Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge.

Purpose: Clinicians rely on imaging features to calculate complexity of renal masses based on validated scoring systems. These scoring methods are labor-intensive and are subjected to interobserver variability. Artificial intelligence has been increasingly utilized by the medical community to solve such issues. However, developing reliable algorithms is usually time-consuming and costly. We created an international community-driven competition (KiTS19) to develop and identify the best system for automatic segmentation of kidneys and kidney tumors in contrast CT and report the results. Methods: A training and test set of CT scans that was manually annotated by trained individuals were generated from consecutive patients undergoing renal surgery for whom demographic, clinical and outcome data were available. The KiTS19 Challenge was a machine learning competition hosted on grand-challenge.org in conjunction with an international conference. Teams were given 3 months to develop their algorithm using a full-annotated training set of images and an unannotated test set was released for 2 weeks from which average Sørensen-Dice coefficient between kidney and tumor regions were calculated across all 90 test cases. Results: There were 100 valid submissions that were based on deep neural networks but there were differences in pre-processing strategies, architectural details, and training procedures. The winning team scored a 0.974 kidney Dice and a 0.851 tumor Dice resulting in 0.912 composite score. Automatic segmentation of the kidney by the participating teams performed comparably to expert manual segmentation but was less reliable when segmenting the tumor. Conclusion: Rapid advancement in automated semantic segmentation of kidney lesions is possible with relatively high accuracy when the data is released publicly, and participation is incentivized. We hope that our findings will encourage further research that would enable the potential of adopting AI into the medical field.

Evaluating the Perceived Importance of Male Ejaculatory Function.

OBJECTIVE: To assess the perceived importance of male ejaculatory function (EjF) from the perspective of adult men and their sexual partners. METHODS: In a large survey study, men were asked about the importance of their own EjF. Sexual partners of men were asked about the general importance their partner's EjF, and whether they would support a partner's decision to pursue BPH treatment despite ejaculatory dysfunction. RESULTS: One hundred and two men completed the survey section regarding their own EjF, and 100 participants completed the survey section assessing the importance of their male partner's EjF. While 55% of men agreed or strongly agreed that "ejaculation is an important part of an enjoyable sexual experience," only 30% of partners similarly agreed or strongly agreed (P = .005). A greater percentage of men (12%) agreed or strongly agreed that they "preferred large semen volume" compared to sexual partners of men (3%), however this was not significant. Sixty eight percent of sexual partners would agree or strongly agree to support their male partner's decision to pursue BPH treatment despite potential ejaculatory dysfunction. CONCLUSION: The perceived importance of EjF differs between men and their sexual partners, as men believe ejaculation to be a more important component of an enjoyable sexual experience than their partners.

The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge.

There is a large body of literature linking anatomic and geometric characteristics of kidney tumors to perioperative and oncologic outcomes. Semantic segmentation of these tumors and their host kidneys is a promising tool for quantitatively characterizing these lesions, but its adoption is limited due to the manual effort required to produce high-quality 3D segmentations of these structures. Recently, methods based on deep learning have shown excellent results in automatic 3D segmentation, but they require large datasets for training, and there remains little consensus on which methods perform best. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) which sought to address these issues and stimulate progress on this automatic segmentation problem. A training set of 210 cross sectional CT images with kidney tumors was publicly released with corresponding semantic segmentation masks. 106 teams from five continents used this data to develop automated systems to predict the true segmentation masks on a test set of 90 CT images for which the corresponding ground truth segmentations were kept private. These predictions were scored and ranked according to their average Sørensen-Dice coefficient between the kidney and tumor across all 90 cases. The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the inter-annotator performance on kidney (0.983) but falling short on tumor (0.923). This challenge has now entered an "open leaderboard" phase where it serves as a challenging benchmark in 3D semantic segmentation.

COP1/DET1/ETS axis regulates ERK transcriptome and sensitivity to MAPK inhibitors.

