Highly accurate and effective deep neural networks in pathological diagnosis of prostate cancer.

PURPOSE: To established an AI system to make the pathological diagnosis of prostate cancer. METHODS: Prostate histopathological whole mount (WM) sections from patients underwent robot-assisted laparoscopic prostatectomy were prepared. All the prostate WM pathological sections were converted to digital image data and marked with different colors on the basis of the ISUP Gleason grade group. The image was then fed into a segmentation algorithm. We chose modified U-Net as our fundamental network architecture. RESULTS: 172 patients were involved in this study. 896 pieces of prostate WM pathological sections from 160 patients, in which 826 pieces of WM sections from 148 patients were assigned to the training set randomly. After image segmentation there were totally 2,138,895 patches, of which 1,646,535 patches were valid for training. The other WM section was arranged for testing. Based on the whole image testing, AI and pathologists presented the same answers among 21 of 22 pieces of sections. To evaluate the diagnostic results at the pixel level, we anticipated correct cancer or non-cancer diagnose from this AI system. The area under the ROC curve as 96.8%. The value of pixel accuracy of three methods (binary analysis, clinically oriented analysis and analysis for different ISUP Gleason grade) were 96.93%, 95.43% and 93.88%, respectively. The value of frequency weighted IoU were 94.32%, 92.13% and 90.21%, respectively. CONCLUSIONS: This AI system is able to assist pathologists to make a final diagnosis, indicating the great potential and a wide-range of applications of AI in the medical field.

The composition and diversity of arbuscular mycorrhizal fungi in karst soils and roots collected from mulberry of different ages / Composição e diversidade de fungos micorrízicos arbusculares em solos cársticos e raízes de amoreira de diferentes idades

ABSTRACT: Arbuscular mycorrhizal fungi (AMF) have been attracted more scientific attentions due to its critical role in enhancement of drought tolerance of plants for growth and vegetation restoration in karst fragile ecosystem. However, scientists know little about the AMF composition and diversity occurring in root systems of mulberry (Morus sp.), and in karst habitats which return land use from mulberry forestry, as well as the effects of soil environment change on the diversity of the AMF communities. To understand: (1) the AMF community composition and diversity at different stage of returning cropland to forest; and (2) the effects of soil environment change on the diversity of the AMF communities, soil and mulberry root samples were collected from Bijie and Libo sites, China, which experienced one and ten years, respectively, after returning croplands to forest. With the high throughput 454-sequencing technology, 8 known genera including 83 virtual species were distinguished and the genera Glomus, Paraglomus, Archaeospora and Diversispora were found to be dominant in soil and root sample. Compared to the samples in Libo, the genera Glomus, Paraglomus, Acaulospora and Claroideoglomus in root samples at Bijie site had a relatively abundance of species indicating that the returning cropland to forest is benefit to the AMF diversity and abundance, which was attribute to the variation of soil physiochemical properties. This conclusion is of great significance for guiding the return of farmland to forests.

RESUMO: Fungos micorrízicos arbusculares (FMA) tem atraído atenções de cientistas devido ao seu papel fundamental no crescimento e na restauração da vegetação de ecossistemas frágeis. No entanto, o conhecimento da composição e da diversidade da FMA em habitats cársticos e que retornem da agricultura para a silvicultura é limitado. Para entender: (1) a composição da Comunidade FMA e diversidade em fase diferente de retornar cultivo para a floresta; e (2) os efeitos da mudança do ambiente do solo sobre a diversidade das comunidades FMA, mostras de solo e de raiz de amoreira (Morus sp.) foram coletadas em Bijie e Libo, China, após um e dez anos de retorno ao cultivo dessa espécie, respectivamente, em sequência ao cultivo agrícola. Utilizando análise molecular e sequenciamento genético, constatou-se oito gêneros conhecidos e a distincão de oitenta e três espécies de FMA. Os gêneros Glomus, Paraglomus, Archaeospora e Diversispora foram dominantes, em solo e raízes. Em comparação as amostras de Libo, os gêneros Glomus, Paraglomus, Acaulospora e Claroideoglomus foram relativamente abundante nas raízes coletadas em Bijie, indicando que o retorno de uma área agrícola para o cultivo de amoreira é benéfico para a diversidade dos FMA, o que é atribuído as propriedades físico-químicas do solo. Essa conclusão é de grande importância para avaliar os efeitos do tipo de uso agrícola na microbiologia do solo.