Evaluating the Margins of Breast Cancer Tumors by Using Digital Breast Tomosynthesis with Deep Learning: A Preliminary Assessment.

BACKGROUND: The assessment information of tumor margins is extremely important for the success of the breast cancer surgery and whether the patient undergoes a second operation. However, conducting surgical margin assessments is a time-consuming task that requires pathology-related skills and equipment, and often cannot be provided in a timely manner. To address this challenge, digital breast tomosynthesis technology was utilized to generate detailed cross-sectional images of the breast tissue and integrate deep learning algorithms for image segmentation, achieving an assessment of tumor margins during surgery. METHODS: this study utilized post-operative tissue samples from 46 patients who underwent breast-conserving treatment, and generated image sets using digital breast tomosynthesis for the training and evaluation of deep learning models. RESULTS: Deep learning algorithms effectively identifying the tumor area. They achieved a Mean Intersection over Union (MIoU) of 0.91, global accuracy of 99%, weighted IoU of 44%, precision of 98%, recall of 83%, F1 score of 89%, and dice coefficient of 93% on the training dataset; for the testing dataset, MIoU was at 83%, global accuracy at 97%, weighted IoU at 38%, precision at 87%, recall rate at 69%, F1 score at 76%, dice coefficient at 86%. CONCLUSIONS: The initial evaluation suggests that the deep learning-based image segmentation method is highly accurate in measuring breast tumor margins. This helps provide information related to tumor margins during surgery, and by using different datasets, this research method can also be applied to the surgical margin assessment of various types of tumors.

Unlocking the Potential of Zebrafish Research with Artificial Intelligence: Advancements in Tracking, Processing, and Visualization.

Zebrafish have become a widely accepted model organism for biomedical research due to their strong cortisol stress response, behavioral strain differences, and sensitivity to both drug treatments and predators. However, experimental zebrafish studies generate substantial data that must be analyzed through objective, accurate, and repeatable analysis methods. Recently, advancements in artificial intelligence (AI) have enabled automated tracking, image recognition, and data analysis, leading to more efficient and insightful investigations. In this review, we examine key AI applications in zebrafish research, including behavior analysis, genomics, and neuroscience. With the development of deep learning technology, AI algorithms have been used to precisely analyze and identify images of zebrafish, enabling automated testing and analysis. By applying AI algorithms in genomics research, researchers have elucidated the relationship between genes and biology, providing a better basis for the development of disease treatments and gene therapies. Additionally, the development of more effective neuroscience tools could help researchers better understand the complex neural networks in the zebrafish brain. In the future, further advancements in AI technology are expected to enable more extensive and in-depth medical research applications in zebrafish, improving our understanding of this important animal model. This review highlights the potential of AI technology in achieving the full potential of zebrafish research by enabling researchers to efficiently track, process, and visualize the outcomes of their experiments.

Improving Breast Cancer Detection and Diagnosis through Semantic Segmentation Using the Unet3+ Deep Learning Framework.

We present an analysis and evaluation of breast cancer detection and diagnosis using segmentation models. We used an advanced semantic segmentation method and a deep convolutional neural network to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images. To improve the segmentation results, we used six models to analyse 309 patients, including 151 benign and 158 malignant tumour images. We compared the Unet3+ architecture with several other models, such as FCN, Unet, SegNet, DeeplabV3+ and pspNet. The Unet3+ model is a state-of-the-art, semantic segmentation architecture that showed optimal performance with an average accuracy of 82.53% and an average intersection over union (IU) of 52.57%. The weighted IU was found to be 89.14% with a global accuracy of 90.99%. The application of these types of segmentation models to the detection and diagnosis of breast cancer provides remarkable results. Our proposed method has the potential to provide a more accurate and objective diagnosis of breast cancer, leading to improved patient outcomes.

The application of artificial intelligence to support biliary atresia screening by ultrasound images: A study based on deep learning models.

