Autonomous assessment of spontaneous retinal venous pulsations in fundus videos using a deep learning framework.

The presence or absence of spontaneous retinal venous pulsations (SVP) provides clinically significant insight into the hemodynamic status of the optic nerve head. Reduced SVP amplitudes have been linked to increased intracranial pressure and glaucoma progression. Currently, monitoring for the presence or absence of SVPs is performed subjectively and is highly dependent on trained clinicians. In this study, we developed a novel end-to-end deep model, called U3D-Net, to objectively classify SVPs as present or absent based on retinal fundus videos. The U3D-Net architecture consists of two distinct modules: an optic disc localizer and a classifier. First, a fast attention recurrent residual U-Net model is applied as the optic disc localizer. Then, the localized optic discs are passed on to a deep convolutional network for SVP classification. We trained and tested various time-series classifiers including 3D Inception, 3D Dense-ResNet, 3D ResNet, Long-term Recurrent Convolutional Network, and ConvLSTM. The optic disc localizer achieved a dice score of 95% for locating the optic disc in 30 milliseconds. Amongst the different tested models, the 3D Inception model achieved an accuracy, sensitivity, and F1-Score of 84 ± 5%, 90 ± 8%, and 81 ± 6% respectively, outperforming the other tested models in classifying SVPs. To the best of our knowledge, this research is the first study that utilizes a deep neural network for an autonomous and objective classification of SVPs using retinal fundus videos.

Radiomics predictive modeling from dual-time-point FDG PET Ki parametric maps: application to chemotherapy response in lymphoma.

BACKGROUND: To investigate the use of dynamic radiomics features derived from dual-time-point (DTP-feature) [18F]FDG PET metabolic uptake rate Ki parametric maps to develop a predictive model for response to chemotherapy in lymphoma patients. METHODS: We analyzed 126 lesions from 45 lymphoma patients (responding n = 75 and non-responding n = 51) treated with chemotherapy from two different centers. Static and DTP radiomics features were extracted from baseline static PET images and DTP Ki parametric maps. Spearman's rank correlations were calculated between static and DTP features to identify features with potential additional information. We first employed univariate analysis to determine correlations between individual features, and subsequently utilized multivariate analysis to derive predictive models utilizing DTP and static radiomics features before and after ComBat harmonization. For multivariate modeling, we utilized both the minimum redundancy maximum relevance feature selection technique and the XGBoost classifier. To evaluate our model, we partitioned the patient datasets into training/validation and testing sets using an 80/20% split. Different metrics for classification including area under the curve (AUC), sensitivity (SEN), specificity (SPE), and accuracy (ACC) were reported in test sets. RESULTS: Via Spearman's rank correlations, there was negligible to moderate correlation between 32 out of 65 DTP features and some static features (ρ < 0.7); all the other 33 features showed high correlations (ρ ≥ 0.7). In univariate modeling, no significant difference between AUC of DTP and static features was observed. GLRLM_RLNU from static features demonstrated a strong correlation (AUC = 0.75, p value = 0.0001, q value = 0.0007) with therapy response. The most predictive DTP features were GLCM_Energy, GLCM_Entropy, and Uniformity, each with AUC = 0.73, p value = 0.0001, and q value < 0.0005. In multivariate analysis, the mean ranges of AUCs increased following harmonization. Use of harmonization plus combining DTP and static features was shown to provide significantly improved predictions (AUC = 0.97 ± 0.02, accuracy = 0.89 ± 0.05, sensitivity = 0.92 ± 0.09, and specificity = 0.88 ± 0.05). All models depicted significant performance in terms of AUC, ACC, SEN, and SPE (p < 0.05, Mann-Whitney test). CONCLUSIONS: Our results demonstrate significant value in harmonization of radiomics features as well as combining DTP and static radiomics models for predicting response to chemotherapy in lymphoma patients.

Source Code for Optimized Parallel Inception: A Fast COVID-19 Screening Software.

