CT Scan Images Research Articles

Comprehensive Approach to TB Diagnosis Powered by Machine Learning in Endemic Countries

Abstract Introduction/Objective Tuberculosis (TB), a leading cause of mortality worldwide, is primarily diagnosed through methods that face numerous challenges, including lengthy result times and diagnostic inaccuracy, particularly in the context of drug-resistant strains and latent infections. This study proposes a novel approach that integrates multiple diagnostic modalities with machine learning to enhance TB diagnosis accuracy. Methods/Case Report The Machine learning model was tailored for the classification of radiological images, specifically CT scans, using original DICOM images to preserve valuable voxel information. The study involved a curated dataset of CT scans from Pakistan, TB-positive (smear+/Culture+ n=72; smear+/culture- n= 3; smear-/Culture+ n=16; smear-/Culture- n=14; clinical and radiological diagnosis only n= 12) and healthy (n=103) scans from COVID-CTSet were included in the training to assess the specificity of the model. Data preprocessing included noise reduction, histogram matching, and data augmentation techniques to ensure a robust training dataset. The methodology also incorporated using k-fold cross validation and a custom learning rate scheduling strategy to optimize the model’s training process. To further test its robustness, the model was evaluated by swapping random patches and analyzing 60 mm patches from the entire CT scan for local feature categorization. Results (if a Case Study enter NA) The model has demonstrated outstanding performance, with sensitivity and specificity exceeding 95% on our internal dataset (n=117) and aligning well with clinical, smear, culture, and anti-TB antibody findings. It also showed promising results on the external NIH TB Portal’s dataset (n= 1,460). The model is robust to variations in CT scanner image quality and noise profiles, maintaining strong generalization across datasets. Even when analyzing random 60mm patches, effectively classifying all local features Conclusion Our study enhances tuberculosis diagnostic methods in endemic regions by blending machine learning with conventional diagnostic techniques. This approach improves TB detection, particularly the early and accurate identification in areas impacted by drug-resistant strains and asymptomatic latent infections. By integrating radiological and clinico-pathological data, we aim to develop a comprehensive diagnostic score. Moving forward, we plan to further integrate this method into clinical decision support systems and adapt the approach to other infectious diseases.

Analysis of Failed Posterior Fossa Decompression and an Effective Revision Surgery in Patients with Basilar Invagination and Atlantoaxial Dislocation.

The objective of this study was to analyze failed posterior fossa decompression (PFD) in patients with basilar invagination and atlantoaxial dislocation (BI-AAD). Revision surgery in these patients is challenging and has been rarely reported. In addition, the anatomical variations of the vertebral artery increase the risk of revision surgery. Here, we introduce the implementation of a new type of one-stage posterior revision surgery, whose difficulties and effects are summarized. A total of 21 patients with BI-AAD who underwent PFD were retrospectively analyzed in our center from November 2017 to April 2021. The revision surgery in all patients was performed through the posterior approach. The Japanese Orthopaedic Association (JOA) score and the Short Term 12 (SF-12) score were employed to evaluate the clinical symptoms and health status. The distance from the tip of the odontoid to Chamberlain's line (DCL), the atlantodental interval (ADI), the clivus-canal angle (CCA), the diameter of the subarachnoid space (DSS), and the craniovertebral junction triangular area (CTA) were assessed radiographically. The pre- and postoperative results were compared by paired t test. The data of 21 consecutive patients were reviewed, with an average follow-up period of 28 ± 14 months. Postoperative imaging showed effectively reduced compression of BI-AAD. No implant failure or neurovascular injury occurred. Eleven patients had vertebral artery abnormalities, but none had vertebral artery injury. All patients had evidence of bone fusion on the CT scan images within a 12-month follow-up period. The JOA and SF-12 scores were significantly improved 1 year postoperatively (p < 0.001). Posterior surgery using the technique of interarticular distraction, fusion with cage grafting, and fixation is a safe and effective revision surgery to treat patients with basilar invagination and atlantoaxial dislocation who failed PFD, which will result in good outcome.

