Deep active learning for classifying cancer pathology reports
Ontology highlight
ABSTRACT: Background
Automated text classification has many important applications in the clinical setting; however, obtaining labelled data for training machine learning and deep learning models is often difficult and expensive. Active learning techniques may mitigate this challenge by reducing the amount of labelled data required to effectively train a model. In this study, we analyze the effectiveness of 11 active learning algorithms on classifying subsite and histology from cancer pathology reports using a Convolutional Neural Network as the text classification model. Results
We compare the performance of each active learning strategy using two differently sized datasets and two different classification tasks. Our results show that on all tasks and dataset sizes, all active learning strategies except diversity-sampling strategies outperformed random sampling, i.e., no active learning. On our large dataset (15K initial labelled samples, adding 15K additional labelled samples each iteration of active learning), there was no clear winner between the different active learning strategies. On our small dataset (1K initial labelled samples, adding 1K additional labelled samples each iteration of active learning), marginal and ratio uncertainty sampling performed better than all other active learning techniques. We found that compared to random sampling, active learning strongly helps performance on rare classes by focusing on underrepresented classes. Conclusions
Active learning can save annotation cost by helping human annotators efficiently and intelligently select which samples to label. Our results show that a dataset constructed using effective active learning techniques requires less than half the amount of labelled data to achieve the same performance as a dataset constructed using random sampling. Supplementary Information
The online version supplementary material available at 10.1186/s12859-021-04047-1.
SUBMITTER: De Angeli K
PROVIDER: S-EPMC7941989 | biostudies-literature | 2021 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundHysteroscopy is a commonly used technique for diagnosing endometrial lesions. It is essential to develop an objective model to aid clinicians in lesion diagnosis, as each type of lesion has a distinct treatment, and judgments of hysteroscopists are relatively subjective. This study constructs a convolutional neural network model that can automatically classify endometrial lesions using hysteroscopic images as input.MethodsAll histopathologically confirmed endometrial lesion images were obtained from the Shengjing Hospital of China Medical University, including endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyps, and submucous myomas. The study included 1851 images from 454 patients. After the images were preprocessed (histogram equalization, addition of noise, rotations, and flips), a training set of 6478 images was input into a tuned VGGNet-16 model; 250 images were used as the test set to evaluate the model's performance. Thereafter, we compared the model's results with the diagnosis of gynecologists.ResultsThe overall accuracy of the VGGNet-16 model in classifying endometrial lesions is 80.8%. Its sensitivity to endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyp, and submucous myoma is 84.0%, 68.0%, 78.0%, 94.0%, and 80.0%, respectively; for these diagnoses, the model's specificity is 92.5%, 95.5%, 96.5%, 95.0%, and 96.5%, respectively. When classifying lesions as benign or as premalignant/malignant, the VGGNet-16 model's accuracy, sensitivity, and specificity are 90.8%, 83.0%, and 96.0%, respectively. The diagnostic performance of the VGGNet-16 model is slightly better than that of the three gynecologists in both classification tasks. With the aid of the model, the overall accuracy of the diagnosis of endometrial lesions by gynecologists can be improved.ConclusionsThe VGGNet-16 model performs well in classifying endometrial lesions from hysteroscopic images and can provide objective diagnostic evidence for hysteroscopists.
| S-EPMC7788977 | biostudies-literature
Project description:Classification of breast cancer subtypes using multi-omics profiles is a difficult problem since the data sets are high-dimensional and highly correlated. Deep neural network (DNN) learning has demonstrated advantages over traditional methods as it does not require any hand-crafted features, but rather automatically extract features from raw data and efficiently analyze high-dimensional and correlated data. We aim to develop an integrative deep learning framework for classifying molecular subtypes of breast cancer. We collect copy number alteration and gene expression data measured on the same breast cancer patients from the Molecular Taxonomy of Breast Cancer International Consortium. We propose a deep learning model to integrate the omics datasets for predicting their molecular subtypes. The performance of our proposed DNN model is compared with some baseline models. Furthermore, we evaluate the misclassification of the subtypes using the learned deep features and explore their usefulness for clustering the breast cancer patients. We demonstrate that our proposed integrative deep learning model is superior to other deep learning and non-deep learning based models. Particularly, we get the best prediction result among the deep learning-based integration models when we integrate the two data sources using the concatenation layer in the models without sharing the weights. Using the learned deep features, we identify 6 breast cancer subgroups and show that Her2-enriched samples can be classified into more than one tumor subtype. Overall, the integrated model show better performance than those trained on individual data sources.
