Coarse-to-fine multi-task training of convolutional neural networks for automated information extraction from cancer pathology reports
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Information extraction and coding of free-text pathology reports is an important activity for cancer registries to support national cancer surveillance. Cancer registrars must process high volumes of pathology reports on an annual basis. In this study, we investigated an automated approach using a coarse-to-fine training of convolutional neural networks (CNNs) for extracting the primary site, histological grade and laterality from unstructured cancer pathology text reports. Our proposed training scheme consists of two stages. In the first stage, the multi-task learning (MTL) with hard parameter sharing approach is used to train a multi-task MT-CNN model for all the tasks. Then, the TM-CNN model parameters are used to initialize a CNN model for each task to be fine trained individually using its corresponding dataset. The performance of our proposed approach was compared against a state-of-the-art CNN and the commonly used SVM classifier. We observed that the proposed model consistently outperformed the base line models, especially for the less prevalent classes. Specifically, the proposed training approach achieved a micro-F score of 0.7749 over 12 ICD-O-3 topography codes which is a significant improvement as compared with state-of-the-art CNN (0.7101) and the SVM (0.6019) classifiers. Also, the results demonstrate the potential of the proposed method for handling class imbalance within each task. It significantly improves macro-F score by 24% and 12% of the primary site and histology grade tasks, respectively.
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
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Savova, G. K., Kipper-Schuler, K. C., Hurdle, J. F., & Meystre, S. M. (2008) · Yearbook of Medical Informatics · doi:10.1055/s-0038-1638592 · Cited by 895 · cited 1×
“With the large volumes of pathology reports generated on an annual basis, manual annotation is costly, error-prone, and not easily scalable [1].”
Background
Cited by
Savova, G. K., Danciu, I., Alamudun, F., Miller, T., Lin, C., Bitterman, D. S., Tourassi, G., & Warner, J. L. (2019) · Cancer Research · doi:10.1158/0008-5472.can-19-0579 · Cited by 170
Self-citationZhou, S., Wang, N., Wang, L., Liu, H., & Zhang, R. (2022) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocac040 · Cited by 119
“The original BERT-large model was pretrained on Wikipedia and BookCorpus.15 The BioBERT model was pretrained on PubMed abstract and PMC full articles that contain about 18 billion words.16 BlueBERT model was pretrained on PubMed abstract and MIMICIII that contain about 4.5 billion words.17 The CharBERT was pretrained…”
InfluentialMitchell, J. R., Szepietowski, P., Howard, R., Reisman, P., Jones, J. D., Lewis, P., Fridley, B. L., & Rollison, D. E. (2022) · Journal of Medical Internet Research · doi:10.2196/27210 · Cited by 45
“There has been considerable prior work using NLP methods to predict ICD-O codes from pathology reports [11,12,16,67].”
BackgroundMethod
Metadata
- Authors
- Alawad, M., Yoon, H.-J., & Tourassi, G. D.
- Venue
- 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)
- Publisher
- IEEE
- Published
- 2018-03
- Pages
- 218-221
- OpenAlex
- W2797227230
- Cited by
- 26
- References
- 2
- FWCI
- 1.35
- Type
- conference paper
- 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.