Computer-assisted System Research Articles

Minimal data requirement for realistic endoscopic image generation with Stable Diffusion.

Computer-assisted surgical systems provide support information to the surgeon, which can improve the execution and overall outcome of the procedure. These systems are based on deep learning models that are trained on complex and challenging-to-annotate data. Generating synthetic data can overcome these limitations, but it is necessary to reduce the domain gap between real and synthetic data. We propose a method for image-to-image translation based on a Stable Diffusion model, which generates realistic images starting from synthetic data. Compared to previous works, the proposed method is better suited for clinical application as it requires a much smaller amount of input data and allows finer control over the generation of details by introducing different variants of supporting control networks. The proposed method is applied in the context of laparoscopic cholecystectomy, using synthetic and real data from public datasets. It achieves a mean Intersection over Union of 69.76%, significantly improving the baseline results (69.76 vs. 42.21%). The proposed method for translating synthetic images into images with realistic characteristics will enable the training of deep learning methods that can generalize optimally to real-world contexts, thereby improving computer-assisted intervention guidance systems.

Improving the quality of chilled semen from Thai native chicken using phosphorus and vitamin B12 supplementation in semen extender

This study aimed to determine phosphorus and vitamin B12 supplementation effect in semen extender on the quality and fertility ability of chilled Thai native rooster semen. Eighty-four ejaculates of semen from 26 Thai native roosters (Burmese x Vietnam crossbreed) were included. Semen was collected by applying dorsal–abdominal massage once a week, pooled, diluted to 500 million sperms per dose, and divided into six groups. The semen samples used for control group were diluted with modified Beltsville poultry semen extender (BPSE). For the treatment groups 2–6: semen samples were diluted with modified BPSE and enriched with phosphorus and vitamin B12 (Octafos® Octa Memorial Co., Ltd., Bangkok, Thailand) at concentrations 0.02%, 0.04%, 0.06%, 0.08%, and 0.10%. Semen fertility ability was tested in six replications by inseminating layer hens. Thirty-six Thai native hens were randomly assigned to three groups (control, 0.04%, and 0.08%) of 12 hens and were inseminated with a dose of 0.2 mL on collecting day. Sperm motion characteristics (i.e., sperm motility, sperm progressive motility, and sperm kinetic parameters) were measured using a computer-assisted sperm analysis system (SCA®, Proiser S.L., Valencia, Spain). Sperm viability, mitochondrial activity, acrosome integrity, plasma membrane integrity, and malondialdehyde (MDA) concentration were also evaluated. The sperm motion characteristics were the highest in the 0.04% supplementation group on all days of collection, especially the VCL and VAP (P < 0.05). The viability, mitochondrial activity, plasma membrane and acrosome integrity of spermatozoa were greater in the 0.04% supplementation group than in the control groups (P < 0.05). The 0.04% supplementation group had the lowest MDA concentration in all days of collection. The 0.04% supplementation group were higher both fertility (66.59% vs. 48.50%: P < 0.05) and hatching rates (58.80% vs. 43.18%: P < 0.05) than in the control group. In conclusion, 0.04% phosphorus and vitamin B12 concentrations supplementation in semen extender improved rooster semen quality and fertility in chilled rooster semen.

The Effect Analysis of the Application of CAI to Japanese Oral Teaching in Colleges

Abstract In this paper, we first analyze the requirements for teaching spoken Japanese in colleges and universities, design a computer-assisted teaching system using C/S and three-layer hybrid architecture, and create a business flow diagram of the system. The second step is to conduct a technical analysis of the computer-assisted teaching system, and Bayesian theory is employed to model the complex system with multi-factor synergy. The effect of the computer-assisted system on Japanese-speaking teaching courses in colleges and universities was analyzed. The results indicated that the students dictated 4,500 words, while the lowest dictated as little as 300 words, but overall, they were more balanced. The prompt word ratio was directly proportional to the number of repetitions by observing the number of single dictations of students.

