Quantifying ear deformity using linear measurements and mathematical modeling is difficult due to the ear’s complex shape. Machine learning techniques, such as convolutional neural networks (CNNs), are well-suited for this role. CNNs are deep learning methods capable of finding complex patterns from medical images, automatically building solution models capable of machine diagnosis. In this study, we applied CNN to automatically identify ear deformity from 2D photographs. Institutional review board (IRB) approval was obtained for this retrospective study to train and test the CNNs. Photographs of patients with and without ear deformity were obtained as standard of care in our photography studio. Profile photographs were obtained for one or both ears. A total of 671 profile pictures were used in this study including: 457 photographs of patients with ear deformity and 214 photographs of patients with normal ears. Photographs were cropped to the ear boundary and randomly divided into training (60%), validation (20%), and testing (20%) datasets. We modified the softmax classifier in the last layer in GoogLeNet, a deep CNN, to generate an ear deformity detection model in Matlab. All images were deemed of high quality and usable for training and testing. It took about 2 hours to train the system and the training accuracy reached almost 100%. The test accuracy was about 94.1%. We demonstrate that deep learning has a great potential in identifying ear deformity. These machine learning techniques hold the promise in being used in the future to evaluate treatment outcomes.

Aim: Metopic craniosynostosis (MCS), with its trigonocephalic head shape, is often treated with either limited incision strip craniectomy (LISC) followed by helmet orthotic treatment, or open cranial vault reconstruction techniques (OCVR). There is controversy regarding resultant shape outcomes among craniofacial surgeons. Those adverse to LISC claim normal head shape is never attained, while proponents believe there is gradual correction to an equivalent outcome. This study aims to quantitate, over time, the three-dimensional (3D) head shapes in patients who have undergone LISC or OCVR intervention for MCS. Methods: Sixty-three 3D images of 26 patients with MCS were analyzed retrospectively. Head shape analyses were performed at: (1) preoperative, (2) 1-month postoperative, (3) 10 to 14 months postoperative (1 year), and (4) 2 years postoperative. Composite 3D head shapes of patients were compared at each time point. Two-dimensional (2D) standardized cross sections of the forehead were also compared. Results: Composite head shapes for both groups were nested, to allow visual comparison as the child’s forehead grows and expands. The difference between LISC and OCVR 2D cross sections was calculated; 108.26 mm preoperatively, 127.18 mm after 1-month postoperative, 51.05 mm after 10 to 14 months postoperative, and 27.03 mm after 2 years postoperative. Conclusions: This study found excellent head shape outcomes for both the LISC and OCVR techniques at 2 years of age. It also corroborates the slow and progressive improvement in head shape with the LISC technique. This study highlights the advantages of 3D photography for measurement of contour outcomes, utilizing both 2D vector and 3D whole head analytical techniques.

Background: Patients increasingly use photographs taken with a front-facing smartphone camera—“selfies”—to discuss their goals with a plastic surgeon. The purpose of this study was to quantify changes in size and perception of facial features when taking a selfie compared to the gold standard of clinical photography. Methods: Thirty volunteers took three series of photographs. A 12-inch and 18-inch series were taken with a front-facing smartphone camera, and the 5-foot clinical photography series was taken with a digital single-lens reflex camera. Afterward, subjects filled out the FACE-Q inventory, once when viewing their 12-inch selfies and once when viewing their clinical photographs. Measurements were taken of the nose, lip, chin, and facial width. Results: Nasal length was, on average, 6.4 percent longer in 12-inch selfies compared to clinical photography, and 4.3 percent longer in 18-inch selfies compared to clinical photography. The alar base width did not change significantly in either set of selfies compared to clinical photography. The alar base to facial width ratio represents the size of the nose in relation to the face. This ratio decreased 10.8 percent when comparing 12-inch selfies to clinical photography (p < 0.0001) and decreased 7.8 percent when comparing 18-inch selfies to clinical photography (p < 0.0001). Conclusions: This study quantifies the change in facial feature size/perception seen in previous camera-to-subject distance studies. With the increasing popularity of front-facing smartphone photographs, these data allow for a more precise conversation between the surgeon and the patient. In addition, the authors’ findings provide data for manufacturers to improve the societal impact of smartphone cameras. CLINICAL QUESTION/LEVEL OF EVIDENCE: Diagnostic, III.

