Multi-task learning for segmentation and classification of tumors in 3D automated breast ultrasound images

Zhou, Yue; Chen, Houjin; Li, Yanfeng; Liu, Qin; Xu, Xuanang; Wang, Shu; Yap, Pew Thian; Shen, Dinggang

doi:10.1016/j.media.2020.101918

Cited by 175 publications

(76 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may be probably explained considering that the classification loss of our Mask-R 2 CNN had a regularization effect during training. This is in line with current considerations in the literature about multi-task learning [13,18].…”

Section: Discussionsupporting

confidence: 90%

Mask-R$$^{2}$$CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images

2021

View full text Add to dashboard Cite

Background and objectives Fetal head-circumference (HC) measurement from ultrasound (US) images provides useful hints for assessing fetal growth. Such measurement is performed manually during the actual clinical practice, posing issues relevant to intra- and inter-clinician variability. This work presents a fully automatic, deep-learning-based approach to HC delineation, which we named Mask-R$$^{2}$$ 2 CNN. It advances our previous work in the field and performs HC distance-field regression in an end-to-end fashion, without requiring a priori HC localization nor any postprocessing for outlier removal. Methods Mask-R$$^{2}$$ 2 CNN follows the Mask-RCNN architecture, with a backbone inspired by feature-pyramid networks, a region-proposal network and the ROI align. The Mask-RCNN segmentation head is here modified to regress the HC distance field. Results Mask-R$$^{2}$$ 2 CNN was tested on the HC18 Challenge dataset, which consists of 999 training and 335 testing images. With a comprehensive ablation study, we showed that Mask-R$$^{2}$$ 2 CNN achieved a mean absolute difference of 1.95 mm (standard deviation $$=\pm 1.92$$ = ± 1.92 mm), outperforming other approaches in the literature. Conclusions With this work, we proposed an end-to-end model for HC distance-field regression. With our experimental results, we showed that Mask-R$$^{2}$$ 2 CNN may be an effective support for clinicians for assessing fetal growth.

show abstract

Section: Discussionsupporting

confidence: 90%

Mask-R$$^{2}$$CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images

2021

View full text Add to dashboard Cite

show abstract

“…In fact, in our research, we found a big difference when comparing the total number of parameters for each single-task and the number of parameters for multiple tasks. In addition, multiple tasks can improve the accuracy of other classi cations by learning the characteristics common to each task [13,21]. However, in our results, the classi cation performance of multi-task models decreased after three tasks.…”

Section: Discussionmentioning

confidence: 85%

A Deep Learning-based Positioning Classification of the Mandibular Third Molars: Is Multi-task Deep Learning Useful?

Sukegawa

Matsuyama

Tanaka

et al. 2021

Preprint

View full text Add to dashboard Cite

Pell and Gregory, and Winter’s classifications are frequently implemented to classify the mandibular third molars and are crucial for safe tooth extraction. This study aimed to evaluate the classification accuracy of convolutional neural network (CNN) deep learning models using cropped panoramic radiographs based on these classifications. We compared the diagnostic accuracy of single-task and multi-task learning after labeling 1,330 images of mandibular third molars from digital radiographs taken at the Department of Oral and Maxillofacial Surgery at a general hospital (2014-2021). The mandibular third molar classifications were analyzed using a VGG 16 model of a CNN. We statistically evaluated performance metrics (accuracy, precision, recall, F1 score, area under the curve [AUC]) for each prediction. We found that single-task learning was superior to multi-task learning (all p<0.05) for all metrics, with large effect sizes and low p-values. Recall and F1 scores for position classification showed medium effect sizes in single and multi-task learning. To our knowledge, this deep learning study is the first to examine single-task and multi-task learning for the classification of mandibular third molars. Our results demonstrated the efficacy of implementing Pell and Gregory, and Winter’s classifications for specific respective tasks.

show abstract

“…However, due to the dataset's limitation, the model's capacity to identify melanoma lesions was restricted, and the proposed method does not provide further insight into the prognosis of melanoma lesions that have received attention in recent studies [ 69 , 70 ]. Recently, the novel techniques for jointing multisegmentation of multiscale feature extraction have been proposed [ 71 , 72 ]. In the future studies, the new technique can be combined to enhance the model's capacity to aware boundary for melanoma lesions and add temporal image data to investigate the model for the prediction of melanoma lesions' prognosis.…”

Section: Discussionmentioning

confidence: 99%

Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion

Yang

Ren

Huang

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Melanoma is a type of skin cancer that often leads to poor prognostic responses and survival rates. Melanoma usually develops in the limbs, including in fingers, palms, and the margins of the nails. When melanoma is detected early, surgical treatment may achieve a higher cure rate. The early diagnosis of melanoma depends on the manual segmentation of suspected lesions. However, manual segmentation can lead to problems, including misclassification and low efficiency. Therefore, it is essential to devise a method for automatic image segmentation that overcomes the aforementioned issues. In this study, an improved algorithm is proposed, termed EfficientUNet++, which is developed from the U-Net model. In EfficientUNet++, the pretrained EfficientNet model is added to the UNet++ model to accelerate segmentation process, leading to more reliable and precise results in skin cancer image segmentation. Two skin lesion datasets were used to compare the performance of the proposed EfficientUNet++ algorithm with other common models. In the PH2 dataset, EfficientUNet++ achieved a better Dice coefficient (93% vs. 76%–91%), Intersection over Union (IoU, 96% vs. 74%–95%), and loss value (30% vs. 44%–32%) compared with other models. In the International Skin Imaging Collaboration dataset, EfficientUNet++ obtained a similar Dice coefficient (96% vs. 94%–96%) but a better IoU (94% vs. 89%–93%) and loss value (11% vs. 13%–11%) than other models. In conclusion, the EfficientUNet++ model efficiently detects skin lesions by improving composite coefficients and structurally expanding the size of the convolution network. Moreover, the use of residual units deepens the network to further improve performance.

show abstract

Multi-task learning for segmentation and classification of tumors in 3D automated breast ultrasound images

Cited by 175 publications

References 27 publications

Mask-R$$^{2}$$CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images

Mask-R$$^{2}$$CNN: a distance-field regression version of Mask-RCNN for fetal-head delineation in ultrasound images

A Deep Learning-based Positioning Classification of the Mandibular Third Molars: Is Multi-task Deep Learning Useful?

Deep Hybrid Convolutional Neural Network for Segmentation of Melanoma Skin Lesion

Contact Info

Product

Resources

About