Distal femoral torsion positioning in total knee arthroplasty shows equal reliability using a computer-assisted system or a robotic arm

IntroductionComputer-assisted or robot-assisted surgery in theory enables optimal positioning in total knee arthroplasty (TKA). The aim of the present study was to evaluate the rotational positioning of the femoral TKA implant using the ROSA Knee® robotic system. The hypothesis was that the accuracy of the rotation obtained by the ROSA Knee® robotic arm was comparable to that obtained by navigation. Material and methodsThis was a retrospective comparative consecutive study involving 140 patients receiving first-line TKA, divided into two equal groups: Navigation, and Robot. Distal epiphyseal torsion of the femur (DETF) was analyzed by comparing preoperative (native DETF) and postoperative (prosthetic DETF) CT scans between groups. ResultsThe mean prosthetic DETF was 2.3°±1.3 for the Navigation group and 2.3°±1.4 for the Robot group (p=0.96), with no significant difference in deviation from DETF target (p=0.07). Assuming±2° range of error, the Navigation group showed 88.6% and the Robot group 90% accuracy (p=0.79). ConclusionThe Rosa Knee® robotic system provided accuracy equivalent to navigation for rotational positioning of the femoral implant. Level of evidenceIV.

Poor usability of computer-assisted navigation for hip fracture surgery

IntroductionThe STRYKER ADAPT computer-assisted navigation system provides intraoperative feedback to the surgeon regarding implant placement of the Gamma3 nail. The usability of the ADAPT system has not been evaluated. The aim of the study was to investigate the perceived usability of the ADAPT system.Materials and methodsThis was a descriptive study with prospectively collected data. ADAPT was introduced at Aarhus University Hospital in February 2021. Prior to introduction, surgeons at the department attended a general introduction to the system. ADAPT was introduced to the surgical nurses and was on display at the surgical ward at more than one occasion, where personal introduction to the system was possible. After introduction, it was mandatory to use ADAPT when using the Gamma3 nail to treat intertrochanteric femur fractures. After each procedure, primary and an eventual supervisor answered a questionnaire, which encompassed the System Usability Scale (SUS) questionnaire. The SUS is a ten-item questionnaire regarding the perceived usability of a system. SUS scores were translated to adjectives, describing user experience on a 7-point adjective scale (worst imaginable, awful, poor, ok, good, excellent, best imaginable). User acceptability, defined as “not acceptable”, “marginal” or “acceptable”, was also used to interpret the SUS scores.ResultsADAPT was used in 50 procedures by 29 different surgeons, with varying skill-level. Median SUS-score after first-time use of ADAPT for all 29 surgeons was 43 (range: 5–60), which translated to “poor” or “not acceptable”. For surgeons who performed ≥ 3 ADAPT-assisted procedures, there were no statistically significant difference in their first to latest SUS-score (median difference: 4.3, p = 0.5). In free text comments ADAPT was positively described as helpful in placement of K-wire and providing educational opportunities for inexperienced surgeons and negatively as inconsistent, slow, time consuming, and causing excessive fluoroscopy.ConclusionsUsability and acceptability of ADAPT was rated as “poor” or “not acceptable” by the majority of operating surgeons. ADAPT has not been used at our institution based on these findings. The System Usability Scale may be used in further research exploring usability and acceptability of novel computer-assisted navigation systems for orthopaedic surgery.

Zone-specific computer-aided diagnosis system aimed at characterizing ISUP ≥ 2 prostate cancers on multiparametric magnetic resonance images: evaluation in a cohort of patients on active surveillance.

To assess a region-of-interest-based computer-assisted diagnosis system (CAD) in characterizing aggressive prostate cancer on magnetic resonance imaging (MRI) from patients under active surveillance (AS). A prospective biopsy database was retrospectively searched for patients under AS who underwent MRI and subsequent biopsy at our institution. MRI lesions targeted at baseline biopsy were retrospectively delineated to calculate the CAD score that was compared to the Prostate Imaging-Reporting and Data System (PI-RADS) version 2 score assigned at baseline biopsy. 186 patients were selected. At baseline biopsy, 51 and 15 patients had International Society of Urological Pathology (ISUP) grade ≥ 2 and ≥ 3 cancer respectively. The CAD score had significantly higher specificity for ISUP ≥ 2 cancers (60% [95% confidence interval (CI): 51-68]) than the PI-RADS score (≥ 3 dichotomization: 24% [CI: 17-33], p = 0.0003; ≥ 4 dichotomization: 32% [CI: 24-40], p = 0.0003). It had significantly lower sensitivity than the PI-RADS ≥ 3 dichotomization (85% [CI: 74-92] versus 98% [CI: 91-100], p = 0.015) but not than the PI-RADS ≥ 4 dichotomization (94% [CI:85-98], p = 0.104). Combining CAD findings and PSA density could have avoided 47/184 (26%) baseline biopsies, while missing 3/51 (6%) ISUP 2 and no ISUP ≥ 3 cancers. Patients with baseline negative CAD findings and PSAd < 0.15ng/mL2 who stayed on AS after baseline biopsy had a 9% (4/44) risk of being diagnosed with ISUP ≥ 2 cancer during a median follow-up of 41months, as opposed to 24% (18/74) for the others. The CAD could help define AS patients with low risk of aggressive cancer at baseline assessment and during subsequent follow-up.

