CT Scan Images Of Patients Research Articles

An Empirical Evaluation of a Novel Ensemble Deep Neural Network Model and Explainable AI for Accurate Segmentation and Classification of Ovarian Tumors Using CT Images.

Ovarian cancer is one of the leading causes of death worldwide among the female population. Early diagnosis is crucial for patient treatment. In this work, our main objective is to accurately detect and classify ovarian cancer. To achieve this, two datasets are considered: CT scan images of patients with cancer and those without, and biomarker (clinical parameters) data from all patients. We propose an ensemble deep neural network model and an ensemble machine learning model for the automatic binary classification of ovarian CT scan images and biomarker data. The proposed model incorporates four convolutional neural network models: VGG16, ResNet 152, Inception V3, and DenseNet 101, with transformers applied for feature extraction. These extracted features are fed into our proposed ensemble multi-layer perceptron model for classification. Preprocessing and CNN tuning techniques such as hyperparameter optimization, data augmentation, and fine-tuning are utilized during model training. Our ensemble model outperforms single classifiers and machine learning algorithms, achieving a mean accuracy of 98.96%, a precision of 97.44%, and an F1-score of 98.7%. We compared these results with those obtained using features extracted by the UNet model, followed by classification with our ensemble model. The transformer demonstrated superior performance in feature extraction over the UNet, with a mean Dice score and mean Jaccard score of 0.98 and 0.97, respectively, and standard deviations of 0.04 and 0.06 for benign tumors and 0.99 and 0.98 with standard deviations of 0.01 for malignant tumors. For the biomarker data, the combination of five machine learning models-KNN, logistic regression, SVM, decision tree, and random forest-resulted in an improved accuracy of 92.8% compared to single classifiers.

Mesenchymal stromal cell therapy for COVID-19-induced ARDS patients: a successful phase 1, control-placebo group, clinical trial

BackgroundAcute respiratory distress syndrome (ARDS) is the devastating complication of the new COVID-19 pandemic, directly correlated with releasing large amounts of inflammatory cytokines. Due to their immunoregulatory features, mesenchymal stromal cells (MSCs) provide a promising approach against this disease. In this regard, this study was designed as a single-center, open-label, phase 1 clinical trial with a control group to examine the safety and explore the possible potency of three injections of umbilical cord-derived MSCs (UC-MSCs) in mild–moderate COVID-19-induced ARDS patients.MethodsTwenty confirmed COVID-19 patients with mild-to-moderate ARDS degree entered the study and were divided into two groups: control group (standard care) and intervention group (standard care + UC-MSCs). The patients received three intravenous infusions of UC-MSCs (1 × {10}^{6} cells/kg BW per injection) every other day. Respiratory markers, CRP levels and specific serum cytokines were assessed four times (days of 0, 5, 10 and 17) during the 17-day follow-up period.ResultsDuring the study, there were no serious adverse effects after cell transplantations. Besides, significant improvement in SPO2/FIO2 ratio and serum CRP levels was observed. On the other hand, a significant decrease (P < 0.05) in serum cytokine levels of IL-6, IFN-g, TNF-α, IL-17 A and a significant increase in serum cytokine levels of TGF-B, IL-1B and IL-10 were observed. Also, no significant changes were observed in CT scan images of patients during the study period.ConclusionOur obtained results demonstrated that multiple intravenous transplantations of allogenic UC-MSCs in non-severe COVID-19-induced ARDS patients are a safe procedure. In addition, this intervention is a hopeful approach to decline cytokine storm and recover respiratory functions. Indeed, more clinical trials with larger sample sizes are required to confirm these results.Trial registration This clinical trial was registered with the Iranian Registry of Clinical Trials (ID: IRCT20160809029275N1 at 2020.05.30).

Medical Image Three-Dimensional Simulation Technology in Hospital Clinical Practice

We performed three-dimensional reconstruction of facial CT scan images of patients with mandibular angle hypertrophy to explore the related factors of mandibular angle hypertrophy. At the same time, the article uses the results of three-dimensional reconstruction to simulate the clinical operation and obtain the final operation method. It was found that all patients were able to obtain the proper surgical plan from the three-dimensional reconstructed images and can get the hypertrophy factor of the mandibular angle. For this reason, we conclude that computer reconstruction simulation technology can obtain the tissue changes before and after osteotomy of mandibular angle hypertrophy and get the cause of hypertrophy. Three-dimensional reconstruction simulation technology is the best auxiliary diagnosis plan for the selection of mandibular angle surgery.

The value of artificial intelligence and imaging diagnosis in the fight against COVID-19.

The outbreak of the new type of coronavirus pneumonia (COVID-19) has caused a huge impact on the world. In this case, only by adhering to the prevention and control methods of early diagnosis, early isolation, and early treatment, can the spread of the virus be prevented to the greatest extent. This article uses artificial intelligence–assisted medical imaging diagnosis as the research object, combines artificial intelligence and CT medical imaging diagnosis, introduces an intelligent COVID-19 detection system, and uses it to achieve COVID-19 disease screening and lesion evaluation. CT examination has the advantages of fast speed and high accuracy, which can provide a favorable basis for clinical diagnosis. This article collected 32 lung CT scan images of patients with confirmed COVID-19. Two professional radiologists analyzed the CT images using traditional imaging diagnostic methods and artificial intelligence–assisted imaging diagnostic methods, and the comparison showed the gap between the two methods. According to experiments, CT imaging diagnosis assisted by artificial intelligence only takes 0.744 min on average, which can save a lot of time and cost compared with the average time of 3.623 min for conventional diagnosis. In terms of comprehensive test accuracy, it can be concluded that the combination of artificial intelligence and imaging diagnosis has extremely high application value in COVID-19 diagnosis.

