We tested the use of a deep learning algorithm to classify the clinical images of 12 skin diseases-basal cell carcinoma, squamous cell carcinoma, intraepithelial carcinoma, actinic keratosis, seborrheic keratosis, malignant melanoma, melanocytic nevus, lentigo, pyogenic granuloma, hemangioma, dermatofibroma, and wart. The convolutional neural network (Microsoft ResNet-152 model; Microsoft Research Asia, Beijing, China) was fine-tuned with images from the training portion of the Asan dataset, MED-NODE dataset, and atlas site images (19,398 images in total). The trained model was validated with the testing portion of the Asan, Hallym and Edinburgh datasets. With the Asan dataset, the area under the curve for the diagnosis of basal cell carcinoma, squamous cell carcinoma, intraepithelial carcinoma, and melanoma was 0.96 ± 0.01, 0.83 ± 0.01, 0.82 ± 0.02, and 0.96 ± 0.00, respectively. With the Edinburgh dataset, the area under the curve for the corresponding diseases was 0.90 ± 0.01, 0.91 ± 0.01, 0.83 ± 0.01, and 0.88 ± 0.01, respectively. With the Hallym dataset, the sensitivity for basal cell carcinoma diagnosis was 87.1% ± 6.0%. The tested algorithm performance with 480 Asan and Edinburgh images was comparable to that of 16 dermatologists. To improve the performance of convolutional neural network, additional images with a broader range of ages and ethnicities should be collected.

Background and purpose — We aimed to evaluate the ability of artificial intelligence (a deep learning algorithm) to detect and classify proximal humerus fractures using plain anteroposterior shoulder radiographs.Patients and methods — 1,891 images (1 image per person) of normal shoulders (n = 515) and 4 proximal humerus fracture types (greater tuberosity, 346; surgical neck, 514; 3-part, 269; 4-part, 247) classified by 3 specialists were evaluated. We trained a deep convolutional neural network (CNN) after augmentation of a training dataset. The ability of the CNN, as measured by top-1 accuracy, area under receiver operating characteristics curve (AUC), sensitivity/specificity, and Youden index, in comparison with humans (28 general physicians, 11 general orthopedists, and 19 orthopedists specialized in the shoulder) to detect and classify proximal humerus fractures was evaluated.Results — The CNN showed a high performance of 96% top-1 accuracy, 1.00 AUC, 0.99/0.97 sensitivity/specificity, and 0.97 Youden index for distinguishing normal shoulders from proximal humerus fractures. In addition, the CNN showed promising results with 65–86% top-1 accuracy, 0.90–0.98 AUC, 0.88/0.83–0.97/0.94 sensitivity/specificity, and 0.71–0.90 Youden index for classifying fracture type. When compared with the human groups, the CNN showed superior performance to that of general physicians and orthopedists, similar performance to orthopedists specialized in the shoulder, and the superior performance of the CNN was more marked in complex 3- and 4-part fractures.Interpretation — The use of artificial intelligence can accurately detect and classify proximal humerus fractures on plain shoulder AP radiographs. Further studies are necessary to determine the feasibility of applying artificial intelligence in the clinic and whether its use could improve care and outcomes compared with current orthopedic assessments.

Although deep learning algorithms have demonstrated expert-level performance, previous efforts were mostly binary classifications of limited disorders. We trained an algorithm with 220,680 images of 174 disorders and validated it using Edinburgh (1,300 images; 10 disorders) and SNU datasets (2,201 images; 134 disorders). The algorithm could accurately predict malignancy, suggest primary treatment options, render multi-class classification among 134 disorders, and improve the performance of medical professionals. The area under the curves for malignancy detection were 0.928 AE 0.002 (Edinburgh) and 0.937 AE 0.004 (SNU). The area under the curves of primary treatment suggestion (SNU) were 0.828 AE 0.012, 0.885 AE 0.006, 0.885 AE 0.006, and 0.918 AE 0.006 for steroids, antibiotics, antivirals, and antifungals, respectively. For multi-class classification, the mean top-1 and top-5 accuracies were 56.7 AE 1.6% and 92.0 AE 1.1% (Edinburgh) and 44.8 AE 1.2% and 78.1 AE 0.3% (SNU), respectively. With the assistance of our algorithm, the sensitivity and specificity of 47 clinicians (21 dermatologists and 26 dermatology residents) for malignancy prediction (SNU; 240 images) were improved by 12.1% (P < 0.0001) and 1.1% (P < 0.0001), respectively. The malignancy prediction sensitivity of 23 non-medical professionals was significantly increased by 83.8% (P < 0.0001). The top-1 and top-3 accuracies of four doctors in the multi-class classification of 134 diseases (SNU; 2,201 images) were increased by 7.0% (P ¼ 0.045) and 10.1% (P ¼ 0.0020), respectively. The results suggest that our algorithm may serve as augmented intelligence that can empower medical professionals in diagnostic dermatology.