Effect of nutraceutical supplementation on semen quality in stallions.

The use of reproductive biotechnologies in equine practice has shown that some stallions are subfertile, so ways to improve fertility have been sought. This study aimed to evaluate the effect of nutraceutical supplementation on improving semen quality in Quarter Horse stallions. Semen from six Quarter Horse stallions was assessed for 4 months every 20days using the computer-assisted semen analysis system. They were evaluated for 60days before supplementation; then, the same stallions were re-evaluated for 60days with nutraceutical supplementation (30g/day). Volume showed no significant difference (p>0.05) with nutraceuticals. Sperm concentration (10x6 ) was significantly higher with supplementation (339.4±17.5 sperm/mL) than without supplementation (224.6±19.9). Sperm abnormalities (%) were significantly (p<0.05) lower with supplementation (14.3±0.6) than without supplementation (19.1±0.4). Sperm kinematic parameters, total motility (TM), progressive motility (PM), rectilinear velocity (VSL), the velocity of the trajectory (VAP) and curvilinear velocity (VCL), were significantly better with supplementation (p<0.05). Based on the results, it is concluded that nutraceutical supplementation improved semen parameters in Quarter Horse stallions.

Granulocyte-Macrophage Colony-Stimulating Factor Cytokine Addition After the Freeze-Thawing Process Improves Human Sperm Motility and Vitality in Asthenoteratozoospermia Patients.

The cryopreservation-thawing process of spermatozoa cells has negative impacts on their structure, function, and fertility parameters, which are known as cryoinjury. Asthenozoospermia patients are more susceptible to cryoinjury. Granulocyte-macrophage colony-stimulating factor (GM-CSF) increases sperm glucose uptake via the induction of glucose transporters, resulting in increased sperm motility. This study aimed to investigate the efficiency of GM-CSF supplementation of the cryopreservation media for semen samples of asthenoteratozoospermia patients. The study was carried out on 20 semen samples from infertile men referred to diagnosing semen analysis. To avoid subjective bias, two main sperm motility parameters, including velocity along the curvilinear path and velocity along the straight-line path were considered by the computer-assisted sperm analysis system. Afterward, each semen sample was divided into three equal aliquots and randomly assigned to one of the following groups: group I (control, freezing media only), group II (+GM-CSF, freezing medium supplemented with 2 μL/mL GM-CSF), or group III (GM-CSF added after thawing and washing). Following semen thawing, standard parameters, mitochondrial membrane potential (MMP), and the DNA Fragmentation Index were analyzed. Total sperm motility (progressive and non-progressive) improved significantly in group III samples after a 30-minute incubation with GM-CSF compared with the control group (26.5% ± 3.1% vs. 17.51% ± 2.59%). However, no differences in progressive motility or sperm morphology were found among the three thawed samples. The percentage of vitality was significantly higher in group III compared with the other two groups (28.38% ± 3.4% vs. 22.4% ± 3.08% and 22.14% ± 2.77%, respectively) (p < 0.05). JC-1 levels (a marker of MMP) were not significantly different between the examined groups (44.95% ± 8.26% vs. 36.61% ± 6.95% vs. 46.67% ± 7.7%, for control, group II, and group III, respectively) (p > 0.05). GM-CSF may be advantageous as an additive after freezing, improving total motility and viability after 30 minutes of post-thaw incubation; however, when supplied to the freezing media before cryopreservation, it is unable to protect against cryoinjury.

Endomapper dataset of complete calibrated endoscopy procedures

Computer-assisted systems are becoming broadly used in medicine. In endoscopy, most research focuses on the automatic detection of polyps or other pathologies, but localization and navigation of the endoscope are completely performed manually by physicians. To broaden this research and bring spatial Artificial Intelligence to endoscopies, data from complete procedures is needed. This paper introduces the Endomapper dataset, the first collection of complete endoscopy sequences acquired during regular medical practice, making secondary use of medical data. Its main purpose is to facilitate the development and evaluation of Visual Simultaneous Localization and Mapping (VSLAM) methods in real endoscopy data. The dataset contains more than 24 hours of video. It is the first endoscopic dataset that includes endoscope calibration as well as the original calibration videos. Meta-data and annotations associated with the dataset vary from the anatomical landmarks, procedure labeling, segmentations, reconstructions, simulated sequences with ground truth and same patient procedures. The software used in this paper is publicly available.