Incidence and morphology of the incisive suture in CT scanning of young children and human fetuses.

Incisive suture is a suture classically described on the oral face of the palate in fetuses and young children. The aim of our study was to describe the evolution of the incisive suture in human fetuses and to evaluate the incidence of this suture in a population of young children under 4years, to determine if there is a possibility of improving the anterior growth of the maxilla, by stimulation of this suture. One hundred and thirty CT scan images of patients aged from birth to 48months have been studied and nine fetal palates aged from 18 to 26weeks of development, have been scanned using high-resolution X-ray micro-computed tomography RESULTS: The CT scan images of patients showed that an incisive suture was present in 33/130 cases (25,4%). All the patients with a suture were under 2years old. The fetal palate study showed that the suture was present in the inferior aspect of the palate (oral cavity) in all cases. The incisive suture increased from 18 to 24weeks. At 26weeks it stopped growing although the intercanine length increased. Considering the closure of the suture in a vertical plane, our study on fetuses has shown that the incisive suture is closing from its superior side (nasal side) to its inferior side. Considering all these results it appears to us that the incisive suture is partially ossified after birth, it cannot be stimulated by orthodontic appliances.

Advanced Deep Learning Embedded Motion Radiomics Pipeline for Predicting Anti-PD-1/PD-L1 Immunotherapy Response in the Treatment of Bladder Cancer: Preliminary Results

A key objective of modern medicine is precision medicine, whose purpose is to personalize the treatment based on the specific characteristics of the patients and their illness. To guide treatment decisions, it is generally necessary to have a sample of the neoplastic tissue, which is obtained only with biopsies or similar invasive surgical procedures. As tumors are heterogeneous in their volume and change over time, a dynamic analysis of diagnostic medical images can provide a better understanding of the entire tumor, both in the screening and follow-up phase. In this work, the authors proposed the use of a radiomics pipeline which is able to characterize the possible response of the oncological patients to the anti- programmed death-ligand protein 1 (PD-L1) immunotherapeutic treatment. The immunotherapeutic treatment consists of a modern therapeutic approach in which the physicians try to reactivate the patient's immune system so that it recognizes and destroys cancer cells. The oncological biomarkers capable of characterizing patients who can benefit from immunotherapy from those who would not, are being studied. One of them is related to the expression of the PD-L1 inhibitor in the surface of neoplastic cells which are analyzed in this paper, considering that the analyzed immunotherapeutic treatment is of the anti-PD-L1 type. In this context, the authors propose a pipeline for an immunotherapy response prediction based on the analysis of only CT-scan images of patients with metastatic bladder cancer. Using a framework based on the use of deep Autoeconder network, CT-scan images were analyzed to extract the features capable of discriminating the patient's response to anti-PD-L1 immunotherapy treatment from those who are not. The preliminary results obtained (accuracy of approximately 86% with a sensitivity of approximately 80% against a specificity of approximately 89%) on the analyzed patient dataset, allows the confirmation of the feasibility of the proposed method. Although validated in a dataset containing patients with only one tumor histology (bladder cancer), the proposed method shows how modern radiomics techniques can contribute significantly in the implementation of non-invasive predictive systems that support the physician in the therapeutic choice. The idea of the authors is to create a form of oncological point of care on an embedded platform that allows physicians to always have a support tool in choosing the best therapy to suggest to the patient.

Adaptive probabilistic approach for selecting tumour knee prosthesis

Tumour knee prostheses reconstruct bone gaps, left after resecting the tumour affected tissues, in limb salvage surgeries of bone cancer patients. They typically comprise of 6-12 different components chosen from a family of components that are manufactured in discrete variations (intended to cater to a wide range of patient conditions including gender, tumour position, leg (left/right), and resection length). These variations generate numerous combinations and selecting a correct set of components from a family of 100 or more total components has made the process difficult for a given patient. This article describes an adaptive probabilistic approach developed for selection of tumour knee prosthesis components, driven by geometric details. These details were extracted from the 3D virtual anatomical model, reconstructed from set of CT scan images of patients. The selection was performed in two steps. First, the grossly undersized and oversized components were eliminated. Then the geometric details of components were mapped, with the measured anatomical parameters of the patient, to form a fuzzy-logic based decision tree. This was based on pre-defined rules compiled from surgeons' experience. A set of measures (geometric difference, bone curvature, knee centre shift, and reconstruction length) were used to evaluate the selected prosthesis components. Evaluation was based on their suitability with respect to the patient's anatomy, and classified with a qualitative tag: ‘most suitable’, ‘probably suitable’, or ‘not suitable’. A case study of distal femur replacement is presented to explain the proposed methodology. This approach eliminates the risk of over and under sizing of the prosthesis components and reduces the average inventory to be maintained for each patient.

Brains--a computer advisor system to aid in CT scan interpretation and cerebral disease diagnosis.

This paper describes a prototype system to aid in the radiological interpretation of CT scan images of patients with cerebral disease. The system is able to provide guidance, both on diagnosis and the need for enhancement.