Search

The current revolution of digital health technology and machine learning offers enormous potential to improve patient care. Nevertheless, it is essential to recognize that dermatology requires an approach different from those of other specialties. For many dermatological conditions, there is a lack of standardized methodology for quantitatively tracking disease progression and treatment response (clinimetrics). Furthermore, dermatological diseases impact patients in complex ways, some of which can be measured only through patient reports (psychometrics). New tools using digital health technology (e.g., smartphone applications, wearable devices) can aid in capturing both clinimetric and psychometric variables over time. With these data, machine learning can inform efforts to improve health care by, for example, the identification of high-risk patient groups, optimization of treatment strategies, and prediction of disease outcomes. We use the term personalized, data-driven dermatology to refer to the use of comprehensive data to inform individual patient care and improve patient outcomes. In this paper, we provide a framework that includes data from multiple sources, leverages digital health technology, and uses machine learning. Although this framework is applicable broadly to dermatological conditions, we use the example of a serious inflammatory skin condition, chronic cutaneous graft-versus-host disease, to illustrate personalized, data-driven dermatology.

Skin biomechanical parameters (dynamic stiffness, frequency, relaxation time, creep, and decrement) measured using a myotonometer (MyotonPRO) could inform the management of sclerotic disease. To determine which biomechanical parameter(s) can accurately differentiate patients with sclerotic chronic graft-versus-host disease from post–hematopoietic cell transplant controls, 15 patients with sclerotic chronic graft-versus-host disease and 11 post–hematopoietic cell transplant controls were measured with the myotonometer on 18 anatomic sites. Logistic regression and two machine learning algorithms (least absolute shrinkage and selection operator regression and random forest) were developed to classify subjects. In univariable analysis, frequency had the highest overfit-corrected area under the curve (0.91). Backward stepwise selection and random forest machine learning identified frequency and relaxation time as the optimal parameters for differentiating patients with sclerotic chronic graft-versus-host disease from post–hematopoietic cell transplant controls. Least absolute shrinkage and selection operator regression selected the combination of frequency and relaxation time (overfit-corrected area under the curve = 0.87). Discriminatory ability was maintained when only the sites accessible while the patient is supine (12 sites) were used. We report the distribution of values for these highly discriminative biomechanical parameters, which could inform the assessment of disease severity in future quantitative biomechanical studies of sclerotic chronic graft-versus-host disease.

Cutaneous erythema is used in diagnosis and response assessment of cutaneous chronic graft-versus-host disease (cGVHD). The development of objective erythema evaluation methods remains a challenge. We used a pre-trained neural network to segment cGVHD erythema by detecting changes relative to a patient’s registered baseline photo. We fixed this change detection algorithm on human annotations from a single photo pair, by using either a traditional approach or by marking definitely affected (“Do Not Miss”, DNM) and definitely unaffected skin (“Do Not Include”, DNI). The fixed algorithm was applied to each of the remaining 47 test photo pairs from six follow-up sessions of one patient. We used both the Dice index and the opinion of two board-certified dermatologists to evaluate the algorithm performance. The change detection algorithm correctly assigned 80% of the pixels, regardless of whether it was fixed on traditional (median accuracy: 0.77, interquartile range 0.62–0.87) or DNM/DNI segmentations (0.81, 0.65–0.89). When the algorithm was fixed on markings by different annotators, the DNM/DNI achieved more consistent outputs (median Dice indices: 0.94–0.96) than the traditional method (0.73–0.81). Compared to viewing only rash photos, the addition of baseline photos improved the reliability of dermatologists’ scoring. The inter-rater intraclass correlation coefficient increased from 0.19 (95% confidence interval lower bound: 0.06) to 0.51 (lower bound: 0.35). In conclusion, a change detection algorithm accurately assigned erythema in longitudinal photos of cGVHD. The reliability was significantly improved by exclusively using confident human segmentations to fix the algorithm. Baseline photos improved the agreement among two dermatologists in assessing algorithm performance.

We present a case of subcutaneous nodular amyloidosis mimicking a pilar cyst. Further evaluation led to the diagnosis of malignant systemic light-chain amyloidosis. The epidemiology and histopathological features of light-chain amyloidosis with cutaneous involvement are reviewed, as well as current recommendations for initial evaluation.

