W-Net: Dense and diagnostic semantic segmentation of subcutaneous and breast tissue in ultrasound images by incorporating ultrasound RF waveform data.

We study the use of raw ultrasound waveforms, often referred to as the "Radio Frequency" (RF) data, for the semantic segmentation of ultrasound scans to carry out dense and diagnostic labeling. We present W-Net, a novel Convolution Neural Network (CNN) framework that employs the raw ultrasound waveforms in addition to the grey ultrasound image to semantically segment and label tissues for anatomical, pathological, or other diagnostic purposes. To the best of our knowledge, this is also the first deep-learning or CNN approach for segmentation that analyzes ultrasound raw RF data along with the grey image. We chose subcutaneous tissue (SubQ) segmentation as our initial clinical goal for dense segmentation since it has diverse intermixed tissues, is challenging to segment, and is an underrepresented research area. SubQ potential applications include plastic surgery, adipose stem-cell harvesting, lymphatic monitoring, and possibly detection/treatment of certain types of tumors. Unlike prior work, we seek to label every pixel in the image, without the use of a background class. A custom dataset consisting of hand-labeled images by an expert clinician and trainees are used for the experimentation, currently labeled into the following categories: skin, fat, fat fascia/stroma, muscle, and muscle fascia. We compared W-Net and attention variant of W-Net (AW-Net) with U-Net and Attention U-Net (AU-Net). Our novel W-Net's RF-Waveform encoding architecture outperformed regular U-Net and AU-Net, achieving the best mIoU accuracy (averaged across all tissue classes). We study the impact of RF data on dense labeling of the SubQ region, which is followed by the analyses of the generalization capability of the networks to patients and analysis on the SubQ tissue classes, determining that fascia tissues, especially muscle fascia in particular, are the most difficult anatomic class to recognize for both humans and AI algorithms. We present diagnostic semantic segmentation, which is semantic segmentation carried out for the purposes of direct diagnostic pixel labeling, and apply it to breast tumor detection task on a publicly available dataset to segment pixels into malignant tumor, benign tumor, and background tissue class. Using the segmented image we diagnose the patient by classifying the breast lesion as either benign or malignant. We demonstrate the diagnostic capability of RF data with the use of W-Net, which achieves the best segmentation scores across all classes.

Real-Time Ultrasound-Assisted Gluteal Fat Grafting.

BACKGROUND: The number of gluteal fat augmentation procedures has increased recently and so has the number of complications. Because of the increased risk of morbidity and mortality when fat is injected intramuscularly, not knowing where fat is injected is concerning. We sought to identify the planes in which fat is injected during the procedure. METHODS: We selected 15 consecutive female patients who desired gluteal fat augmentation. All patients had epidural anesthesia and the gluteal region was infiltrated with a vasoconstrictive solution. With the patient in prone position, an ultrasound probe placed on the buttocks was used to identify the fascial layers. While decanted fat was being injected with a blunt cannula, the images were projected wirelessly to a screen, so that the surgeon and assistant could follow the planes in which the cannula was being introduced and the fat injected. RESULTS: The mean volume of harvested fat was 3533 ml and the mean volume of fat injected per gluteal region was 528 ml. The evaluation of the depth and location of the cannula was performed in real time with the ultrasound, accurately and reliably identifying the planes of fat injection. All injections were subcutaneous. The downsides of this technique were the purchase cost of the ultrasound device, increased surgical time, the need for an assistant to follow the cannula and the probe constantly, and the learning curve. CONCLUSION: Real-time ultrasound-assisted gluteal fat grafting is reliable and may avoid injuring the deep vessels, further decreasing the risks of major complications.