Please use this identifier to cite or link to this item:
http://hdl.handle.net/11375/28413
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | LOKKER, CYNTHIA | - |
dc.contributor.author | GONZALEZ, RICARDO | - |
dc.date.accessioned | 2023-03-30T14:55:27Z | - |
dc.date.available | 2023-03-30T14:55:27Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://hdl.handle.net/11375/28413 | - |
dc.description.abstract | Background: Numerous machine learning (ML) models have been developed for breast cancer using various types of data (e.g., images, text). Successful external validation (EV) of ML models is considered as important evidence of their generalizability. Objectives: Assess the performance of externally validated ML models based on histopathology images for diagnosis, classification, prognosis, or treatment outcome prediction in female breast cancer. Methods: A systematic search of MEDLINE, EMBASE, CINAHL, IEEE, MICCAI, and SPIE conferences was performed for studies published between January 2010 and February 2022. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was employed, and the results were narratively described. Results: Of the 2339 retrieved citations, eight journal articles and two conference proceedings met inclusion criteria. Three studies externally validated ML models for diagnosis, four for classification, two for prognosis, and one for both classification and prognosis. Most studies used Convolutional Neural Networks and one used logistic regression algorithms. For diagnostic/classification models, the most common performance metrics reported in the EV were accuracy and area under the curve, which were above 87% and 90%, respectively, using pathologists' annotations/diagnoses as ground truth. The hazard ratios in the EV of prognostic ML models were between 1.7 (95% CI, 1.2–2.6) and 1.8 (95% CI, 1.3–2.7) to predict distant disease‑free survival; 1.91 (95% CI, 1.11-3.29) for recurrence, and between 0.09 (95% CI, 0.01–0.70) and 0.65 (95% CI, 0.43–0.98) for overall survival, using clinical data as ground truth. Conclusion: Despite EV being an important step before the clinical application of a ML model, it hasn't been performed routinely. The large variability in the training/validation datasets, methods, performance metrics, and reported information limited the comparison of the models and the analysis of their results. Increasing the availability of validation datasets and implementing standardized methods and reporting protocols may facilitate future analyses. | en_US |
dc.language.iso | en | en_US |
dc.subject | Machine learning | en_US |
dc.subject | Histopathology | en_US |
dc.subject | Breast cancer | en_US |
dc.subject | Diagnosis | en_US |
dc.subject | Prognosis | en_US |
dc.subject | Treatment outcome prediction | en_US |
dc.subject | External validation | en_US |
dc.subject | Artificial intelligence | en_US |
dc.subject | Computer vision | en_US |
dc.title | PERFORMANCE OF EXTERNALLY VALIDATED MACHINE LEARNING MODELS BASED ON HISTOPATHOLOGY IMAGES FOR THE DIAGNOSIS, CLASSIFICATION, PROGNOSIS, OR TREATMENT OUTCOME PREDICTION IN FEMALE BREAST CANCER: A SYSTEMATIC REVIEW | en_US |
dc.type | Thesis | en_US |
dc.contributor.department | eHealth | en_US |
dc.description.degreetype | Thesis | en_US |
dc.description.degree | Master of Science (MSc) | en_US |
dc.description.layabstract | Breast cancer is the most frequently diagnosed cancer and the leading cause of cancer deaths in women. Microscopic analysis of tissues taken from the breast is the standard method for diagnosis. Using digital images of these tissues, researchers have been training computer software to identify and classify breast cancer and to predict future behavior and response to treatments. These computer algorithms are called “machine learning models.” It is important to test how well machine learning models perform with new images—ones that were not used during the development of the models and differ from the development data in some aspect such that they can be considered independent from the development data and process (external data). This systematic review looks at the performance of machine learning models that used microscopic pictures of breast cancer and were tested with external data. | en_US |
Appears in Collections: | Open Access Dissertations and Theses |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Gonzalez_Ricardo_202303_MSc.docx | 601.16 kB | Microsoft Word XML | View/Open |
Items in MacSphere are protected by copyright, with all rights reserved, unless otherwise indicated.