A quantitative analysis of the improvement provided by comprehensive annotation on CT lesion detection using deep learning.

Autor: Ma J; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA., Yoon JH; Department of Radiology, Columbia University Irving Medical Center, New York, New York, USA., Lu L; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA., Yang H; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA., Guo P; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA., Yang D; Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China., Li J; Department of Radiology, Beijing Friendship Hospital, Capital Medical University, Beijing, China., Shen J; Medical Imaging Department, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Guangzhou, China., Schwartz LH; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA., Zhao B; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
Jazyk: angličtina
Zdroj: Journal of applied clinical medical physics [J Appl Clin Med Phys] 2024 Sep; Vol. 25 (9), pp. e14434. Date of Electronic Publication: 2024 Jul 30.
DOI: 10.1002/acm2.14434
Abstrakt: Background: Data collected from hospitals are usually partially annotated by radiologists due to time constraints. Developing and evaluating deep learning models on these data may result in over or under estimation PURPOSE: We aimed to quantitatively investigate how the percentage of annotated lesions in CT images will influence the performance of universal lesion detection (ULD) algorithms.
Methods: We trained a multi-view feature pyramid network with position-aware attention (MVP-Net) to perform ULD. Three versions of the DeepLesion dataset were created for training MVP-Net. Original DeepLesion Dataset (OriginalDL) is the publicly available, widely studied DeepLesion dataset that includes 32 735 lesions in 4427 patients which were partially labeled during routine clinical practice. Enriched DeepLesion Dataset (EnrichedDL) is an enhanced dataset that features fully labeled at one or more time points for 4145 patients with 34 317 lesions. UnionDL is the union of the OriginalDL and EnrichedDL with 54 510 labeled lesions in 4427 patients. Each dataset was used separately to train MVP-Net, resulting in the following models: OriginalCNN (replicating the original result), EnrichedCNN (testing the effect of increased annotation), and UnionCNN (featuring the greatest number of annotations).
Results: Although the reported mean sensitivity of OriginalCNN was 84.3% using the OriginalDL testing set, the performance fell sharply when tested on the EnrichedDL testing set, yielding mean sensitivities of 56.1%, 66.0%, and 67.8% for OriginalCNN, EnrichedCNN, and UnionCNN, respectively. We also found that increasing the percentage of annotated lesions in the training set increased sensitivity, but the margin of increase in performance gradually diminished according to the power law.
Conclusions: We expanded and improved the existing DeepLesion dataset by annotating additional 21 775 lesions, and we demonstrated that using fully labeled CT images avoided overestimation of MVP-Net's performance while increasing the algorithm's sensitivity, which may have a huge impact to the future CT lesion detection research. The annotated lesions are at https://github.com/ComputationalImageAnalysisLab/DeepLesionData.
(© 2024 The Author(s). Journal of Applied Clinical Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)
Databáze: MEDLINE
Externí odkaz: