Deep Learning-based Dot and Globule Segmentation with Pixel and Blob-based Metrics for Evaluation -- Data
Deep learning (DL) applied to whole dermoscopic images has shown unprecedented accuracy in differentiating images of melanoma from benign lesions. We hypothesize that accuracy in whole-image deep learning suffers because whole lesion analysis lacks evaluation of dermoscopic structures. DL also suffers a “black box” characterization because it offers only probabilities to the physician and no visible structures. We propose the detection of structures called globules and dots as a means to improve precision in melanoma detection. We compare two encoder-decoder architectures to detect globule and dots: UNET vs. UNET++. For each of these architectures, we compare three pipelines: with test time augmentation (TTA), without TTA, and without TTA but with checkpoint ensembles. We use an SE-RESNEXT encoder and a symmetric decoder. The pixel-based F-1 scores for globule and dot detection based on UNET++ and UNET techniques with checkpoint ensembles were found to be 0.632 and 0.628, respectively. The blob-based UNET++ and UNET F-1 (50 percent intersection) scores were 0.696 and 0.685, respectively. This agreement score is over twice the statistical correlation score measured among specialists. We propose UNET++ globule and dot detection as a technique that offers two potential advantages: increased diagnostic accuracy and visible structure detection to better explain DL results. We present a public globule and dot database to aid progress in automatic detection of these structures.
The datasets contain the three zip files with the following descriptions,
"images.zip" : jpeg images of the ISIC19 images for which globule masks were created
"globule masks-exact.zip" : pixel exact globule masks
"globule masks-dilatedEllipseKernel3.zip" : exact globule masks dilated using an ellipse morphological kernel with dimensions 3x3 (Used in the paper).
You may wish to download and view individual files.
Nambisan, Ananad K.; Lama, Norsang; Hagerty, Jason; Smith, Colin; Rajeh, Ahmad; Phan, Thanh; Swinfard, Samantha; and Stanley, R. Joe, "Deep Learning-based Dot and Globule Segmentation with Pixel and Blob-based Metrics for Evaluation -- Data" (2022). Research Data. 10.
Electrical and Computer Engineering
Keywords and Phrases
Machine Learning; Deep Learning; Data processing; Melanoma; Globules; Feature Segmentation
© 2022 Missouri University of Science and Technology, All rights reserved.