A5057141769- Ovarian cancer diagnosis and treatment
- Fetal and Pediatric Neurological Disorders
- Artificial Intelligence in Healthcare and Education
- Epigenetics and DNA Methylation
- Histone Deacetylase Inhibitors Research
- Advanced Neural Network Applications
- Autopsy Techniques and Outcomes
- COVID-19 diagnosis using AI
- Peptidase Inhibition and Analysis
- Radiomics and Machine Learning in Medical Imaging
- Congenital Heart Disease Studies
- Medical Image Segmentation Techniques
- Radiation Dose and Imaging
- Intraperitoneal and Appendiceal Malignancies
- Cancer-related molecular mechanisms research
- Machine Learning in Healthcare
- Genomics and Chromatin Dynamics
- Cancer Mechanisms and Therapy
- AI in cancer detection
- Lung Cancer Diagnosis and Treatment
- FOXO transcription factor regulation
- Cancer-related Molecular Pathways
- Congenital Diaphragmatic Hernia Studies
- Ultrasound in Clinical Applications
- Hippo pathway signaling and YAP/TAZ
Keio University Hospital
2020-2022
National Cancer Centre Japan
2022
Keio University
2019-2021
Artificial Intelligence (AI) technologies have recently been applied to medical imaging for diagnostic support. With respect fetal ultrasound screening of congenital heart disease (CHD), it is still challenging achieve consistently accurate diagnoses owing its manual operation and the technical differences among examiners. Hence, we proposed an architecture Supervised Object detection with Normal data Only (SONO), based on a convolutional neural network (CNN), detect cardiac substructures...
Diagnostic support tools based on artificial intelligence (AI) have exhibited high performance in various medical fields. However, their clinical application remains challenging because of the lack explanatory power AI decisions (black box problem), making it difficult to build trust with professionals. Nevertheless, visualizing internal representation deep neural networks will increase and improve confidence professionals decisions. We propose a novel learning-based explainable “graph chart...
Image segmentation is the pixel-by-pixel detection of objects, which most challenging but informative in fundamental tasks machine learning including image classification and object detection. Pixel-by-pixel required to apply support fetal cardiac ultrasound screening; we have detect substructures precisely are small change shapes dynamically with heartbeats, such as ventricular septum. This task difficult for general methods DeepLab v3+, U-net. Hence, here proposed a novel method named...
The application of segmentation methods to medical imaging has the potential create novel diagnostic support models. With respect fetal ultrasound, thoracic wall is a key structure on assessment chest region for examiners recognize relative orientation and size structures inside thorax, which are critical components in neonatal prognosis. In this study, improve performance ultrasound videos, we proposed model-agnostic method using deep learning techniques: Multi-Frame + Cylinder (MFCY)....
Acoustic shadows are common artifacts in medical ultrasound imaging. The caused by objects that reflect such as bones, and they shown dark areas images. Detecting is crucial for assessing the quality of This will be a pre-processing further image processing or recognition aiming computer-aided diagnosis. In this paper, we propose an auto-encoding structure estimates shadowed their intensities. model once splits input into estimated shadow shadow-free through its encoder decoder. Then, it...
Abstract High-grade serous ovarian carcinoma (HGSOC) is the most aggressive gynecological malignancy, resulting in approximately 70% of cancer deaths. However, it still unclear how genetic dysregulations and biological processes generate malignant subtype HGSOC. Here we show that expression levels microtubule affinity-regulating kinase 3 ( MARK3 ) are downregulated HGSOC, its downregulation significantly correlates with poor prognosis HGSOC patients. overexpression suppresses cell...
Ovarian clear cell carcinoma (OCCC) has a poor prognosis, and its therapeutic strategy not been established. PRELP is leucine-rich repeat protein in the extracellular matrix of connective tissues. Although anchors basement membrane to tissue absent most epithelial cancers, much remains unknown regarding function as regulator ligand-mediated signaling pathways. Here, we obtained sets differentially expressed genes by expression using OCCC lines. We found that more than 1000 were significantly...
Proline/arginine-rich end leucine-rich repeat protein (PRELP) is a member of the small proteoglycan family extracellular matrix proteins, which markedly suppressed in majority early-stage epithelial cancers and plays role regulating epithelial-mesenchymal transition by altering cell-cell adhesion. Although PRELP an important factor development progression bladder cancer, mechanism gene repression remains unclear.Here, we show that mRNA expression cancer cells alleviated HDAC inhibitors...
Although chromatin immunoprecipitation and next-generation sequencing (ChIP-seq) using formalin-fixed paraffin-embedded tissue (FFPE) has been reported, it remained elusive whether they retained accurate transcription factor binding. Here, we developed a method to identify the binding sites of insulator CTCF genome-wide distribution histone modifications involved in transcriptional activation. Importantly, provide evidence that ChIP-seq datasets obtained from FFPE samples are similar or even...
Abstract High-grade serous ovarian carcinoma (HGSOC) is the most lethal gynecological malignancy. To date, profiles of gene mutations and copy number alterations in HGSOC have been well characterized. However, patterns epigenetic transcription factor dysregulation not yet fully elucidated. In this study, we performed integrative omics analyses a series stepwise model cells originating from human fallopian tube secretory epithelial (HFTSECs) to investigate early tumorigenesis. Assay for...
Abstract Objective this prospective cohort study aimed to assess the safety and efficacy of bevacizumab combined with chemotherapy in Japanese patients relapsed ovarian, fallopian tube or primary peritoneal cancer. Methods study, 40 cancer selected receive were enrolled. Patients poor general condition excluded. Each patient was monitored prospectively for adverse events, administration status, disease status survival. Treatment continued until intolerable events progression. The endpoint...
The abnormal findings of the fetal cardiothoracic area ratio (CTAR) and cardiac axis (CA) are manifested as a result various factors such heart dysfunction compensatory state. Therefore, these indexes convenient highly useful for primary screening. We have been developing artificial intelligence (AI) powered diagnostic support technologies ultrasound. In this study, we constructed deep learning-based model that automatically measures above in cross-section with four-chamber view (4CV)...