Determining the Optimal Morphometry of Pedicle Screws in Lumbar and Thoracic Spine in the Iranian Population

Background: The improper length and direction of pedicle screw may also cause it to penetrate the adjacent organs. Unknowing the safe zone of dimensions and directions of the pedicles is essential to proper screw placement. Methods: The present study is a cross-sectional morphometric study on patients with spinal trauma referred to the neurosurgical department in 2021. The MARCO PACS software scale measured the CT scan images and included the vertebral left pedicle diameter, pedicle body distance, body aorta distance, pedicle diameter, height, and area. The entry point and direction of the pedicle screw were made with the “free-hand” method. Results: 301 patients were included, consisting of 113 females (37.5%) and 188 males (62.5%). The mean age of the participants was 42.87±12.3 years. “Among all T12 vertebra parameters, just body aorta distance was not significant between genders (p-value=0.311). The pedicle height and body aorta distance were lowest among 18-35 years patients (p-value=0.001) (p-value=0.003), respectively. Post-hoc analysis revealed a significant difference between 18-35 and 51-70 years for body aorta distance in the L1 vertebra (p-value=0.002). Conclusion: The present investigation has shown significant differences between genders for optimal left pedicle screw parameters, which should be considered before surgery.

Multifractal Analysis in Age-Based Classification for COVID-19 Patients’ CT-Scan Images with Different Noise Levels

Recently, many number of people various countries contracted the COVID-19 (C-19) disease. The identification of this harmful disease and other pneumonia diseases is an important process in the medical world. CT-Scan is mainly prescribed to predict the severity of lung diseases affected by C-19 and other pneumonia diseases. Generally, a CT-Scan image is represented as a grayscale image (GI). Biomedical-oriented GIs are more complex and they are too difficult to recognize the status of lung diseases directly from the experimental images. To address this type of medical problem, a multifractal approach can be applied to analyze and illustrate the GIs in detail. Therefore, the multifractal dimensional analysis is used to diagnose and explore the vehemence of the contamination levels in the lungs. In this study, the complexity of CT-Scan images of C-19 patients is analyzed in order to perform a comparison in terms of age and noise levels. It was also discovered that the intricate of CT-Scan images is considerably varied for patients aged 50 and above when compared to younger subjects. This comparative study indicates that the deadly virus affects elderly persons compared to youngsters. The proposed age-based classification is supported by image processing techniques, qualitative measures, and statistical tools. The obtained results are demonstrated graphically by Generalized Fractal Dimensions (GFD) spectrum, 3D visualization, ANOVA table, and box plots to expose the rate of discrimination of complexity in CT-Scan lung images.

Estimation and experiment on acoustic properties of rice straw (estimation of sound absorption coefficient based on CT image)

The sound absorption characteristics of rice straw were estimated using micro-CT scan images and theoretical analysis. Since it is difficult to express the structure and dimensions of rice straw in a regular manner, the voids in the straw were approximated as clearance between two parallel planes based on the micro-CT scan images. Using the surface area of the straw and the volume of the voids, a theoretical estimation of the sound absorption coefficient of the straw was made. Propagation constants, characteristic impedance, and normal incident sound absorption coefficient were obtained for the derived clearance. Since the rice straw is tubular, the sound absorption coefficient was also obtained assuming that an arbitrary CT scan image is continuous in the thickness direction. In addition, the sound absorption coefficient was estimated from ordinary photographs taken of the sample incident surface. In the experiments, the sound absorption coefficient was measured using a two-microphone impedance tube. The theoretical values were close to the experimental value.