COVID-19 and swine-origin influenza A (H1N1) are both pandemics that sparked significant concern worldwide. These two viruses have the same symptoms and occur at a collision timeline. Optimized Parallel Inception (OPI) presents a new strategy to screen the COVID-19 from H1N1 with use of only symptoms. In this paper, the process of preprocessing, screening, and specifying feature importance by OPI and particle swarm optimization is presented. Experimental results indicate 98.88 accuracy for screening COVID-19, H1N1, and Neither COVID-19 Nor H1N1.

Fast COVID-19 versus H1N1 screening using Optimized Parallel Inception.

COVID-19 and swine-origin influenza A (H1N1) are both pandemics that sparked significant concern worldwide. Since these two diseases have common symptoms, a fast COVID-19 versus H1N1 screening helps better manage patients at healthcare facilities. We present a novel deep model, called Optimized Parallel Inception, for fast screening of COVID-19 and H1N1 patients. We also present a Semi-supervised Generative Adversarial Network (SGAN) to address the problem related to the smaller size of the COVID-19 and H1N1 research data. To evaluate the proposed models, we have merged two separate COVID-19 and H1N1 data from different sources to build a new dataset. The created dataset includes 4,383 positive COVID-19 cases, 989 positive H1N1 cases, and 1,059 negative cases. We applied SGAN on this dataset to remove issues related to unequal class densities. The experimental results show that the proposed model's screening accuracy is 99.2% and 99.6% for COVID-19 and H1N1, respectively. According to our analysis, the most significant symptoms and underlying chronic diseases for COVID-19 versus H1N1 screening are dry cough, breathing problems, diabetes, and gastrointestinal.

Reallocation of water resources according to social, economic, and environmental parameters.

Population growth, urbanization, and industrial development have significantly increased water demands in many countries, raising the concerns about water resources sustainability to meet the needs of humans and the environment. Furthermore, the economy-oriented allocation of water resources has caused many socio-environmental problems. The main goal of this study is to develop a system dynamics modeling framework that integrates economic, social, and environmental dimensions for the decision of water resources allocation. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is used to rank modeling scenarios and identify the best strategy for water allocation. In the application to East Azerbaijan province of Iran, six industry groups (including chemical, food and beverage, non-metal, machinery and equipment, metal, and textile), thirteen water allocation scenarios, and five criteria (including profit index, employment index, return of surface water, groundwater sustainability index, and total allocated water) were considered. The TOPSIS results showed that in the best scenario most water was allocated to the non-metal industry with a relative distance of 0.63 to the ideal solution. On the other hand, the current water allocation scenario ranked seventh, indicating that significant improvements are required to take into account the social, economic, and environmental factors for optimal reallocation of water resources among different industry users.

FCOD: Fast COVID-19 Detector based on deep learning techniques.

The sudden COVID-19 pandemic has caused a serious global concern due to infections and mortality rates. It is a hazardous disease that has recently become the biggest crisis in the modern era. Due to the limitation of test kits and the need for screening and rapid diagnosis of patients, it is essential to perform a self-operating detection model as a fast recognition system to detect COVID-19 infection and prevent the spread among the people. In this paper, we propose a novel technique called Fast COVID-19 Detector (FCOD) to have a fast detection of COVID-19 using X-ray images. The FCOD is a deep learning model based on the Inception architecture that uses 17 depthwise separable convolution layers to detect COVID-19. Depthwise separable convolution layers decrease the computation costs, time, and they can have a reducing role in the number of parameters compared to the standard convolution layers. To evaluate FCOD, we used covid-chestxray-dataset, which contains 940 publicly available typical chest X-ray images. Our results show that FCOD can provide accuracy, F1-score, and AUC of 96%, 96%, and 0.95%, respectively in classifying COVID-19 during 0.014 s for each case. The proposed model can be employed as a supportive decision-making system to assist radiologists in clinics and hospitals to screen patients immediately.

Anterior ischemic optic neuropathy as a rare manifestation of COVID-19: a case report.