| S-EPMC7473884 | biostudies-literature
Project description:PurposeArtificial intelligence (AI) techniques are increasingly being used to classify retinal diseases. In this study we investigated the ability of a convolutional neural network (CNN) in categorizing histological images into different classes of retinal degeneration.MethodsImages were obtained from a chemically induced feline model of monocular retinal dystrophy and split into training and testing sets. The training set was graded for the level of retinal degeneration and used to train various CNN architectures. The testing set was evaluated through the best architecture and graded by six observers. Comparisons between model and observer classifications, and interobserver variability were measured. Finally, the effects of using less training images or images containing half the presentable context were investigated.ResultsThe best model gave weighted-F1 scores in the range 85% to 90%. Cohen kappa scores reached up to 0.86, indicating high agreement between the model and observers. Interobserver variability was consistent with the model-observer variability in the model's ability to match predictions with the observers. Image context restriction resulted in model performance reduction by up to 6% and at least one training set size resulted in a model performance reduction of 10% compared to the original size.ConclusionsDetecting the presence and severity of up to three classes of retinal degeneration in histological data can be reliably achieved with a deep learning classifier.Translational relevanceThis work lays the foundations for future AI models which could aid in the evaluation of more intricate changes occurring in retinal degeneration, particularly in other types of clinically derived image data.
| S-EPMC8196406 | biostudies-literature
Project description:Clinical workflows in oncology rely on predictive and prognostic molecular biomarkers. However, the growing number of these complex biomarkers tends to increase the cost and time for decision-making in routine daily oncology practice; furthermore, biomarkers often require tumour tissue on top of routine diagnostic material. Nevertheless, routinely available tumour tissue contains an abundance of clinically relevant information that is currently not fully exploited. Advances in deep learning (DL), an artificial intelligence (AI) technology, have enabled the extraction of previously hidden information directly from routine histology images of cancer, providing potentially clinically useful information. Here, we outline emerging concepts of how DL can extract biomarkers directly from histology images and summarise studies of basic and advanced image analysis for cancer histology. Basic image analysis tasks include detection, grading and subtyping of tumour tissue in histology images; they are aimed at automating pathology workflows and consequently do not immediately translate into clinical decisions. Exceeding such basic approaches, DL has also been used for advanced image analysis tasks, which have the potential of directly affecting clinical decision-making processes. These advanced approaches include inference of molecular features, prediction of survival and end-to-end prediction of therapy response. Predictions made by such DL systems could simplify and enrich clinical decision-making, but require rigorous external validation in clinical settings.
| S-EPMC7884739 | biostudies-literature
Project description:Childhood medulloblastoma (MB) is a threatening malignant tumor affecting children all over the globe. It is believed to be the foremost common pediatric brain tumor causing death. Early and accurate classification of childhood MB and its classes are of great importance to help doctors choose the suitable treatment and observation plan, avoid tumor progression, and lower death rates. The current gold standard for diagnosing MB is the histopathology of biopsy samples. However, manual analysis of such images is complicated, costly, time-consuming, and highly dependent on the expertise and skills of pathologists, which might cause inaccurate results. This study aims to introduce a reliable computer-assisted pipeline called CoMB-Deep to automatically classify MB and its classes with high accuracy from histopathological images. This key challenge of the study is the lack of childhood MB datasets, especially its four categories (defined by the WHO) and the inadequate related studies. All relevant works were based on either deep learning (DL) or textural analysis feature extractions. Also, such studies employed distinct features to accomplish the classification procedure. Besides, most of them only extracted spatial features. Nevertheless, CoMB-Deep blends the advantages of textural analysis feature extraction techniques and DL approaches. The CoMB-Deep consists of a composite of DL techniques. Initially, it extracts deep spatial features from 10 convolutional neural networks (CNNs). It then performs a feature fusion step using discrete wavelet transform (DWT), a texture analysis method capable of reducing the dimension of fused features. Next, the CoMB-Deep explores the best combination of fused features, enhancing the performance of the classification process using two search strategies. Afterward, it employs two feature selection techniques on the fused feature sets selected in the previous step. A bi-directional long-short term memory (Bi-LSTM) network; a DL-based approach that is utilized for the classification phase. CoMB-Deep maintains two classification categories: binary category for distinguishing between the abnormal and normal cases and multi-class category to identify the subclasses of MB. The results of the CoMB-Deep for both classification categories prove that it is reliable. The results also indicate that the feature sets selected using both search strategies have enhanced the performance of Bi-LSTM compared to individual spatial deep features. CoMB-Deep is compared to related studies to verify its competitiveness, and this comparison confirmed its robustness and outperformance. Hence, CoMB-Deep can help pathologists perform accurate diagnoses, reduce misdiagnosis risks that could occur with manual diagnosis, accelerate the classification procedure, and decrease diagnosis costs.