Introduction and Objectives: Surgical treatment for trigonocephaly aims to eliminate a stigmatizing deformity, yet the severity that captures unwanted attention is unknown. Surgeons intervene at different points of severity, eliciting controversy. This study used eye tracking to investigate when deformity is perceived. Material and Methods: Three-dimensional photogrammetric images of a normal child and a child with trigonocephaly were mathematically deformed, in 10% increments, to create a spectrum of 11 images. These images were shown to participants using an eye tracker. Participants’ gaze patterns were analyzed, and participants were asked if each image looked “normal” or “abnormal.” Results: Sixty-six graduate students were recruited. Average dwell time toward pathologic areas of interest (AOIs) increased proportionally, from 0.77 ± 0.33 seconds at 0% deformity to 1.08 ± 0.75 seconds at 100% deformity ( P < .0001). A majority of participants did not agree an image looked “abnormal” until 90% deformity from any angle. Conclusion: Eye tracking can be used as a proxy for attention threshold toward orbitofrontal deformity. The amount of attention toward orbitofrontal AOIs increased proportionally with severity. Participants did not generally agree there was “abnormality” until deformity was severe. This study supports the assertion that surgical intervention may be best reserved for more severe deformity.

Objectives Vascular anomalies such as capillary malformations (CMs) and infantile hemangiomas (IHs) are common pediatric vascular disorders that are treated with therapeutic laser. The treatment method, however, relies on subjective evaluation of clinical findings and can have unpredictable results. Raster‐scanning optoacoustic mesoscopy (RSOM) is an innovative imaging technology using pulsed‐light laser to excite hemoglobin, generating ultrasound waves that are converted into three‐dimensional images of tissues. RSOM can provide objective information about superficial structures such as the microvasculature of vascular anomalies. Materials and Methods In this study, we explore the clinical potential of RSOM to study vascular anomalies before and after laser treatment. We scanned nine patients with CM (n = 6) and IH (n = 3) who underwent laser treatment and calculated the blood vessel volume. Results Overall, there was a posttreatment volume increase in CM, and a decrease in IH. Conclusion These findings support the possibility that RSOM may have a role in developing an objective method of evaluating these lesions, leading to a tailored treatment approach and avoidance of adverse outcomes.

No abstract

The Tagliacozzi cross arm flap has been historically described for repair of large nasal defects. The authors report what we believe is the youngest case in modern literature of nasal reconstruction with a Tagliacozzi flap, in a 6-year-old girl. Due to her poor face and scalp skin quality, the more modern reconstructive options of a forehead flap or free tissue transfer were not deemed suitable. Two delay procedures and a complex splint were required to position the medial arm fasciocutaneous flap over the nasal construct. The arm was immobilized for 3 weeks to allow for vascularization of the recipient bed. The child successfully tolerated the splint. She has improved breathing and nasal contour.

OBJECTIVE A literature gap exists comparing whole head shape outcome following correction of sagittal craniosynostosis. The objective of this multicenter study was to provide an analysis of long-term results following three different endoscopic strip craniectomy techniques for correction of sagittal craniosynostosis: 1) spring-assisted strip craniectomy, 2) wide-strip craniectomy with biparietal and bitemporal barrel-stave wedge osteotomies plus helmet orthosis, and 3) narrow-strip craniectomy plus orthosis without barrel staves. METHODS Pre- and postoperative 3D stereophotogrammetric images were collected from patients who underwent craniosynostosis surgery. Procedures were divided among institutions as follows: spring-assisted strip craniectomies were performed at Atrium Health Wake Forest Baptist Hospital; narrow-strip craniectomies were performed at St. Louis Children’s Hospital by one craniofacial surgeon; and wide-vertex craniectomies were performed at St. Louis Children’s Hospital prior to 2010, and then continued at Children’s Medical Center Dallas. Pre- and postoperative 3D whole-head composite images were generated for each procedure to visually represent outcomes at final follow-up and compared with age-matched normal controls. RESULTS Patients in the spring-assisted strip craniectomy group showed normalization of frontal bossing and skull height compared with age-matched controls, whereas patients undergoing wide-strip craniectomy showed greater correction of occipital protrusion. Patients in the narrow-strip craniectomy cohort had intermediate results between these outcomes. Nested aggregate head shapes showed good correction of head shapes from all techniques. CONCLUSIONS This large, retrospective, multicenter study illustrated whole head shape outcomes from three different craniectomy procedures. Although each procedure showed some differences in loci of primary correction, all three surgical methods demonstrated good correction of primary scaphocephalic deformity.