Improved PAA algorithm for breast mass detection in mammograms.

Mammography screening is instrumental in the early detection and diagnosis of breast cancer by identifying masses in mammograms. With the rapid development of deep learning, numerous deep learning-based object detection algorithms have been explored for mass detection studies. However, these methods often yield a high false positive rate per image (FPPI) while achieving a high true positive rate (TPR). To maintain a higher TPR while also ensuring lower FPPI, we improved the Probability Anchor Assignment (PAA) algorithm to enhance the detection capability for mammographic characteristics with our previous work. We considered three dimensions: the backbone network, feature fusion module, and dense detection heads. The final experiment showed the effectiveness of the proposed method, and the TPR/FPPI values of the final improved PAA algorithm were 0.96/0.56 on the INbreast datasets. Compared to other methods, our method stands distinguished with its effectiveness in addressing the imbalance between positive and negative classes in cases of single lesion detection.

Naringenin restricts the colonization and growth of Ralstonia solanacearum in tobacco mutant KCB-1.

Bacterial wilt severely jeopardizes plant growth and causes enormous economic loss in the production of many crops, including tobacco (Nicotiana tabacum). Here, we first demonstrated that the roots of bacterial wilt-resistant tobacco mutant KCB-1 can limit the growth and reproduction of Ralstonia solanacearum. Secondly, we demonstrated that KCB-1 specifically induced an upregulation of naringenin content in root metabolites and root secretions. Further experiments showed that naringenin can disrupt the structure of R. solanacearum, inhibit the growth and reproduction of R. solanacearum, and exert a controlling effect on bacterial wilt. Exogenous naringenin application activated the resistance response in tobacco by inducing the burst of reactive oxygen species and salicylic acid deposition, leading to transcriptional reprogramming in tobacco roots. Additionally, both external application of naringenin in CB-1 and overexpression of the Nicotiana tabacum chalcone isomerase (NtCHI) gene, which regulates naringenin biosynthesis, in CB-1 resulted in a higher complexity of their inter-root bacterial communities than in untreated CB-1. Further analysis showed that naringenin could be used as a marker for resistant tobacco. The present study provides a reference for analyzing the resistance mechanism of bacterial wilt-resistant tobacco and controlling tobacco bacterial wilt.

Breast cancer detection and classification in mammogram using a three-stage deep learning framework based on PAA algorithm.

In recent years, deep learning has been used to develop an automatic breast cancer detection and classification tool to assist doctors. In this paper, we proposed a three-stage deep learning framework based on an anchor-free object detection algorithm, named the Probabilistic Anchor Assignment (PAA) to improve diagnosis performance by automatically detecting breast lesions (i.e., mass and calcification) and further classifying mammograms into benign or malignant. Firstly, a single-stage PAA-based detector roundly finds suspicious breast lesions in mammogram. Secondly, we designed a two-branch ROI detector to further classify and regress these lesions that aim to reduce the number of false positives. Besides, in this stage, we introduced a threshold-adaptive post-processing algorithm with dense breast information. Finally, the benign or malignant lesions would be classified by an ROI classifier which combines local-ROI features and global-image features. In addition, considering the strong correlation between the task of detection head of PAA and the task of whole mammogram classification, we added an image classifier that utilizes the same global-image features to perform image classification. The image classifier and the ROI classifier jointly guide to enhance the feature extraction ability and further improve the performance of classification. We integrated three public datasets of mammograms (CBIS-DDSM, INbreast, MIAS) to train and test our model and compared our framework with recent state-of-the-art methods. The results show that our proposed method can improve the diagnostic efficiency of radiologists by automatically detecting and classifying breast lesions and classifying benign and malignant mammograms.

SALIS transcriptionally represses IGFBP3/Caspase-7-mediated apoptosis by associating with STAT5A to promote hepatocellular carcinoma.

Hepatocellular carcinoma (HCC) is the most common subtype of liver cancer and the second most fatal cancer in the world despite the great therapeutic advances in the past two decades, which reminds us of the gap in fully understanding the oncogenic mechanism of HCC. To explore the key factors contributing to the progression of HCC, we identified a LncRNA, termed SALIS (Suppression of Apoptosis by LINC01186 Interacting with STAT5A), functions in promoting the proliferation, colony formation, migration and invasion while suppressing apoptosis in HCC cells. Mechanistic study indicated SALIS physically associates with transcription factor STAT5A and binds to the promoter regions of IGFBP3 and Caspase-7 to transcriptionally repress their expression and further inhibit apoptosis. Our findings identified SALIS as an oncogene to promote HCC by physically binding with STAT5A to inhibit the expression of pro-apoptotic IGFBP3 and Caspase-7, which suggests novel therapeutic targets for HCC treatments.