CR‐SSL: A closely related self‐supervised learning based approach for improving breast ultrasound tumor segmentation

Abstract

Breast ultrasound (BUS) tumor segmentation can help with the early detection of breast cancer; however, the lack of human-labeled training data is a big problem in this area. To deal with this, we propose a novel self-supervised learning approach (CR-SSL), where several related pretext tasks like unsupervised segmentation and edge detection are firstly learned, followed by the target tumor segmentation based fine-tuning. Learning such related pretext tasks ensures better representation learning. Experimental study shows that CR-SSL can improve the mean Dice and Jaccard scores by more than 4-5%, with ≥0.6 scores while having access to only 20-50 human-labeled training samples. The best Dice scores of 0.7303 and 0.8207, and Jaccard scores of 0.7082 and 0.8015 are obtained by CR-SSL on the test datasets. Compared with the No-SSL baseline, CR-SSL can achieve (10-20)% improvements in segmentation quality while working in small-sized training dataset scenarios, suggesting its high potential practical utility.

Is despeckling necessary for deep learning based ultrasound image segmentation?

“…Self-supervised methods pretrain through pretext tasks [82] or contrast learning [83], and then the pretrained weights are fine-tuned for downstream tasks with limited labeled data.…”

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

“…Self-supervised methods pretrain through pretext tasks [78] or contrast learning [79], and then the pretrained weights are fine-tuned for downstream tasks with limited labeled data.…”

Diabetic Foot Ulcer Identification: A Review

“…Foot ulcers are the most common reason diabetic people are admitted to hospitals. The comprehensive evaluation and risk assessment of a diabetic individual’s feet necessitate a multidisciplinary foot care team [ 10 , 11 , 12 , 13 , 14 ]. Treatment must involve a patient’s medical records, lab test results, and assessments of their subcutaneous, nervous system, cardiovascular, musculoskeletal, rheumatological, and vascular states.…”

“…Foot ulcers are the most common reason diabetic people are admitted to hospitals. The comprehensive evaluation and risk assessment of a diabetic individual's feet necessitate a multidisciplinary foot care team [10][11][12][13][14]. Treatment must involve a patient's medical records, lab Diabetic foot ulcers (DFUs) are a common consequence of poorly treated diabetes that can harm the feet, right down to the bones.…”