Sialon ceramic tool material has become one of the most ideal materials for the high-speed cutting of superalloy materials. However, studies on the geometric structure of sialon ceramic solid end mill is lacking at the present. In this work, the geometric structure of sialon ceramic end mills was designed for difficult-to-machine nickel-based superalloy materials. The cutting force and heat, flank wear and machined surface quality were analyzed to study the effect of the main parameters on tool performance. The results showed that the end mill experienced severe flank wear and chipping, which were the leading cause of its failure during high-speed cutting. The cutting force and temperature decreased gradually with the increase in the helix angle. With the increase in the rake angle, the flank wear and the quality of the machined surface of the specimen first decreased and then increased. With the increase in the relief angle, the cutting temperature of the ceramic end mill gradually decreased, and the cutting force and the machined surface roughness showed an initial decrease and then increased. When the helix angle, rake angle and relief angle were 35°, −15° and 12°, respectively, the sialon ceramic end mill exhibited the best cutting performance and obtained better machined surface quality in the nickel-based superalloys.
Abstract Background Adjuvant therapy for patients with cervical cancer (CC) with intermediate-risk factors remains controversial. The objectives of the present study are to assess the prognoses of patients with early-stage CC with pathological intermediate-risk factors and to provide a reference for adjuvant therapy choice. Materials and Methods This retrospective study included 481 patients with stage IB–IIA CC. Cox proportional hazards regression analysis, machine learning (ML) algorithms, Kaplan-Meier analysis, and the area under the receiver operating characteristic curve (AUC) were used to develop and validate prediction models for disease-free survival (DFS) and overall survival (OS). Results A total of 35 (7.3%) patients experienced recurrence, and 20 (4.2%) patients died. Two prediction models were built for DFS and OS using clinical information, including age, lymphovascular space invasion, stromal invasion, tumor size, and adjuvant treatment. Patients were divided into high-risk or low-risk groups according to the risk score cutoff value. The Kaplan-Meier analysis showed significant differences in DFS (p = .001) and OS (p = .011) between the two risk groups. In the traditional Sedlis criteria groups, there were no significant differences in DFS or OS (p > .05). In the ML-based validation, the best AUCs of DFS at 2 and 5 years were 0.69/0.69, and the best AUCs of OS at 2 and 5 years were 0.88/0.63. Conclusion Two prognostic assessment models were successfully established, and risk grouping stratified the prognostic risk of patients with CC with pathological intermediate-risk factors. Evaluation of long-term survival will be needed to corroborate these findings. Implications for Practice The Sedlis criteria are intermediate-risk factors used to guide postoperative adjuvant treatment in patients with cervical cancer. However, for patients meeting the Sedlis criteria, the choice of adjuvant therapy remains controversial. This study developed two prognostic models based on pathological intermediate-risk factors. According to the risk score obtained by the prediction model, patients can be further divided into groups with high or low risk of recurrence and death. The prognostic models developed in this study can be used in clinical practice to stratify prognostic risk and provide more individualized adjuvant therapy choices to patients with early-stage cervical cancer.
In this paper, we propose an autonomous method for robot navigation based on a multi-camera setup that takes advantage of a wide field of view. A new multi-task network is designed for handling the visual information supplied by the left, central and right cameras to find the passable area, detect the intersection and infer the steering. Based on the outputs of the network, three navigation indicators are generated and then combined with the high-level control commands extracted by the proposed MapNet, which are finally fed into the driving controller. The indicators are also used through the controller for adjusting the driving velocity, which assists the robot to adjust the speed for smoothly bypassing obstacles. Experiments in real-world environments demonstrate that our method performs well in both local obstacle avoidance and global goal-directed navigation tasks.
Small cell lung cancer (SCLC) is one of the most common types of malignant tumors, characterized by rapid growth and early metastasis spread. Early and accurate diagnosis of SCLC is vital for improved survival. Accurate cancer segmentation helps doctors understand the location and size of cancer and make better diagnostic decisions. However, manual segmentation of lung cancers from large amounts of medical images is a time-consuming and challenging task. In this paper, we propose a hybrid segmentation network (referred to as HSN) based on convolutional neural network (CNN) to automatically segment SCLC from computed tomography (CT) images. The design philosophy of our model is to combine a lightweight 3D CNN to learn long-range 3D contextual information and a 2D CNN to learn fine-grained semantic information, which is essential for accurate cancer segmentation. We propose a hybrid features fusion module to effectively fuse the 2D and 3D features and to jointly train these two CNNs. We utilize a generalized Dice loss function to tackle the severe class imbalance problem in data. A dataset consists of 134 CT scans was constructed to evaluate our model. Our model achieved high performances with a mean Dice score of 0.888, a mean sensitivity score of 0.872 and a mean precision of 0.909, outperforming the other state-of-the-art 2D and 3D CNN methods by a large margin.