| S-EPMC8193683 | biostudies-literature
Project description:ObjectiveThis paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology reports for use in the Victorian Cancer Registry.Materials and methodsIn addition to traditional supervised learning methods such as conditional random fields and support vector machines, active learning (AL) approaches were investigated to optimize training production and further improve classification performance. The project involved two pilot sites in Victoria, Australia (Lake Imaging (Ballarat) and Peter MacCallum Cancer Centre (Melbourne)) and, in collaboration with the NSW Central Registry, one pilot site at Westmead Hospital (Sydney).ResultsThe reportability classifier performance achieved 98.25% sensitivity and 96.14% specificity on the cancer registry's held-out test set. Up to 92% of training data needed for supervised machine learning can be saved by AL.DiscussionAL is a promising method for optimizing the supervised training production used in classification of radiology reports. When an AL strategy is applied during the data selection process, the cost of manual classification can be reduced significantly.ConclusionsThe most important practical application of the reportability classifier is that it can dramatically reduce human effort in identifying relevant reports from the large imaging pool for further investigation of cancer. The classifier is built on a large real-world dataset and can achieve high performance in filtering relevant reports to support cancer registries.
| S-EPMC4147614 | biostudies-literature
Project description:Vocalizations are widely used for communication between animals. Mice use a large repertoire of ultrasonic vocalizations (USVs) in different social contexts. During social interaction recognizing the partner's sex is important, however, previous research remained inconclusive whether individual USVs contain this information. Using deep neural networks (DNNs) to classify the sex of the emitting mouse from the spectrogram we obtain unprecedented performance (77%, vs. SVM: 56%, Regression: 51%). Performance was even higher (85%) if the DNN could also use each mouse's individual properties during training, which may, however, be of limited practical value. Splitting estimation into two DNNs and using 24 extracted features per USV, spectrogram-to-features and features-to-sex (60%) failed to reach single-step performance. Extending the features by each USVs spectral line, frequency and time marginal in a semi-convolutional DNN resulted in a performance mid-way (64%). Analyzing the network structure suggests an increase in sparsity of activation and correlation with sex, specifically in the fully-connected layers. A detailed analysis of the USV structure, reveals a subset of male vocalizations characterized by a few acoustic features, while the majority of sex differences appear to rely on a complex combination of many features. The same network architecture was also able to achieve above-chance classification for cortexless mice, which were considered indistinguishable before. In summary, spectrotemporal differences between male and female USVs allow at least their partial classification, which enables sexual recognition between mice and automated attribution of USVs during analysis of social interactions.
