Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net Variants
The identification of vascular network structures is one of the key fields of research in medical imaging. The segmentation of dorsal hand vein patterns form NIR images is not only the basis for reliable biometric identification, but would also provide a significant tool in assisting medical interve...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/15/2620 |
| _version_ | 1797441399607525376 |
|---|---|
| author | Szidónia Lefkovits Simina Emerich László Lefkovits |
| author_facet | Szidónia Lefkovits Simina Emerich László Lefkovits |
| author_sort | Szidónia Lefkovits |
| collection | DOAJ |
| description | The identification of vascular network structures is one of the key fields of research in medical imaging. The segmentation of dorsal hand vein patterns form NIR images is not only the basis for reliable biometric identification, but would also provide a significant tool in assisting medical intervention. Precise vein extraction would help medical workers to exactly determine the needle entry point to efficiently gain intravenous access for different clinical purposes, such as intravenous therapy, parenteral nutrition, blood analysis and so on. It would also eliminate repeated attempts at needle pricks and even facilitate an automatic injection procedure in the near future. In this paper, we present a combination of unsupervised and supervised dorsal hand vein segmentation from near-infrared images in the NCUT database. This method is convenient due to the lack of expert annotations of publicly available vein image databases. The novelty of our work is the automatic extraction of the veins in two phases. First, a geometrical approach identifies tubular structures corresponding to veins in the image. This step is considered gross segmentation and provides labels (Label I) for the second CNN-based segmentation phase. We visually observe that different CNNs obtain better segmentation on the test set. This is the reason for building an ensemble segmentor based on majority voting by nine different network architectures (U-Net, U-Net++ and U-Net3+, all trained with BCE, Dice and focal losses). The segmentation result of the ensemble is considered the second label (Label II). In our opinion, the new Label II is a better annotation of the NCUT database than the Label I obtained in the first step. The efficiency of computer vision algorithms based on artificial intelligence algorithms is determined by the quality and quantity of the labeled data used. Furthermore, we prove this statement by training ResNet–UNet in the same manner with the two different label sets. In our experiments, the Dice scores, sensitivity and specificity with ResNet–UNet trained on Label II are superior to the same classifier trained on Label I. The measured Dice scores of ResNet–UNet on the test set increase from 90.65% to 95.11%. It is worth mentioning that this article is one of very few in the domain of dorsal hand vein segmentation; moreover, it presents a general pipeline that may be applied for different medical image segmentation purposes. |
| first_indexed | 2024-03-09T12:23:27Z |
| format | Article |
| id | doaj.art-1eb05b4919e1400e9367d48e9a37e415 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T12:23:27Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-1eb05b4919e1400e9367d48e9a37e4152023-11-30T22:37:42ZengMDPI AGMathematics2227-73902022-07-011015262010.3390/math10152620Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net VariantsSzidónia Lefkovits0Simina Emerich1László Lefkovits2Department of Electrical Engineering and Information Technology, Faculty of Engineering and Information Technology, George Emil Palade University of Medicine, Pharmacy, Science, and Technology of Targu Mures, Gheorghe Marinescu Street 38, 540139 Târgu Mureș, RomaniaCommunications Department, Faculty of Electronics, Telecommunications and Information Technology, Technical University of Cluj-Napoca, Memorandumului 28, 400114 Cluj-Napoca, RomaniaComputational Intelligence Research Group, Departament of Electrical Engineering, Sapientia Hungarian University of Transylvania, Sos. Sighișoarei 1/C, 540485 Corunca, RomaniaThe identification of vascular network structures is one of the key fields of research in medical imaging. The segmentation of dorsal hand vein patterns form NIR images is not only the basis for reliable biometric identification, but would also provide a significant tool in assisting medical intervention. Precise vein extraction would help medical workers to exactly determine the needle entry point to efficiently gain intravenous access for different clinical purposes, such as intravenous therapy, parenteral nutrition, blood analysis and so on. It would also eliminate repeated attempts at needle pricks and even facilitate an automatic injection procedure in the near future. In this paper, we present a combination of unsupervised and supervised dorsal hand vein segmentation from near-infrared images in the NCUT database. This method is convenient due to the lack of expert annotations of publicly available vein image databases. The novelty of our work is the automatic extraction of the veins in two phases. First, a geometrical approach identifies tubular structures corresponding to veins in the image. This step is considered gross segmentation and provides labels (Label I) for the second CNN-based segmentation phase. We visually observe that different CNNs obtain better segmentation on the test set. This is the reason for building an ensemble segmentor based on majority voting by nine different network architectures (U-Net, U-Net++ and U-Net3+, all trained with BCE, Dice and focal losses). The segmentation result of the ensemble is considered the second label (Label II). In our opinion, the new Label II is a better annotation of the NCUT database than the Label I obtained in the first step. The efficiency of computer vision algorithms based on artificial intelligence algorithms is determined by the quality and quantity of the labeled data used. Furthermore, we prove this statement by training ResNet–UNet in the same manner with the two different label sets. In our experiments, the Dice scores, sensitivity and specificity with ResNet–UNet trained on Label II are superior to the same classifier trained on Label I. The measured Dice scores of ResNet–UNet on the test set increase from 90.65% to 95.11%. It is worth mentioning that this article is one of very few in the domain of dorsal hand vein segmentation; moreover, it presents a general pipeline that may be applied for different medical image segmentation purposes.https://www.mdpi.com/2227-7390/10/15/2620dorsal hand veinsegmentationtubular structure extractionResNet–UNetU-Net++U-Net3+ |
| spellingShingle | Szidónia Lefkovits Simina Emerich László Lefkovits Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net Variants Mathematics dorsal hand vein segmentation tubular structure extraction ResNet–UNet U-Net++ U-Net3+ |
| title | Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net Variants |
| title_full | Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net Variants |
| title_fullStr | Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net Variants |
| title_full_unstemmed | Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net Variants |
| title_short | Boosting Unsupervised Dorsal Hand Vein Segmentation with U-Net Variants |
| title_sort | boosting unsupervised dorsal hand vein segmentation with u net variants |
| topic | dorsal hand vein segmentation tubular structure extraction ResNet–UNet U-Net++ U-Net3+ |
| url | https://www.mdpi.com/2227-7390/10/15/2620 |
| work_keys_str_mv | AT szidonialefkovits boostingunsuperviseddorsalhandveinsegmentationwithunetvariants AT siminaemerich boostingunsuperviseddorsalhandveinsegmentationwithunetvariants AT laszlolefkovits boostingunsuperviseddorsalhandveinsegmentationwithunetvariants |