Fast deep learning correspondence for neuron tracking and identification in C.elegans using synthetic training.

Comparative analysis of deep convolution neural network models on small scale datasets

In recent years, discriminative learning methods have widely been used in various areas of Natural Language Processing (NLP). These methods achieve the best performance, when the set of training and testing samples have the same distribution. However, in many applications of NLP, the lack of labeled datasets for some domains is a serious challenge. In such conditions, we need to develop a model based on domains with rich labeled instances and apply it to the domain with no labeled instances. In this research, a method for sentiment classification of opinions into positive and negative groups, which represent the users' feelings, is offered based on multi-source transfer learning. The proposed method here employs Spectral Feature Alignment algorithm to adapt different domains. Furthermore, according to the Majority Voting, accuracy is assigned to classifications trained on different domains based on the Majority Voting Error. Ultimately, decisions are made for each classification based on the calculated error. The Amazon datasets for four different categories, each of which contains 1000 positive and 1000 negative samples, are exploited to train the proposed model. Meanwhile, each category includes unlabeled samples that are used to select pivot features. The accuracy values of 85.5%, 86.4%, 83.5% and 90.1% obtained for Electronics, DVD, Books and Kitchen domains respectively, show the effectiveness of the proposed method compared with similar methods.

目的 基于计算机的胸腔X线影像疾病检测和分类目前存在误诊率高，准确率低的问题。本文在视觉Transformer（vision Transformer，ViT）预训练模型的基础上，通过迁移学习方法，实现胸腔X线影像辅助诊断，提高诊断准确率和效率。方法 选用带有卷积神经网络（convolutional neural network，CNN）的ViT模型，其在超大规模自然图像数据集中进行了预训练；通过微调模型结构，使用预训练的ViT模型参数初始化主干网络，并迁移至胸腔X线影像数据集中再次训练，实现疾病多标签分类。结果 在IU X-Ray数据集中对ViT迁移学习前、后模型平均AUC（area under ROC curve）得分进行对比分析实验。结果表明，预训练ViT模型平均AUC得分为0.774，与不使用迁移学习相比提升了0.208。并针对模型结构和数据预处理进行了消融实验，对ViT中的注意力机制进行可视化，进一步验证了模型有效性。最后使用Chest X-Ray14和CheXpert数据集训练微调后的ViT模型，平均AUC得分为0.839和0.806，与对比方法相比分别有0.014～0.031的提升。结论 与其他方法相比，ViT模型胸腔X线影像的多标签分类精确度更高，且迁移学习可以在降低训练成本的同时提升ViT模型的分类性能和泛化性。消融实验与模型可视化表明，包含CNN结构的ViT模型能重点关注有意义的区域，高效获取胸腔X线影像的视觉特征。;Objective The chest X-ray-relevant screening and diagnostic method is essential for radiology nowadays. Most of chest X-ray images interpretation is still restricted by clinical experience and challenged for misdiagnose and missed diagnoses. To detect and identify one or more potential diseases in images automatically，it is beneficial for improving diagnostic efficiency and accuracy using computer-based technique. Compared to natural images，multiple lesions are challenged to be detected and distinguished accurately in a single image because abnormal areas have a small proportion and complex representations in chest X-ray images. Current convolutional neural network（CNN）based deep learning models have been widely used in the context of medical imaging. The structure of the CNN convolution kernel has sensitive to local detail information，and it is possible to extract richer image features. However，the convolution kernel cannot be used to get global information，and the features-extracted are restricted of redundant information like its relevance of background， muscles，and bones. The model’s performance in multi-label classification tasks are affected to a certain extent. At present，the vision Transformer（ViT）model has achieved its priorities in computer vision-related tasks. The ViT can be used to capture information simultaneously and effectively for multiple regions of the entire image. However，it is required to use large-scale dataset training to achieve good performance. Due to some factors like patient privacy and manual annotate costs，the size of the chest X-ray image data set has been limited. To reduce the model's dependence on data scale and improve the performance of multi-label classification，we develop the CNN-based ViT pre-training model in terms of the transfer learning method for diagnosis-assisted of chest X-ray image and multi-label classification. Method The CNN-based ViT model is pre-trained on a huge scale ground truth dataset，and it is used to obtain the initial parameters of the model. The model structure is fine-tuned according to the features of chest X-ray dataset. A 1×1 convolution layer is used to convert the chest X-ray images channels between 1 to 3. The number of output nodes of the linear layer in the classifier is balanced from 1 000 to the number of chest X-ray classification labels，and the Sigmoid is used as an activation function. The parameters of the backbone network are initialized in terms of the pre-trained ViT model parameters，and it is trained in the chest X-ray dataset after that to complete multi-label classification. The experiment is configured of Python3. 7 and PyTorch1. 8 to construct the model and RTX3090 GPU for training. Stochastic gradient descent（SGD）optimizer，binary cross-entropy（BCE）loss function，an initial learning rate of 1E-3，the cosine annealing learning rate decay are used. For training，each image is scaled to a size of 512×512 pixels，and a 224×224 pixels area and it is then cropped in random as the model input，and data augmentation is performed randomly by some of the flipping，perspective transformation， shearing，translation，zooming，and changing brightness. For testing，the chest X-ray image is scaled to 256×256 pixels and center crop a 224×224 area to input the trained model. Result The experiment is performed on the IU X-Ray，which is a small-scale chest X-ray dataset. This model is evaluated in quantitative using the average of area under ROC curve （AUC）scores across all classification labels. The results show that the average AUC score of the pre-trained ViT model is 0. 774. The accuracy and training efficiency of the non-pre-trained ViT model is dropped significantly. The average AUC score is reached to 0. 566 only，which is 0. 208 lower. In addition，the attention mechanism heat map is generated based on the ViT model，which can strengthen the interpretability of the model. A series of ablation experiments are carried out for data augmentation，model structure，and batch size design. The fine-tuned ViT model is trained on the Chest-Ray14 and CheXpert dataset as well. The average AUC score is reached to 0. 839 and 0. 806，which is optimized by 0. 014 and 0. 031. Conclusion A pre-trained ViT model is used for the multi-label classification of chest X-ray images via transfer learning. The experimental results illustrate that the ViT has its stronger multi-label classification performance in chest Xray images，and its attention mechanism is beneficial for lesions precision-focused like the interior of the chest cavity and the heart. Transfer learning is potential to improve the classification performance and model generalization of the ViT in small-scale datasets，and the training cost is reduced greatly. Ablation experiments demonstrate that the incorporated model of CNN and Transformer has its priority beyond single-structure model. Data enhancement and the batch size cutting can improve the performance of the model，but smaller scale of batch is still interlinked to longer training span. To improve the model's ability，we predict that future research direction can be focused on the extraction for complex disease and highlevel semantic information，such as their small lesions，disease location，and severity.

