Search

Node embedding refers to learning or generating low-dimensional representations for nodes in a given graph. In the era of big data and large graphs, there has been a growing interest in node embedding across a wide range of applications, ranging from social media to healthcare. Numerous research efforts have been invested in searching for node embeddings that maximally preserve the associated graph properties. However, each embedding technique has its own limitations. This paper presents a method for generating deep neural node embeddings that encode dissimilarity scores between pairs of nodes with the help of prototype nodes spread throughout the target graph. The proposed technique is adaptable to various notions of dissimilarity and yields efficient embeddings capable of estimating the dissimilarity between any two pairs of nodes in a graph. We compare our technique against relevant state-of-the-art similar embedding techniques. Superior results have been demonstrated in a number of experiments using several benchmark datasets.

Objectives: To develop an imaging prognostic model for idiopathic pulmonary fibrosis (IPF) patients using hybrid auto-segmentation radiomics analysis, and compare the predictive ability between the radiomics analysis and conventional visual score methods. Methods: Data from 72 IPF patients who had undergone CT were analyzed. In the radiomics analysis, quantitative CT analysis was performed using the semi-auto-segmentation method. In the visual method, the extent of radiologic abnormalities was evaluated and the overall percentage of lung involvement was calculated by averaging values for six lung zones. Using a training cohort of 50 cases, we generated a radiomics model and a visual score model. Subsequently, we investigated the predictive ability of these models in a testing cohort of 22 cases. Results: Three significant prognostic factors such as contrast, Idn, and cluster shade were selected by LASSO Cox regression analysis. In the visual method, multivariate Cox regression analysis revealed that honeycombing and reticulation were significant prognostic factors. Subsequently, a predictive nomogram for prognosis in IPF patients was established using these factors. In the testing cohort, the c-index of the visual and radiomics nomograms were 0.68 and 0.74, respectively. When dividing the cohort into high-risk and low-risk groups using the median nomogram score, significant differences in overall survival (OS) in the visual and radiomics models were observed (P=0.000 and P=0.0003, respectively). Conclusions: The prediction model with hybrid radiomics analysis had a better ability to predict OS in IPF patients than that of the visual method.

Abstract To predict grade ≥ 2 radiation pneumonitis (RP) in patients with locally advanced non-small cell lung cancer (NSCLC) using multi-region radiomics analysis. Data from 77 patients with NSCLC who underwent definitive radiotherapy between 2008 and 2018 were analyzed. Radiomic feature extraction from the whole lung (whole-lung radiomics analysis) and imaging- and dosimetric-based segmentation (multi-region radiomics analysis) were performed. Patients with RP grade ≥ 2 or

Background: The current study aims to predict the recurrence of cervical cancer patients treated with radiotherapy from radiomics features on pretreatment T1- and T2-weighted MR images. Methods: A total of 89 patients were split into model training (63 patients) and model testing (26 patients). The predictors of recurrence were selected using the least absolute shrinkage and selection operator (LASSO) regression. The machine learning used neural network classifiers. Results: Using LASSO analysis of radiomics, we found 25 features from the T1-weighted and 4 features from T2-weighted MR images, respectively. The accuracy was highest with the combination of T1- and T2-weighted MR images. The model performances with T1- or T2-weighted MR images were 86.4% or 89.4% accuracy, 74.9% or 38.1% sensitivity, 81.8% or 72.2% specificity, and 0.89 or 0.69 of the area under the curve (AUC). The model performance with the combination of T1- and T2-weighted MR images was 93.1% accuracy, 81.6% sensitivity, 88.7% specificity, and 0.94 of AUC. Conclusions: The radiomics analysis with T1- and T2-weighted MR images could highly predict the recurrence of cervix cancer after radiotherapy. The variation of the distribution and the difference in the pixel number at the peripheral and the center were important predictors.

Abstract Background Schistosomiasis is prevalent in tropical and subtropical areas and rarely reported in developed countries. Schistosomiasis often occurs as a chronic illness, which can cause liver and intestinal damage. Appendicitis is an unusual complication of schistosomiasis. We herein present a case of acute appendicitis associated with the presence of schistosome eggs in a sailor from the Philippines. Case presentation A 34-year-old Filipino man who worked as a sailor presented to our hospital with a 2-day history of acute right lower quadrant abdominal pain and fever. A physical examination revealed right lower quadrant abdominal pain with signs of peritoneal irritation, including rebound tenderness. Computed tomography revealed thickening of the appendix associated with mural calcification and fluid collection around the cecum. Based on these findings, the preoperative diagnosis was acute appendicitis. Laparoscopic appendectomy was performed. Swelling of the appendix and contaminated ascites were observed intraoperatively, but there was no evidence of appendiceal perforation. A histopathological examination showed inflammation of the appendix wall and numerous ovoid bodies present within the submucosa, many of which were calcified. Severe infiltration of lymphocytes and fibrosis were recognized around the oval bodies. The numerous oval bodies were morphologically consistent with schistosomiasis. The final diagnosis was acute phlegmonous appendicitis associated with the presence of schistosome eggs. We examined the patient for signs of adult worm activity, but the results of stool ova and parasite examinations performed twice were negative. He was discharged and returned to his country on postoperative day 9. Conclusions The incidence of schistosomal appendicitis, which is seldom reported in developed countries, is expected to increase in Japan in the near future. Clinicians should suspect schistosome eggs as a cause of acute appendicitis in patients who have emigrated from or are traveling from endemic areas, and when mural calcification of the appendix is observed on imaging.

In November 2011, a 61-year-old woman was diagnosed with squamous cell carcinoma (SCC) of the cervix in a uterus didelphys with vaginal septum. The patient was diagnosed with Fédération Internationale de Gynécologie et d’Obstétrique (FIGO) stage IIB because of infiltration to the left parametrium without infiltration to the pelvic wall. The patient was treated with external-beam radiotherapy (EBRT) and brachytherapy (BT), using concomitant chemotherapy with cisplatin. A total of 50 Gy were delivered (2 Gy/fraction/day) to the pelvis, with a central shield after 40 Gy. The patient was treated four times with BT (6 Gy × 4 fractions), with tandem and ovoid applicators inserted once to the left side; tandem to the left side and ovoid bilaterally were inserted twice; and tandem to the right side and ovoid bilaterally were inserted once. Six years and 8 months after the start of treatment, the patient had had no relapse or severe late adverse effects. For accurate diagnosis and optimal treatment of the uterus didelphys, careful interview and pelvic examination at initial diagnosis of a patient are very important.

PurposeThe current study proposed a model to predict the response of brain metastases (BMs) treated by Gamma knife radiosurgery (GKRS) using a machine learning (ML) method with radiomics features. The model can be used as a decision tool by clinicians for the most desirable treatment outcome.Methods and MaterialUsing MR image data taken by a FLASH (3D fast, low-angle shot) scanning protocol with gadolinium (Gd) contrast-enhanced T1-weighting, the local response (LR) of 157 metastatic brain tumors was categorized into two groups (Group I: responder and Group II: non-responder). We performed a radiomics analysis of those tumors, resulting in more than 700 features. To build a machine learning model, first, we used the least absolute shrinkage and selection operator (LASSO) regression to reduce the number of radiomics features to the minimum number of features useful for the prediction. Then, a prediction model was constructed by using a neural network (NN) classifier with 10 hidden layers and rectified linear unit activation. The training model was evaluated with five-fold cross-validation. For the final evaluation, the NN model was applied to a set of data not used for model creation. The accuracy and sensitivity and the area under the receiver operating characteristic curve (AUC) of the prediction model of LR were analyzed. The performance of the ML model was compared with a visual evaluation method, for which the LR of tumors was predicted by examining the image enhancement pattern of the tumor on MR images.ResultsBy the LASSO analysis of the training data, we found seven radiomics features useful for the classification. The accuracy and sensitivity of the visual evaluation method were 44 and 54%. On the other hand, the accuracy and sensitivity of the proposed NN model were 78 and 87%, and the AUC was 0.87.ConclusionsThe proposed NN model using the radiomics features can help physicians to gain a more realistic expectation of the treatment outcome than the traditional method.

Background: This study aimed to propose a machine learning model to predict the local response of resectable locally advanced esophageal squamous cell carcinoma (LA-ESCC) treated by neoadjuvant chemoradiotherapy (NCRT) using pretreatment 18-fluorodeoxyglucose positron emission tomography (FDG PET) images. Methods: The local responses of 98 patients were categorized into two groups (complete response and noncomplete response). We performed a radiomics analysis using five segmentations created on FDG PET images, resulting in 4250 features per patient. To construct a machine learning model, we used the least absolute shrinkage and selection operator (LASSO) regression to extract radiomics features optimal for the prediction. Then, a prediction model was constructed by using a neural network classifier. The training model was evaluated with 5-fold cross-validation. Results: By the LASSO analysis of the training data, 22 radiomics features were extracted. In the testing data, the average accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve score of the five prediction models were 89.6%, 92.7%, 89.5%, and 0.95, respectively. Conclusions: The proposed machine learning model using radiomics showed promising predictive accuracy of the local response of LA-ESCC treated by NCRT.

