Registered multi-device/staining histology image dataset for domain-agnostic machine learning models.

Variations in color and texture of histopathology images are caused by differences in staining conditions and imaging devices between hospitals. These biases decrease the robustness of machine learning models exposed to out-of-domain data. To address this issue, we introduce a comprehensive histopathology image dataset named PathoLogy Images of Scanners and Mobile phones (PLISM). The dataset consisted of 46 human tissue types stained using 13 hematoxylin and eosin conditions and captured using 13 imaging devices. Precisely aligned image patches from different domains allowed for an accurate evaluation of color and texture properties in each domain. Variation in PLISM was assessed and found to be significantly diverse across various domains, particularly between whole-slide images and smartphones. Furthermore, we assessed the improvement in domain shift using a convolutional neural network pre-trained on PLISM. PLISM is a valuable resource that facilitates the precise evaluation of domain shifts in digital pathology and makes significant contributions towards the development of robust machine learning models that can effectively address challenges of domain shift in histological image analysis.

Restaining-based annotation for cancer histology segmentation to overcome annotation-related limitations among pathologists.

Numerous cancer histopathology specimens have been collected and digitized over the past few decades. A comprehensive evaluation of the distribution of various cells in tumor tissue sections can provide valuable information for understanding cancer. Deep learning is suitable for achieving these goals; however, the collection of extensive, unbiased training data is hindered, thus limiting the production of accurate segmentation models. This study presents SegPath-the largest annotation dataset (>10 times larger than publicly available annotations)-for the segmentation of hematoxylin and eosin (H&E)-stained sections for eight major cell types in cancer tissue. The SegPath generating pipeline used H&E-stained sections that were destained and subsequently immunofluorescence-stained with carefully selected antibodies. We found that SegPath is comparable with, or outperforms, pathologist annotations. Moreover, annotations by pathologists are biased toward typical morphologies. However, the model trained on SegPath can overcome this limitation. Our results provide foundational datasets for machine-learning research in histopathology.

Functional genomics screening identifies aspartyl-tRNA synthetase as a novel prognostic marker and a therapeutic target for gastric cancers.

Efficient molecular targeting therapies for most gastric cancers (GCs) are currently lacking, despite GC being one of the most frequent and often devastating malignancies worldwide. Thus, identification of novel therapeutic targets for GC is in high demand. Recent advancements of high-throughput nucleic acid synthesis methods combined with next-generation sequencing (NGS) platforms have made it feasible to conduct functional genomics screening using large-scale pooled lentiviral libraries aimed at discovering novel cancer therapeutic targets. In this study, we performed NGS-based functional genomics screening for human GC cell lines using an originally constructed 6,399 shRNA library targeting all 2,096 human metabolism genes. Our screening identified aspartyl-tRNA synthetase (DARS) as a possible candidate for a therapeutic target for GC. In-house tissue microarrays containing 346 cases of GC combined with public datasets showed that patients with high expression levels of DARS protein exhibited more advanced clinicopathologic parameters and a worse prognosis, specifically among diffuse-type GC patients. Both in vitro and in vivo experiments concretely evidenced that DARS inhibition achieved robust growth suppression of GC cells. Moreover, RNA sequencing of GC cell lines under shRNA-mediated DARS knockdown suggested that DARS inhibition exerts its effect through the inactivation of multiple p-ERK pathways. This MAPK-related growth suppression by DARS inhibition would also be applicable to other cancers; thus, it is warranted to investigate the expression and clinical significance of DARS in a wide spectrum of malignancies. Taken together, NGS-based high-throughput pooled lentiviral screening showed DARS as a novel prognostic marker and a promising therapeutic target for GC. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Universal encoding of pan-cancer histology by deep texture representations.

Cancer histological images contain rich biological and clinical information, but quantitative representation can be problematic and has prevented the direct comparison and accumulation of large-scale datasets. Here, we show successful universal encoding of cancer histology by deep texture representations (DTRs) produced by a bilinear convolutional neural network. DTR-based, unsupervised histological profiling, which captures the morphological diversity, is applied to cancer biopsies and reveals relationships between histologic characteristics and the response to immune checkpoint inhibitors (ICIs). Content-based image retrieval based on DTRs enables the quick retrieval of histologically similar images using The Cancer Genome Atlas (TCGA) dataset. Furthermore, via comprehensive comparisons with driver and clinically actionable gene mutations, we successfully predict 309 combinations of genomic features and cancer types from hematoxylin-and-eosin-stained images. With its mounting capabilities on accessible devices, such as smartphones, universal encoding for cancer histology has a strong impact on global equalization for cancer diagnosis and therapies.

Rectal cancer developing from an anastomotic site 18 years after resection due to intussusception caused by Peutz-Jeghers polyposis in a 31-year-old man: a case report.

BACKGROUND: Peutz-Jeghers syndrome (PJS) is an autosomal dominant disorder characterized by hamartomatous polyposis of the gastrointestinal tract. It is associated with a high risk of malignancy in the gastrointestinal tract, as well as in other organs. We report a case of colon cancer at the anastomotic site that occurred 18 years after high anterior resection of the rectum for intussusception caused by Peutz-Jeghers polyposis. CASE PRESENTATION: A 31-year-old man with PJS, who had undergone high anterior resection of the rectum for intussusception at the age of 12, presented to our hospital complaining of hematochezia. Colonoscopy revealed a hemorrhagic tumor protruding from the anastomotic site, which was histologically diagnosed as an adenocarcinoma. We performed a low anterior resection of the rectum including the anastomotic site, with combined resection of the strongly adherent ileum. Histological examination revealed that the adenocarcinoma had developed from the submucosal area, where the normal rectal mucosa had been incorporated into the stromal and bone tissues, resulting in heterotopic ossification in the anastomotic region. These findings suggested that the reconstructive surgical procedure or postoperative complications, such as anastomotic leakage, had formed the cavity where the cancer had developed. CONCLUSIONS: We concluded that the cancer might be derived from the rectal mucosa with malignant potential that was present in the anastomotic region and exacerbated by the presence of chronic inflammation in the cavity after the patient's initial operation.

The Significant Antitumor Activity of Nivolumab in Lung Adenocarcinoma with Choriocarcinomatous Features.

We report the case of a 60-year-old Japanese man with a metastatic brain tumor that caused ataxia. As a consequence of resection of a cerebellar tumor, the tumor was diagnosed as a poorly differentiated adenocarcinoma with choriocarcinomatous features. The patient underwent bronchoscopy, leading to a diagnosis of the same histology as the brain tumor. After the administration of first-line chemotherapy and maintenance therapy due to progressive disease, he was given nivolumab and obtained a partial response; however, 11-months later, computed tomography showed tumor progression. Our experience suggests that nivolumab has strong activity, even in patients with a rare form of lung cancer.