Publications by authors named "H S Muti"
Article Synopsis
- Homologous recombination deficiency (HRD) is a key biomarker for predicting which cancer patients might respond to PARP inhibitors, but testing for HRD is complex.* -
- The researchers created a deep learning pipeline using attention-weighted multiple instance learning (attMIL) to predict HRD status from routine histology images, achieving varying accuracy rates across different cancer types.* -
- Results showed that HRD can be predicted directly from histology slides for multiple cancers, with the model demonstrating promising accuracy, particularly for endometrial, pancreatic, and lung cancers.*
Background: Tumor-Adipose-Feature (TAF) as well as SARIFA (Stroma AReactive Invasion Front Areas) are two histologic features/biomarkers linking tumor-associated adipocytes to poor outcomes in colorectal cancer (CRC) patients. Whereas TAF was identified by deep learning (DL) algorithms, SARIFA was established as a human-observed histopathologic biomarker.
Methods: To study the overlap between TAF and SARIFA, we performed a systematic pathological review of TAF based on all published image tiles.
Latent diffusion models (LDMs) have emerged as a state-of-the-art image generation method, outperforming previous Generative Adversarial Networks (GANs) in terms of training stability and image quality. In computational pathology, generative models are valuable for data sharing and data augmentation. However, the impact of LDM-generated images on histopathology tasks compared to traditional GANs has not been systematically studied.
View Article and Find Full Text PDFDeep Learning (DL) can predict biomarkers from cancer histopathology. Several clinically approved applications use this technology. Most approaches, however, predict categorical labels, whereas biomarkers are often continuous measurements.
View Article and Find Full Text PDF