Aim: A variety of manifestations in different organs could be associated with severe COVID-19; for example, ocular manifestations. Case report: A 52-year-old male complaining of sudden onset unilateral painless vision loss in the right eye for 1 month (started just 1 week after COVID-19 remission) came to the ophthalmology clinic. On further evaluations, he was diagnosed with anterior ischemic optic neuropathy (AION). Considering his past history and the result of evaluations, the hypothesis of association between AION and COVID-19 was proposed. Results & discussion: Ocular and neurologic manifestations of COVID-19 are more likely to happen in patients with more severe conditions. Complications occur secondary to two basic mechanisms including severe inflammatory response and hypercoagulable state. Conclusion: Our findings indicated that non-arteritic AION is another manifestation of microangiopathic/thrombotic events which may occur in the course of COVID-19.

SSP: Early prediction of sepsis using fully connected LSTM-CNN model.

BACKGROUND: Sepsis is a life-threatening condition that occurs due to the body's reaction to infections, and it is a leading cause of morbidity and mortality in hospitals. Early prediction of sepsis onset facilitates early interventions that promote the survival of suspected patients. However, reliable and intelligent systems for predicting sepsis are scarce. METHODS: This paper presents a novel technique called Smart Sepsis Predictor (SSP) to predict sepsis onset in patients admitted to an intensive care unit (ICU). SSP is a deep neural network architecture that encompasses long short-term memory (LSTM), convolutional, and fully connected layers to achieve early prediction of sepsis. SSP can work in two modes; Mode 1 uses demographic data and vital signs, and Mode 2 uses laboratory test results in addition to demographic data and vital signs. To evaluate SSP, we have used the 2019 PhysioNet/CinC Challenge dataset, which includes the records of 40,366 patients admitted to the ICU. RESULTS: To compare SSP with existing state-of-the-art methods, we have measured the accuracy of the SSP in 4-, 8-, and 12-h prediction windows using publicly available data. Our results show that the SSP performance in Mode 1 and Mode 2 is much higher than existing methods, achieving an area under the receiver operating characteristic curve (AUROC) of 0.89 and 0.92, 0.88 and 0.87, and 0.86 and 0.84 for 4 h, 8 h, and 12 h before sepsis onset, respectively. CONCLUSIONS: Using ICU data, sepsis onset can be predicted up to 12 h in advance. Our findings offer an early solution for mitigating the risk of sepsis onset.

Mesenchymal stem cell-derived exosomes: a new therapeutic approach to osteoarthritis?

Degenerative disorders of joints, especially osteoarthritis (OA), result in persistent pain and disability and high costs to society. Nevertheless, the molecular mechanisms of OA have not yet been fully explained. OA is characterized by destruction of cartilage and loss of extracellular matrix (ECM). It is generally agreed that there is an association between pro-inflammatory cytokines and the development of OA. There is increased expression of matrix metalloproteinase (MMP) and "a disintegrin and metalloproteinase with thrombospondin motifs" (ADAMTS). Mesenchymal stem cells (MSCs) have been explored as a new treatment for OA during the last decade. It has been suggested that paracrine secretion of trophic factors, in which exosomes have a crucial role, contributes to the mechanism of MSC-based treatment of OA. The paracrine secretion of exosomes may play a role in the repair of joint tissue as well as MSC-based treatments for other disorders. Exosomes isolated from various stem cells may contribute to tissue regeneration in the heart, limbs, skin, and other tissues. Recent studies have indicated that exosomes (or similar particles) derived from MSCs may suppress OA development. Herein, for first time, we summarize the recent findings of studies on various exosomes derived from MSCs and their effectiveness in the treatment of OA. Moreover, we highlight the likely mechanisms of actions of exosomes in OA.

Therapy assessment of bone metastatic disease in the era of 223radium.

PURPOSE: Defining an optimal imaging modality for assessment of therapy and the best time of evaluation are pivotal for ideal patient's management. METHODS: 223Ra (Xofigo®, formerly Alpharadin) has been approved by the FDA and European Medicines Agency for treatment of metastatic castration-resistant prostate cancer with painful osseous involvement. RESULTS: PET/CT imaging using various radiotracers such as 18F-FDG, 18F-FCH, 68Ga-PSMA and 18F-NaF have been investigated to mitigate the limitations of conventional imaging modalities. Diagnostic radiotracers that have properties similar to a therapeutic radiotracer will precisely assess of the possibility and efficacy of a treatment; this is the theranostic concept. An example of a diagnostic test employed for selecting targeted therapy is the combined use of 18F-fluoride PET/CT for evaluation of possible therapy with 223Ra. CONCLUSION: This review examines the most recent publications related to this topic.

68Ga-PSMA-HBED Uptake on Cervicothoracic (Stellate) Ganglia, a Common Pitfall on PET/CT.

Ga-PSMA-HBED PET/CT showed promising results in staging and restaging of prostate cancer. However, nonspecific uptake has been reported in the celiac ganglia. In this case series, we showed faint radiotracer uptake on upper thoracic region in the location of cervicothoracic (stellate) ganglia. This ganglion is located anterior to the transverse process of C7 vertebra, inferior to subclavian artery, and superior to the neck of the first rib.

18F-NaF-PET/CT and 99mTc-MDP Bone Scintigraphy in the Detection of Bone Metastases in Prostate Cancer.

99mTc-MDP whole-body bone scintigraphy is a highly sensitive imaging method that has been used for decades to evaluate prostate cancer bone metastasis based on its availability and low cost; however, because of accumulation of this radiotracer in degenerative, traumatic, and inflammatory lesions, it suffers from noncomparable specificity. The modality is also used to monitor response to therapy and to predict patients' prognosis. As planar imaging may not give enough information for lesion detection or anatomical localization, it can be supplemented with SPECT to increase image contrast particularly in the evaluation of small and complex skeleton. In addition, hybrid SPECT/CT can be used to assess both functional and morphologic changes leading to more accurate detection of the metastatic bone lesions in a single-section test. 18F-NaF-PET/CT offers excellent advantages in investigating bone metastases. It provides greater spatial resolution and better image quality, resulting in better sensitivity and specificity. Furthermore, 18F-NaF-PET/CT is able to evaluate response to therapy more accurately and to detect occult bone metastases in lower prostate-specific antigen levels when comparing with conventional 99mTc-labeled whole-body bone scan. Owing to smaller administered dose and shorter half-life of 18F-NaF, the total actual radiation absorbed dose is almost comparable with 99mTc-labeled conventional bone scintigraphy. Hence, we believe that conventional bone scintigraphy would be replaced by 18F-NaF-PET/CT in the assessment of metastatic bone disease where PET/CT scanners are available.

Evaluation of Prostate Cancer Bone Metastases with 18F-NaF and 18F-Fluorocholine PET/CT.

18F-fluorocholine is a specific promising agent for imaging tumor cell proliferation, particularly in prostate cancer, using PET/CT. It is a beneficial tool in the early detection of marrow-based metastases because it excludes distant metastases and evaluates the response to hormone therapy. In addition, 18F-fluorocholine has the potential to differentiate between degenerative and malignant osseous abnormalities because degenerative changes are not choline-avid; however, the agent may accumulate in recent traumatic bony lesions. On the other hand, 18F-NaF PET/CT can indicate increased bone turnover and is generally used in the assessment of primary and secondary osseous malignancies, the evaluation of response to treatment, and the clarification of abnormalities on other imaging modalities or clinical data. 18F-NaF PET/CT is a highly sensitive method in the evaluation of bone metastases from prostate cancer, but it has problematic specificity, mainly because of tracer accumulation in degenerative and inflammatory bone diseases. In summary, 18F-NaF PET/CT is a highly sensitive method, but 18F-fluorocholine PET/CT can detect early bone marrow metastases and provide greater specificity in the detection of bone metastases in patients with prostate cancer. However, the difference seems not to be significant.

Giant Cell Tumor of the Tendon Sheath With Discordant Metabolism as a False Positive on Staging of Mantle Cell Lymphoma.

A baseline F-FDG PET/CT scan in a patient with mantle cell lymphoma showed diffuse minimally FDG-avid lymphadenopathy and splenomegaly. There was also a focus of uptake in the left subscapularis muscle without a CT correlate. A post-chemotherapy scan showed interval decrease in size, and resolution of FDG uptake, of the lymph nodes and spleen. Persistent activity was seen in the subscapularis muscle. Posttreatment biopsy of the FDG-avid lesion showed a benign giant cell tumor of tendon sheath. This case illustrates that a lesion with a markedly discordant SUV should raise suspicion for a second process.

