Fully Automated Versions of Clinically Validated Nephrometry Scores Demonstrate Superior Predictive Utility versus Human Scores.

OBJECTIVE: To automate the generation of three validated nephrometry scoring systems on preoperative computerised tomography (CT) scans by developing artificial intelligence (AI)-based image processing methods. Subsequently, we aimed to evaluate the ability of these scores to predict meaningful pathological and perioperative outcomes. PATIENTS AND METHODS: A total of 300 patients with preoperative CT with early arterial contrast phase were identified from a cohort of 544 consecutive patients undergoing surgical extirpation for suspected renal cancer. A deep neural network approach was used to automatically segment kidneys and tumours, and then geometric algorithms were used to measure the components of the concordance index (C-Index), Preoperative Aspects and Dimensions Used for an Anatomical classification of renal tumours (PADUA), and tumour contact surface area (CSA) nephrometry scores. Human scores were independently calculated by medical personnel blinded to the AI scores. AI and human score agreement was assessed using linear regression and predictive abilities for meaningful outcomes were assessed using logistic regression and receiver operating characteristic curve analyses. RESULTS: The median (interquartile range) age was 60 (51-68) years, and 40% were female. The median tumour size was 4.2 cm and 91.3% had malignant tumours. In all, 27% of the tumours were high stage, 37% high grade, and 63% of the patients underwent partial nephrectomy. There was significant agreement between human and AI scores on linear regression analyses (R ranged from 0.574 to 0.828, all P < 0.001). The AI-generated scores were equivalent or superior to human-generated scores for all examined outcomes including high-grade histology, high-stage tumour, indolent tumour, pathological tumour necrosis, and radical nephrectomy (vs partial nephrectomy) surgical approach. CONCLUSIONS: Fully automated AI-generated C-Index, PADUA, and tumour CSA nephrometry scores are similar to human-generated scores and predict a wide variety of meaningful outcomes. Once validated, our results suggest that AI-generated nephrometry scores could be delivered automatically from a preoperative CT scan to a clinician and patient at the point of care to aid in decision making.

The Cooked Meat Carcinogen 2-Amino-1-methyl-6-phenylimidazo[4,5-b]pyridine Hair Dosimeter, DNA Adductomics Discovery, and Associations with Prostate Cancer Pathology Biomarkers.

Well-done cooked red meat consumption is linked to aggressive prostate cancer (PC) risk. Identifying mutation-inducing DNA adducts in the prostate genome can advance our understanding of chemicals in meat that may contribute to PC. 2-Amino-1-methyl-6-phenylimidazo[4,5-b]pyridine (PhIP), a heterocyclic aromatic amine (HAA) formed in cooked meat, is a potential human prostate carcinogen. PhIP was measured in the hair of PC patients undergoing prostatectomy, bladder cancer patients under treatment for cystoprostatectomy, and patients treated for benign prostatic hyperplasia (BPH). PhIP hair levels were above the quantification limit in 123 of 205 subjects. When dichotomizing prostate pathology biomarkers, the geometric mean PhIP hair levels were higher in patients with intermediate and elevated-risk prostate-specific antigen values than lower-risk values <4 ng/mL (p = 0.03). PhIP hair levels were also higher in patients with intermediate and high-risk Gleason scores ≥7 compared to lower-risk Gleason score 6 and BPH patients (p = 0.02). PC patients undergoing prostatectomy had higher PhIP hair levels than cystoprostatectomy or BPH patients (p = 0.02). PhIP-DNA adducts were detected in 9.4% of the patients assayed; however, DNA adducts of other carcinogenic HAAs, and benzo[a]pyrene formed in cooked meat, were not detected. Prostate specimens were also screened for 10 oxidative stress-associated lipid peroxidation (LPO) DNA adducts. Acrolein 1,N2-propano-2'-deoxyguanosine adducts were detected in 54.5% of the patients; other LPO adducts were infrequently detected. Acrolein adducts were not associated with prostate pathology biomarkers, although DNA adductomic profiles differed between PC patients with low and high-grade Gleason scores. Many DNA adducts are of unknown origin; however, dG adducts of formaldehyde and a series of purported 4-hydroxy-2-alkenals were detected at higher abundance in a subset of patients with elevated Gleason scores. The PhIP hair biomarker and DNA adductomics data support the paradigm of well-done cooked meat and oxidative stress in aggressive PC risk.

