Machine vision-assisted identification of the lung adenocarcinoma category and high-risk tumor area based on CT images

Smartphone-deployable and all-in-one machine vision for visual quantification analysis based on distance readout of electrophoresis titration biosensor

As a class of point-of-care (POC) assays with visible distance readout (thermometer style), the electrophoresis titration (ET) biosensor affords high robustness, versatility, and simplicity for point-of-care quantification. However, naked-eye observation of the distance readout is unreliable in POC settings and manual processing of distance readout is time-consuming. Herein, we developed a smartphone-deployable and all-in-one machine vision for four ET biosensors (bovine serum albumin, melamine, uric acid, glutathione) to classify and quantify the samples simultaneously. To ensure accurate and rapid quantification on the smartphone, we customized the decolorization methods and edge detection operators to balance the region of interest (ROI) extraction performance and processing speed. We then established a dataset of 180 distance readout images to endow our machine vision with the ability to classify four sample types. Consequently, our machine vision demonstrated high accuracy in determining the sample type (>97.2%) and concentration (>97.3%). Moreover, expanding its applications to other targets was readily achieved by including distance readout images of other ET biosensors (e.g., hemoglobin A1c) in the dataset. Therefore, our strategy of constructing machine vision is compatible with the versatile ET biosensor technique, suggesting that the same strategy can be used for other thermometer-style POC assays.

Non-small cell lung cancer detection through knowledge distillation approach with teaching assistant

Non-small cell lung cancer (NSCLC) exhibits a comparatively slower rate of metastasis in contrast to small cell lung cancer, contributing to approximately 85% of the global patient population. In this work, leveraging CT scan images, we deploy a knowledge distillation technique within teaching assistant (TA) and student frameworks for NSCLC classification. We employed various deep learning models, CNN, VGG19, ResNet152v2, Swin, CCT, and ViT, and assigned roles as teacher, teaching assistant and student. Evaluation underscores exceptional model performance in performance metrics achieved via cost-sensitive learning and precise hyperparameter (alpha and temperature) fine-tuning, highlighting the model's efficiency in lung cancer tumor prediction and classification. The applied TA (ResNet152) and student (CNN) models achieved 90.99% and 94.53% test accuracies, respectively, with optimal hyperparameters (alpha = 0.7 and temperature = 7). The implementation of the TA framework improves the overall performance of the student model. After obtaining Shapley values, explainable AI is applied with a partition explainer to check each class's contribution, further enhancing the transparency of the implemented deep learning techniques. Finally, a web application designed to make it user-friendly and classify lung types in recently captured images. The execution of the three-stage knowledge distillation technique proved efficient with significantly reduced trainable parameters and training time applicable for memory-constrained edge devices.

Lung adenocarcinoma identification based on hybrid feature selections and attentional convolutional neural networks

Lung adenocarcinoma, a chronic non-small cell lung cancer, needs to be detected early. Tumor gene expression data analysis is effective for early detection, yet its challenges lie in a small sample size, high dimensionality, and multi-noise characteristics. In this study, we propose a lung adenocarcinoma convolutional neural network (LATCNN), a deep learning model tailored for accurate lung adenocarcinoma prediction and identification of key genes. During the feature selection stage, we introduce a hybrid algorithm. Initially, the fast correlation-based filter (FCBF) algorithm swiftly filters out irrelevant features, followed by applying the k-means-synthetic minority over-sampling technique (k-means-SMOTE) method to address category imbalance. Subsequently, we enhance the particle swarm optimization (PSO) algorithm by incorporating fast-decay dynamic inertia weights and utilizing the classification and regression tree (CART) as the fitness function for the second stage of feature selection, aiming to further eliminate redundant features. In the classifier construction stage, we present an attention convolutional neural network (atCNN) that incorporates an attention mechanism. This improved model conducts feature selection post lung adenocarcinoma gene expression data analysis for classification and prediction. The results show that LATCNN effectively reduces the feature dimensions and accurately identifies 12 key genes with accuracy, recall, F1 score, and MCC of 99.70%, 99.33%, 99.98%, and 98.67%, respectively. These performance metrics surpass those of other comparative models, highlighting the significance of this research for advancing lung adenocarcinoma treatment.

A boundary-guided transformer for measuring distance from rectal tumor to anal verge on magnetic resonance images

Accurate measurement of the distance from the tumor's lowest boundary to the anal verge (DTAV) provides an important reference value for treatment of rectal cancer, but the standard measurement method (colonoscopy) causes substantial pain. Therefore, we propose a method for automatically measuring the DTAV on sagittal magnetic resonance (MR) images. We designed a boundary-guided transformer that can accurately segment the rectum and tumor. From the segmentation results, we estimated the DTAV by automatically extracting the anterior rectal wall from the tumor's lowest point to the anal verge and then calculating its physical length. Experiments were conducted on a rectal tumor MR imaging (MRI) dataset to evaluate the efficacy of our method. The results showed that our method outperformed surgeons with 6 years of experience (p < 0.001). Furthermore, by referring to our segmentation results, attending and resident surgeons could improve their measurement precision and efficiency.

A deep learning based CT image analytics protocol to identify lung adenocarcinoma category and high-risk tumor area

We present a protocol which implements deep learning-based identification of the lung adenocarcinoma category with high accuracy and generalizability, and labeling of the high-risk area on Computed Tomography (CT) images. The protocol details the execution of the python project based on the dataset used in the original publication or a custom dataset. Detailed steps include data standardization, data preprocessing, model implementation, results display through heatmaps, and statistical analysis process with Origin software or python codes.

For complete details on the use and execution of this protocol, please refer to Chen et al. (2022).

•

A deep learning protocol to identify the lung adenocarcinoma category

•

Identification of high-risk tumor areas

•

Code environment setup and code implementation

•

Code provided for data processing, deep model development, and results analyses

Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics.