IMPORTANCE Detection of cutaneous cancer on the face using deep-learning algorithms has been challenging because various anatomic structures create curves and shades that confuse the algorithm and can potentially lead to false-positive results.OBJECTIVE To evaluate whether an algorithm can automatically locate suspected areas and predict the probability of a lesion being malignant. DESIGN, SETTING, AND PARTICIPANTS Region-based convolutional neural network technology was used to create 924 538 possible lesions by extracting nodular benign lesions from 182 348 clinical photographs. After manually or automatically annotating these possible lesions based on image findings, convolutional neural networks were trained with 1 106 886 image crops to locate and diagnose cancer. Validation data sets (2844 images from 673 patients; mean [SD] age, 58.2 [19.9] years; 308 men [45.8%]; 185 patients with malignant tumors, 305 with benign tumors, and 183 free of tumor) were obtained from 3 hospitals between January 1, 2010, and September 30, 2018. MAIN OUTCOMES AND MEASURESThe area under the receiver operating characteristic curve, F1 score (mean of precision and recall; range, 0.000-1.000), and Youden index score (sensitivity + specificity −1; 0%-100%) were used to compare the performance of the algorithm with that of the participants. RESULTSThe algorithm analyzed a mean (SD) of 4.2 (2.4) photographs per patient and reported the malignancy score according to the highest malignancy output. The area under the receiver operating characteristic curve for the validation data set (673 patients) was 0.910. At a high-sensitivity cutoff threshold, the sensitivity and specificity of the model with the 673 patients were 76.8% and 90.6%, respectively. With the test partition (325 images; 80 patients), the performance of the algorithm was compared with the performance of 13 board-certified dermatologists, 34 dermatology residents, 20 nondermatologic physicians, and 52 members of the general public with no medical background. When the disease screening performance was evaluated at high sensitivity areas using the F1 score and Youden index score, the algorithm showed a higher F1 score (0.831 vs 0.653 [0.126], P < .001) and Youden index score (0.675 vs 0.417 [0.124], P < .001) than that of nondermatologic physicians. The accuracy of the algorithm was comparable with that of dermatologists (F1 score, 0.831 vs 0.835 [0.040]; Youden index score, 0.675 vs 0.671 [0.100]). CONCLUSIONS AND RELEVANCEThe results of the study suggest that the algorithm could localize and diagnose skin cancer without preselection of suspicious lesions by dermatologists.

Earlobe keloid can form after cosmetic ear piercing, trauma, or burns, and it poses several difficulties in treatment and distinctive cosmetic implications. Treatment methods for earlobe keloids include both surgical and nonsurgical methods. After excision of the earlobe keloid, healing by secondary intention, primary suture, skin graft, or local flap has revealed some disadvantages. The authors approached this problem with a new excision and covering method. The surgery was performed under local anesthesia. Skin over the keloid was dissected from the keloid mass as a flap, which they termed a "keloid fillet flap," and the keloid mass was completely removed. Subcutaneous sutures were not used, and the keloid fillet flaps were closed with 6-0 nylon sutures after trimming. Other intraoperative or postoperative preventive procedures, such as steroid injection, pressure device, or irradiation, were not applied primarily. In the period from May of 1999 to October of 2000, nine earlobe keloids in eight patients were treated with this protocol. One patient had bilateral keloids. Of the eight patients, there were six women and two men, ranging in age from 21 to 61 years (mean age, 28.5 years). The causes of keloids were ear piercing in six cases and trauma in three cases. The largest lesion was 3 cm in its greatest dimension, and the smallest was 1.5 cm (mean, 2.3 cm). All flaps survived completely. There were four cases of recurrence. Seven cases, including two recurrences, showed good results. The authors believe the recurrence of earlobe keloid was closely related to the method for coverage of the defect after its surgical excision, and the "5 As and one B" (Asepsis, Atraumatic technique, Absence of raw surface, Avoidance of tension, Accurate approximation of wound margin, and complete Bleeding control) are important factors in reducing the recurrence rate of earlobe keloids in surgical excision. The authors' protocol is very effective in closing the defect after surgical excision of earlobe keloids and offers many advantages over other surgical approaches. The recurrence rate of earlobe keloid may be lower than in their results if other intraoperative and postoperative treatment procedures are combined with their protocol.

No abstract