RESUMO
BACKGROUND: Previous research studies have demonstrated that medical content image retrieval can play an important role by assisting dermatologists in skin lesion diagnosis. However, current state-of-the-art approaches have not been adopted in routine consultation, partly due to the lack of interpretability limiting trust by clinical users. OBJECTIVE: This study developed a new image retrieval architecture for polarized or dermoscopic imaging guided by interpretable saliency maps. This approach provides better feature extraction, leading to better quantitative retrieval performance as well as providing interpretability for an eventual real-world implementation. METHODS: Content-based image retrieval (CBIR) algorithms rely on the comparison of image features embedded by convolutional neural network (CNN) against a labeled data set. Saliency maps are computer vision-interpretable methods that highlight the most relevant regions for the prediction made by a neural network. By introducing a fine-tuning stage that includes saliency maps to guide feature extraction, the accuracy of image retrieval is optimized. We refer to this approach as saliency-enhanced CBIR (SE-CBIR). A reader study was designed at the University Hospital Zurich Dermatology Clinic to evaluate SE-CBIR's retrieval accuracy as well as the impact of the participant's confidence on the diagnosis. RESULTS: SE-CBIR improved the retrieval accuracy by 7% (77% vs 84%) when doing single-lesion retrieval against traditional CBIR. The reader study showed an overall increase in classification accuracy of 22% (62% vs 84%) when the participant is provided with SE-CBIR retrieved images. In addition, the overall confidence in the lesion's diagnosis increased by 24%. Finally, the use of SE-CBIR as a support tool helped the participants reduce the number of nonmelanoma lesions previously diagnosed as melanoma (overdiagnosis) by 53%. CONCLUSIONS: SE-CBIR presents better retrieval accuracy compared to traditional CBIR CNN-based approaches. Furthermore, we have shown how these support tools can help dermatologists and residents improve diagnosis accuracy and confidence. Additionally, by introducing interpretable methods, we should expect increased acceptance and use of these tools in routine consultation.
RESUMO
The FOXO transcription factors control proliferation and apoptosis in different cell types. Their activity is regulated by posttranslational modifications, mainly by the PI3K-PKB pathway, which controls nuclear export and degradation. We show that FOXO1 is highly expressed in normal germinal center B cells as well as in non-Hodgkin lymphomas, including follicular lymphoma, diffuse large B-cell lymphoma, mucosa-associated lymphoid tissue non-Hodgkin lymphoma, B-cell chronic lymphocytic leukemia, and mantle cell lymphoma. In contrast, in 31 of 32 classical Hodgkin lymphoma (cHL) cases, Hodgkin and Reed-Sternberg cells were FOXO1 negative. Neoplastic cells of nodular lymphocyte-predominant Hodgkin lymphoma were negative in 14 of 20 cases. FOXO1 was down-regulated in cHL cell lines, whereas it was expressed in non-Hodgkin lymphoma cell lines at levels comparable with normal B cells. Ectopic expression of a constitutively active FOXO1 induced apoptosis in cHL cell lines and blocked proliferation, accompanied with cell-cycle arrest in the G(0)/G(1) phase. We found that, in cHL cell lines, FOXO1 is inactivated by multiple mechanisms, including constitutive activation of AKT/PKB and MAPK/ERK kinases and up-regulation of microRNAs miR-96, miR-182, and miR-183. These results suggest that FOXO1 repression contributes to cHL lymphomagenesis.