| S-EPMC7347231 | biostudies-literature
Project description:Despite great advances, molecular cancer pathology is often limited to the use of a small number of biomarkers rather than the whole transcriptome, partly due to computational challenges. Here, we introduce a novel architecture of Deep Neural Networks (DNNs) that is capable of simultaneous inference of various properties of biological samples, through multi-task and transfer learning. It encodes the whole transcription profile into a strikingly low-dimensional latent vector of size 8, and then recovers mRNA and miRNA expression profiles, tissue and disease type from this vector. This latent space is significantly better than the original gene expression profiles for discriminating samples based on their tissue and disease. We employed this architecture on mRNA transcription profiles of 10750 clinical samples from 34 classes (one healthy and 33 different types of cancer) from 27 tissues. Our method significantly outperforms prior works and classical machine learning approaches in predicting tissue-of-origin, normal or disease state and cancer type of each sample. For tissues with more than one type of cancer, it reaches 99.4% accuracy in identifying the correct cancer subtype. We also show this system is very robust against noise and missing values. Collectively, our results highlight applications of artificial intelligence in molecular cancer pathology and oncological research. DeePathology is freely available at https://github.com/SharifBioinf/DeePathology .
| S-EPMC6848155 | biostudies-literature
Project description:BackgroundLung cancer is the leading cause of cancer deaths worldwide. Clinical staging of lung cancer plays a crucial role in making treatment decisions and evaluating prognosis. However, in clinical practice, approximately one-half of the clinical stages of lung cancer patients are inconsistent with their pathological stages. As one of the most important diagnostic modalities for staging, chest computed tomography (CT) provides a wealth of information about cancer staging, but the free-text nature of the CT reports obstructs their computerization.ObjectiveWe aimed to automatically extract the staging-related information from CT reports to support accurate clinical staging of lung cancer.MethodsIn this study, we developed an information extraction (IE) system to extract the staging-related information from CT reports. The system consisted of the following three parts: named entity recognition (NER), relation classification (RC), and postprocessing (PP). We first summarized 22 questions about lung cancer staging based on the TNM staging guideline. Next, three state-of-the-art NER algorithms were implemented to recognize the entities of interest. Next, we designed a novel RC method using the relation sign constraint (RSC) to classify the relations between entities. Finally, a rule-based PP module was established to obtain the formatted answers using the results of NER and RC.ResultsWe evaluated the developed IE system on a clinical data set containing 392 chest CT reports collected from the Department of Thoracic Surgery II in the Peking University Cancer Hospital. The experimental results showed that the bidirectional encoder representation from transformers (BERT) model outperformed the iterated dilated convolutional neural networks-conditional random field (ID-CNN-CRF) and bidirectional long short-term memory networks-conditional random field (Bi-LSTM-CRF) for NER tasks with macro-F1 scores of 80.97% and 90.06% under the exact and inexact matching schemes, respectively. For the RC task, the proposed RSC showed better performance than the baseline methods. Further, the BERT-RSC model achieved the best performance with a macro-F1 score of 97.13% and a micro-F1 score of 98.37%. Moreover, the rule-based PP module could correctly obtain the formatted results using the extractions of NER and RC, achieving a macro-F1 score of 94.57% and a micro-F1 score of 96.74% for all the 22 questions.ConclusionsWe conclude that the developed IE system can effectively and accurately extract information about lung cancer staging from CT reports. Experimental results show that the extracted results have significant potential for further use in stage verification and prediction to facilitate accurate clinical staging.
| S-EPMC8339987 | biostudies-literature
Project description:The quantification and identification of cellular phenotypes from high-content microscopy images has proven to be very useful for understanding biological activity in response to different drug treatments. The traditional approach has been to use classical image analysis to quantify changes in cell morphology, which requires several nontrivial and independent analysis steps. Recently, convolutional neural networks have emerged as a compelling alternative, offering good predictive performance and the possibility to replace traditional workflows with a single network architecture. In this study, we applied the pretrained deep convolutional neural networks ResNet50, InceptionV3, and InceptionResnetV2 to predict cell mechanisms of action in response to chemical perturbations for two cell profiling datasets from the Broad Bioimage Benchmark Collection. These networks were pretrained on ImageNet, enabling much quicker model training. We obtain higher predictive accuracy than previously reported, between 95% and 97%. The ability to quickly and accurately distinguish between different cell morphologies from a scarce amount of labeled data illustrates the combined benefit of transfer learning and deep convolutional neural networks for interrogating cell-based images.
| S-EPMC6484664 | biostudies-literature