main regions-of-interest, namely the Intervertebral Disc, Posterior Element, and Thecal Sac, and three auxiliary regions-of-interest that includes the Area between Anterior and Posterior elements. A novel contour evolution algorithm is then applied to improve the accuracy of the segmentation results along important region boundaries. Nine anatomical landmarks on the image are located by delineating the region boundaries found in the segmented image before the anteroposterior diameter and foraminal widths can be measured. The performance of the proposed algorithm was evaluated through a set of experiments on the Lumbar Spine MRI dataset containing MRI studies of 515 patients. These experiments compare the performance of our contour evolution algorithm with the Geodesic Active Contour and Chan-Vese methods over 22 different setups. We found that our method works best when our contour evolution algorithm is applied to improve the accuracy of both the label images used to train the SegNet model and the automatically segmented image. The average error of the calculated right and left foraminal distances relative to their expert-measured distances are 0.28 mm (p = 0.92) and 0.29 mm (p = 0.97), respectively. The average error of the calculated anteroposterior diameter relative to their expert-measured diameter is 0.90 mm (p = 0.92). The method also achieves 96.7% agreement with an expert opinion on determining the severity of the Intervertebral Disc herniations.

The Difference in the Cyclin D1 Expression in Advanced Stage Nasopharyngeal Cancer based on Treatment Response: A Retrospective Cohort Study.

BACKGROUND: nasopharyngeal cancer (NPC) is the most common type of head and neck cancer in Indonesia (28.4%). Reports showed that 18.9% of cases came with advanced stage. Chemotherapy play important role in advanced stage. However, patients with the same stage of the disease may have different treatment response, likely due to the different tumor biological characteristics. Cyclin D1 is a protein involved in the cell cycle, which will stimulate proliferation. This study aimed to examine the proportion of cyclin D1 in NPC and its association with treatment response. METHODS: a retrospective cohort study was conducted on advanced NPC patients that underwent chemotherapy at Cipto Mangunkusumo Hospital from 2015 until 2018. Cyclin D1 immunohistochemistry staining was done by antigen retrieval methods using the cyclin D1 NovocastraTM monoclonal antibody. The cyclin D1 expression was evaluated with h-score. Treatment response was reviewed based on the RECIST 1.1 criteria. RESULTS: fifteen subjects (48.4%) had a positive expression of cyclin D1. Higher proportion of cyclin D1 positive was found in responsive group compare with non-responsive group (66.7% vs. 33.3%, p = 0.032). Statistically significant difference in mean h-score was observed between the subjects who responded and those who did not respond (116.24 SD57.80 vs. 77.97 SD45.27, p = 0.048). CONCLUSION: this study suggests that a higher expression of cyclin D1 is associated with a good treatment response in NPC patients.

The Importance of Chest CT Scan in COVID-19.

The coronavirus disease 2019 (COVID-19) is a highly transmissible acute respiratory disease that is caused by the Severe Acute Respiratory Syndrome CoronaVirus-2 (SARS-CoV-2), a beta coronavirus first discovered in Wuhan, China, in late 2019. COVID-19 has been spreading swiftly globally, and as of March 2020, has been officially declared a pandemic by the World Health Organization (WHO). One of the challenges in managing COVID-19 is the identification of a swift, accessible, and reliable diagnostic modality that could serve as an alternative to a reverse-transcriptase polymerase chain reaction (RT-PCR). As of the writing of this paper, RT-PCR is still the recommended tool in diagnosing COVID-19, but the notion of a more prompt and accurate diagnostic tool is a possibility worth looking into. The objective of this case study is to investigate the importance and utility of chest computed tomography (CT) in the diagnosis of COVID-19, as increasing pieces of evidence suggest that chest CT could prove useful in the clinical pathway in diagnosing COVID-19.

Undifferentiated Nasopharyngeal Carcinoma Presenting with Shoulder Mass.

Nasopharyngeal cancer (NPC) is the most common cancer among head and neck cancer that usually presented with unilateral neck mass. Unusual symptoms of NPC can lead us to diagnosis misleading and delayed definitive treatment. We present a case of NPC with bone metastasis in the shoulder. A 33-year-old female presented with right shoulder mass caused by undifferentiated carcinoma of unknown primary, based on biopsy of shoulder mass. After four months, she was complaining painless neck swelling, headache, and hearing impairment in the left ear. Bone MRI showed malignant bone tumour in the right humerus. Neck CT scan showed mass in the nasopharyngeal and bilateral lymphadenopathy. Biopsy in nasopharyngeal revealed undifferentiated carcinoma of nasopharyngeal cancer (WHO-3 type A). The patient was diagnosed as NPC stage IVb and thus was treated with palliative chemotherapy. After three cycles of cisplatin docetaxel, patient condition improved.

Presentation, etiology, and outcome of brain infections in an Indonesian hospital: A cohort study.

BACKGROUND: Little detailed knowledge is available regarding the etiology and outcome of CNS infection, particularly in HIV-infected individuals, in low-resource settings. METHODS: From January 2015 to April 2016, we prospectively included all adults with suspected CNS infection in a referral hospital in Jakarta, Indonesia. Systematic screening included HIV testing, CSF examination, and neuroimaging. RESULTS: A total of 274 patients with suspected CNS infection (median age 26 years) presented after a median of 14 days with headache (77%), fever (78%), seizures (27%), or loss of consciousness (71%). HIV coinfection was common (54%), mostly newly diagnosed (30%) and advanced (median CD4 cell count 30/µL). Diagnosis was established in 167 participants (65%), including definite tuberculous meningitis (TBM) (n = 44), probable TBM (n = 48), cerebral toxoplasmosis (n = 48), cryptococcal meningitis (n = 14), herpes simplex virus/varicella-zoster virus/cytomegalovirus encephalitis (n = 10), cerebral lymphoma (n = 1), neurosyphilis (n = 1), and mucormycosis (n = 1). In-hospital mortality was 32%; 6-month mortality was 57%. The remaining survivors had either moderate or severe disability (36%) according to Glasgow Outcome Scale. CONCLUSION: In this setting, patients with CNS infections present late with severe disease and often associated with advanced HIV infection. Tuberculosis, toxoplasmosis, and cryptococcosis are common. High mortality and long-term morbidity underline the need for service improvements and further study.