PURPOSE: Early confirmation or ruling out biliary atresia (BA) is essential for infants with delayed onset of jaundice. In the current practice, percutaneous liver biopsy and intraoperative cholangiography (IOC) remain the golden standards for diagnosis. In Taiwan, the diagnostic methods are invasive and can only be performed in selective medical centers. However, referrals from primary physicians and local pediatricians are often delayed because of lacking clinical suspicions. Ultrasounds (US) are common screening tools in local hospitals and clinics, but the pediatric hepatobiliary US particularly requires well-trained imaging personnel. The meaningful comprehension of US is highly dependent on individual experience. For screening BA through human observation on US images, the reported sensitivity and specificity were achieved by pediatric radiologists, pediatric hepatobiliary experts, or pediatric surgeons. Therefore, this research developed a tool based on deep learning models for screening BA to assist pediatric US image reading by general physicians and pediatricians. METHODS: De-identified hepatobiliary US images of 180 patients from Taichung Veterans General Hospital were retrospectively collected under the approval of the Institutional Review Board. Herein, the top network models of ImageNet Large Scale Visual Recognition Competition and other network models commonly used for US image recognition were included for further study to classify US images as BA or non-BA. The performance of different network models was expressed by the confusion matrix and receiver operating characteristic curve. There were two methods proposed to solve disagreement by US image classification of a single patient. The first and second methods were the positive-dominance law and threshold law. During the study, the US images of three successive patients suspected to have BA were classified by the trained models. RESULTS: Among all included patients contributing US images, 41 patients were diagnosed with BA by surgical intervention and 139 patients were either healthy controls or had non-BA diagnoses. In this study, a total of 1,976 original US images were enrolled. Among them, 417 and 1,559 raw images were from patients with BA and without BA, respectively. Meanwhile, ShuffleNet achieved the highest accuracy of 90.56% using the same training parameters as compared with other network models. The sensitivity and specificity were 67.83% and 96.76%, respectively. In addition, the undesired false-negative prediction was prevented by applying positive-dominance law to interpret different images of a single patient with an acceptable false-positive rate, which was 13.64%. For the three consecutive patients with delayed obstructive jaundice with IOC confirmed diagnoses, ShuffleNet achieved accurate diagnoses in two patients. CONCLUSION: The current study provides a screening tool for identifying possible BA by hepatobiliary US images. The method was not designed to replace liver biopsy or IOC, but to decrease human error for interpretations of US. By applying the positive-dominance law to ShuffleNet, the false-negative rate and the specificities were 0 and 86.36%, respectively. The trained deep learning models could aid physicians other than pediatric surgeons, pediatric gastroenterologists, or pediatric radiologists, to prevent misreading pediatric hepatobiliary US images. The current artificial intelligence (AI) tool is helpful for screening BA in the real world.

Semantic Segmentation of the Malignant Breast Imaging Reporting and Data System Lexicon on Breast Ultrasound Images by Using DeepLab v3.

In this study, an advanced semantic segmentation method and deep convolutional neural network was applied to identify the Breast Imaging Reporting and Data System (BI-RADS) lexicon for breast ultrasound images, thereby facilitating image interpretation and diagnosis by providing radiologists an objective second opinion. A total of 684 images (380 benign and 308 malignant tumours) from 343 patients (190 benign and 153 malignant breast tumour patients) were analysed in this study. Six malignancy-related standardised BI-RADS features were selected after analysis. The DeepLab v3+ architecture and four decode networks were used, and their semantic segmentation performance was evaluated and compared. Subsequently, DeepLab v3+ with the ResNet-50 decoder showed the best performance in semantic segmentation, with a mean accuracy and mean intersection over union (IU) of 44.04% and 34.92%, respectively. The weighted IU was 84.36%. For the diagnostic performance, the area under the curve was 83.32%. This study aimed to automate identification of the malignant BI-RADS lexicon on breast ultrasound images to facilitate diagnosis and improve its quality. The evaluation showed that DeepLab v3+ with the ResNet-50 decoder was suitable for solving this problem, offering a better balance of performance and computational resource usage than a fully connected network and other decoders.

