Intelligent skin cancer diagnosis using improved particle swarm optimization and deep learning models
Open accessThe DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
In this research, we propose an intelligent decision support system for skin cancer detection. Since generating an effective lesion representation is a vital step to ensure the success of lesion classification, the discriminative power of different types of features is exploited. Specifically, we combine clinically important asymmetry, border irregularity, colour and dermoscopic structure features with texture features extracted using Grey Level Run Length Matrix, Local Binary Patterns, and Histogram of Oriented Gradients operators for lesion representation. Then, we propose two enhanced Particle Swarm Optimization (PSO) models for feature optimization. The first model employs adaptive acceleration coefficients, multiple remote leaders, in-depth sub-dimension feature search and re-initialization mechanisms to overcome stagnation. The second model uses random acceleration coefficients, instead of adaptive ones, based on non-linear circle, sine and helix functions, respectively, to increase diversification and intensification. Ensemble classifiers are also constructed with each base model trained using each optimized feature subset. A deep convolutional neural network is devised whose hyper-parameters are fine-tuned using the proposed PSO models. Extensive experimental studies using dermoscopic skin lesion data, medical data from the UCI machine learning repository, and ALL-IDB2 image data are conducted to evaluate the model efficiency systematically. The results from empirical evaluations and statistical tests indicate the superiority of the proposed models over other advanced PSO variants and classical search methods pertaining to discriminative feature selection and optimal hyper-parameter identification for deep learning networks in lesion classification as well as other disease diagnosis.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,370
Particle swarm optimization: An overview
Poli, R., Kennedy, J., & Blackwell, T. (2007) · Swarm Intelligence · doi:10.1007/s11721-007-0002-0 · Cited by 21,101
Peng, H., Long, F., & Ding, C. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.159 · Cited by 10,544 · cited 1×
“Moreover, two well-known filter methods are also used for comparison of feature selection, i.e. Minimum Redundancy and Maximum Relevance (mRMR) [42] and ReliefF [43].”
Estimating attributes: Analysis and extensions of RELIEF
Kononenko, I. (1994) · Lecture Notes in Computer Science · doi:10.1007/3-540-57868-4_57 · Cited by 2,958 · cited 1×
“Moreover, two well-known filter methods are also used for comparison of feature selection, i.e. Minimum Redundancy and Maximum Relevance (mRMR) [42] and ReliefF [43].”
Learning and optimization using the clonal selection principle
de Castro, L. N., & Von Zuben, F. J. (2002) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2002.1011539 · Cited by 2,240 · cited 1×
“The above acceleration coefficient generation mechanism is also motivated by the clonal mutation processes and certain characteristics of the clonal selection theory where the antibodies with the highest affinities are cloned proportionally to their antigenic affinities and the attributes of these clones are subsequen…”
A Survey on Evolutionary Computation Approaches to Feature Selection
Xue, B., Zhang, M., Browne, W. N., & Yao, X. (2016) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2015.2504420 · Cited by 1,841 · cited 2×
“Other feature selection processes incorporated with other search methods in our study are also wrapper-based methods where feature selection is guided by the fitness evaluation in correspondence with the classification model [41].”
Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks
Yu, L., Chen, H., Dou, Q., Qin, J., & Heng, P.-A. (2017) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2642839 · Cited by 1,140 · cited 1×
“Yu et al. [15] proposed deep CNNs for melanoma classification.”
PH2 - A dermoscopic image database for research and benchmarking
Mendonca, T., Ferreira, P. M., Marques, J. S., Marcal, A. R. S., & Rozeira, J. (2013) · 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2013.6610779 · Cited by 1,009 · cited 5×
“Edinburgh Research and Innovation (Dermofit) [33] and the Dermatology Service of Hospital Pedro Hispano (PH2) [34] data sets.”
InfluentialWhale optimization approaches for wrapper feature selection
Mafarja, M., & Mirjalili, S. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2017.11.006 · Cited by 825 · cited 1×
“Three enhanced Whale Optimization Algorithms (WOA) were proposed in [14] for feature selection, which incorporated WOA with tournament, roulette wheel selection and crossover and mutation operators, respectively.”
Domhan, T., Springenberg, J. T., & Hutter, F. (2015) · FreiDok plus (Universitätsbibliothek Freiburg) · Cited by 670
Deep learning ensembles for melanoma recognition in dermoscopy images
Codella, N. C. F., Nguyen, Q.-B., Pankanti, S., Gutman, D. A., Helba, B., Halpern, A. C., & Smith, J. R. (2017) · IBM Journal of Research and Development · doi:10.1147/jrd.2017.2708299 · Cited by 644 · cited 1×
“Codella et al. [17] proposed ensembles of deep learning models for melanoma detection.”
Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network
Li, Y., & Shen, L. (2018) · Sensors · doi:10.3390/s18020556 · Cited by 634 · cited 1×
“Bozorgtabar et al. [20] proposed deep networks guided by local unsupervised learning for lesion segmentation, while Li and Shen [21] developed a comprehensive deep architecture consisting of the Lesion Indexing Network (LIN) and the Lesion Feature Network (LFN) for skin lesion classification.”
Xue, B., Zhang, M., & Browne, W. N. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2013.09.018 · Cited by 614
All-IDB: The acute lymphoblastic leukemia image database for image processing
Labati, R. D., Piuri, V., & Scotti, F. (2011) · 2011 18th IEEE International Conference on Image Processing · doi:10.1109/icip.2011.6115881 · Cited by 514
Two Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Color Features
Barata, C., Ruela, M., Francisco, M., Mendonca, T., & Marques, J. S. (2014) · IEEE Systems Journal · doi:10.1109/jsyst.2013.2271540 · Cited by 453 · cited 1×
“Barata et al. [16] proposed global and local methods for melanoma classification, and indicated the efficiency of colour features over texture features for melanoma identification.”
Recent Advances in Artificial Immune Systems: Models and Applications
Dasgupta, D., Yu, S., & Nino, F. (2011) · Applied Soft Computing · doi:10.1016/j.asoc.2010.08.024 · Cited by 396
A Micro-GA Embedded PSO Feature Selection Approach to Intelligent Facial Emotion Recognition
Mistry, K., Zhang, L., Neoh, S. C., Lim, C. P., & Fielding, B. (2017) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2549639 · Cited by 354 · cited 5×
“…incorporated with a micro-GA concept was proposed for horizontal and vertical LBP-based texture feature selection for facial expression recognition [12], whereas a threshold-based PSO model (ThBPSO) was developed in [13] for pose and illumination invariant facial feature selection in face…”
InfluentialSelf-citationDermoscopic Image Segmentation via Multistage Fully Convolutional Networks
Bi, L., Kim, J., Ahn, E., Kumar, A., Fulham, M., & Feng, D. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2017.2712771 · Cited by 338 · cited 1×
“[48] Multistage Fully Convolutional Networks 3 N/A 0.”
Ballerini, L., Fisher, R. B., Aldridge, B., & Rees, J. (2013) · Lecture Notes in Computational Vision and Biomechanics · doi:10.1007/978-94-007-5389-1_4 · Cited by 273 · cited 1×
“The proposed research is evaluated using two skin lesion data sets, i.e. Edinburgh Research and Innovation (Dermofit) [33] and the Dermatology Service of Hospital Pedro Hispano (PH2) [34] (BBPSO), Cultural Algorithm (CA), ThBPSO [13], Genetic PSO (GPSO) [35], MPSO [4], GMPSO [10], F-BPSO [36],…”
Enhanced leader PSO (ELPSO): A new PSO variant for solving global optimisation problems
Jordehi, A. R. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2014.10.026 · Cited by 263
Chaotic maps based on binary particle swarm optimization for feature selection
Chuang, L.-Y., Yang, C.-H., & Li, J.-C. (2011) · Applied Soft Computing · doi:10.1016/j.asoc.2009.11.014 · Cited by 232 · cited 1×
“Chuang et al. [9] proposed a chaotic binary PSO (BPSO) model for feature selection.”
A dynamic neighborhood learning based particle swarm optimizer for global numerical optimization
Nasir, M., Das, S., Maity, D., Sengupta, S., Halder, U., & Suganthan, P. N. (2012) · Information Sciences · doi:10.1016/j.ins.2012.04.028 · Cited by 222 · cited 1×
“…(CA), ThBPSO [13], Genetic PSO (GPSO) [35], MPSO [4], GMPSO [10], F-BPSO [36], FS-BPSO [36], Enhanced Leader PSO (ELPSO) [37], PSO with multiple subpopulations (MFOPSO) [38], Autonomous Particles Groups for PSO (AGPSO) [39], Dynamic Neighbourhood Learning PSO (DNLPSO) [40], and BBPSOV [11].”