Biomonitoring DNA Adducts of Cooked Meat Carcinogens in Human Prostate by Nano Liquid Chromatography-High Resolution Tandem Mass Spectrometry: Identification of 2-Amino-1-methyl-6-phenylimidazo[4,5-b]pyridine DNA Adduct.

Epidemiologic studies have reported an association between frequent consumption of well-done cooked meats and prostate cancer risk. However, unambiguous physiochemical markers of DNA damage from carcinogens derived from cooked meats, such as DNA adducts, have not been identified in human samples to support this paradigm. We have developed a highly sensitive nano-LC-Orbitrap MS n method to measure DNA adducts of several carcinogens originating from well-done cooked meats, tobacco smoke, and environmental pollution, including 2-amino-1-methyl-6-phenylimidazo[4,5-b]pyridine (PhIP), 2-amino-9H-pyrido[2,3-b]indole (AαC), 2-amino-3,8-dimethylimidazo[4,5-f]quinoxaline (MeIQx), benzo[a]pyrene (B[a]P), and 4-aminobiphenyl (4-ABP). The limit of quantification (LOQ) of the major deoxyguanosine (dG) adducts of these carcinogens ranged between 1.3 and 2.2 adducts per 10 9 nucleotides per 2.5 µg of DNA assayed. The DNA adduct of PhIP, N-(deoxyguanosin-8-yl)-PhIP (dG-C8-PhIP) was identified in 11 out of 35 patients, at levels ranging from 2 to 120 adducts per 10 9 nucleotides. The dG-C8 adducts of AαC and MeIQx, and the B[a]P adduct, 10-(deoxyguanosin-N 2 -yl)-7,8,9-trihydroxy-7,8,9,10-tetrahydrobenzo[a]pyrene (dG-N 2 -B[a]PDE) were not detected in any specimen, whereas N-(deoxyguanosin-8-yl)-4-ABP (dG-C8-4-ABP) was identified in one subject (30 adducts per 10 9 nucleotides). PhIP-DNA adducts also were recovered quantitatively from formalin fixed paraffin embedded (FFPE) tissues, signifying FFPE tissues can serve as biospecimens for carcinogen DNA adduct biomarker research. Our biomarker data provide support to the epidemiological observations implicating PhIP, one of the most mass-abundant heterocyclic aromatic amines formed in well-done cooked meats, as a DNA-damaging agent that may contribute to the etiology of prostate cancer.

AI-generated R.E.N.A.L.+ Score Surpasses Human-generated Score in Predicting Renal Oncologic Outcomes.

OBJECTIVE: To determine whether we can surpass the traditional R.E.N.A.L. nephrometry score (H-score) prediction ability of pathologic outcomes by creating artificial intelligence (AI)-generated R.E.N.A.L.+ score (AI+ score) with continuous rather than ordinal components. We also assessed the AI+ score components' relative importance with respect to outcome odds. METHODS: This is a retrospective study of 300 consecutive patients with preoperative computed tomography scans showing suspected renal cancer at a single institution from 2010 to 2018. H-score was tabulated by three trained medical personnel. Deep neural network approach automatically generated kidney segmentation masks of parenchyma and tumor. Geometric algorithms were used to automatically estimate score components as ordinal and continuous variables. Multivariate logistic regression of continuous R.E.N.A.L. components was used to generate AI+ score. Predictive utility was compared between AI+, AI, and H-scores for variables of interest, and AI+ score components' relative importance was assessed. RESULTS: Median age was 60years (interquartile range 51-68), and 40% were female. Median tumor size was 4.2 cm (2.6-6.12), and 92% were malignant, including 27%, 37%, and 23% with high-stage, high-grade, and necrosis, respectively. AI+ score demonstrated superior predictive ability over AI and H-scores for predicting malignancy (area under the curve [AUC] 0.69 vs 0.67 vs 0.64, respectively), high stage (AUC 0.82 vs 0.65 vs 0.71, respectively), high grade (AUC 0.78 vs 0.65 vs 0.65, respectively), pathologic tumor necrosis (AUC 0.81 vs 0.72 vs 0.74, respectively), and partial nephrectomy approach (AUC 0.88 vs 0.74 vs 0.79, respectively). Of AI+ score components, the maximal tumor diameter ("R") was the most important outcomes predictor. CONCLUSION: AI+ score was superior to AI-score and H-score in predicting oncologic outcomes. Time-efficient AI+ score can be used at the point of care, surpassing validated clinical scoring systems.

