Search

The integration of an artificial intelligence tool into pathologists' workflow may lead to a more accurate and timely diagnosis of melanocytic lesions, directly patient care. The objective of this study was to create and evaluate the performance of such a model in achieving clinical-grade diagnoses of Spitz nevi, dermal and junctional melanocytic nevi, and melanomas.We created a beginner-level training environment by teaching our algorithm to perform cytologic inferences on 136,216 manually annotated tiles of hematoxylin and eosin-stained slides consisting of unequivocal melanocytic nevi, Spitz nevi, and invasive melanoma cases. We sequentially trained and tested our network to provide a final diagnosis-classification on 39 cases in total. Positive predictive value (precision) and sensitivity (recall) were used to measure our performance.The tile-classification algorithm predicted the 136,216 irrelevant, melanoma, melanocytic nevi, and Spitz nevi tiles at sensitivities of 96%, 93%, 94% and 73%, respectively. The final trained model was able to correctly classify and predict the correct diagnosis in 85.7% of unseen cases (n = 28), reporting at or near screening-level performances for precision and recall of melanoma (76.2%, 100.0%), melanocytic nevi (100.0%, 75.0%), and Spitz nevi (100.0%, 75.0%).Our pilot study proves that convolutional networks trained on cellular morphology to classify melanocytic proliferations can be used as a powerful tool to assist pathologists in screening for melanoma versus other benign lesions.

Dermatology residents have 3 years to master core competencies related to the delivery of patient care, preservation of medical professionalism, and responsible use of health care; however, it is crucial for residents to recognize other things outside of their formal curriculum that are equally vital to their training. Over the years, we have observed residents and now offer our own perspectives. We have collectively observed five extracurricular aspects commonly overlooked by dermatology residents that are important to their education and future practice. (

Primary cytotoxic T cell lymphomas (CTCLs) are a rare subset of aggressive, poor-prognosis T-cell lymphomas targeting the skin; they include primary cutaneous γδT-cell lymphoma, primary cutaneous VD8+ aggressive epidermotropic T cell lymphoma (PCAETCL), and cytotoxic CTCL not otherwise specified. Lee et al report that all 3 subsets have JAK-STAT activation, but PCAETCL uniquely carries JAK2 gene fusions that may render them especially susceptible to JAK inhibitors.

Background: Primary cytotoxic T cell lymphomas are a heterogenous collection of ill-defined diseases with aggressive disease course and poor response to conventional therapy. Of these, primary cutaneous CD8+ aggressive epidermotropic T cell lymphoma and cutaneous T cell lymphoma, not otherwise specified, have undergone few to no systematic analyses of its genetic landscape. In this study, we classify these lymphomas based on their histological and clinical features and perform systematic genomic analyses to find novel therapeutic targets. Methods: We clinically characterize 35 patients from 10 institutions with cytotoxic T cell lymphoma and performed integrative clinical, pathological, and genetic analyses. We perform Archer™ Heme Fusion on an initial 24 FFPE samples. In addition, we perform DNA and/or RNA sequencing on 11 cases. We functionally validate our genetic findings by transducing alterations into Ba/F3 cells and subsequently performing biochemical assays. In this setting, we assess sensitivity to FDA-approved small molecule inhibitors. We provide orthogonal evidence of transcriptional upregulation by geneset enrichment analysis. Results: We find kinase fusions impacting JAK-STAT signaling in all primary cutaneous CD8+ aggressive epidermotropic T cell lymphomas in our cohort. Three of these fusions have not previously been described in cancer. Known fusions have been shown to upregulate JAK-STAT signaling. Upon each transduction, CAPRIN1-JAK2 and SELENOI-ABL1 cause increased phosphorylation and display IL-3-independent growth compared to control. Upon treatments to small molecule inhibitors, ruxolitinib and imatinib respectively, CAPRIN1-JAK2 and SELENOI-ABL1 expressing cells exhibit sensitivity. Cutaneous T cell lymphoma, not otherwise specified, harbor JAK-STAT hotspot mutations but not kinase fusions. Conclusions: All 9 primary cutaneous CD8+ aggressive epidermotropic T cell lymphomas in our series harbor kinase fusions, while the majority of the cutaneous T cell lymphoma, not otherwise specified, cases in our cohort harbor hotspot JAK/STAT mutations. We provide evidence that the of presence these alterations, which are associated with inhibitor response, depend on cytotoxic T cell lymphoma histology.

Background: Expenditures for postacute care in total joint arthroplasty (TJA) have risen dramatically over recent decades. Therefore, efforts are underway to better identify cost savings in postacute rehabilitation centers, such as skilled nursing facilities (SNFs). The primary purpose of this study was to analyze gait training achievements in post-TJA patients in the interval between hospital discharge and the patients’ first 4 days at the SNF. Identification of potential losses in therapeutic progress may lead the way for improved patient care, outcomes, and cost savings. Our hypothesis is that patients discharged to an SNF will have a decline in gait achievements upon transfer from the hospital. Methods: A total of 68 patients who underwent TJA were included. The total distance ambulated during physical therapy (PT) was recorded for the last day of hospital therapy and the first 4 days at the SNF as well as the reported visual analog scale (VAS) pain scores. Results: There was a 73% decline in distance ambulated on SNF day 0 ( Hospital: 138.6 ft vs SNF: 37.9 ft; P < .001) and a 50% decline on SNF day 1 ( Hospital: 103.0 ft; SNF vs 51.1 ft; P < .001) compared to the last hospital session. There were no significant differences in distance walked on SNF days 3 and 4 relative to the last hospital session. The VAS pain scores did not significantly differ on SNF days 0 and 1 compared to the last hospital day but began to significantly decline on SNF day 3 ( Hospital: 4.9; SNF: 3.3; P = .02) and day 4 ( Hospital: 3.9; SNF: 2.3; P = .03). Conclusion: There was a significant decline in ambulatory proficiency in post-TJA patients on the day of and the day following hospital discharge to an SNF. These deficits cannot be attributed to heightened pain levels. Early and progressive ambulation is a recognized component of appropriate PT following TJA. This study therefore highlights the transition from hospital to SNF as a crucial and novel target for improvement in post-TJA care.