Improving Dermoscopy Image Classification Using Color Constancy
Fidalgo Barata, A., Celebi, E., & Marques, J. (2014) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2014.2336473 · Cited by 214 · cited 2×
“[44] Colour Constancy + Bag-ofFeatures + K-means + SVM 3 10-fold 0.”
Skin lesion image segmentation using Delaunay Triangulation for melanoma detection
Pennisi, A., Bloisi, D. D., Nardi, D., Giampetruzzi, A. R., Mondino, C., & Facchiano, A. (2016) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2016.05.002 · Cited by 205 · cited 1×
“[50] Artefact Removal + Skin Detection + Lesion Segmentation & Binary Mask + AdaBoost 3 N/A 0.”
Autonomous Particles Groups for Particle Swarm Optimization
Mirjalili, S., Lewis, A., & Sadiq, A. S. (2014) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-014-1156-x · Cited by 184 · cited 1×
“…(CA), ThBPSO [13], Genetic PSO (GPSO) [35], MPSO [4], GMPSO [10], F-BPSO [36], FS-BPSO [36], Enhanced Leader PSO (ELPSO) [37], PSO with multiple subpopulations (MFOPSO) [38], Autonomous Particles Groups for PSO (AGPSO) [39], Dynamic Neighbourhood Learning PSO (DNLPSO) [40], and BBPSOV [11].”
Issa, M., Hassanien, A. E., Oliva, D., Helmi, A., Ziedan, I., & Alzohairy, A. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.01.019 · Cited by 165 · cited 1×
“Issa et al. [5] proposed a hybrid optimization method, known as ASCA-PSO, which integrated an enhanced sine cosine optimization algorithm (SCA) with the PSO model.”
Improved particle swarm optimization algorithm and its application in text feature selection
Lu, Y., Liang, M., Ye, Z., & Cao, L. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.07.005 · Cited by 154 · cited 1×
“Lu et al. [8] proposed six PSO models for feature selection in text categorization, including PSO with (1) fixed inertia weight, (2) liner decreasing inertia weight, (3) fixed constriction factor, (4) adaptive constriction factor, (5) synchronous inertia weight and constriction factor, and (6)…”
An Intelligent Decision Support System for Leukaemia Diagnosis using Microscopic Blood Images
Neoh, S. C., Srisukkham, W., Zhang, L., Todryk, S. M., Greystoke, B., Lim, C. P., Hossain, M. A., & Aslam, N. (2015) · Scientific Reports · doi:10.1038/srep14938 · Cited by 143 · cited 2×
“acute lymphoblastic leukaemia) and 60 negative samples [52, 53].”
Self-citationPatwal, R. S., Narang, N., & Garg, H. (2017) · Energy · doi:10.1016/j.energy.2017.10.052 · Cited by 139 · cited 1×
“Patwal et al. [6] developed another modified PSO model, namely time varying acceleration coefficient PSO with mutation strategies (TVAC-PSOMS).”
Intelligent leukaemia diagnosis with bare-bones PSO based feature optimization
Srisukkham, W., Zhang, L., Neoh, S. C., Todryk, S. M., & Lim, C. P. (2017) · Applied Soft Computing · doi:10.1016/j.asoc.2017.03.024 · Cited by 132 · cited 6×
“The experimental settings in our study are also in agreement with the recommended settings reported in other related studies for discriminative feature selection [10, 11, 12, 28].”
InfluentialSelf-citationA System for the Detection of Pigment Network in Dermoscopy Images Using Directional Filters
Barata, C., Marques, J. S., & Rozeira, J. (2012) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2012.2209423 · Cited by 126 · cited 2×
“[51] Lesion or Pigment Ratio + Boosting Algorithm 3 10-fold 0.”
Adaptive melanoma diagnosis using evolving clustering, ensemble and deep neural networks
Tan, T. Y., Zhang, L., & Lim, C. P. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.06.015 · Cited by 122 · cited 1×
“Both factors require the search of the corresponding strength space to find an optimal value [29-32].”
Self-citationEvolving Ensemble Models for Image Segmentation Using Enhanced Particle Swarm Optimization
Tan, T. Y., Zhang, L., Lim, C. P., Fielding, B., Yu, Y., & Anderson, E. (2019) · IEEE Access · doi:10.1109/access.2019.2903015 · Cited by 121 · cited 1×
“Both factors require the search of the corresponding strength space to find an optimal value [29-32].”
Self-citationA region-based image caption generator with refined descriptions
Kinghorn, P., Zhang, L., & Shao, L. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.07.014 · Cited by 119 · cited 1×
“Optimization of the deep network structures [55-57] will also be explored to further evaluate efficiency of the resulting models.”