Experimental study on acidizing of natural gas hydrate reservoirs

Abstract Natural gas hydrates (NGH) are a promising resource. Due to the weak cementation of hydrate reservoirs, the reservoirs are prone to sand production or destabilization during hydrate dissociation. Samples of hydrate sediments were manually prepared, consolidated using a cementing agent, and then subjected to flow experiments using an acid solution. Comparative experiments were also conducted with unconsolidated samples. The consolidation samples could maintain the skeleton morphology after acidizing, and no sand production was observed; the unconsolidated samples had severe skeleton deformation after acidizing and serious sand production. The permeability of the consolidation samples after acidizing was 2.95mD, and porosity increased by 8.56%; the permeability of the unconsolidated samples after acidizing was 1.26mD, and the porosity decreased by 7.45%. CT scan images and mercury intrusion curves show good pore development after acidizing the consolidation samples, while the unconsolidated samples have poor pore development and sand plugging after acidizing. This result is because the cementing agent can consolidate the sand and gravel so that it will not be dislodged and transported during the acidizing process, thus maintaining reservoir stability. This study demonstrates the feasibility of acid modification technology in hydrate reservoirs, which is informative for the safe development of gas hydrates.

FocalNeXt: A ConvNeXt augmented FocalNet architecture for lung cancer classification from CT-scan images

Early and accurate diagnosis of lung cancer, a life-threatening disease, is critical to the successful treatment of patients with the disease. On the other hand, it is well known that the integration of computer-aided diagnosis (CAD) systems into the diagnostic workflow facilitates the process and improves the diagnostic results of automated systems by reducing the difficulties associated with human observation. In this paper, we present FocalNeXt, a new ConvNeXt-augmented FocalNet architecture specifically designed for automated lung cancer detection from computed tomography (CT) scan images. By combining the strong attention mechanism of FocalNet and the feature extraction mechanism of ConvNeXt within the vision transformer paradigm, FocalNeXt aims to improve diagnostic accuracy. Our comprehensive evaluation of a publicly available Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases (IQ-OTH/NCCD) CT-scan dataset includes rigorous comparisons and an ablation study. FocalNeXt achieved an accuracy of 99.81%, outperforming the state-of-the-art methods. The model also excelled in sensitivity (99.78%), recall (99.36%), and F1-score (99.56%), positioning FocalNeXt as a leading model for lung cancer detection. The ablation study further demonstrated its efficacy and underscored the robustness of FocalNeXt in different configurations. The results underline its potential to contribute to advances in medical imaging and personalized healthcare.

Fibre waviness reduction in thermoplastic pultrusion by using DREF yarns

Non-reactive thermoplastic pultrusion impregnation issues are mitigated by using hybrid input materials. Co-wound (CW) and commingled yarns are an assembly of continuous polymer and reinforcement fibres. Continuous thermoplastic fibres have shown to induce waviness in the reinforcement fibres during pultrusion due to their shrinkage at high temperature. DREF yarns are composed of a core of continuous reinforcement fibres onto which discontinuous polymer fibres are applied using the friction spinning process. This study, based on the application of 3N and 0N tension on CW and DREF yarns, aimed to highlight the contribution of discontinuous polymer fibres on reducing reinforcement waviness in pultruded rods. CW yarns’ reaction to heating showed continuous polyethylene terephthalate (PET) fibres shrinkage resulting in wavy glass fibres (GF). Conversely, the GF in DREF yarns remained straight. Pultrusion experiments with yarn tension of 3N were done to alleviate the GF waviness. However, the porosity was rather high at 4.2% for CW rods and 2.3% for DREF rods. Pultrusion experiments without tension showed lower porosity of level of 2.9% for CW yarns and as low as 1.1% for DREF yarns. However, CT-scan image indicated GF waviness in CW rods. GF in DREF rods remained straight. The in-plane shear strength reached 119 MPa. Thermoplastic pultrusion using DREF yarns resulted in composites without reinforcement fibre waviness, lower porosity level and superior shear strength.