The determination of transcriptional regulatory networks is key to the understanding of biological systems. However, the experimental determination of transcriptional regulatory networks in the laboratory remains difficult and time-consuming, while current computational methods to infer these networks (typically from gene-expression data) achieve only modest accuracy. The latter can be attributed in part to the limitations of a single-organism approach. Computational biology has long used comparative and, more generally, evolutionary approaches to extend the reach and accuracy of its analyses. We therefore use an evolutionary approach to the inference of regulatory networks, which enables us to study evolutionary models for these networks as well as to improve the accuracy of inferred networks. Since the regulatory networks evolve along with the genomes, we consider that the regulatory networks for a family of organisms are related to each other through the same phylogenetic tree. These relationships contain information that can be used to improve the accuracy of inferred networks. Advances in the study of evolution of regulatory networks provide evidence to establish evolutionary models for regulatory networks, which is an important component of our evolutionary approach. We use two network evolutionary models, a basic model that considers only the gains and losses of regulatory connections during evolution, and an extended model that also takes into account the duplications and losses of genes. With the network evolutionary models, we design refinement algorithms to make use of the phylogenetic relationships to refine noisy regulatory networks for a family of organisms. These refinement algorithms include: RefineFast and RefineML, which are two-step iterative algorithms, and ProPhyC and ProPhyCC, which are based on a probabilistic phylogenetic model. For each algorithm we first design it with the basic network evolutionary model and then generalize it to the extended evolutionary model. All these algorithms are computationally efficient and are supported by extensive experimental results showing that they yield substantial improvement in the quality of the input noisy networks. In particular, ProPhyC and ProPhyCC further improve the performance of RefineFast and RefineML. Besides the four refinement algorithms mentioned above, we also design an algorithm based on transfer learning theory called tree transfer learning (TTL). TTL differs from the previous four refinement algorithms in the sense that it takes the gene-expression data for the family of organisms as input, instead of their inferred noisy networks. TTL then learns the network structures for all the organisms at once, meanwhile taking advantage of the phylogenetic relationships. Although this approach outperforms an inference algorithm used alone, it does not perform better than ProPhyC, which indicates that the ProPhyC framework makes good use of the phylogenetic information.