Incorporating the Breast Imaging Reporting and Data System Lexicon with a Fully Convolutional Network for Malignancy Detection on Breast Ultrasound.

In this study, we applied semantic segmentation using a fully convolutional deep learning network to identify characteristics of the Breast Imaging Reporting and Data System (BI-RADS) lexicon from breast ultrasound images to facilitate clinical malignancy tumor classification. Among 378 images (204 benign and 174 malignant images) from 189 patients (102 benign breast tumor patients and 87 malignant patients), we identified seven malignant characteristics related to the BI-RADS lexicon in breast ultrasound. The mean accuracy and mean IU of the semantic segmentation were 32.82% and 28.88, respectively. The weighted intersection over union was 85.35%, and the area under the curve was 89.47%, showing better performance than similar semantic segmentation networks, SegNet and U-Net, in the same dataset. Our results suggest that the utilization of a deep learning network in combination with the BI-RADS lexicon can be an important supplemental tool when using ultrasound to diagnose breast malignancy.

An improved ChIP-seq peak detection system for simultaneously identifying post-translational modified transcription factors by combinatorial fusion, using SUMOylation as an example.

BACKGROUND: Post-translational modification (PTM) of transcriptional factors and chromatin remodelling proteins is recognized as a major mechanism by which transcriptional regulation occurs. Chromatin immunoprecipitation (ChIP) in combination with high-throughput sequencing (ChIP-seq) is being applied as a gold standard when studying the genome-wide binding sites of transcription factor (TFs). This has greatly improved our understanding of protein-DNA interactions on a genomic-wide scale. However, current ChIP-seq peak calling tools are not sufficiently sensitive and are unable to simultaneously identify post-translational modified TFs based on ChIP-seq analysis; this is largely due to the wide-spread presence of multiple modified TFs. Using SUMO-1 modification as an example; we describe here an improved approach that allows the simultaneous identification of the particular genomic binding regions of all TFs with SUMO-1 modification. RESULTS: Traditional peak calling methods are inadequate when identifying multiple TF binding sites that involve long genomic regions and therefore we designed a ChIP-seq processing pipeline for the detection of peaks via a combinatorial fusion method. Then, we annotate the peaks with known transcription factor binding sites (TFBS) using the Transfac Matrix Database (v7.0), which predicts potential SUMOylated TFs. Next, the peak calling result was further analyzed based on the promoter proximity, TFBS annotation, a literature review, and was validated by ChIP-real-time quantitative PCR (qPCR) and ChIP-reChIP real-time qPCR. The results show clearly that SUMOylated TFs are able to be pinpointed using our pipeline. CONCLUSION: A methodology is presented that analyzes SUMO-1 ChIP-seq patterns and predicts related TFs. Our analysis uses three peak calling tools. The fusion of these different tools increases the precision of the peak calling results. TFBS annotation method is able to predict potential SUMOylated TFs. Here, we offer a new approach that enhances ChIP-seq data analysis and allows the identification of multiple SUMOylated TF binding sites simultaneously, which can then be utilized for other functional PTM binding site prediction in future.

Whole-genome sequencing and identification of Morganella morganii KT pathogenicity-related genes.