Impact of scapula anatomical landmark positioning on scapular orientation using CT-based 3D models: an intra-observer repeatability and inter-observer reproducibility study

HypothesisThe primary objective of this study was to assess intra-observer repeatability and inter-observer reproducibility of the 3D coordinates of a set of scapula anatomical landmarks obtained by manual positioning on conventional supine CT-scan based scapula surface models. The secondary objective was to assess intra-observer repeatability and inter-observer reproducibility of the resulting 3D scapular orientation. It was hypothesized that the 3D scapular orientation reliability would be better or similar than established reliability of intra-operative baseplate positioning (i.e. version and inclination) in reverse total shoulder arthroplasty (rTSA). MethodsThree anatomical landmarks, i.e. acromial angle (AA), inferior angle (IA), and trigonum scapulae (TS), were manually positioned on 81 scapula surface models using updated landmark definitions. These models were obtained by the segmentation of CT-scan images acquired from patients undergoing elective rTSA procedures at the Department of Surgery at Geneva University Hospitals between May 2022 and December 2023. This procedure was repeated 3 times per scapula by 3 independent observers. A set of parameters corresponding to the 3D landmark coordinates (expressed in an average scapula coordinate system) and the 3D scapular orientation (expressed as three angles related to the retraction/protraction, lateral/medial rotation, and internal/external rotation) were computed. Intra-observer repeatability and inter-observer reproducibility were assessed for each of these parameters using an intra-class correlation as a relative reliability metric. Standard error of measurement (SEM) was also reported as an absolute reliability metric. ResultsIntra-observer ICC and inter-observer ICC ranged from poor to moderate for AA, poor to excellent for IA, and poor to excellent for TS. However, low SEM, ranging from 0.4 mm to 2.4 mm for intra-observer repeatability and from 0.2 mm to 1.8 mm for inter-observer reproducibility, were obtained for every coordinate of each anatomical landmark. This results in poor to moderate intra-observer ICC and inter-observer ICC for scapula angular orientation. Again, low SEM, ranging from 0.4° to 0.8° for intra-observer repeatability and 0.4° to 0.6° for inter-observer reproducibility, were obtained, arguing for reliable measurements. Discussion and ConclusionThis study demonstrates that manual positioning of the three scapula anatomical landmarks recommended by the International Society of Biomechanics can be performed in a reliable manner across measures and observers on surface bone models obtained from CT-scan images. However, a clear and standardized definition of these landmarks is needed to ensure consistency across measurements.

Flexural properties of fiber-reinforced concrete using hybrid recycled steel fibers and manufactured steel fibers

This study investigates the flexural properties of fiber-reinforced concrete (FRC) using a hybrid mix of recycled steel fibers (RSF) from waste tires and manufactured steel fibers (MSF). The aim of this study is to demonstrate hybrid steel fiber reinforcement as a more environmentally sustainable alternative to traditional single-fiber systems, by assessing whether hybrid reinforcement can achieve or surpass the performance of conventional single-manufactured steel fiber reinforcement. Using a novel four-stage methodology, this paper presents a comprehensive and detailed evaluation of mechanical and ductility performance through three-point bending tests, digital image correlation (DIC), CT-scans, and scanning electron microscopy (SEM). The results from flexural stress-deflection curves were used to evaluate the flexural strength and toughness. This was followed by an in-depth eight-stage DIC analysis and Surface Damage Index (SDI) curves throughout the test. CT-scan images were used to quantify the proportion of fibers classified as pulled-out, ruptured, or bridging the crack, while SEM analyzed the efficiency of fiber reinforcement through microstructural evaluations, further validating the findings of this study. Results show that hybrid reinforcement significantly enhances both toughness and ductility while reducing surface damage. MSFs in the hybrid system improve post-peak ductility and energy absorption by bridging large cracks, while RSFs prevent micro-cracks, increasing pre-peak rigidity. CT-scan analysis reveals that the inclusion of RSFs reduces pulled-out MSFs by 26%, further boosting flexural performance. SEM confirms the superior bond of MSFs with the concrete matrix in hybrid samples. Additionally, higher fiber content in FRC enhances toughness and ductility while reducing surface damage. This research advances our understanding of hybrid fiber-reinforced concrete and promotes more sustainable construction practices through the use of recycled steel fibers. By leveraging the combination of new methodologies, the study effectively targets gaps in the current research landscape, offering a comprehensive approach to improving performance and sustainability in construction materials.