Self-citationFace recognition using transform domain feature extraction and PSO-based feature selection
Krisshna, N. L. A., Deepak, V. K., Manikantan, K., & Ramachandran, S. (2014) · Applied Soft Computing · doi:10.1016/j.asoc.2014.05.007 · Cited by 109 · cited 2×
“…with a micro-GA concept was proposed for horizontal and vertical LBP-based texture feature selection for facial expression recognition [12], whereas a threshold-based PSO model (ThBPSO) was developed in [13] for pose and illumination invariant facial feature selection in face recognition.”
An efficient machine learning approach for the detection of melanoma using dermoscopic images
Waheed, Z., Waheed, A., Zafar, M., & Riaz, F. (2017) · International Conference on Communication, Computing and Digital Systems (C-CODE) · doi:10.1109/c-code.2017.7918949 · Cited by 108 · cited 1×
“[46] Colour (HSV)+ Gray-Level Cooccurrence Matrix + SVM 3 3-fold 0.”
Particle swarm optimization-based feature selection in sentiment classification
Shang, L., Zhou, Z., & Liu, X. (2016) · Soft Computing · doi:10.1007/s00500-016-2093-2 · Cited by 102 · cited 2×
“…Pedro Hispano (PH2) [34] (BBPSO), Cultural Algorithm (CA), ThBPSO [13], Genetic PSO (GPSO) [35], MPSO [4], GMPSO [10], F-BPSO [36], FS-BPSO [36], Enhanced Leader PSO (ELPSO) [37], PSO with multiple subpopulations (MFOPSO) [38], Autonomous Particles Groups for PSO (AGPSO) [39], Dynamic…”
Celebi, M. E., & Schaefer, G. (2012) · Lecture notes in computational vision and biomechanics · doi:10.1007/978-94-007-5389-1 · Cited by 92
Evolving Image Classification Architectures With Enhanced Particle Swarm Optimisation
Fielding, B., & Zhang, L. (2018) · IEEE Access · doi:10.1109/access.2018.2880416 · Cited by 85 · cited 1×
“Optimization of the deep network structures [55-57] will also be explored to further evaluate efficiency of the resulting models.”
Self-citationSaez, A., Sanchez-Monedero, J., Gutierrez, P. A., & Hervas-Martinez, C. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2015.2506270 · Cited by 83 · cited 2×
“Sáez et al. [3] conducted thickness classification for melanoma lesions.”
Chang, W. (2015) · Applied Soft Computing · doi:10.1016/j.asoc.2015.04.002 · Cited by 75 · cited 1×
“…(CA), ThBPSO [13], Genetic PSO (GPSO) [35], MPSO [4], GMPSO [10], F-BPSO [36], FS-BPSO [36], Enhanced Leader PSO (ELPSO) [37], PSO with multiple subpopulations (MFOPSO) [38], Autonomous Particles Groups for PSO (AGPSO) [39], Dynamic Neighbourhood Learning PSO (DNLPSO) [40], and BBPSOV [11].”
A hierarchical and regional deep learning architecture for image description generation
Kinghorn, P., Zhang, L., & Shao, L. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.09.013 · Cited by 69 · cited 1×
“Both factors require the search of the corresponding strength space to find an optimal value [29-32].”
Self-citationNayak, D. R., Dash, R., & Majhi, B. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.12.030 · Cited by 65 · cited 2×
“Nayak et al. [4] employed a modified PSO (MPSO) model to optimize the input weights and hidden biases of an Extreme Learning Machine (ELM) for pathological brain detection from MR images.”
Fusion of structural and textural features for melanoma recognition
Adjed, F., Gardezi, S. J. S., Ababsa, F., Faye, I., & Dass, S. C. (2017) · IET Computer Vision · doi:10.1049/iet-cvi.2017.0193 · Cited by 65 · cited 1×
“Moreover, Adjed et al. [2] employed the fusion of structural features and textual features for melanoma classification.”