BACKGROUND: The opportunistic enterobacterium, Morganella morganii, which can cause bacteraemia, is the ninth most prevalent cause of clinical infections in patients at Changhua Christian Hospital, Taiwan. The KT strain of M. morganii was isolated during postoperative care of a cancer patient with a gallbladder stone who developed sepsis caused by bacteraemia. M. morganii is sometimes encountered in nosocomial settings and has been causally linked to catheter-associated bacteriuria, complex infections of the urinary and/or hepatobiliary tracts, wound infection, and septicaemia. M. morganii infection is associated with a high mortality rate, although most patients respond well to appropriate antibiotic therapy. To obtain insights into the genome biology of M. morganii and the mechanisms underlying its pathogenicity, we used Illumina technology to sequence the genome of the KT strain and compared its sequence with the genome sequences of related bacteria. RESULTS: The 3,826,919-bp sequence contained in 58 contigs has a GC content of 51.15% and includes 3,565 protein-coding sequences, 72 tRNA genes, and 10 rRNA genes. The pathogenicity-related genes encode determinants of drug resistance, fimbrial adhesins, an IgA protease, haemolysins, ureases, and insecticidal and apoptotic toxins as well as proteins found in flagellae, the iron acquisition system, a type-3 secretion system (T3SS), and several two-component systems. Comparison with 14 genome sequences from other members of Enterobacteriaceae revealed different degrees of similarity to several systems found in M. morganii. The most striking similarities were found in the IS4 family of transposases, insecticidal toxins, T3SS components, and proteins required for ethanolamine use (eut operon) and cobalamin (vitamin B12) biosynthesis. The eut operon and the gene cluster for cobalamin biosynthesis are not present in the other Proteeae genomes analysed. Moreover, organisation of the 19 genes of the eut operon differs from that found in the other non-Proteeae enterobacterial genomes. CONCLUSIONS: This is the first genome sequence of M. morganii, which is a clinically relevant pathogen. Comparative genome analysis revealed several pathogenicity-related genes and novel genes not found in the genomes of other members of Proteeae. Thus, the genome sequence of M. morganii provides important information concerning virulence and determinants of fitness in this pathogen.

Genetic copy number variants in myocardial infarction patients with hyperlipidemia.

BACKGROUND: Cardiovascular disease is the chief cause of death in Taiwan and many countries, of which myocardial infarction (MI) is the most serious condition. Hyperlipidemia appears to be a significant cause of myocardial infarction, because it causes atherosclerosis directly. In recent years, copy number variation (CNV) has been analyzed in genomewide association studies of complex diseases. In this study, CNV was analyzed in blood samples and SNP arrays from 31 myocardial infarction patients with hyperlipidemia. RESULTS: We identified seven CNV regions that were associated significantly with hyperlipidemia and myocardial infarction in our patients through multistage analysis (P<0.001), at 1p21.3, 1q31.2 (CDC73), 1q42.2 (DISC1), 3p21.31 (CDCP1), 10q11.21 (RET) 12p12.3 (PIK3C2G) and 16q23.3 (CDH13), respectively. In particular, the CNV region at 10q11.21 was examined by quantitative real-time PCR, the results of which were consistent with microarray findings. CONCLUSIONS: Our preliminary results constitute an alternative method of evaluating the relationship between CNV regions and cardiovascular disease. These susceptibility CNV regions may be used as biomarkers for early-stage diagnosis of hyperlipidemia and myocardial infarction, rendering them valuable for further research and discussion.

AVATAR: a database for genome-wide alternative splicing event detection using large scale ESTs and mRNAs.

UNLABELLED: In the past years, identification of alternative splicing (AS) variants has been gaining momentum. We developed AVATAR, a database for documenting AS using 5,469,433 human EST sequences and 26,159 human mRNA sequences. AVATAR contains 12000 alternative splicing sites identified by mapping ESTs and mRNAs with the whole human genome sequence. AVATAR also contains AS information for 6 eukaryotes. We mapped EST alignment information into a graph model where exons and introns are represented with vertices and edges, respectively. AVATAR can be queried using, (1) gene names, (2) number of identified AS events in a gene, (3) minimal number of ESTs supporting a splicing site, etc. as search parameters. The system provides visualized AS information for queried genes. AVAILABILITY: The database is available for free at http://avatar.iecs.fcu.edu.tw/

Mining colon cancer specific alternative splicing in EST database.

Among 75218 splicing sites, 137 colon cancer specific alternative splicing isoforms were found by mining EST database. Alternative splicing database were first constructed by aligning EST to genomic sequence. Numbers of ESTs from normal or cancer colon tissue supporting splicing isoform at each splicing site were then queried and analyzed with Fisher exact test. There were 53 3' splicing, 42 5' splicing, 40 exon skipping and 2 mutual exclusive cancer specific splicing isoforms.