Unconventional reservoir stimulation method based on electrohydraulic discharge shock and frequency resonance technology

To increase the production of unconventional oil and gas, it is necessary to improve reservoir porosity through reservoir reconstruction. High voltage electro-hydraulic discharge can generate strong shock waves, which not only meets the requirements of reservoir reconstruction, but also has the advantages of high efficiency and environmental protection, and has become a research hotspot. In order to further improve the effectiveness of reservoir transformation, a reservoir stimulation method based on electrohydraulic discharge shock and frequency resonance is proposed. Firstly, an electrohydraulic discharge equipment was designed, and according to the material and structure of the designed rod plate electrode, a theoretical electrohydraulic discharge model was built based on the bubble theory. The high voltage breakdown process under the condition of applied voltage of 12 kV and electrode gap of 2 mm is simulated in detail. The simulation results show that the discharge time is within 0.3 μs, and the extremely short discharge time not only produces strong shock waves, but also forms an arc channel to cause circuit damping oscillation. Then, an electrohydraulic discharge experimental platform was built according to the developed equipment. The discharge process was recorded by a high-precision oscilloscope, and the arc formation was photographed by a high-speed camera. The experimental results not only verify the correctness of the theoretical analysis, but also confirm that the developed electro-hydraulic discharge device can generate 0-60 Hz adjustable electrical pulses and has the ability to cause reservoir resonance. Finally, a comparative experiment was carried out with shale core samples to test the influence of resonance factors on the development of internal fractures in unconventional reservoir rocks. The CT scan images show that the shale fracture porosity in the resonance group increased by 46.4 %, which is much higher than that in the non-resonance group (11.8%). To further test the frequency resonance effect on reservoir reconstruction, a field test was carried out on the coalbed methane wells in Shanxi using the developed equipment. The experimental results show that the average gas production rate after on-site construction is increased from 11.46 m3/h to 12.49 m3/h, an increase of 8.99 %, indicating that the proposed technology can significantly promote the development of rock fractures and enhance the production recovery.

A Multidisciplinary Assessment of Standard Low Dose Versus Ultra-low Dose Chest CT Scans for Pectus Excavatum Imaging

AimEvaluation of ultra-low dose chest CT imaging for the assessment of pectus excavatum severity as determined by pediatric radiologists and pediatric surgeons using Haller (HI) and Correction indices (CI). MethodsA single institution, prospective evaluation of patients being evaluated for pectus excavatum were scanned with a standard low-dose chest CT protocol (CARE) followed by a consecutive ultra-low dose CT scan (ULTRA). 3 surgeons and 4 radiologists were instructed to determine HI and CI in each series. The Intraclass Correlation Coefficient (ICC) was used to calculate the agreement level between CARE and ULTRA. Bland–Altman (BA) and scatter plots were also performed to determine bias of each approach. Results32 patients had CARE and ULTRA consecutively. The ICC for HI demonstrated good reliability with a value of 0.89 and excellent reliability for CI with a value of 0.91. The reliability for HI was greater in the surgeon group (0.89) compared to the radiologist group (0.88). The reliability for CI was greater in the radiologist group (0.92) compared to the surgeon group (0.90). The Bland Altman plots for the HI and CI demonstrate no consistent bias for CARE or ULTRA approach when evaluating HI and CI. ConclusionUltra-low dose CT scan imaging compared to standard low-dose CT appears to be a reliable alternative for evaluating PE severity as assessed by HI and CI. This work supports the evaluation and potential development of a standardized CT imaging protocol capable of reducing radiation exposure without sacrificing imaging for PE patients. Level of Evidence2.

An Artificial Intelligence Algorithm Integrated into the Clinical Workflow Can Ensure High Quality Acute Intracranial Hemorrhage CT Diagnostic.