Aberrant activation of MAPK signaling leads to the activation of oncogenic transcriptomes. How MAPK signaling is coupled with the transcriptional response in cancer is not fully understood. In 2 MAPK-activated tumor types, gastrointestinal stromal tumor and melanoma, we found that ETV1 and other Pea3-ETS transcription factors are critical nuclear effectors of MAPK signaling that are regulated through protein stability. Expression of stabilized Pea3-ETS factors can partially rescue the MAPK transcriptome and cell viability after MAPK inhibition. To identify the players involved in this process, we performed a pooled genome-wide RNAi screen using a fluorescence-based ETV1 protein stability sensor and identified COP1, DET1, DDB1, UBE3C, PSMD4, and COP9 signalosome members. COP1 or DET1 loss led to decoupling between MAPK signaling and the downstream transcriptional response, where MAPK inhibition failed to destabilize Pea3 factors and fully inhibit the MAPK transcriptome, thus resulting in decreased sensitivity to MAPK pathway inhibitors. We identified multiple COP1 and DET1 mutations in human tumors that were defective in the degradation of Pea3-ETS factors. Two melanoma patients had de novo DET1 mutations arising after vemurafenib treatment. These observations indicate that MAPK signaling-dependent regulation of Pea3-ETS protein stability is a key signaling node in oncogenesis and therapeutic resistance to MAPK pathway inhibition.

Aberrant Activation of a Gastrointestinal Transcriptional Circuit in Prostate Cancer Mediates Castration Resistance.

Prostate cancer exhibits a lineage-specific dependence on androgen signaling. Castration resistance involves reactivation of androgen signaling or activation of alternative lineage programs to bypass androgen requirement. We describe an aberrant gastrointestinal-lineage transcriptome expressed in ∼5% of primary prostate cancer that is characterized by abbreviated response to androgen-deprivation therapy and in ∼30% of castration-resistant prostate cancer. This program is governed by a transcriptional circuit consisting of HNF4G and HNF1A. Cistrome and chromatin analyses revealed that HNF4G is a pioneer factor that generates and maintains enhancer landscape at gastrointestinal-lineage genes, independent of androgen-receptor signaling. In HNF4G/HNF1A-double-negative prostate cancer, exogenous expression of HNF4G at physiologic levels recapitulates the gastrointestinal transcriptome, chromatin landscape, and leads to relative castration resistance.

ETV1-Positive Cells Give Rise to BRAFV600E -Mutant Gastrointestinal Stromal Tumors.

Gastrointestinal stromal tumor (GIST) is the most common subtype of sarcoma. Despite clinical advances in the treatment of KIT/PDGFRA-mutant GIST, similar progress against KIT/PDGFRA wild-type GIST, including mutant BRAF-driven tumors, has been limited by a lack of model systems. ETV1 is a master regulator in the intestinal cells of Cajal (ICC), thought to be the cells of origin of GIST. Here, we present a model in which the ETV1 promoter is used to specifically and inducibly drive Cre recombinase in ICC as a strategy to study GIST pathogenesis. Using a conditional allele for BrafV600E , a mutation observed in clinical cases of GIST, we observed that BrafV600E activation was sufficient to drive ICC hyperplasia but not GIST tumorigenesis. In contrast, combining BrafV600E activation with Trp53 loss was sufficient to drive both ICC hyperplasia and formation of multifocal GIST-like tumors in the mouse gastrointestinal tract with 100% penetrance. This mouse model of sporadic GIST model was amenable to therapeutic intervention, and it recapitulated clinical responses to RAF inhibition seen in human GIST. Our work offers a useful in vivo model of human sporadic forms of BRAF-mutant GIST to help unravel its pathogenesis and therapeutic response to novel experimental agents. Cancer Res; 77(14); 3758-65. ©2017 AACR.

Recurrent activating mutations of G-protein-coupled receptor CYSLTR2 in uveal melanoma.

Uveal melanomas are molecularly distinct from cutaneous melanomas and lack mutations in BRAF, NRAS, KIT, and NF1. Instead, they are characterized by activating mutations in GNAQ and GNA11, two highly homologous α subunits of Gαq/11 heterotrimeric G proteins, and in PLCB4 (phospholipase C ß4), the downstream effector of Gαq signaling. We analyzed genomics data from 136 uveal melanoma samples and found a recurrent mutation in CYSLTR2 (cysteinyl leukotriene receptor 2) encoding a p.Leu129Gln substitution in 4 of 9 samples that lacked mutations in GNAQ, GNA11, and PLCB4 but in 0 of 127 samples that harbored mutations in these genes. The Leu129Gln CysLT2R mutant protein constitutively activates endogenous Gαq and is unresponsive to stimulation by leukotriene. Expression of Leu129Gln CysLT2R in melanocytes enforces expression of a melanocyte-lineage signature, drives phorbol ester-independent growth in vitro, and promotes tumorigenesis in vivo. Our findings implicate CYSLTR2 as a uveal melanoma oncogene and highlight the critical role of Gαq signaling in uveal melanoma pathogenesis.