Referral patterns for undescended testis: A 7 year comparative analysis of primary care providers.

INTRODUCTION: Cryptorchidism, or undescended testis (UDT), is identified in 1% of boys by one year of age and carries long term risks of infertility and testicular neoplasia. In 2014, the American Urological Association (AUA) released a guideline statement stating that patients with UDT should be referred to a urologist by 6 months of age in order to facilitate timely surgical correction. This study is the follow-up to a 2010 study assessing referral patterns to our university center from primary care providers. OBJECTIVE: In this new study, we aim to identify changes in referral patterns in response to the establishment of the 2014 AUA guidelines and to understand how our referring physicians stay abreast of current knowledge regarding UDT. STUDY DESIGN: A 9 question anonymous survey regarding UDT referral patterns was sent to providers who had previously referred a patient to our pediatric urology practice. The results were categorized by specialty and were compared to the similar survey from 2010. RESULTS: Surveys were sent to 500 physicians with 138 (27.6%) responses received. Less than half of respondents reported that they would refer a boy with unilateral or bilateral palpable UDT by 6 months of age (37.0% and 38.4% respectively). This was not significantly different than the 2010 survey (p = 0.68 and 0.27 respectively). Two-thirds of physicians would refer a patient with unilateral nonpalpable UDT within the recommended time frame (68.8%); this was also unchanged from 2010 (p = 0.87). There was an improvement in respondents who would refer immediately for bilateral nonpalpable testes from 49.8% in 2010 to 53.6% in 2017 (p = 0.01). Residency training was most commonly cited as the primary source of knowledge regarding UDT although 89.3% of respondents citing this were >5 years removed from residency training. DISCUSSION: Delayed referral patterns were reported by the majority of providers for palpable UDT and by greater than one-third of providers for nonpalpable UDT. There was minimal change in referral patterns between 2010 and 2017 despite the release of the AUA cryptorchidism guidelines in 2014. In both 2010 and 2017, residency training was identified as the primary source of knowledge regarding management of UDT. CONCLUSION: These findings suggest an unmet need for education regarding contemporary management of UDT for the primary care physicians in our community.

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.

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.

Image Descriptors for Weakly Annotated Histopathological Breast Cancer Data.

INTRODUCTION: Cancerous Tissue Recognition (CTR) methodologies are continuously integrating advancements at the forefront of machine learning and computer vision, providing a variety of inference schemes for histopathological data. Histopathological data, in most cases, come in the form of high-resolution images, and thus methodologies operating at the patch level are more computationally attractive. Such methodologies capitalize on pixel level annotations (tissue delineations) from expert pathologists, which are then used to derive labels at the patch level. In this work, we envision a digital connected health system that augments the capabilities of the clinicians by providing powerful feature descriptors that may describe malignant regions. MATERIAL AND METHODS: We start with a patch level descriptor, termed Covariance-Kernel Descriptor (CKD), capable of compactly describing tissue architectures associated with carcinomas. To leverage the recognition capability of the CKDs to larger slide regions, we resort to a multiple instance learning framework. In that direction, we derive the Weakly Annotated Image Descriptor (WAID) as the parameters of classifier decision boundaries in a Multiple Instance Learning framework. The WAID is computed on bags of patches corresponding to larger image regions for which binary labels (malignant vs. benign) are provided, thus obviating the necessity for tissue delineations. RESULTS: The CKD was seen to outperform all the considered descriptors, reaching classification accuracy (ACC) of 92.83%. and area under the curve (AUC) of 0.98. The CKD captures higher order correlations between features and was shown to achieve superior performance against a large collection of computer vision features on a private breast cancer dataset. The WAID outperform all other descriptors on the Breast Cancer Histopathological database (BreakHis) where correctly classified malignant (CCM) instances reached 91.27 and 92.00% at the patient and image level, respectively, without resorting to a deep learning scheme achieves state-of-the-art performance. DISCUSSION: Our proposed derivation of the CKD and WAID can help medical experts accomplish their work accurately and faster than the current state-of-the-art.