The growth performance of pond-reared common carp (Cyprinus carpio) larvae propagated using cryopreserved sperm.

The aim of our study was to determine the efficacy of utilizing cryopreserved common carp sperm (in comparison to fresh sperm) for propagation at a Hungarian aquaculture facility. The sperm was frozen in 5mL straws using an extender method that was previously tested in common carp. Sperm motility was monitored using a computer-assisted sperm analysis system. The hatching and malformation rates among the specimens were recorded before the stocking of larvae in both groups. The growth (body weight, total length) and survival rates of the fish were measured during the pre-nursing (from May to June: between 1 and 26days post hatching) and grow-out periods (from June to October: between 26 and 105days post hatching) of the same year. The fresh sperm, which was collected and pooled prior to fertilization, showed high MOT (97%), pMOT (92%), VCL (106µms-1), LIN (75%), and ALH (1.84µm). Prior to the fertilization trial of the cryopreserved sperm, low MOT (34%), pMOT (14%), and VCL (61µms-1) values were observed in frozen-thawed sperm. A significantly higher hatching rate was measured in the fresh sperm group (87%) when compared to the cryopreserved sperm group (42%). No significant difference in the overall malformation rate was observed in larvae originating from either the fresh or frozen sperm. A significant difference between the two test groups was observed in the incidence of deformed tails (fresh: 20%, cryopreserved: 55%). Except for one sampling period, no significant difference in the body weight and total length of the fish larvae was found between the two groups throughout the pre-nursing and grow-out periods. A significantly higher larvae survival rate was noted in the fresh sperm (72%) as compared to the cryopreserved group (43%) by the end of the pre-nursing stage. However, no significant difference in survival rate was observed for the cryopreserved sperm (96%) in comparison to the fresh sperm (95%) by the end of the grow-out stage. The results of this study showed, for the first time in large-scale pond culturing, an equal growth and viability in larvae propagated from cryopreserved sperm when compared to fresh sperm (despite the limited available rearing ponds provided by the commercial company).

Improving diagnosis accuracy with an intelligent image retrieval system for lung pathologies detection: a features extractor approach

Detecting lung pathologies is critical for precise medical diagnosis. In the realm of diagnostic methods, various approaches, including imaging tests, physical examinations, and laboratory tests, contribute to this process. Of particular note, imaging techniques like X-rays, CT scans, and MRI scans play a pivotal role in identifying lung pathologies with their non-invasive insights. Deep learning, a subset of artificial intelligence, holds significant promise in revolutionizing the detection and diagnosis of lung pathologies. By leveraging expansive datasets, deep learning algorithms autonomously discern intricate patterns and features within medical images, such as chest X-rays and CT scans. These algorithms exhibit an exceptional capacity to recognize subtle markers indicative of lung diseases. Yet, while their potential is evident, inherent limitations persist. The demand for abundant labeled data during training and the susceptibility to data biases challenge their accuracy. To address these formidable challenges, this research introduces a tailored computer-assisted system designed for the automatic retrieval of annotated medical images that share similar content. At its core lies an intelligent deep learning-based features extractor, adept at simplifying the retrieval of analogous images from an extensive chest radiograph database. The crux of our innovation rests upon the fusion of YOLOv5 and EfficientNet within the features extractor module. This strategic fusion synergizes YOLOv5's rapid and efficient object detection capabilities with EfficientNet's proficiency in combating noisy predictions. The result is a distinctive amalgamation that redefines the efficiency and accuracy of features extraction. Through rigorous experimentation conducted on an extensive and diverse dataset, our proposed solution decisively surpasses conventional methodologies. The model's achievement of a mean average precision of 0.488 with a threshold of 0.9 stands as a testament to its effectiveness, overshadowing the results of YOLOv5 + ResNet and EfficientDet, which achieved 0.234 and 0.257 respectively. Furthermore, our model demonstrates a marked precision improvement, attaining a value of 0.864 across all pathologies—a noteworthy leap of approximately 0.352 compared to YOLOv5 + ResNet and EfficientDet. This research presents a significant stride toward enhancing radiologists' workflow efficiency, offering a refined and proficient tool for retrieving analogous annotated medical images.