Although there have been reports of the successful diagnosis of skin disorders using deep learning, unrealistically large clinical image datasets are required for artificial intelligence (AI) training. We created datasets of standardized nail images using a region-based convolutional neural network (R-CNN) trained to distinguish the nail from the background.We used R-CNN to generate training datasets of 49,567 images, which we then used to fine-tune the ResNet-152 and VGG-19 models. The validation datasets comprised 100 and 194 images from Inje University (B1 and B2 datasets, respectively), 125 images from Hallym University (C dataset), and 939 images from Seoul National University (D dataset).The AI (ensemble model; ResNet-152 + VGG-19 + feedforward neural networks) results showed test sensitivity/specificity/ area under the curve values of (96.0 / 94.7 / 0.98), (82.7 / 96.7 / 0.95), (92.3 / 79.3 / 0.93), (87.7 / 69.3 / 0.82) for the B1, B2, C, and D datasets.With a combination of the B1 and C datasets, the AI Youden index was significantly (p = 0.01) higher than that of 42 dermatologists doing the same assessment manually. For B1+C and B2+ D dataset combinations, almost none of the dermatologists performed as well as the AI. By training with a dataset comprising 49,567 images, we achieved a diagnostic accuracy for onychomycosis using deep learning that was superior to that of most of the dermatologists who participated in this study.

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.

BackgroundEarly detection followed by prompt intervention is essential for the treatment of periprosthetic joint infection (PJI). D-dimer, a fibrin degradation product, characteristically changes rapidly during early postoperative period and has a short half-life. The aim of this prospective study was to measure postoperative change of D-dimer level after joint arthroplasty in conjunction with ESR and CRP.MethodsESR, CRP, and D-dimer levels were measured on the day before surgery, postoperative days 1, 2, 3, and 5 and weeks 2 and 6 in 65 patients who underwent elective primary total hip arthroplasty (38 hips in 38 patients) or total knee arthroplasty (27 knees in 27 patients). We compared perioperative changes of the three biomarkers.ResultsESR level was elevated from postoperative day 1 and reached a peak level of 45 mm/h at postoperative day 5. The elevation persisted until postoperative week 6. CRP level was elevated from postoperative day 1 and reached a peak level of 10 mg/dl between postoperative day 2 and day 3. The CRP level was decreased to the normal level around postoperative week 2. D-dimer level was sharply elevated and peaked to 4.5 μg/dl at postoperative day 1. At postoperative day 2, it decreased to baseline level. After then, it slowly elevated again and reached a second peak at postoperative week 2.ConclusionD-dimer showed a more rapid rise and fall than ESR and CRP in very early postoperative period. The D-dimer test might be effective in early detection of PJI, if combined with levels of ESR and CRP. The postoperative change of D-dimer in our study can serve as a baseline for early diagnosis of PJI.

No abstract

Peripheral artery disease (PAD) is a common condition with high morbidity. While measurement of tissue oxygen saturation (S(t)O(2)) has been demonstrated, this is the first study to assess both S(t)O(2) and relative blood flow (rBF) in the extremities of PAD patients. Diffuse optics is employed to measure hemodynamic response to treadmill and pedal exercises in 31 healthy controls and 26 patients. For S(t)O(2), mild and moderate/severe PAD groups show pronounced differences compared with controls. Pre-exercise mean S(t)O(2) is lower in PAD groups by 9.3% to 10.6% compared with means of 63.5% to 66.2% in controls. For pedal, relative rate of return of S(t)O(2) to baseline is more rapid in controls (p < 0.05). Patterns of rBF also differ among groups. After both exercises, rBF tend to occur at depressed levels among severe PAD patients compared with healthy (p < 0.05); post-treadmill, rBF tend to occur at elevated levels among healthy compared with severe PAD patients (p < 0.05). Additionally, relative rate of return to baseline S(t)O(2) is more rapid among subjects with reduced levels of depression in rBF (p = 0.041), even after adjustment for ankle brachial index. This suggests a physiologic connection between rBF and oxygenation that can be measured using diffuse optics, and potentially employed as an evaluative tool in further studies.