Image classification and prediction using transfer learning in colab notebook

Even though the P300 based speller has proved to be usable by real patients, it is not a user-friendly system. The necesarry calibration session and slow spelling make the system tedious. We present a machine learning approach to P300 spelling that enables us to remove the calibration session. We achieve this by a combination of unsupervised training, transfer learning across subjects and language models. On top of that, we can increase the spelling speed by incorporating a dynamic stopping approach. This yields a P300 speller that works instantly and with high accuracy and spelling speed, even for unseen subjects.

The prevalence of age-related brain issues has risen in developed countries because of changes in lifestyle. Alzheimer's disease leads to a rapid and irreversible decline in cognitive abilities by damaging memory cells. A ResNet-18-based system is proposed, integrating Depth Convolution with a Squeeze and Excitation (SE) block to minimize tuning parameters. This design is based on analyses of existing deep learning architectures and feature extraction techniques. Additionally, pre-trained ResNet-18 models were created with and without the SE block to compare ROC and accuracy values across different hyperparameters. The proposed model achieved ROC values of 95% for Alzheimer's Disease (AD), 95% for Cognitively Normal (CN), and 93% for Mild Cognitive Impairment (MCI), with a maximum test accuracy of 88.51%. However, the pre-trained model with SE had 93.26% accuracy and ROC values of 98%, 99%, and 98%, while the model without SE had 94%, 97%, and 94% ROC values and 92.41% accuracy. Collecting medical data can be expensive and raises ethical concerns. Small data sets are also prone to local minima issues in the cost function. A scratch model that experiences extensive hyperparameter tuning may end up being either overfitted or underfitted. Class imbalance also reduces performance. Transfer learning is most effective with small, imbalanced datasets, and pre-trained models with SE blocks perform better than others. The proposed model introduced a method to reduce training parameters and prevent overfitting from imbalanced medical data. Overall performance findings show that the suggested approach performs better than the state-of-the-art techniques.

Recent progress in machine learning has been mainly due to the availability of large amounts of annotated data used for training complex models with deep architectures. Annotating this training data becomes burdensome and creates a major bottleneck in maintaining machine-learning databases. Moreover, these trained models fail to generalize to new categories or new varieties of the same categories. This is because new categories or new varieties have data distribution different from the training data distribution. To tackle these problems, this thesis proposes to develop a family of transfer-learning techniques that can deal with different training (source) and testing (target) distributions with the assumption that the availability of annotated data is limited in the testing domain. This is done by using the auxiliary data-abundant source domain from which useful knowledge is transferred that can be applied to data-scarce target domain. This transferable knowledge serves as a prior that biases target-domain predictions and prevents the target-domain model from overfitting. Specifically, we explore structural priors that encode relational knowledge between different data entities, which provides more informative bias than traditional priors. The choice of the structural prior depends on the information availability and the similarity between the two domains. Depending on the domain similarity and the information availability, we divide the transfer learning problem into four major categories and propose different structural priors to solve each of these sub-problems. This thesis first focuses on the unsupervised-domain-adaptation problem, where we propose to minimize domain discrepancy by transforming labeled source-domain data to be close to unlabeled target-domain data. For this problem, the categories remain the same across the two domains and hence we assume that the structural relationship between the source-domain samples is carried over to the target domain. Thus, graph or hyper-graph is constructed as the structural prior from both domains and a graph/hyper-graph matching formulation is used to transform samples in the source domain to be closer to samples in the target domain. An efficient optimization scheme is then proposed to tackle the time and memory inefficiencies associated with the matching problem. The few-shot learning problem is studied next, where we propose to transfer knowledge from source-domain categories containing abundantly labeled data to novel categories in the target domain that contains only few labeled data. The knowledge transfer biases the novel category predictions and prevents the model from overfitting. The knowledge is encoded using a neural-network-based prior that transforms a data sample to its corresponding class prototype. This neural network is trained from the source-domain data and applied to the target-domain data, where it transforms the few-shot samples to the novel-class prototypes for better recognition performance. The few-shot learning problem is then extended to the situation, where we do not have access to the source-domain data but only have access to the source-domain class prototypes. In this limited information setting, parametric neural-network-based priors would overfit to the source-class prototypes and hence we seek a non-parametric-based prior using manifolds. A piecewise linear manifold is used as a structural prior to fit the source-domain-class prototypes. This structure is extended to the target domain, where the novel-class prototypes are found by projecting the few-shot samples onto the manifold. Finally, the zero-shot learning problem is addressed, which is an extreme case of the few-shot learning problem where we do not have any labeled data in the target domain. However, we have high-level information for both the source and target domain categories in the form of semantic descriptors. We learn the relation between the sample space and the semantic space, using a regularized neural network so that classification of the novel categories can be carried out in a common representation space. This same neural network is then used in the target domain to relate the two spaces. In case we want to generate data for the novel categories in the target domain, we can use a constrained generative adversarial network instead of a traditional neural network. Thus, we use structural priors like graphs, neural networks and manifolds to relate various data entities like samples, prototypes and semantics for these different transfer learning sub-problems. We explore additional post-processing steps like pseudo-labeling, domain adaptation and calibration and enforce algorithmic and architectural constraints to further improve recognition performance. Experimental results on standard transfer learning image recognition datasets produced competitive results with respect to previous work. Further experimentation and analyses of these methods provided better understanding of machine learning as well.