Effects of Computer-Assisted Reading Learning System on Chinese Reading Comprehension

Effects of Computer-Assisted Reading Learning System on Chinese Reading Comprehension

3D simulation of interosseous interference in sagittal split ramus osteotomy for mandibular asymmetry

BackgroundThe purpose of this study was to evaluate the pattern of predicted interosseous interference and to determine the influencing factor to volume of bony interference using a computer-assisted simulation system. This retrospective study recruited 116 patients with mandibular prognathism who had undergone sagittal split ramus osteotomy (SSRO) with or without maxillary osteotomy. The patients were divided into 3 groups according to the amount of menton (Me) deviation: less than 2 mm (Group 1), 2–4 mm (Group 2), and more than 4 mm (Group 3). Changes in the distal segments following BSSRO and the volume of the interosseous interference between the proximal and distal segments were simulated after matching preoperative occlusion and postoperative expected occlusion with the cone-beam computed tomography data. Ramal inclinations and other skeletal measurements were analyzed before surgery, immediately after surgery, and at least 6 months after surgery.ResultsThe anticipated interosseous interference was more frequently noted on the contralateral side of chin deviation (long side) than the deviated site (short side) in Groups 2 and 3. More interference volume was predicted at the long side (186 ± 343.9 mm3) rather than the short side (54.4 ± 124.4 mm3) in Group 3 (p = 0.033). The bilateral difference in the volume of the interosseous interference of the osteotomized mandible was significantly correlated with the Me deviation (r = − 0.257, p = 0.009) and bilateral ramal inclination (r = 0.361, p < 0.001). The predictor variable that affected the volume of the osseous interference at each side was the amount of Me deviation (p = 0.010).ConclusionBy using the 3D simulation system, the potential site of bony collision could be visualized and successfully reduced intraoperatively. Since the osseous interference can be existed on any side, unilaterally or bilaterally, 3D surgical simulation is necessary before surgery to predict the osseous interference and improve the ramal inclination.

Chemoresistance Mechanisms in Non-Small Cell Lung Cancer-Opportunities for Drug Repurposing.

Globally, lung cancer contributes significantly to the public health burden-associated mortality. As this form of cancer is insidious in nature, there is an inevitable diagnostic delay leading to chronic tumor development. Non-small cell lung cancer (NSCLC) constitutes 80-85% of all lung cancer cases, making this neoplasia form a prevalent subset of lung carcinoma. One of the most vital aspects for proper diagnosis, prognosis, and adequate therapy is the precise classification of non-small cell lung cancer based on biomarker expression profiling. This form of biomarker profiling has provided opportunities for improvements in patient stratification, mechanistic insights, and probable druggable targets. However, numerous patients have exhibited numerous toxic side effects, tumor relapse, and development of therapy-based chemoresistance. As a result of these exacting situations, there is a dire need for efficient and effective new cancer therapeutics. De novo drug development approach is a costly and tedious endeavor, with an increased attrition rate, attributed, in part, to toxicity-related issues. Drug repurposing, on the other hand, when combined with computer-assisted systems biology approach, provides alternatives to the discovery of new, efficacious, and safe drugs. Therefore, in this review, we focus on a comparison of the conventional therapy-based chemoresistance mechanisms with the repurposed anti-cancer drugs from three different classes-anti-parasitic, anti-depressants, and anti-psychotics for cancer treatment with a primary focus on NSCLC therapeutics. Certainly, amalgamating these novel therapeutic approaches with that of the conventional drug regimen in NSCLC-affected patients will possibly complement/synergize the existing therapeutic modalities. This approach has tremendous translational significance, since it can combat drug resistance and cytotoxicity-based side effects and provides a relatively new strategy for possible application in therapy of individuals with NSCLC.

Custom YOLO Object Detection Model for COVID-19 Diagnosis

The emergence and spread of the new coronavirus (COVID-19) poses a new public health threat to the entire world (SARS-CoV-2). This new virus is highly contagious and pathogenetically different from other mainstream respiratory viruses. Clinical staff can benefit from Computer Aided Diagnostics (CAD) systems that combine deep learning algorithms and image processing technologies as diagnostic tools for COVID-19. These tools also help to better understand the course of the disease. In most cases, medical staff and healthcare facilities would be more equipped to promptly diagnose COVID-19 for patients with improved flexibility. To examine the training performance of the contemporary YOLOv4 model, this work presents the development of a computer-assisted automatic detection system that focuses specifically on identifying viral cells in blood samples from patients using electron microscopy images to detect the infected blood cell. The mean average precision of the proposed custom model is 86.5%mAP, making it suitable for the upcoming COVID-19 monitoring systems.

