RESUMO
BACKGROUND: Histologic examination of resected pancreatic cancer after neoadjuvant therapy (NAT) is used to assess the effect of NAT and may guide the choice for adjuvant treatment. However, evaluating residual tumor burden in pancreatic cancer is challenging given tumor response heterogeneity and challenging histomorphology. Artificial intelligence techniques may offer a more reproducible approach. METHODS: From 64 patients, one H&E-stained slide of resected pancreatic cancer after NAT was digitized. Three separate classes were manually outlined in each slide (i.e., tumor, normal ducts, and remaining epithelium). Corresponding segmentation masks and patches were generated and distributed over training, validation, and test sets. Modified U-nets with varying encoders were trained, and F1 scores were obtained to express segmentation accuracy. RESULTS: The highest mean segmentation accuracy was obtained using modified U-nets with a DenseNet161 encoder. Tumor tissue was segmented with a high mean F1 score of 0.86, while the overall multiclass average F1 score was 0.82. CONCLUSIONS: This study shows that artificial intelligence-based assessment of residual tumor burden is feasible given the promising obtained F1 scores for tumor segmentation. This model could be developed into a tool for the objective evaluation of the response to NAT and may potentially guide the choice for adjuvant treatment.
RESUMO
BACKGROUND: Sternocostoclavicular hyperostosis (SCCH; ORPHA178311) is a rare inflammatory disorder of the axial skeleton, the precise pathophysiology of which remains to be established. We addressed the potential association of SCCH with autoimmune processes by evaluating the lifetime prevalence of autoimmune disease in 70 patients with adult-onset SCCH and 518 SCCH-unaffected first-degree relatives (parents, siblings and children). Danish hospital registry data for autoimmune diseases were used as reference data. RESULTS: The mean age of interviewed patients was 56.3 years (range 26-80 years) and 86% were female. Interviewed patients belonged to 63 families, with four families having clusters of 2-3 patients. A diagnosis of at least one autoimmune disease was reported in 20 SCCH patients (29%) and in 47 relatives (9.1%), compared to an estimated 3.9% prevalence of autoimmune disease in the Danish reference population. A diversity of autoimmune diseases was reported in SCCH patients and relatives, most frequently psoriasis vulgaris (14%). Palmoplantar pustulosis was reported by 28 patients (40%). In SCCH patients, inclusion of palmoplantar pustulosis as putative autoimmune disease increased the overall prevalence to 54%. CONCLUSIONS: The high prevalence of autoimmune disease in patients with sternocostoclavicular hyperostosis and their first-degree relatives suggests that autoimmunity may play a role in the still elusive pathophysiology of the intriguing osteogenic response to inflammation observed in this rare bone disorder.