Zhang, Y., Zhang, L., Neoh, S. C., Mistry, K., & Hossain, M. A. (2015) · Expert Systems with Applications · doi:10.1016/j.eswa.2015.07.022 · Cited by 59 · cited 5×
“…Dermatology Service of Hospital Pedro Hispano (PH2) [34] (BBPSO), Cultural Algorithm (CA), ThBPSO [13], Genetic PSO (GPSO) [35], MPSO [4], GMPSO [10], F-BPSO [36], FS-BPSO [36], Enhanced Leader PSO (ELPSO) [37], PSO with multiple subpopulations (MFOPSO) [38], Autonomous Particles Groups for PSO…”
InfluentialSelf-citationSkin lesion segmentation using deep convolution networks guided by local unsupervised learning
Bozorgtabar, B., Sedai, S., Roy, P. K., & Garnavi, R. (2017) · IBM Journal of Research and Development · doi:10.1147/jrd.2017.2708283 · Cited by 55 · cited 1×
“Bozorgtabar et al. [20] proposed deep networks guided by local unsupervised learning for lesion segmentation, while Li and Shen [21] developed a comprehensive deep architecture consisting of the Lesion Indexing Network (LIN) and the Lesion Feature Network (LFN) for skin lesion classification.”
Classifier ensemble reduction using a modified firefly algorithm: An empirical evaluation
Zhang, L., Srisukkham, W., Neoh, S. C., Lim, C. P., & Pandit, D. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.10.001 · Cited by 55 · cited 3×
“Ensemble classifiers are able to yield more reliable results in comparison with those of single classifiers [28].”
Self-citationAn intelligent decision support system for skin cancer detection from dermoscopic images
Tan, T. Y., Zhang, L., & Jiang, M. X. (2016) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/fskd.2016.7603521 · Cited by 54 · cited 5×
“For the sub-dimension based search for subsection 1, the PSO operation defined in Equations (1)-(2) is applied to sub-dimensions [1, 108] with the remaining two subsections comprising dimensions [109, 216] and [217, 324] fixed.”
InfluentialSelf-citationMelanoma recognition using extended set of descriptors and classifiers
Kruk, M., Świderski, B., Osowski, S., Kurek, J., Słowińska, M., & Walecka, I. (2015) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-015-0099-9 · Cited by 46 · cited 1×
“The final classification results were obtained by averaging the outputs of all SVMs. Kruk et al. [18] proposed a skin cancer detection system, which consisted of image filtering, comprehensive ABCD feature extraction, feature selection, and non-melanoma/melanoma classification.”
On the role of texture and color in the classification of dermoscopy images
Marques, J. S., Barata, C., & Mendonça, T. (2012) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2012.6346942 · Cited by 42 · cited 2×
“Although the deep CNN model employs a lower image resolution (200×200), a small experimental set-up and a lower training ratio, its performance is comparable to those of related studies using higher image resolutions [2, 44, 45, 47, 51].”
Partial order label decomposition approaches for melanoma diagnosis
Sánchez‐Monedero, J., Pérez‐Ortiz, M., Sáez, A., Gutiérrez, P. A., & Hervás‐Martínez, C. (2017) · Applied Soft Computing · doi:10.1016/j.asoc.2017.11.042 · Cited by 22 · cited 1×
“Sánchez-Monedero et al. [19] conducted not only melanoma classification but also the identification of different stages of lesions.”
Improving a bag of words approach for skin cancer detection in dermoscopic images
Alfed, N., Khelifi, F., & Bouridane, A. (2016) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit.2016.7593529 · Cited by 15 · cited 2×
“[45] Colour Histograms + Colour Moments + HOG + Codebook Generation + SVM/AdaBoost 3 5-fold 0.”
Detection of Pigment Networks in Dermoscopy Images
Eltayef, K., Li, Y., & Liu, X. (2017) · Journal of Physics Conference Series · doi:10.1088/1742-6596/787/1/012033 · Cited by 10
Cited by
Kourou, K., Exarchos, K. P., Papaloukas, C., Sakaloglou, P., Exarchos, T., & Fotiadis, D. I. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.10.006 · Cited by 165
“DL frameworks were also designed and developed in [50–54] based on the CNN architecture for the analysis of CT and dermoscopy images in liver and skin cancer, respectively.”
MethodMelarkode, N., Srinivasan, K., Qaisar, S. M., & Plawiak, P. (2023) · Cancers · doi:10.3390/cancers15041183 · Cited by 144
Metadata
- Authors
- Tan, T. Y., Zhang, L., & Lim, C. P.
- Venue
- Applied Soft Computing
- Publisher
- Elsevier BV
- Published
- 2019-11
- Volume
- 84
- Pages
- 105725
- ISSN
- 1568-4946 (ISSN-L)
- OpenAlex
- W2969546126
- Cited by
- 159
- References
- 53
- FWCI
- 6.71
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.