Publications by authors named "Chiew Seow Fan"
The human epidermal growth factor receptor 2 (HER2) gene is a critical biomarker for determining amplification status and targeting clinical therapies in breast cancer treatment. This study introduces a computer-aided method that automatically measures and scores HER2 gene status from invasive tissue regions of breast cancer using whole slide images (WSI) through silver hybridization (SISH) staining. Image processing and deep learning techniques are employed to isolate untruncated and non-overlapping single nuclei from cancer regions.
View Article and Find Full Text PDFArticle Synopsis
- Triple-negative breast cancer (TNBC) is challenging to treat due to poor prognosis and lack of effective therapies; targeting PD-L1 may offer potential benefits.
- A study in Malaysia involved 138 advanced TNBC patients, assessing PD-L1 positivity using tissue samples.
- Results showed 37.7% had positive PD-L1 expression, with a notable association between PD-L1 positivity and resected tumor samples.
Article Synopsis
- Fluorescence in situ hybridization (FISH) is the standard method for checking HER2 status in breast cancer, but it has downsides like needing special training and facing signal degradation; an alternative method, silver-enhanced in situ hybridization (SISH), offers a more durable solution for analysis via bright-field microscopy.* -
- This study introduces a novel deep learning approach to classify Normal, Amplified, and Non-Amplified regions in HER2-SISH whole slide images, aiming to improve accuracy over traditional methods.* -
- Using a private dataset, the researchers achieved a striking 99.9% patch-level accuracy and an average accuracy of 98% through k-fold cross-validation, suggesting that this deep
Recent advancements in medical imaging have greatly enhanced the application of computational techniques in digital pathology, particularly for the classification of breast cancer using in situ hybridization (ISH) imaging. HER2 amplification, a key prognostic marker in 20-25% of breast cancers, can be assessed through alterations in gene copy number or protein expression. However, challenges persist due to the heterogeneity of nuclear regions and complexities in cancer biomarker detection.
View Article and Find Full Text PDFObjectives: Accurate subtyping of breast cancer is crucial for its diagnosis, management, and prognostication. This study aimed to determine the association of magnetic resonance imaging (MRI) breast features with the molecular subtype and aggressiveness of breast cancer in a multi-ethnic population.
Methods: Treatment-naive patients with invasive breast carcinoma were included in this retrospective study.
Breast cancer is one of the most common cancers in Malaysia. Recently, a new nomenclature was introduced for breast cancers with human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) 1+, or 2+ with negative in situ hybridization (ISH), i.e.
View Article and Find Full Text PDFObjective: To assess the association between breast cancer tumour stroma and magnetic resonance imaging (MRI) features.
Materials And Methods: A total of 84 patients with treatment-naïve invasive breast cancer were enrolled into this retrospective study. The tumour stroma ratio (TSR) was estimated from the amount of tumour stroma in the pathology specimen of the breast tumour.
Pilomatricoma, also known as Pilamatrixoma or Malherbe's calcifying epithelioma, is a benign skin tumour with a bimodal age distribution between the paediatric and elderly age groups. Although it was previously thought to be rare, recent studies have revealed that it is quite common. Typically, pilomatricoma is diagnosed following histopathological examination of the lesion as it is frequently misdiagnosed with other types of skin pathology.
View Article and Find Full Text PDF