As an important part of emotion research, facial expression recognition is a necessary condition for intelligent interaction between human and machine, which has an important research significance and a potential commercial value. Convolutional neural network (CNN) is an effective method to recognize facial emotions, which can perform feature extraction and classification simultaneously, and can automatically discover multiple levels of representations in data. Due to the fact that there are millions of parameters involved in training the convolutional neural network model, and there is a large demand for marked samples, transfer learning is often used to fine-tune the pre-trained model for a small target sample set. However, there are often some content differences between data sets during deep transfer learning, which will affect the recognition ability of feature extraction. In order to improve the facial expression recognition ability in transfer learning, a hybrid transfer learning model based on an improved convolution restricted boltzmann machine (CRBM) model and a CNN model is proposed in this paper. This method is fused by two learning abilities of these two models. When the pre-trained CNN model is transferred to a small target set, the CRBM is used to replace the full connection layer in the CNN model, and the CRBM layer and the sofmax layer will be retrained on the target set. The added CRBM layer can not only fully connects all feature maps, but can also learn about the unique statistical characteristics about the target set, which eliminates the influence of content differences between data sets, and extracts higher-order statistical features of facial expression images from the target set. The proposed method is evaluated based on four publicly available facial expression databases: JAFFE, FER2013, SFEW and RAF-DB. The new method can achieve better performance than most state-of-the-art methods, and it can effectively prevent the negative influence of transfer learning features between different data sets.

We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned object models consisting of a fusion of multiple object properties. Unlike traditional transfer learning, there can be severe differences in the data distributions, resulting from differences in sensing, sensory processing, or even representations, that each robot uses to learn. Furthermore, only some properties may overlap between the two robots. We show that in such cases, the abstraction of raw sensory data into an intermediate representation can be used not only to aid learning, but also the transfer of knowledge. Further, we utilize statistical metrics, learned during an interactive process where the robots jointly explore the environment, to determine which underlying properties are shared between the robots. We demonstrate results in a visual classification task where objects are represented via a combination of properties derived from different modalities: color, texture, shape, and size. Using our methods, two heterogeneous robots utilizing different sensors and representations are able to successfully transfer support vector machine (SVM) classifiers among each other, resulting in speedups during learning.

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate the weights of a target model based on task identity. Continual learning (CL) is less difficult for this class of models thanks to a simple key feature: instead of recalling the input-output relations of all previously seen data, task-conditioned hypernetworks only require rehearsing task-specific weight realizations, which can be maintained in memory using a simple regularizer. Besides achieving state-of-the-art performance on standard CL benchmarks, additional experiments on long task sequences reveal that task-conditioned hypernetworks display a very large capacity to retain previous memories. Notably, such long memory lifetimes are achieved in a compressive regime, when the number of trainable weights is comparable or smaller than target network size. We provide insight into the structure of low-dimensional task embedding spaces (the input space of the hypernetwork) and show that task-conditioned hypernetworks demonstrate transfer learning. Finally, forward information transfer is further supported by empirical results on a challenging CL benchmark based on the CIFAR-10/100 image datasets.

