A whole-slide foundation model for digital pathology from real-world data.

Digital pathology poses unique computational challenges, as a standard gigapixel slide may comprise tens of thousands of image tiles1-3. Prior models have often resorted to subsampling a small portion of tiles for each slide, thus missing the important slide-level context4. Here we present Prov-GigaPath, a whole-slide pathology foundation model pretrained on 1.3 billion 256 × 256 pathology image tiles in 171,189 whole slides from Providence, a large US health network comprising 28 cancer centres. The slides originated from more than 30,000 patients covering 31 major tissue types. To pretrain Prov-GigaPath, we propose GigaPath, a novel vision transformer architecture for pretraining gigapixel pathology slides. To scale GigaPath for slide-level learning with tens of thousands of image tiles, GigaPath adapts the newly developed LongNet5 method to digital pathology. To evaluate Prov-GigaPath, we construct a digital pathology benchmark comprising 9 cancer subtyping tasks and 17 pathomics tasks, using both Providence and TCGA data6. With large-scale pretraining and ultra-large-context modelling, Prov-GigaPath attains state-of-the-art performance on 25 out of 26 tasks, with significant improvement over the second-best method on 18 tasks. We further demonstrate the potential of Prov-GigaPath on vision-language pretraining for pathology7,8 by incorporating the pathology reports. In sum, Prov-GigaPath is an open-weight foundation model that achieves state-of-the-art performance on various digital pathology tasks, demonstrating the importance of real-world data and whole-slide modelling.

Shikonin selectively induces apoptosis in human prostate cancer cells through the endoplasmic reticulum stress and mitochondrial apoptotic pathway.

BACKGROUND: Despite the recent progress in screening and therapy, a majority of prostate cancer cases eventually attain hormone refractory and chemo-resistant attributes. Conventional chemotherapeutic strategies are effective at very high doses for only palliative management of these prostate cancers. Therefore chemo-sensitization of prostate cancer cells could be a promising strategy for increasing efficacy of the conventional chemotherapeutic agents in prostate cancer patients. Recent studies have indicated that the chemo-preventive natural agents restore the pro-apoptotic protein expression and induce endoplasmic reticulum stress (ER stress) leading to the inhibition of cellular proliferation and activation of the mitochondrial apoptosis in prostate cancer cells. Therefore reprogramming ER stress-mitochondrial dependent apoptosis could be a potential approach for management of hormone refractory chemoresistant prostate cancers. We aimed to study the effects of the natural naphthoquinone Shikonin in human prostate cancer cells. RESULTS: The results indicated that Shikonin induces apoptosis in prostate cancer cells through the dual induction of the endoplasmic reticulum stress and mitochondrial dysfunction. Shikonin induced ROS generation and activated ER stress and calpain activity. Moreover, addition of antioxidants attenuated these effects. Shikonin also induced the mitochondrial apoptotic pathway mediated through the enhanced expression of the pro-apoptotic Bax and inhibition of Bcl-2, disruption of the mitochondrial membrane potential (MMP) followed by the activation of caspase-9, caspase-3, and PARP cleavage. CONCLUSION: The results suggest that shikonin could be useful in the therapeutic management of hormone refractory prostate cancers due to its modulation of the pro-apoptotic ER stress and mitochondrial apoptotic pathways.