RiPa-Net: Recognition of Rice Paddy Diseases with Duo-Layers of CNNs Fostered by Feature Transformation and Selection.

Rice paddy diseases significantly reduce the quantity and quality of crops, so it is essential to recognize them quickly and accurately for prevention and control. Deep learning (DL)-based computer-assisted expert systems are encouraging approaches to solving this issue and dealing with the dearth of subject-matter specialists in this area. Nonetheless, a major generalization obstacle is posed by the existence of small discrepancies between various classes of paddy diseases. Numerous studies have used features taken from a single deep layer of an individual complex DL construction with many deep layers and parameters. All of them have relied on spatial knowledge only to learn their recognition models trained with a large number of features. This study suggests a pipeline called "RiPa-Net" based on three lightweight CNNs that can identify and categorize nine paddy diseases as well as healthy paddy. The suggested pipeline gathers features from two different layers of each of the CNNs. Moreover, the suggested method additionally applies the dual-tree complex wavelet transform (DTCWT) to the deep features of the first layer to obtain spectral-temporal information. Additionally, it incorporates the deep features of the first layer of the three CNNs using principal component analysis (PCA) and discrete cosine transform (DCT) transformation methods, which reduce the dimension of the first layer features. The second layer's spatial deep features are then combined with these fused time-frequency deep features. After that, a feature selection process is introduced to reduce the size of the feature vector and choose only those features that have a significant impact on the recognition process, thereby further reducing recognition complexity. According to the results, combining deep features from two layers of different lightweight CNNs can improve recognition accuracy. Performance also improves as a result of the acquired spatial-spectral-temporal information used to learn models. Using 300 features, the cubic support vector machine (SVM) achieves an outstanding accuracy of 97.5%. The competitive ability of the suggested pipeline is confirmed by a comparison of the experimental results with findings from previously conducted research on the recognition of paddy diseases.

Computer-assisted generation of anaesthesia report during laparoscopic procedures

Abstract Automatic generation of intraoperative anaesthesia reports has great potential to generate accurate and efficient documentation and allow the anaesthesiologists to utilise their time more optimally. However, automatically generating anaesthesia reports represents a demanding component in future operating rooms. In this paper, a computer-assisted system for anaesthesiology report generation during laparoscopic surgery is proposed. Data from anaesthesia machine, patient monitor, and surgical devices were acquired and analysed. The system proved to generate more accurate, efficient, and better readable reports compared to hand-written ones by clinicians. Moreover, additional information that describes surgical activities and events was also added by analysing surgical data.

Intraoperative navigation system use increases accuracy of glenoid component inclination but not functional outcomes in reverse total shoulder arthroplasty: a prospective comparative study.

While the use of computer-assisted navigation systems in prosthetic implantation is steadily increasing, its utility in reverse shoulder arthroplasty (RSA) remains unclear. The purpose of this study was to evaluate the clinical utility of an intraoperative navigation system in patients undergoing RSA. Patients undergoing navigated or standard RSA at a single institution between September 2020 and December 2021 were prospectively enrolled. Exclusion criteria included noncompliance with study procedures or humeral fracture. Outcome measures included postoperative version and inclination, range of motion (ROM), complications, and patient-reported outcome measurements (PROMs: American Shoulder and Elbow Surgeons score [ASES], Disabilities of the Arm, Shoulder, and Hand score [DASH], Simple Shoulder Test [SST], and Visual Analog Scale [VAS]) at final follow-up. The final cohort contained 16 patients with navigation and 17 with standard RSA at a mean follow-up of 16months (range 12-18months). Average age was 72years (range 66-80years), 8 male (24%) and 25 female (76%). There were no differences in demographics between groups (p > 0.05). At baseline, the navigated group had a greater proportion of Walch B1 and B2 glenoids (p = 0.04). There were no differences between groups regarding baseplate type and native/planned/postoperative glenoid version and inclination. In both groups, planned and postoperative versions were not significantly different (p = 0.76). Patients who did not have navigation demonstrated significant differences between planned and postoperative inclination (p = 0.04), while those with navigation did not (p = 0.09). PROM scores did not differ between groups at final follow-up for SST (p = 0.64), DASH (p = 0.38), ASES (p = 0.77), or VAS (p = 0.1). No difference in final ROM was found between groups (p > 0.05). Over 50% of all screws in both groups were positioned outside the second cortex (p = 0.37), albeit with no complications. There were no statistically significant differences in ROM, PROMs, and satisfaction between patients receiving computer-navigated and standard RSA at a short-term follow-up. Despite more severe preoperative glenoid erosion in the navigated group, all patients were able to achieve an appropriate neutral axis postoperatively. The cost effectiveness and appropriate use of computer-navigated RSA warrant specific investigation in future studies. II, prospective cohort study. 9/1/2020 to 12/31/2021.

