Deep Learning Features Can Improve Radiomics-Based Prostate Cancer Aggressiveness Prediction.

PURPOSE: Emerging evidence suggests that the use of artificial intelligence can assist in the timely detection and optimization of therapeutic approach in patients with prostate cancer. The conventional perspective on radiomics encompassing segmentation and the extraction of radiomic features considers it as an independent and sequential process. However, it is not necessary to adhere to this viewpoint. In this study, we show that besides generating masks from which radiomic features can be extracted, prostate segmentation and reconstruction models provide valuable information in their feature space, which can improve the quality of radiomic signatures models for disease aggressiveness classification. MATERIALS AND METHODS: We perform 2,244 experiments with deep learning features extracted from 13 different models trained using different anatomic zones and characterize how modeling decisions, such as deep feature aggregation and dimensionality reduction, affect performance. RESULTS: While models using deep features from full gland and radiomic features consistently lead to improved disease aggressiveness prediction performance, others are detrimental. Our results suggest that the use of deep features can be beneficial, but an appropriate and comprehensive assessment is necessary to ensure that their inclusion does not harm predictive performance. CONCLUSION: The study findings reveal that incorporating deep features derived from autoencoder models trained to reconstruct the full prostate gland (both zonal models show worse performance than radiomics only models), combined with radiomic features, often lead to a statistically significant increase in model performance for disease aggressiveness classification. Additionally, the results also demonstrate that the choice of feature selection is key to achieving good performance, with principal component analysis (PCA) and PCA + relief being the best approaches and that there is no clear difference between the three proposed latent representation extraction techniques.

Analysis of domain shift in whole prostate gland, zonal and lesions segmentation and detection, using multicentric retrospective data.

Despite being one of the most prevalent forms of cancer, prostate cancer (PCa) shows a significantly high survival rate, provided there is timely detection and treatment. Computational methods can help make this detection process considerably faster and more robust. However, some modern machine-learning approaches require accurate segmentation of the prostate gland and the index lesion. Since performing manual segmentations is a very time-consuming task, and highly prone to inter-observer variability, there is a need to develop robust semi-automatic segmentation models. In this work, we leverage the large and highly diverse ProstateNet dataset, which includes 638 whole gland and 461 lesion segmentation masks, from 3 different scanner manufacturers provided by 14 institutions, in addition to other 3 independent public datasets, to train accurate and robust segmentation models for the whole prostate gland, zones and lesions. We show that models trained on large amounts of diverse data are better at generalizing to data from other institutions and obtained with other manufacturers, outperforming models trained on single-institution single-manufacturer datasets in all segmentation tasks. Furthermore, we show that lesion segmentation models trained on ProstateNet can be reliably used as lesion detection models.

Understanding the Binding Specificity of G-Protein Coupled Receptors toward G-Proteins and Arrestins: Application to the Dopamine Receptor Family.

G-Protein coupled receptors (GPCRs) are involved in a myriad of pathways key for human physiology through the formation of complexes with intracellular partners such as G-proteins and arrestins (Arrs). However, the structural and dynamical determinants of these complexes are still largely unknown. Herein, we developed a computational big-data pipeline that enables the structural characterization of GPCR complexes with no available structure. This pipeline was used to study a well-known group of catecholamine receptors, the human dopamine receptor (DXR) family and its complexes, producing novel insights into the physiological properties of these important drug targets. A detailed description of the protein interfaces of all members of the DXR family (D1R, D2R, D3R, D4R, and D5R) and the corresponding protein interfaces of their binding partners (Arrs: Arr2 and Arr3; G-proteins: Gi1, Gi2, Gi3, Go, Gob, Gq, Gslo, Gssh, Gt2, and Gz) was generated. To produce reliable structures of the DXR family in complex with either G-proteins or Arrs, we performed homology modeling using as templates the structures of the ß2-adrenergic receptor (ß2AR) bound to Gs, the rhodopsin bound to Gi, and the recently acquired neurotensin receptor-1 (NTSR1) and muscarinic 2 receptor (M2R) bound to arrestin (Arr). Among others, the work demonstrated that the three partner groups, Arrs and Gs- and Gi-proteins, are all structurally and dynamically distinct. Additionally, it was revealed the involvement of different structural motifs in G-protein selective coupling between D1- and D2-like receptors. Having constructed and analyzed 50 models involving DXR, this work represents an unprecedented large-scale analysis of GPCR-intracellular partner interface determinants. All data is available at www.moreiralab.com/resources/dxr.