Extended Low Anterior Resection with a Circular Stapler in Patients with Rectal Cancer: a Single Center Experience.

BACKGROUND: to evaluate the outcome of stapled colo-anal anastomoses after extended low anterior resection for distal rectal carcinoma. MATERIALS AND METHODS: A retrospective study of fifty patients who underwent colo- anal anastomoses after extended low anterior resection was conducted at Imam Hospital from September 2007 up to July 2012. RESULTS: The distance of the tumor from anal verge was 3 to 8 cm. Anastomotic leakage developed in 6% of patients and defecation problems in 16% . One-year local recurrence was 6% while three-year local recurrence was 4%. One-year systemic recurrence was seen in 22% while three-year systemic recurrence was seen in 20%. CONCLUSIONS: Colo-anal anastomoses after extended low anterior resection for distal rectal carcinoma can be conducted safely.

Pediatric presentation of splenic marginal zone lymphoma on FDG PET/CT scan.

Splenic marginal zone lymphoma (SMZL) comprises about 1% of B-cell lymphomas and typically occurs after the age of 50 years. Pediatric SMZL is very rare, and no FDG PET/CT imaging of the disease has been reported. In the current study, a 4-year-old boy with biopsy-proven SMZL had FDG PET/CT for staging, which showed increased metabolic activity in the spleen and left cervical lymph nodes. A second FDG PET/CT for evaluation of treatment response showed complete resolution of abnormal FDG uptake in the nodes and spleen with decrease in size of the nodes.

Traumatic left anterior descending coronary artery-right ventricle fistula: a case report.

Traumatic coronary artery-cameral fistulas (TCAF) are rare and may present secondary to penetrating injuries (80%) or iatrogenic traumas. Early operative intervention remains the recommended treatment modality for accidental traumatic coronary artery fistulas. We report the case of a 17-year-old man who presented with left anterior descending coronary artery-right ventricle fistula following penetrating cardiac trauma, which was successfully repaired surgically.

Primary Actinomycosis of the Breast Presenting as a Breast Mass.

BACKGROUND: Primary actinomycosis of the breast is a rare disease which may present as sinus tract or with mass-like features mimicking malignancy. Clinical presentation makes it difficult to distinguish primary actinomycosis from mastitis and inflammatory carcinoma. CASE REPORT: A 48-year-old woman presented with a mass in the left breast of 2 months duration. Physical examination was significant for a non-tender mass in the left breast. Histopathologic examination of the excisional biopsy of the mass showed granulomatous inflammation with grains of Actinomyces israelii. CONCLUSIONS: Actinomycosis of the breast usually presents as a recurrent abscess with fistulas. It may sometimes present as a breast lump, which is difficult to distinguish from inflammatory carcinoma. The diagnosis is made by histopathologic examination of the specimen, in which we can see the characteristic sulfur granules representing the bacterial colonies. Prolonged antibiotic therapy with penicillin is the treatment of choice.

Incidence of genitourinary cancers in the Islamic Republic of Iran: a survey in 2005.

We here report the incidence of different types of genitourinary cancers among the Iranian population according to the records of the Iran Ministry of Health and Medical Education. In a population-based cancer-registry study in 2005, all recorded data in pathology laboratories, freestanding cancer clinics and treatment centers, physician offices, and other state central registries were obtained with the assistance of Iran Universities of Medical Sciences and sent to the Diseases Management Center in the Health Ministry. The prevalences of urological cancers were as follows: bladder cancer 48.3%; prostate cancer 33.4%; renal cell carcinoma 10.3%; renal pelvis and ureter cancer 0.75%; testicular cancer 6.15%; penile cancer 0.15%; urethral cancer 0.45%; and other unspecified urinary cancers 0.43%. The male to female ratios for the various common urological cancers varied between 1.69 (renal cell carcinoma) and 7.75 (unspecified urinary cancers). The incidence of prostate cancer among our population was dramatically higher than in other countries of Asia. However, bladder cancer was found to be the commonest of the genitourinary cancers, especially in elderly patients, among our population.