Deep Active Learning for Computer Vision Tasks: Methodologies, Applications, and Challenges

Wu, Mingxi; Li, Chen; Yao, Zehuan

doi:10.3390/app12168103

Cited by 23 publications

(14 citation statements)

References 134 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Active learning is an iterative machine learning procedure, in which the model learning process is divided into iterations and in each iteration a group of new samples is selected based on a designed strategy and added to the model training dataset [32,36,37]. In each iteration of the active learning process, the current model is used to generate predictions on all unlabeled data points.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

Vasanthakumari,

Zhu,

Brettin

et al. 2024

Cancers

View full text Add to dashboard Cite

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Active learning has been used in many computer vision applications [37] such as autonomous navigation [42,43], and biomedical image analysis [40,44]. Autonomous navigation systems require enormous amount of data as images or point clouds to ensure reliable and safe operations.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

Vasanthakumari,

Zhu,

Brettin

et al. 2024

Cancers

View full text Add to dashboard Cite

show abstract

“…Recently, in the field of digital pathology, there have been studies that combine methods for removing false-labeled patch images with uncertainty-based AL strategies [ 22 ], or that consider both uncertainty and representation in patch-based analysis [ 15 ]. However, the use of an AL strategy based on uncertainty can be challenging when dealing with noisy real-world industrial data, as most DL studies use clean or minimally noisy (dirty) publicly available datasets, potentially worsening performance when noisy samples are queried [ 23 ]. Noisy images can be generated in the workplace due to various issues, such as out-of-focus scanning, missing tissue, air bubbles, poor staining, poor sectioning, tissue artifacts, tissue folding, or poor dehydration [ 24 , 25 ], leading to poor quality patch images.…”

Section: Introductionmentioning

confidence: 99%

A predicted-loss based active learning approach for robust cancer pathology image analysis in the workplace

Kim,

Quiñones Robles,

et al. 2024

BMC Med Imaging

View full text Add to dashboard Cite

Background Convolutional neural network-based image processing research is actively being conducted for pathology image analysis. As a convolutional neural network model requires a large amount of image data for training, active learning (AL) has been developed to produce efficient learning with a small amount of training data. However, existing studies have not specifically considered the characteristics of pathological data collected from the workplace. For various reasons, noisy patches can be selected instead of clean patches during AL, thereby reducing its efficiency. This study proposes an effective AL method for cancer pathology that works robustly on noisy datasets. Methods Our proposed method to develop a robust AL approach for noisy histopathology datasets consists of the following three steps: 1) training a loss prediction module, 2) collecting predicted loss values, and 3) sampling data for labeling. This proposed method calculates the amount of information in unlabeled data as predicted loss values and removes noisy data based on predicted loss values to reduce the rate at which noisy data are selected from the unlabeled dataset. We identified a suitable threshold for optimizing the efficiency of AL through sensitivity analysis. Results We compared the results obtained with the identified threshold with those of existing representative AL methods. In the final iteration, the proposed method achieved a performance of 91.7% on the noisy dataset and 92.4% on the clean dataset, resulting in a performance reduction of less than 1%. Concomitantly, the noise selection ratio averaged only 2.93% on each iteration. Conclusions The proposed AL method showed robust performance on datasets containing noisy data by avoiding data selection in predictive loss intervals where noisy data are likely to be distributed. The proposed method contributes to medical image analysis by screening data and producing a robust and effective classification model tailored for cancer pathology image processing in the workplace.

show abstract

“…This model offers advanced segmentation capabilities to accurately identify pulmonary embolism regions [ 33 ]. Wu et al explored computer-aided PE detection using VoxelNet, a deep learning method designed for the analysis of 3D CT images through processing volumetric elements (voxels) in order to automatically detect pulmonary embolisms and other airway obstructions [ 34 ]. Furthermore, Khan et al achieved an 88% accuracy with a CNN model based on DenseNet201 when analyzing 9446 CT angiography scans from the RSNA-Kaggle database [ 35 ].…”

Section: Introductionmentioning

confidence: 99%

An Enhanced Mask R-CNN Approach for Pulmonary Embolism Detection and Segmentation

Doğan,

Selçuk,

Alkan

2024

Diagnostics

View full text Add to dashboard Cite

Pulmonary embolism (PE) refers to the occlusion of pulmonary arteries by blood clots, posing a mortality risk of approximately 30%. The detection of pulmonary embolism within segmental arteries presents greater challenges compared with larger arteries and is frequently overlooked. In this study, we developed a computational method to automatically identify pulmonary embolism within segmental arteries using computed tomography (CT) images. The system architecture incorporates an enhanced Mask R-CNN deep neural network trained on PE-containing images. This network accurately localizes pulmonary embolisms in CT images and effectively delineates their boundaries. This study involved creating a local data set and evaluating the model predictions against pulmonary embolisms manually identified by expert radiologists. The sensitivity, specificity, accuracy, Dice coefficient, and Jaccard index values were obtained as 96.2%, 93.4%, 96.%, 0.95, and 0.89, respectively. The enhanced Mask R-CNN model outperformed the traditional Mask R-CNN and U-Net models. This study underscores the influence of Mask R-CNN’s loss function on model performance, providing a basis for the potential improvement of Mask R-CNN models for object detection and segmentation tasks in CT images.

show abstract

Deep Active Learning for Computer Vision Tasks: Methodologies, Applications, and Challenges

Cited by 23 publications

References 134 publications

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

A predicted-loss based active learning approach for robust cancer pathology image analysis in the workplace

An Enhanced Mask R-CNN Approach for Pulmonary Embolism Detection and Segmentation

Contact Info

Product

Resources

About