Pneumonia is a lung infection and causes the inflammation of the small air sacs (Alveoli) in one or both lungs. Proper and faster diagnosis of pneumonia at an early stage is imperative for optimal patient care. Currently, chest X-ray is considered as the best imaging modality for diagnosing pneumonia. However, the interpretation of chest X-ray images is challenging. To this end, we aimed to use an automated convolutional neural network-based transfer-learning approach to detect pneumonia in paediatric chest radiographs. Herein, an automated convolutional neural network-based transfer-learning approach using four different pre-trained models (i.e. VGG19, DenseNet121, Xception, and ResNet50) was applied to detect pneumonia in children (1-5 years) chest X-ray images. The performance of different proposed models for testing data set was evaluated using five performances metrics, including accuracy, sensitivity/recall, Precision, area under curve, and F1 score. All proposed models provide accuracy greater than 83.0% for binary classification. The pre-trained DenseNet121 model provides the highest classification performance of automated pneumonia classification with 86.8% accuracy, followed by Xception model with an accuracy of 86.0%. The sensitivity of the proposed models was greater than 91.0%. The Xception and DenseNet121 models achieve the highest classification performance with F1-score greater than 89.0%. The plotted area under curve of receiver operating characteristics of VGG19, Xception, ResNet50, and DenseNet121 models are 0.78, 0.81, 0.81, and 0.86, respectively. Our data showed that the proposed models achieve a high accuracy for binary classification. Transfer learning was used to accelerate training of the proposed models and resolve the problem associated with insufficient data. We hope that these proposed models can help radiologists for a quick diagnosis of pneumonia at radiology departments. Moreover, our proposed models may be useful to detect other chest-related diseases such as novel Coronavirus 2019. Herein, we used transfer learning as a machine learning approach to accelerate training of the proposed models and resolve the problem associated with insufficient data. Our proposed models achieved accuracy greater than 83.0% for binary classification.

Accurate patient outcome prediction in the intensive care unit (ICU) can potentially lead to more effective and efficient patient care. Deep learning models are capable of learning from data to accurately predict patient outcomes, but they typically require large amounts of data and computational resources. Transfer learning (TL) can help in scenarios where data and computational resources are scarce by leveraging pretrained models. While TL has been widely used in medical imaging and natural language processing, it has been rare in electronic health record (EHR) analysis. Furthermore, domain adaptation (DA) has been the most common TL method in general, whereas inductive transfer learning (ITL) has been rare. To the best of our knowledge, DA and ITL have never been studied in-depth in the context of EHR-based ICU patient outcome prediction. This study investigated DA, as well as rarely researched ITL, in EHR-based ICU patient outcome prediction under simulated, varying levels of data scarcity. Two patient cohorts were used in this study: (1) eCritical, a multicenter ICU data from 55,689 unique admission records from 48,672 unique patients admitted to 15 medical-surgical ICUs in Alberta, Canada, between March 2013 and December 2019, and (2) Medical Information Mart for Intensive Care III, a single-center, publicly available ICU data set from Boston, Massachusetts, acquired between 2001 and 2012 containing 61,532 admission records from 46,476 patients. We compared DA and ITL models with baseline models (without TL) of fully connected neural networks, logistic regression, and lasso regression in the prediction of 30-day mortality, acute kidney injury, ICU length of stay, and hospital length of stay. Random subsets of training data, ranging from 1% to 75%, as well as the full data set, were used to compare the performances of DA and ITL with the baseline models at various levels of data scarcity. Overall, the ITL models outperformed the baseline models in 55 of 56 comparisons (all P values <.001). The DA models outperformed the baseline models in 45 of 56 comparisons (all P values <.001). ITL resulted in better performance than DA in terms of the number of times and the margin with which it outperformed the baseline models. In 11 of 16 cases (8 of 8 for ITL and 3 of 8 for DA), TL models outperformed baseline models when trained using 1% data subset. TL-based ICU patient outcome prediction models are useful in data-scarce scenarios. The results of this study can be used to estimate ICU outcome prediction performance at different levels of data scarcity, with and without TL. The publicly available pretrained models from this study can serve as building blocks in further research for the development and validation of models in other ICU cohorts and outcomes.

