DermX: An end-to-end framework for explainable automated dermatological diagnosis.

Dermatological diagnosis automation is essential in addressing the high prevalence of skin diseases and critical shortage of dermatologists. Despite approaching expert-level diagnosis performance, convolutional neural network (ConvNet) adoption in clinical practice is impeded by their limited explainability, and by subjective, expensive explainability validations. We introduce DermX, an end-to-end framework for explainable automated dermatological diagnosis. DermX is a clinically-inspired explainable dermatological diagnosis ConvNet, trained using DermXDB, a 554 image dataset annotated by eight dermatologists with diagnoses, supporting explanations, and explanation attention maps. DermX+ extends DermX with guided attention training for explanation attention maps. Both methods achieve near-expert diagnosis performance, with DermX, DermX+, and dermatologist F1 scores of 0.79, 0.79, and 0.87, respectively. We assess the explanation performance in terms of identification and localization by comparing model-selected with dermatologist-selected explanations, and gradient-weighted class-activation maps with dermatologist explanation maps, respectively. DermX obtained an identification F1 score of 0.77, while DermX+ obtained 0.79. The localization F1 score is 0.39 for DermX and 0.35 for DermX+. These results show that explainability does not necessarily come at the expense of predictive power, as our high-performance models provide expert-inspired explanations for their diagnoses without lowering their diagnosis performance.

Deformation-based atrophy computation by surface propagation and its application to Alzheimer's disease.

Obtaining regional volume changes from a deformation field is more precise when using simplex counting (SC) compared with Jacobian integration (JI) due to the numerics involved in the latter. Although SC has been proposed before, numerical properties underpinning the method and a thorough evaluation of the method against JI is missing in the literature. The contributions of this paper are: (a) we propose surface propagation (SP)-a simplification to SC that significantly reduces its computational complexity; (b) we will derive the orders of approximation of SP which can also be extended to SC. In the experiments, we will begin by empirically showing that SP is indeed nearly identical to SC, and that both methods are more stable than JI in presence of moderate to large deformation noise. Since SC and SP are identical, we consider SP as a representative of both the methods for a practical evaluation against JI. In a real application on Alzheimer's disease neuroimaging initiative data, we show the following: (a) SP produces whole brain and medial temporal lobe atrophy numbers that are significantly better than JI at separating between normal controls and Alzheimer's disease patients; (b) SP produces disease group atrophy differences comparable to or better than those obtained using FreeSurfer, demonstrating the validity of the obtained clinical results. Finally, in a reproducibility study, we show that the voxel-wise application of SP yields significantly lower variance when compared to JI.

Predicting knee cartilage loss using adaptive partitioning of cartilage thickness maps.

This study investigates whether measures of knee cartilage thickness can predict future loss of knee cartilage. A slow and a rapid progressor group was determined using longitudinal data, and anatomically aligned cartilage thickness maps were extracted from MRI at baseline. A novel machine learning framework was then trained using these maps. Compared to measures of mean cartilage plate thickness, group separation was increased by focusing on local cartilage differences. This result is central for clinical trials where inclusion of rapid progressors may help reduce the period needed to study effects of new disease-modifying drugs for osteoarthritis.

On Subregional Analysis of Cartilage Loss from Knee MRI.

OBJECTIVE: Understanding how knee cartilage is affected by osteoarthritis (OA) is critical in the development of sensitive biomarkers that may be used as surrogate endpoints in clinical trials. The objective of this study was to analyze longitudinal changes in cartilage thickness using detailed change maps and to examine if current methods for subregional analysis are able to capture the underlying cartilage changes. MATERIALS AND METHODS: MRI images of 267 knees from 135 participants were acquired at baseline and 21-month follow-up and processed using a fully automatic framework for cartilage segmentation and quantification. The framework provides an anatomical coordinate system that allows for direct comparison across cartilage thickness maps. The reproducibility of this method was evaluated on 37 scan-rescan image pairs. RESULTS: In OA knees, an annualized thickness loss of 3.7% was observed in the medial femoral cartilage plate (MF) whereas subregional measurements varied between -9.0% (loss) and 1.6%. The largest changes were observed in the posterior part of the MF. In the medial tibial cartilage plate (MT), a thickness increase of 0.4% was observed whereas subregional measurements varied between -0.8% (loss) and 1.6%. In addition, notable differences in the patterns of cartilage change were observed between genders. CONCLUSIONS: This study indicated that the spatial changes, although highly heterogeneous, showed distinct patterns of cartilage thinning and cartilage thickening in both the MF and the MT. These patterns were not accurately reflected when thickness changes were averaged over large, predefined subregions as defined in current methods for subregional analysis.

A framework for optimizing measurement weight maps to minimize the required sample size.

We propose a fully automatic statistical framework for identifying the non-negative, real-valued weight map that best discriminate between two groups of objects. Given measurements on a spatially defined grid, a numerical optimization scheme is used to find the weight map that minimizes the sample size required to discriminate the two groups. The weight map produced by the method reflects the relative importance of the different areas in the objects, and the resulting sample size reduction is an important end goal in situations where data collection is difficult or expensive. An example is in clinical studies where the cost and the patient burden are directly related to the number of participants needed for the study. In addition, inspection of the weight map might provide clues that can lead to a better clinical understanding of the objects and pathologies being studied. The method is evaluated on synthetic data and on clinical data from knee cartilage MRI. The clinical data contain a total of 159 subjects aged 21-81 years and ranked from zero to four on the Kellgren-Lawrence osteoarthritis severity scale. Compared to a uniform weight map, we achieve sample size reductions up to 58% for cartilage thickness measurements. Based on quantifications from both morphometric and textural based imaging features, we also identify the most pathological areas in the articular cartilage.

The child suicide risk assessment: a screening measure of suicide risk in pre-adolescents.

This study documents the initial reliability and validity of the Child Suicide Risk Assessment (CSRA) for children under the age of 13. The revised CSRA retained 18 of 20 original items based on item-specific psychometric data from 140 pre-adolescents in out-of-home treatment programs. The CSRA demonstrated adequate internal consistency (alpha=.69) for a multi-dimensional scale (3 factors: Worsening Depression, Lack of Support, and Death as Escape). CSRA scores correlated significantly with criterion measures of prior suicide attempts and ideations. A receiver operating characteristic (ROC) curve discriminated significantly between prior attempters and non-attempters and was used to select preliminary CSRA cut-off scores for identifying substantial suicide risk. The CSRA is the first screening measure of suicide risk in pre-adolescents validated by associations with suicide attempts as well as ideations.