The effect of dose-delivery time with flattening filter (FF) and flattening filter-free (FFF) photon beams based on microdosimetric kinetic model (MKM) was investigated in this study. Monte Carlo simulation with the particle and heavy ion transport code system (PHITS) was performed to calculate the dose-mean lineal energy yD (keV/μm) of FF and FFF 6 MV photon beams using the IAEA phase-space files of Varian TrueBeam linear accelerator. Human non-small cell lung cancer NCI-H460 cells were used to determine the MKM parameters under the condition that dose-delivery times with continuous irradiation were 1, 5, 10, 30, and 60 min, and the adsorbed dose was 2, 4, and 8 Gy in this study. In addition, the relative biological effectiveness (RBE) of FF and FFF photon beams were calculated for evaluating the effect of dose delivery time. The RBE of FF decreased to 99.8% and 97.5% with 5 and 60 min for 2 Gy in comparison to 99.6% and 95.1% for 8 Gy, respectively. Meanwhile, that of FFF decreased to 99.5% and 94.9% with 5 and 60 min for 2 Gy in comparison to 99.5% and 94.9% for 8 Gy, respectively. Dose-delivery time has an effect on the RBE with photon beams. In other words, the dose-delivery time should be considered during radiation therapy. Furthermore, FFF photon beams were an effective irradiation method compared to FF in dose-delivery time on account of improving clinic throughput.

A 21-year-old male patient was transferred to the emergency room of our hospital after suffering seat belt abdominal injury in a traffic accident. Abdominal computed tomography revealed a massive hematoma in the abdominal cavity associated with deep hepatic lacerations in the right lobe. The presence of a solid tissue possibly containing pneumobilia was observed above the greater omentum. These findings were consistent with a tentative diagnosis of hepatic laceration due to blunt trauma; therefore, this prompted us to perform emergency laparotomy. The operative findings revealed a massive hematoma and pulsatile bleeding from the lacerated liver and a retroperitoneal hepatoma, which was most likely due to subcapsular injury of the right kidney. In accordance with the preoperative imaging studies, a pale liver fragment on the greater omentum was observed, which was morphologically consistent with the defect in the posterior segment of the liver. Since the damaged area of the liver broadly followed the course of the middle hepatic vein, we carefully inspected and isolated the inflow vessels and eventually performed a right hepatic lobectomy. The patient’s postoperative course was uneventful, and he was doing well at 10 months after surgery.

Background: The objective was to enhance the biological compensation factor related to irradiation interruption in a short time (short irradiation interruption) in hypoxic tumors using a refined microdosimetric kinetic model (MKM) for photon radiation therapy. Materials and methods: The biological dose differences were calculated for CHO-K1 cells exposed to a photon beam, considering interruptions of (τ) of 0-120 min and pO2 at oxygen levels of 0.075-160 mm Hg. The interrupted dose fraction (IDF) was defined as the percentage ratio of the dose delivered before short irradiation interruption to the total dose, which ranged from 10-90%. The compensated dose was calculated based on an IDF of 10-90% for a dose of 2-8 Gy and oxygen levels of 0.075-160 mm Hg. Results: The Δ with and without short irradiation interruption was more pronounced with a higher dose and increased pO2. It exceeded 3% between IDF of 50% and either 10% or 90% and occurred more than τ = 50 min at 0.075 mm Hg, τ = 20 min at 3 mm Hg, τ = 20 min at 8 mm Hg, τ = 20 min at 15 mm Hg, τ = 20 min at 38 mm Hg, and τ = 20 min at 160 mm Hg. The dose compensation factor was greater at higher IDF rates. Conclusion: The biological dose decreased with longer interruption times and higher oxygen concentrations. The improved model can compensate for the biological doses at various oxygen concentrations. Advances in knowledge: The current study improved the dose compensation method for the decrease in the biological effect owing to short irradiation interruption by considering the oxygen concentration. [ABSTRACT FROM AUTHOR]