Leukocytes are an essential component of the human defense system, accurate segmentation of leukocyte images is a crucial step towards automating detection. Most existing methods for leukocyte images segmentation relied on fully supervised semantic segmentation (FSSS) with extensive pixel-level annotations, which are time-consuming and labor-intensive. To address this issue, this paper proposes a weakly supervised semantic segmentation (WSSS) approach for leukocyte images utilizing improved class activation maps (CAMs). Firstly, to alleviate ambiguous boundary problem between leukocytes and background, preprocessing technique is employed to enhance the image quality. Secondly, attention mechanism is added to refine the CAMs generated by improving the matching of local and global features. Random walks, dense conditional random fields and hole filling were leveraged to obtain final pseudo-segmentation labels. Finally, a fully supervised segmentation network is trained with pseudo-segmentation labels. The method is evaluated on BCCD and TMAMD datasets. Experimental results demonstrate that by employing the pseudo segmentation annotations generated through this method can be utilized to train UNet as close as possible to FSSS. This method effectively reduces manual annotation cost while achieving WSSS of leukocyte images.
Objective: To investigate the predictive performance of machine learning classifiers for the discrimination of low and high nuclear grade clear-cell renal cell carcinoma (ccRCC) based on different phases of computed tomography (CT) images. Methods: A total of 51 consecutive patients with pathologically proven ccRCC (including 41 low-grade [grade 1 or 2] and 10 high-grade [grade 3 or 4] ccRCC) from January 2017 to December 2019 were enrolled in this retrospective study. Radiomic features were extracted from the corticomedullary phase (CMP), nephrographic phase (NP), and excretory phase (EP) CT images. A random forest classifier was established to differentiate low-grade from high-grade ccRCC. The performances of machine learning classifiers based on features from single-phase, two-phase CT images were compared with each other. Results: The 100 texture features were extracted from CMP, NP, EP, and two-phase CT images, respectively, and a random forest model was used for feature ranking and selection. The random forest machine learning classifier based on two-phase CMP-NP CT images (area under the receiver operating characteristic curve [AUC] = 0.90) obtained the best diagnostic performance for distinguishing low-grade and high-grade ccRCC, followed by single-phase NP (AUC = 0.83), two-phase NP-EP (AUC = 0.80), CMP-EP (AUC = 0.76), single-phase CMP (AUC = 0.74), and EP (AUC = 0.70). Conclusion: Image features extracted from NP and CMP are more effective than those from other CT phases in differentiating low-and high-grade ccRCC based on machine learning-based classification modeling.
Abstract Background:Low back pain (LBP) is a prevalent symptom worldwide, and lum-bar magnetic resonance imaging (MRI) is a crucial technique for elucidating the etiology of LBP. However, interpreting these complex MR images is repetitive and time-consuming for radiologists. In addition, medical professionals with different experience levels may make different interpretations. This study evaluated the YOLOv8n model to detect and automatically grade lumbar disk herniation (LDH) and lumbar central canal stenosis (LCCS) in lumbar axial MRI. Methods: A total of 273 and 100 lumbar axial T2w MR images obtained from the Pingtan Branch of Fujian Medical University Union Hospital from January 2023 to December 2023 were used as training and testing datasets, respectively. Three clinicians annotated all MR images according to the MSU and Schizas grading standards. The receptive-field coordinated attention and cross-stage part YOLOv8n (RFCACSP-YOLOv8n) based on YOLOv8n comprises a backbone network for feature extraction, a neck network for multiscale information fusion, 1 and a head network for regression prediction. Our team has designed a module named RFCACSP to replace the C2f module. The RFCACSP module adopts the concept of a cross-stage partial network and integrates a receptive-field coordinated attention convolutional module that was improved based on coordinated attention. In addition, we reduced the number of layers in the neck network from three to two. The improved model is named RFCACSP-YOLOv8n. We used the YOLOv8n and RFCACSP-YOLOv8n models to detect and automatically grade LDH and LCCS on axial T2w MR images of the lumbar spine and compared the performance of the two models. Box precision (boxes), recall (R), mean average precision at an IoU threshold of 0.5 (mAP50), and mean average precision from an IoU threshold of 0.5–0.95 (mAP50-95) were used to assess the performance of the model on the datasets. Result:Confusion matrix statistics based on the datasets provided by the Ping-tan Branch of Fujian Medical University Union Hospital found more samples classified as LDH grade 1A and 1C and LCCS grade A2. On the test dataset, RFCACSP-YOLOv8n outperforms YOLOv8n, showing 1.9% and 2.3% improvement in mAP and mAP50-95, respectively. Furthermore, RFCACSP-YOLOv8n could focus on improving the prediction accuracy of the major grades in the region, with grades 1A, 1C, and A2. Conclusion: The RFCACSP-YOLOv8n model demonstrated excellent performance in detecting and automatically grading LDH and LCCS on axial T2w MR images.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)