Opening the Black Box: Spatial Transcriptomics and the Relevance of Artificial Intelligence-Detected Prognostic Regions in High-Grade Serous Carcinoma.

Image-based deep learning models are used to extract new information from standard hematoxylin and eosin pathology slides; however, biological interpretation of the features detected by artificial intelligence (AI) remains a challenge. High-grade serous carcinoma of the ovary (HGSC) is characterized by aggressive behavior and chemotherapy resistance, but also exhibits striking variability in outcome. Our understanding of this disease is limited, partly due to considerable tumor heterogeneity. We previously trained an AI model to identify HGSC tumor regions that are highly associated with outcome status but are indistinguishable by conventional morphologic methods. Here, we applied spatially resolved transcriptomics to further profile the AI-identified tumor regions in 16 patients (8 per outcome group) and identify molecular features related to disease outcome in patients who underwent primary debulking surgery and platinum-based chemotherapy. We examined formalin-fixed paraffin-embedded tissue from (1) regions identified by the AI model as highly associated with short or extended chemotherapy response, and (2) background tumor regions (not identified by the AI model as highly associated with outcome status) from the same tumors. We show that the transcriptomic profiles of AI-identified regions are more distinct than background regions from the same tumors, are superior in predicting outcome, and differ in several pathways including those associated with chemoresistance in HGSC. Further, we find that poor outcome and good outcome regions are enriched by different tumor subpopulations, suggesting distinctive interaction patterns. In summary, our work presents proof of concept that AI-guided spatial transcriptomic analysis improves recognition of biologic features relevant to patient outcomes.

Increased MIB-1 expression in salivary gland pleomorphic adenoma that recurs and undergoes malignant transformation.

The objective of this retrospective study was to explore possible changes in histopathological features and expression of cyclin D1 and MIB-1 in salivary gland pleomorphic adenoma (PA) that recur or undergo malignant transformation. Knowledge of these characteristics might help to guide the management of these rare tumors. The histopathology and immunohistochemical staining characteristics of such tumors were analyzed in a cohort of 65 patients constituting three different groups of tumors: PA, recurrent pleomorphic adenoma (RPA) and carcinoma ex PA (CxPA). The RPAs were divided into two subgroups: primary PA that were known to recur later (PA-prim) and recurrent tumors appearing after a primary tumor (PA-rec). RPAs and CxPAs were compared with PAs without recurrence, which served as a control group. In our study, CxPA and PA-rec, but not PA-prim, showed increased MIB-1 expression compared with the control group. Neither cyclin D1 expression nor any histopathological features showed any association in statistical analyses. CxPA showed increased mitotic activity, squamous metaplasia, and nuclear atypia. Tumor multifocality was more frequent in PA-rec and CxPA. The different MIB-1 expression in CxPA and PA-rec in comparison to PA-prim suggests that the changes in expression could develop after the primary tumor.

Artificial intelligence-based image analysis can predict outcome in high-grade serous carcinoma via histology alone.

High-grade extrauterine serous carcinoma (HGSC) is an aggressive tumor with high rates of recurrence, frequent chemotherapy resistance, and overall 5-year survival of less than 50%. Beyond determining and confirming the diagnosis itself, pathologist review of histologic slides provides no prognostic or predictive information, which is in sharp contrast to almost all other carcinoma types. Deep-learning based image analysis has recently been able to predict outcome and/or identify morphology-based representations of underlying molecular alterations in other tumor types, such as colorectal carcinoma, lung carcinoma, breast carcinoma, and melanoma. Using a carefully stratified HGSC patient cohort consisting of women (n = 30) with similar presentations who experienced very different treatment responses (platinum free intervals of either ≤ 6 months or ≥ 18 months), we used whole slide images (WSI, n = 205) to train a convolutional neural network. The neural network was trained, in three steps, to identify morphologic regions (digital biomarkers) that are highly associating with one or the other treatment response group. We tested the classifier using a separate 22 slide test set, and 18/22 slides were correctly classified. We show that a neural network based approach can discriminate extremes in patient response to primary platinum-based chemotherapy with high sensitivity (73%) and specificity (91%). These proof-of-concept results are novel, because for the first time, prospective prognostic information is identified specifically within HGSC tumor morphology.

Thyroid pathology in PTEN-hamartoma tumor syndrome: characteristic findings of a distinct entity.

BACKGROUND: Phosphatase and tensin homolog deleted on chromosome ten (PTEN)-hamartoma tumor syndrome (PHTS) is a complex disorder caused by germline inactivating mutations of the PTEN tumor suppressor gene. PHTS includes Cowden syndrome (CS), Bannayan-Riley-Ruvalcaba syndrome (BRRS), and Proteus-like syndromes. Affected individuals develop both benign and malignant tumors in a variety of tissues, including the thyroid. This study is to better characterize and describe the thyroid pathology within the different entities of this syndrome, and examine whether there is an association between specific thyroid findings and different PTEN mutations. METHODS: Twenty patients with known PTEN mutations, and/or clinical diagnosis of PHTS, and thyroid pathology were identified: 14 with CS and 6 with BRRS. RESULTS: Thyroid pathology findings were as follows: multiple adenomatous nodules in a background of lymphocytic thyroiditis (LT) in 75%, papillary carcinoma in 60%, LT alone in 55%, follicular carcinoma in 45%, C-cell hyperplasia in 55%, and follicular adenomas in 25%. Within the papillary carcinoma group, there were 6 microcarcinomas, 5 follicular variants, and 1 classical type. CONCLUSIONS: There were no morphologic differences between the thyroid findings in CS and BRRS. Also, there was no correlation between specific PTEN germline mutations (exons 5, 6, and 8) and pathologic findings. Distinctive and characteristic findings in PHTS include multiple unique adenomatous nodules in a background of LT, and C-cell hyperplasia; it is vital that pathologists recognize the classical histologic features of this syndrome to alert clinicians to the possibility of this syndrome in their patients.