Public Perceptions of Artificial Intelligence and Robotics in Medicine.

Objective: To understand better the public perception and comprehension of medical technology such as artificial intelligence (AI) and robotic surgery. In addition to this, to identify sensitivity to their use to ensure acceptability and quality of counseling. Subjects and Methods: A survey was conducted on a convenience sample of visitors to the MN Minnesota State Fair (n = 264). Participants were randomized to receive one of two similar surveys. In the first, a diagnosis was made by a physician and in the second by an AI application to compare confidence in human and computer-based diagnosis. Results: The median age of participants was 45 (interquartile range 28-59), 58% were female (n = 154) vs 42% male (n = 110), 69% had completed at least a bachelor's degree, 88% were Caucasian (n = 233) vs 12% ethnic minorities (n = 31) and were from 12 states, mostly from the Upper Midwest. Participants had nearly equal trust in AI vs physician diagnoses. However, they were significantly more likely to trust an AI diagnosis of cancer over a doctor's diagnosis when responding to the version of the survey that suggested that an AI could make medical diagnoses (p = 9.32e-06). Though 55% of respondents (n = 145) reported that they were uncomfortable with automated robotic surgery, the majority of the individuals surveyed (88%) mistakenly believed that partially autonomous surgery was already happening. Almost all (94%, n = 249) stated that they would be willing to pay for a review of medical imaging by an AI if available. Conclusion: Most participants express confidence in AI providing medical diagnoses, sometimes even over human physicians. Participants generally express concern with surgical AI, but they mistakenly believe that it is already being performed. As AI applications increase in medical practice, health care providers should be cognizant of the potential amount of misinformation and sensitivity that patients have to how such technology is represented.

Public Perceptions on the Influence of Diet and Kidney Stone Formation.

Introduction: Public awareness regarding the influence of diet on kidney stones is unknown. We sought to evaluate such perceptions among an unselected community cohort. Materials and Methods: A survey was created to assess perception of beverages/foods on risk of kidney stone formation. Surveys were distributed to attendees of a State Fair. Participants were categorized to determine the effect of stone history on prevention knowledge (no prior stone vs prior stone). Results: Seven hundred fifty-three participants completed the survey, including 264 (35%) with a prior stone. Participants with prior stones were less likely to believe stones were preventable compared to those without (56% vs 65%, p = 0.01). Appropriate perceptions regarding influence of diet on stones were highest for water (>90% of participants) and cola/salt/red meat (>50%). Fewer than half of respondents correctly identified the influence of the remaining 14 substances. On multivariable analysis, stone formers were more likely to correctly identify the influence of lemonade (odds ratio [OR] 2.09; 95% confidence interval [CI] 1.32-3.31), nuts (OR 2.60; 95% CI 1.60-4.23), and spinach (OR 5.06; 95% CI 2.89-8.86), but less likely to identify the influence of coffee (OR 0.43; 95% CI 0.23-0.82) and red meat (OR 0.52; 95% CI 0.23-0.59). Conclusion: Patients with prior stones hold different attitudes regarding the influence of certain foods and drinks on stone formation relative to the public. Such attitudes are not always correct, and as a group they are less likely to believe in dietary stone prevention. Such findings may indicate confusion among stone formers and highlight an opportunity for improved dietary counseling.