Intracranial hemorrhage (ICH) is alife-threatening condition requiring rapid diagnostic and therapeutic action. This study evaluates whether Artificial intelligence (AI) can provide high-quality ICH diagnostics and turnaround times suitable for routine radiological practice. Aconvolutional neural network (CNN) was trained and validated to detect ICHs on DICOM images of cranial CT (CCT) scans, utilizing about 674,000 individually labeled slices. The CNN was then incorporated into acommercial AI engine and seamlessly integrated into three pilot centers in Germany. Areal-world test-dataset was extracted and manually annotated by two experienced experts. The performance of the AI algorithm against the two raters was assessed and compared to the inter-rater agreement. The overall time ranging from data acquisition to the delivery of the AI results was analyzed. Out of 6284 CCT examinations acquired in three different centers, 947 (15%) had ICH. Breakdowns of hemorrhage types included 8% intraparenchymal, 3% intraventricular, 6% subarachnoidal, 7% subdural, < 1% epidural hematomas. Comparing the AI's performance on asubset of 255 patients with two expert raters, it achieved asensitivity of 0.90, aspecificity of 0.96, an accuracy of 0.96. The corresponding inter-rater agreement was 0.84, 0.98, and 0.96. The overall median processing times for the three centers were 9, 11, and 12 min, respectively. We showed that an AI algorithm for the automatic detection of ICHs can be seamlessly integrated into clinical workflows with minimal turnaround time. The accuracy was on par with radiology experts, making the system suitable for routine clinical use.

Non-invasive, fast, and high-performance EGFR gene mutation prediction method based on deep transfer learning and model stacking for patients with Non-Small Cell Lung Cancer

PurposeTo propose an intelligent, non-invasive, highly precise, and rapid method to predict the mutation status of the Epidermal Growth Factor Receptor (EGFR) to accelerate treatment with Tyrosine Kinase Inhibitor (TKI) for patients with untreated adenocarcinoma Non-Small Cell Lung Cancer. Materials and methodsReal-world data from 521 patients with adenocarcinoma NSCLC who performed a CT scan and underwent surgery or pathological biopsy to determine EGFR gene mutation between January 2021 and July 2022, is collected. Solutions to the problems that prevent the model from achieving very high precision, namely: human errors made during the annotation of the database and the low precision of the output decision of the model, are proposed. Thus, among the 521 analyzed cases, only 40 were selected as patients with EGFR gene mutation and 98 cases with wild-type EGFR. ResultsThe proposed model is trained, validated, and tested on 12,040 2D images extracted from the 138 CT scans images where patients were randomly partitioned into training (80 %) and test (20 %) sets. The performance obtained for EGFR gene mutation prediction was 95.22 % for accuracy, 960.2 for F1_score, 95.89 % for precision, 96.92 % for sensitivity, 94.01 % for Cohen kappa, and 98 % for AUC. ConclusionAn EGFR gene mutation status prediction method, with high-performance thanks to an intelligent prediction model entrained by highly accurate annotated data is proposed. The outcome of this project will facilitate rapid decision-making when applying a TKI as an initial treatment.

Identification of hepatic metastasis from an unrevealed adenoid cystic carcinoma by PET/CT: A case report.

Adenoid cystic carcinoma is a rare malignant tumor of the salivary glands, with few reports of metastasis to the liver in the literature. We present a case where an isolated hepatic lesion of adenoid cystic carcinoma was identified using 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT). A 76-year-old male experienced abdominal pain and underwent an enhanced CT scan and magnetic resonance imaging, which revealed a liver mass. Subsequent 18F-FDG PET/CT identified hypermetabolic lesions in both the left and right lobes of the liver, suggesting malignancy, with no other abnormalities detected. A liver biopsy confirmed the diagnosis of adenoid cystic carcinoma. No intervention. Following confirmation of the diagnosis, the patient chose to discontinue treatment and was discharged. Hepatic metastasis from adenoid cystic carcinoma may be detected before the identification of the primary lesion. 18F-FDG PET/CT plays a critical role in differentiating benign from malignant liver tumors, selecting potential biopsy sites, and assessing the extent of metastatic disease.

