Explainable Deep Learning and Biomechanical Modeling for TMJ Disorder Morphological Risk Factors.

Clarifying multifactorial musculoskeletal disorder etiologies supports risk analysis and development of targeted prevention and treatment modalities. Deep learning enables comprehensive risk factor identification through systematic analysis of disease datasets but does not provide sufficient context for mechanistic understanding, limiting clinical applicability for etiological investigations. Conversely, multiscale biomechanical modeling can evaluate mechanistic etiology within the relevant biomechanical and physiological context. We propose a hybrid approach combining 3D explainable deep learning and multiscale biomechanical modeling; we applied this approach to investigate temporomandibular joint (TMJ) disorder etiology by systematically identifying risk factors and elucidating mechanistic relationships between risk factors and TMJ biomechanics and mechanobiology. Our 3D convolutional neural network recognized TMJ disorder patients through subject-specific morphological features in condylar, ramus, and chin. Driven by deep learning model outputs, biomechanical modeling revealed that small mandibular size and flat condylar shape were associated with increased TMJ disorder risk through increased joint force, decreased tissue nutrient availability and cell ATP production, and increased TMJ disc strain energy density. Combining explainable deep learning and multiscale biomechanical modeling addresses the "mechanism unknown" limitation undermining translational confidence in clinical applications of deep learning and increases methodological accessibility for smaller clinical datasets by providing the crucial biomechanical context.

Cutaneous Involvement by Refractory Celiac Disease Type 2 Histologically Mimicking Mycosis Fungoides.

ABSTRACT: Refractory celiac disease (RCD) is a rare condition characterized by persistent malabsorptive symptoms and villous atrophy despite a gluten-free diet. While RCD type 1 has a normal intraepithelial lymphocyte phenotype, RCD type 2 is defined by the presence of immunophenotypically aberrant and monoclonal intraepithelial T lymphocytes, with a high propensity to transform to enteropathy-associated T-cell lymphoma (EATL). Although dermatological manifestations of celiac disease are common, presentation with cutaneous involvement by abnormal lymphocytes of RCD type 2 or EATL is rare, with few histologic descriptions in the literature. We describe the case of a 66-year-old man with a history of celiac disease presenting with a generalized, erythematous papular rash over his torso, upper arms, and legs. Biopsy of his skin lesions showed prominent hyperkeratosis with underlying spongiosis and interface change. Increased intraepithelial (epidermotropic) lymphocytes were observed, out of proportion to the level of spongiosis, but not overly atypical in appearance. Immunohistochemistry revealed an aberrant T-cell immunophenotype (CD3/2/7 positive; CD5/4/8 negative), raising suspicion for a cutaneous T-cell lymphoproliferative disorder. A duodenal biopsy demonstrated total villous atrophy with a morphologically bland population of epitheliotropic T lymphocytes showing the same aberrant immunophenotype. Similar cells were also identified by flow cytometry in the peripheral blood. In conjunction with the history of celiac disease, a diagnosis of RCD type 2 or 'EATL in situ' with cutaneous involvement was made. Cutaneous RCD type 2 or EATL should be considered as differential diagnoses in patients with a history of celiac disease and histopathology reminiscent of epidermotropic forms of cutaneous T-cell lymphoma.

Large unrepaired aortopulmonary window--survival into the seventh decade.

Aortopulmonary (AP) window is a rare cardiac malformation. We report a patient with Eisenmenger syndrome secondary to a large unrepaired AP window who gave birth to three children in her thirties, survived into her fifties with relatively preserved quality of life, and died at age 60.