A Framework for Detecting Thyroid Cancer from Ultrasound and Histopathological Images Using Deep Learning, Meta-Heuristics, and MCDM Algorithms.

Computer-assisted diagnostic systems have been developed to aid doctors in diagnosing thyroid-related abnormalities. The aim of this research is to improve the diagnosis accuracy of thyroid abnormality detection models that can be utilized to alleviate undue pressure on healthcare professionals. In this research, we proposed deep learning, metaheuristics, and a MCDM algorithms-based framework to detect thyroid-related abnormalities from ultrasound and histopathological images. The proposed method uses three recently developed deep learning techniques (DeiT, Swin Transformer, and Mixer-MLP) to extract features from the thyroid image datasets. The feature extraction techniques are based on the Image Transformer and MLP models. There is a large number of redundant features that can overfit the classifiers and reduce the generalization capabilities of the classifiers. In order to avoid the overfitting problem, six feature transformation techniques (PCA, TSVD, FastICA, ISOMAP, LLE, and UMP) are analyzed to reduce the dimensionality of the data. There are five different classifiers (LR, NB, SVC, KNN, and RF) evaluated using the 5-fold stratified cross-validation technique on the transformed dataset. Both datasets exhibit large class imbalances and hence, the stratified cross-validation technique is used to evaluate the performance. The MEREC-TOPSIS MCDM technique is used for ranking the evaluated models at different analysis stages. In the first stage, the best feature extraction and classification techniques are chosen, whereas, in the second stage, the best dimensionality reduction method is evaluated in wrapper feature selection mode. Two best-ranked models are further selected for the weighted average ensemble learning and features selection using the recently proposed meta-heuristics FOX-optimization algorithm. The PCA+FOX optimization-based feature selection + random forest model achieved the highest TOPSIS score and performed exceptionally well with an accuracy of 99.13%, F2-score of 98.82%, and AUC-ROC score of 99.13% on the ultrasound dataset. Similarly, the model achieved an accuracy score of 90.65%, an F2-score of 92.01%, and an AUC-ROC score of 95.48% on the histopathological dataset. This study exploits the combination novelty of different algorithms in order to improve the thyroid cancer diagnosis capabilities. This proposed framework outperforms the current state-of-the-art diagnostic methods for thyroid-related abnormalities in ultrasound and histopathological datasets and can significantly aid medical professionals by reducing the excessive burden on the medical fraternity.

A comprehensive computer-aided system for an early-stage diagnosis and classification of diabetic macular edema

Diabetic macular edema (DME) is a condition of retinal swelling due to the accumulation of leaked plasma in the extracellular space in the retina, known as the macula. DME is a chronic progressive retinal disorder that likely results in permanent complete blindness. The early signs of DME are not discernible by merely suspecting the fundus picture with the naked eye. Therefore, a computer-assisted diagnostic system could aid ophthalmologists in screening, diagnosing, and treating DME. This study proposes an efficient and complete model for early diagnosis and staging of DME. To overcome the challenges in precise localization of fovea, blood vessel network extraction, and accurate lesion segmentation, improved image relative subtraction, Gabor wavelet filter, and novel advanced fuzzy c-means clustering algorithms are introduced, respectively. Finally, the Bayesian classifier using the Gaussian function with expectation maximization is used for DME grading. The accurate optic disc and fovea localization, exudates’ segmentation, and classification improved the overall system’s performance. The proposed model achieves an average accuracy of 96.17%, 98.60%, 97.85%, and 98.80% for optic disc detection, fovea localization, exudates segmentation, and DME classification, respectively. The performance of the proposed model compared to the competitive studies illustrates the superiority of the suggested methodology.