Synthesis of targeted doxorubicin-loaded gold nanorod −mesoporous manganese dioxide core–shell nanostructure for ferroptosis, chemo-photothermal therapy in vitro and in vivo

In the current study, a core–shell inorganic nanostructure comprising a gold nanorod core and −mesoporous manganese dioxide shell was synthesized. Then, the mesoporous manganese dioxide shell was loaded with doxorubicin (DOX) and then coated with pluronic F127 and pluronic F127-folic acid conjugate (1.5:1 wt ratio of pluronic F127: pluronic F127-folic acid conjugate) to prepare targeted final platform. In this design, mesoporous manganese dioxide acted as a reservoir for DOX loading, anti-hypoxia, and MRI contrast agent, while the gold nanorod core acted as a photothermal and CT scan imaging agent. DOX was encapsulated in the mesoporous manganese dioxide shell with a loading capacity and loading efficiency of 19.8 % ± 0.2 and 99.0 % ± 0.9, respectively. The in vitro release experiment showed the impact of glutathione (GSH), mildly acidic pH, and laser irradiating toward accelerated stimuli-responsive DOX release. The ·OH production of the prepared platform was verified by methylene blue (MB) decomposition reaction. Furthermore, thermal imaging exhibited the ability of the prepared platform to convert the NIR irradiation to heat. In vitro cytotoxicity tests on the folate receptor-positive 4 T1 cell line revealed the remarkable cytotoxicity of the targeted formulation compared to the nontargeted formulation (statistically significant). The MTT experiment demonstrated that exposure to laser 808 irradiation enhanced cytotoxicity of the targeted formulation (p < 0.0001). The production of ROS in 4 T1 cells following treatment with the targeted formulation was demonstrated by the dichloro-dihydro-fluorescein diacetate (DCFH-DA) assay. Furthermore, in vivo investigations by implementing subcutaneous 4 T1 tumorized female BABL/c mice indicated that the prepared platform was an effective system in suppressing tumor growth by combining chemotherapy with PTT (photothermal therapy). Additionally, simultanous PTT and anti-hypoxic activity of this system showed potent tumor growth suppression impact. The percent of tumor size reduction in mice treated with FA-F127-DOX@Au-MnO2 + 808 nm laser compared to the control group was 99.7 %. The results of the biodistribution investigation showed tumor accumulation and modified pharmacokinetics of the targeted system. Lastly, 6 and 24 h post-intravenous injection, CT-scan and MR imagings capability of the prepared platform was verified in preclinical stage. The prepared multipurpose system introduces great opportunity to provide multiple treatment strategy along with multimodal imaging capability in a single platform for breast cancer treatment.

COVID-19 diagnosis based on CT scan image segmentation using multi-scale convolutional neural network

The COVID-19 pandemic continues to pose significant health challenges worldwide. While traditional methods like Reverse Transcription Polymerase Chain Reaction (RT-PCR) are widely used for diagnosis, they often suffer from limitations in speed and accessibility. This chapter proposes an automatic COVID-19 diagnosis technique using CT scan image segmentation, offering a promising alternative for early detection. The proposed method leverages Convolutional Neural Networks (CNNs), enhanced with a multi-scale approach, to capture more detailed semantic features and achieve high-quality segmentation despite challenges such as low image resolution, varying infection characteristics, and limited training data. To address the data scarcity issue, various data augmentation techniques, including scale variation, translation, and rotation, were applied to enhance the model's performance. The proposed CNN was evaluated using the COVID-19 CT dataset, achieving an overall accuracy of 96.85%, with COVID-19 sensitivity at 93.31%, Common Pneumonia sensitivity at 92.93%, and a true negative rate of 97.82%. These results demonstrate the effectiveness and efficiency of the proposed method in detecting COVID-19 at an early stage, reducing the need for human intervention, and accelerating the diagnostic process. Compared to existing methods, this approach offers significant improvements in accuracy and reliability, making it a valuable tool in the ongoing fight against the pandemic.