BackgroundChronic graft-versus-host disease (cGVHD) is a significant cause of long-term morbidity and mortality in patients after allogeneic hematopoietic cell transplantation. Skin is the most commonly affected organ, and visual assessment of cGVHD can have low reliability. Crowdsourcing data from nonexpert participants has been used for numerous medical applications, including image labeling and segmentation tasks. ObjectiveThis study aimed to assess the ability of crowds of nonexpert raters—individuals without any prior training for identifying or marking cGHVD—to demarcate photos of cGVHD-affected skin. We also studied the effect of training and feedback on crowd performance. MethodsUsing a Canfield Vectra H1 3D camera, 360 photographs of the skin of 36 patients with cGVHD were taken. Ground truth demarcations were provided in 3D by a trained expert and reviewed by a board-certified dermatologist. In total, 3000 2D images (projections from various angles) were created for crowd demarcation through the DiagnosUs mobile app. Raters were split into high and low feedback groups. The performances of 4 different crowds of nonexperts were analyzed, including 17 raters per image for the low and high feedback groups, 32-35 raters per image for the low feedback group, and the top 5 performers for each image from the low feedback group. ResultsAcross 8 demarcation competitions, 130 raters were recruited to the high feedback group and 161 to the low feedback group. This resulted in a total of 54,887 individual demarcations from the high feedback group and 78,967 from the low feedback group. The nonexpert crowds achieved good overall performance for segmenting cGVHD-affected skin with minimal training, achieving a median surface area error of less than 12% of skin pixels for all crowds in both the high and low feedback groups. The low feedback crowds performed slightly poorer than the high feedback crowd, even when a larger crowd was used. Tracking the 5 most reliable raters from the low feedback group for each image recovered a performance similar to that of the high feedback crowd. Higher variability between raters for a given image was not found to correlate with lower performance of the crowd consensus demarcation and cannot therefore be used as a measure of reliability. No significant learning was observed during the task as more photos and feedback were seen. ConclusionsCrowds of nonexpert raters can demarcate cGVHD images with good overall performance. Tracking the top 5 most reliable raters provided optimal results, obtaining the best performance with the lowest number of expert demarcations required for adequate training. However, the agreement amongst individual nonexperts does not help predict whether the crowd has provided an accurate result. Future work should explore the performance of crowdsourcing in standard clinical photos and further methods to estimate the reliability of consensus demarcations.

Circulating tumor cells in the bloodstream are sensitive indicators for metastasis and disease prognosis. Circulating cells have usually been monitored via extraction from blood, and more recently in vivousing free-space optics; however, long-term intravital monitoring of rare circulating cells remains a major challenge. We demonstrate the application of a two-photon-fluorescence optical fiber probe for the detection of cells in whole blood and in vivo. A double-clad fiber was used to enhance the detection sensitivity. Two-channel detection was employed to enable simultaneous measurement of multiple fluorescent markers. Because the fiber probe circumvents scattering and absorption from whole blood, the detected signal strength from fluorescent cells was found to be similar in phosphate-buffered saline (PBS) and in whole blood. The detection efficiency of cells labeled with the membrane-binding dye 1,1′-dioctadecyl-3,3,3′,3′-tetramethylindoldicarbocyanine, 4-chlorobenzenesulfonate (DiD) was demonstrated to be the same in PBS and in whole blood. A high detection efficiency of green fluorescent protein (GFP)–expressing cells in whole blood was also demonstrated. To characterize in vivodetection, DiD-labeled untransfected and GFP-transfected cells were injected into live mice, and the cell circulation dynamics was monitored in real time. The detection efficiency of GFP-expressing cells in vivowas consistent with that observed ex vivoin whole blood. [ABSTRACT FROM AUTHOR]

We demonstrate enhanced sensitivity in two-photon flow cytometry with an extended cavity laser excitation source. At low power, the home-built 20-MHz oscillator was able to detect a significantly larger fraction, in either phosphate buffered saline (PBS) or whole blood, of green fluorescent protein (GFP)–expressing MCA-207 cells cross-labeled with the membrane-binding lipophilic dye DiD. A geometrical model is used to explain unique features of the signals resulting from the different spatial distribution of DiD and GFP. These unique features include sub-square law scaling of unsaturated two-photon signal, a sigmoidal sensitivity curve for detection under varying powers for cell detection thresholds as low as a single photon, and uncorrelated signal strengths in two detection channels. [ABSTRACT FROM AUTHOR]

Flow cytometry is a powerful technique for quantitative characterization of fluorescence in cells. Quantitation is achieved by ensuring a high degree of uniformity in the optical excitation and detection, generally by using a highly controlled flow. Two-photon excitation has the advantages that it enables simultaneous excitation of multiple dyes and achieves a very high SNR through simplified filtering and fluorescence background reduction. We demonstrate that two-photon excitation in conjunction with a targeted multidye labeling strategy enables quantitative flow cytometry even under conditions of nonuniform flow, such as may be encountered in simple capillary flow or in vivo. By matching the excitation volume to the size of a cell, single-cell detection is ensured. Labeling cells with targeted nanoparticles containing multiple fluorophores enables normalization of the fluorescence signal and thus quantitative measurements under nonuniform excitation. Flow cytometry using two-photon excitation is demonstrated for detection and differentiation of particles and cells both in vitro in a glass capillary and in vivo in the blood stream of live mice. The technique also enables us to monitor the fluorescent dye labeling dynamics in vivo. In addition, we present a unique two-beam scanning method to conduct cell size measurement in nonuniform flow. [ABSTRACT FROM AUTHOR]