Accurate automatic quantitative cephalometry are essential for orthodontics. However, manual labeling of cephalometric landmarks is tedious and subjective, which also must be performed by professional doctors. In recent years, deep learning has gained attention for its success in computer vision field. It has achieved large progress in resolving problems like image classification or image segmentation. In this paper, we propose a two-step method which can automatically detect cephalometric landmarks on skeletal X-ray images. First, we roughly extract a region of interest (ROI) patch for each landmark by registering the testing image to training images, which have annotated landmarks. Then, we utilize pre-trained networks with a backbone of ResNet50, which is a state-of-the-art convolutional neural network, to detect each landmark in each ROI patch. The network directly outputs the coordinates of the landmarks. We evaluate our method on two datasets: ISBI 2015 Grand Challenge in Dental X-ray Image Analysis and our own dataset provided by Shandong University. The experiments demonstrate that the proposed method can achieve satisfying results on both SDR (Successful Detection Rate) and SCR (Successful Classification Rate). However, the computational time issue remains to be improved in the future.
Oral squamous cell carcinoma (OSCC) is one of the most common malignant tumors worldwide. Patients with poorly differentiated OSCC often exhibit a poor prognosis. AUNIP (Aurora Kinase A and Ninein Interacting Protein), also known as AIBp, plays a key role in cell cycle and DNA damage repair. However, the function of AUNIP in OSCC remains elusive. The differentially expressed genes (DEGs) were obtained using R language. Receiver operating characteristic curve analysis was performed to identify diagnostic markers for OSCC. The effectiveness of AUNIP in diagnosing OSCC was evaluated by machine learning. AUNIP expression was analyzed in publicly available databases and clinical specimens. Bioinformatics analysis and in vitro experiments were conducted to explore biological functions and prognostic value of AUNIP in OSCC. The gene integration analysis revealed 90 upregulated DEGs. One candidate biomarker, AUNIP, for the diagnosis of OSCC was detected, and its expression gradually increased along with malignant differentiation of OSCC. Bioinformatics analysis demonstrated that AUNIP could be associated with tumor microenvironment, human papillomavirus infection, and cell cycle in OSCC. The suppression of AUNIP inhibited OSCC cell proliferation and resulted in G0/G1 phase arrest in OSCC cells. The survival analysis showed that AUNIP overexpression predicted poor prognosis of OSCC patients. AUNIP could serve as a candidate diagnostic and prognostic biomarker for OSCC and suppression of AUNIP may be a potential approach to preventing and treating OSCC. FUND: Taishan Scholars Project in Shandong Province (ts201511106) and the National Natural Science Foundation of China (Nos. 61603218).
20 December 2023 in Multimedia Tools and Applications
Lung cancer constitutes the most severe cause of cancer-related mortality. Recent evidence supports that early detection by means of computed tomography (CT) scans significantly reduces mortality rates. Given the remarkable progress of Vision Transformers (ViTs) in the field of computer vision, we have delved into comparing the performance of ViTs versus Convolutional Neural Networks (CNNs) for the automatic identification of lung cancer based on a dataset of 212 medical images. Importantly, neither ViTs nor CNNs require lung nodule annotations to predict the occurrence of cancer. To address the dataset limitations, we have trained both ViTs and CNNs with three advanced techniques: transfer learning, self-supervised learning, and sharpness-aware minimizer. Remarkably, we have found that CNNs achieve highly accurate prediction of a patient’s cancer status, with an outstanding recall (93.4%) and area under the Receiver Operating Characteristic curve (AUC) of 98.1%, when trained with self-supervised learning. Our study demonstrates that both CNNs and ViTs exhibit substantial potential with the three strategies. However, CNNs are more effective than ViTs with the insufficient quantities of dataset.
1 January 2018 in International Journal of Medical Sciences
Objectives: To provide insight into the biological effects of activated Yes-associated protein (YAP) on the proliferation, apoptosis, and senescence of human periodontal ligament stem cells (h-PDLSCs).
Background: Histologic phenotype identification of Non-Small Cell Lung Cancer (NSCLC) is essential for treatment planning and prognostic prediction. The prediction model based on radiomics analysis has the potential to quantify tumor phenotypic characteristics non-invasively. However, most existing studies focus on relatively small datasets, which limits the performance and potential clinical applicability of their constructed models.Methods: To fully explore the impact of different datasets on radiomics studies related to the classification of histological subtypes of NSCLC, we retrospectively collected three datasets from multi-centers and then performed extensive analysis. Each of the three datasets was used as the training dataset separately to build a model and was validated on the remaining two datasets. A model was then developed by merging all the datasets into a large dataset, which was randomly split into a training dataset and a testing dataset. For each model, a total of 788 radiomic features were extracted from the segmented tumor volumes. Then three widely used features selection methods, including minimum Redundancy Maximum Relevance Feature Selection (mRMR), Sequential Forward Selection (SFS), and Least Absolute Shrinkage and Selection Operator (LASSO) were used to select the most important features. Finally, three classification methods, including Logistics Regression (LR), Support Vector Machines (SVM), and Random Forest (RF) were independently evaluated on the selected features to investigate the prediction ability of the radiomics models.Results: When using a single dataset for modeling, the results on the testing set were poor, with AUC values ranging from 0.54 to 0.64. When the merged dataset was used for modeling, the average AUC value in the testing set was 0.78, showing relatively good predictive performance.Conclusions: Models based on radiomics analysis have the potential to classify NSCLC subtypes, but their generalization capabilities should be carefully considered.