Many applications require precise estimates of high-dimensional covariance matrices. The standard estimator is the sample covariance matrix, which is conceptually simple, fast to compute and has favorable properties in the limit of infinitely many observations. The picture changes when the dimensionality is of the same order as the number of observations. In such cases, the eigenvalues of the sample covariance matrix are highly biased, the condition number becomes large and the inversion of the matrix gets numerically unstable.&#13;\nA number of alternative estimators are superior in the high-dimensional setting, which include as subcategories structured estimators, regularized estimators and spectrum correction methods. In this thesis I contribute to all three areas. &#13;\nIn the area of structured estimation, I focus on models with low intrinsic dimensionality. I analyze the bias in Factor Analysis, the state-of-the-art factor model and propose Directional Variance Adjustment (DVA) Factor Analysis, which reduces bias and yields improved estimates of the covariance matrix.&#13;\nAnalytical shrinkage of Ledoit and Wolf (LW-Shrinkage) is the most popular regularized estimator. I contribute in three aspects: first, I provide a theoretical analysis of the behavior of LW-Shrinkage in the presence of pronounced eigendirections, a case of great practical relevance. I show that LW-Shrinkage does not perform well in this setting and propose aoc-Shrinkage which yields significant improvements. Second, I discuss the effect of autocorrelation on LW-Shrinkage and review the Sancetta-Estimator, an extension of LW-Shrinkage to autocorrelated data. I show that the Sancetta-Estimator is biased and propose a theoretically and empirically superior estimator with reduced bias. Third, I propose an extension of shrinkage to multiple shrinkage targets. Multi-Target Shrinkage is not restricted to covariance estimation and allows for many interesting applications which go beyond regularization, including transfer learning. I provide a detailed theoretical and empirical analysis.&#13;\nSpectrum correction approaches the problem of covariance estimation by improving the estimates of the eigenvalues of the sample covariance matrix. I discuss the state-of-the-art approach, Nonlinear Shrinkage, and propose a cross-validation based covariance (CVC) estimator which yields competitive performance at increased numerical stability and greatly reduced complexity and computational cost. On all data sets considered, CVC is on par or superior in comparison to the regularized and structured estimators.&#13;\nIn the last chapter, I conclude with a discussion of the advantages and disadvantages of all covariance estimators presented in this thesis and give situation-specific recommendations. In addition, the appendix contains a systematic analysis of Linear Discriminant Analysis as a model application, which sheds light on the interdependency between the generative model of the data and various covariance estimators.

Caveolae are plasma membrane invaginations whose formation requires caveolin-1 (Cav1), the adaptor protein polymerase I, and the transcript release factor (PTRF or CAVIN1). Caveolae have an important role in cell functioning, signaling, and disease. In the absence of CAVIN1/PTRF, Cav1 forms non-caveolar membrane domains called scaffolds. In this work, we train machine learning models to automatically distinguish between caveolae and scaffolds from single molecule localization microscopy (SMLM) data. We apply machine and deep learning algorithms to discriminate biological structures from SMLM data. Our work is the first that is leveraging machine and deep learning approaches to automatically identifying biological structures from SMLM data. In particular, we develop and compare three binary classification methods to identify whether or not a given 3D cluster of Cav1 proteins is a caveolae. The first uses a random forest classifier applied to 28 hand-picked features, the second uses a convolutional neural net (CNN) applied to a projection of the point clouds onto three planes, and the third uses a PointNet model, a recent development that can directly take point clouds as its input. We validate our methods on a dataset of super-resolution microscopy images of PC3 prostate cancer cells labeled for Cav1. Specifically, we have images from two cell populations: 10 PC3 and 10 CAVIN1/PTRF-transfected PC3 cells (PC3-PTRF cells) that form caveolae. We obtained a balanced set of 1714 different cellular structures. Our results show that both the random forest on hand selected features and the deep learning approach achieve high accuracy in distinguishing the intrinsic features of the caveolae and non-caveolae biological structures. More specifically, both random forest and deep CNN classifiers achieve classification accuracy reaching 94% on our test set, while the PointNet model only reached 83% accuracy. We also discuss the pros and cons of the different approaches. Additional information about individual files is in the accompanying CSV file (item_metadata.csv). This dataset was originally deposited in the Simon Fraser University institutional repository.