Sentidos da inclusão de alunos com deficiência na educação superior: olhares a partir da Universidade Federal de Juiz de Fora / Sense of inclusion of students with disabilities in higher education: looks from the Federal University of Juiz de Fora / Sentidos de la inclusión de alumnos con deficiencia en la educación superior: miradas a partir de la Universidad Federal de Juiz de Fora

Esta pesquisa tem como objetivo discutir o processo de inclusão de alunos com deficiência na educação superior brasileira, com especial foco nos sentidos mobilizados por esta inclusão nos discursos ali circulantes. Com caráter exploratório-descritivo, nos valemos da Análise de Discurso na ótica francesa para explorar o processo de produção de sentidos nas estatísticas oficias sobre esta inclusão no Brasil e em uma instituição federal de educação superior, realizando ainda, entrevistas com alunos autodeclarados com deficiência e demais sujeitos que com esses se relacionam no cotidiano universitário. Com as análises empreendidas, identificamos falhas nos dados oficiais sobre a presença de alunos com deficiência na educação superior brasileira, relacionadas tanto a ausência de mecanismos para levantamento desses dados na instituição base, quanto ao não reconhecimento da condição de deficiência por parte dos alunos que a possuem. Já em relação aos sentidos de sua inclusão, esta tem sido avaliada pelos sujeitos da educação superior enquanto presença ou enquanto provimento de condições de acessibilidade arquitetônica, indicando um despreparo e um desconhecimento para o provimento de condições de permanência para este aluno na educação superior, perpetuando barreiras à sua participação em igualdade de condições.

This research aims to discuss the process of inclusion of students with disabilities in Brazilian higher education, with a special focus on the senses mobilized by this inclusion in the circulating discourses. With an exploratory-descriptive character, we use the Discourse Analysis from the French perspective to explore the process of meaning production in the official statistics on this inclusion in Brazil and in a federal institution of higher education, also conducting interviews with self-declared students with disabilities and other subjects that with these are related in the daily life of the university. With the analyzes undertaken, we identified flaws in the official data on the presence of students with disabilities in Brazilian higher education, related both to the absence of mechanisms to collect these data in the base institution, and to the non-recognition of the deficiency condition by students that have. Regarding the meanings of their inclusion, this has been evaluated by the subjects of higher education as a presence or as a provision of architectural accessibility, indicating a lack of preparation and lack of knowledge for the provision of conditions of permanence for this student in higher education, perpetuating barriers to their participation on equal terms.

En esta investigación se tiene como objetivo, discutir el proceso de inclusión de alumnos con deficiencia en la educación superior brasileña, con especial enfoque a los sentidos movilizados por esta inclusión en los discursos allí circulantes. Con carácter exploratorio-descriptivo, nos valemos del Análisis de Discurso en la óptica francesa para explorar el proceso de producción de sentidos en las estadísticas oficias sobre esta inclusión en Brasil y en una institución federal de educación superior, realizando aun, entrevistas con alumnos auto declarados con deficiencia y demás sujetos que con estos se relacionan en el cotidiano universitario. Con los análisis emprendidos, identificamos fallas en los datos oficiales sobre la presencia de alumnos con deficiencia en la educación superior brasileña, relacionadas a ausencia de mecanismos para recopilación de estos datos en la institución base, y, también al no reconocimiento de la condición de deficiencia por parte de los alumnos que la poseen. Ya en relación a los sentidos de su inclusión, esta ha sido evaluada por los sujetos de la educación superior como presencia o como desestime de condiciones de accesibilidad arquitectónica, indicando falta de preparación y desconocimiento para el desestime de condiciones de permanencia para este alumno en la educación superior, perpetuando obstáculos a su participación en igualdad de condiciones.