Investigation of Type A Aortic Dissection Using Computational Modelling.

Aortic dissection is a catastrophic failure of the endothelial wall that could lead to malperfusion or rupture. Computational modelling tools may help detect arterial damage. Technological advancements have led to more sophisticated forms of modelling being made available to low-grade computers. These devices can create 3D models with clinical data, where the clinical blood pressure waveforms' model can be used to form boundary conditions for assessing hemodynamic parameters, modelling blood flow propagation along the aorta to predict the development of cardiovascular disease. This study presents patient-specific data for a rare case of severe Type A aortic dissection. CT scan images were taken nine months apart, consisting of the artery both before and after dissection. The results for the pre-dissection CT showed that the pressure waveform at the ascending aorta was higher, and the systolic pressure was lagging at the descending aorta. For the post-dissection analysis, we observed the same outcome; however, the amplitude for the waveform (systolic pressure) at the ascending aorta increased in the false lumen by 25% compared to the true lumen by 3%. Also, the waveform peak (systolic) was leading by 0.01 s. The hemodynamic parameter of wall shear stress (WSS) predicted the aneurysm's existence at the ascending aorta, as well as potential aortic dissection. The high WSS contours were located at the tear location at the peak blood flow of 0.14 s, which shows the potential of this tool for earlier diagnosis of aortic dissection.

A Deep Learning Architectures for Kidney Disease Classification

Deep learning has become an extremely powerful tool for complex tasks such as image classification and segmentation. The medical industry often lacks high-quality, balanced datasets, which can be a challenge for deep learning algorithms that need sufficiently large amounts of data to train and increase their performance. This is especially important in the context of kidney issues such as for stones, cysts and tumors. We used deep learning models for this study to classify or detect several types of kidney diseases. We use different classification models, such as VGG-19, (CNNs) Convolutional Neural Networks, ResNet- 101, VGG-16, ResNet-50, and DenseNet-169, which can be enhanced through techniques such as classification, segmentation, and transfer learning. These algorithms can help improve model accuracy by allowing them to learn from multiple datasets. This technique has the potential to revolutionize the diagnosis and treatment of kidney problems as it enables more accurate and effective classification of CT-scan images. This may ultimately lead to better patient outcomes and improved overall health outcomes. INDEX TERMS Kidney disease, deep learning, image classification, convolutional neural networks (CNNs), segmentation, transfer learning, CT-scan images.

Using a three-dimensional-printed device with the patient's maxillary dental impression allows to perform minimally invasive brain biopsies in dogs and cats: a preliminary study.

To develop an innovative process for stereotactic brain biopsies in dogs and cats that would provide a definitive diagnosis and optimize the management of patients with brain lesions. 4 dogs and 1 cat diagnosed with 1 or more brain lesion(s) underwent brain biopsies between March 24, 2023, and October 25, 2023. Based on trajectories selected on images of MRI and CT scan performed on each patient, a computerized software program was used to design a 3-D-printed patient-specific device with maxillary dental impression located on a baseplate to secure the patient's head and with insertion ports for the biopsy instrumentations located on a C-arm. As proof of concept, the device was successfully used in 2 cadavers before being used on clinical patients. All biopsy samples were submitted for histopathological examination. Histological diagnosis was obtained in 80% (4/5) of the cases (choroid plexus tumor, astrocytoma, meningioma, and chronic meningoencephalitis of unknown origin). In 1 patient, the results of biopsy were nondiagnostic; postmortem diagnosis was consistent with a low-grade oligodendroglioma. All the patients were discharged within 24 hours after the procedure without complications. This novel stereotactic system allows the surgeon to perform safe, easy-to-use, inexpensive, and minimally invasive precise brain biopsies in dogs and cats, without complications. This unique technique could be applied to any size and type of skull and for any type of brain lesions and would provide diagnostic information that would be valuable for future treatment planning and prognosis.