Artificial intelligence-based recurrence prediction outperforms classical histopathological methods in pulmonary adenocarcinoma biopsies

INTRODUCTION

Between 10 and 50% of early-stage lung adenocarcinoma patients experience local or distant recurrence. Histological parameters such as a solid or micropapillary growth pattern are well-described risk factors for recurrence. However, not every patient presenting with such a pattern will develop recurrence. Designing a model which can more accurately predict recurrence on small biopsy samples can aid the stratification of patients for surgery, (neo-)adjuvant therapy, and follow-up.

MATERIAL AND METHODS

In this study, a statistical model on biopsies fed with histological data from early and advanced-stage lung adenocarcinomas was developed to predict recurrence after surgical resection. Additionally, a convolutional neural network (CNN)-based artificial intelligence (AI) classification model, named AI-based Lung Adenocarcinoma Recurrence Predictor (AILARP), was trained to predict recurrence, with an ImageNet pre-trained EfficientNet that was fine-tuned on lung adenocarcinoma biopsies using transfer learning. Both models were validated using the same biopsy dataset to ensure that an accurate comparison was demonstrated.

RESULTS

The statistical model had an accuracy of 0.49 for all patients when using histology data only. The AI classification model yielded a test accuracy of 0.70 and 0.82 and an area under the curve (AUC) of 0.74 and 0.87 on patch-wise and patient-wise hematoxylin and eosin (H&E) stained whole slide images (WSIs), respectively.

CONCLUSION

AI classification outperformed the traditional clinical approach for recurrence prediction on biopsies by a fair margin. The AI classifier may stratify patients according to their recurrence risk, based only on small biopsies. This model warrants validation in a larger lung biopsy cohort.

Artificial Intelligence in Digital Pathology for Bladder Cancer: Hype or Hope? A Systematic Review

Bladder cancer (BC) diagnosis and prediction of prognosis are hindered by subjective pathological evaluation, which may cause misdiagnosis and under-/over-treatment. Computational pathology (CPATH) can identify clinical outcome predictors, offering an objective approach to improve prognosis. However, a systematic review of CPATH in BC literature is lacking. Therefore, we present a comprehensive overview of studies that used CPATH in BC, analyzing 33 out of 2285 identified studies. Most studies analyzed regions of interest to distinguish normal versus tumor tissue and identify tumor grade/stage and tissue types (e.g., urothelium, stroma, and muscle). The cell's nuclear area, shape irregularity, and roundness were the most promising markers to predict recurrence and survival based on selected regions of interest, with >80% accuracy. CPATH identified molecular subtypes by detecting features, e.g., papillary structures, hyperchromatic, and pleomorphic nuclei. Combining clinicopathological and image-derived features improved recurrence and survival prediction. However, due to the lack of outcome interpretability and independent test datasets, robustness and clinical applicability could not be ensured. The current literature demonstrates that CPATH holds the potential to improve BC diagnosis and prediction of prognosis. However, more robust, interpretable, accurate models and larger datasets-representative of clinical scenarios-are needed to address artificial intelligence's reliability, robustness, and black box challenge.

The value of prognostic and predictive parameters in early-stage lung adenocarcinomas: A comparison between biopsies and resections

INTRODUCTION

Since lung adenocarcinoma (LUAD) biopsies are usually small, it is questionable if their prognostic and predictive information is comparable to what is offered by large resection specimens. This study compares LUAD biopsies and resection specimens for their ability to provide prognostic and predictive parameters.

METHODS

We selected 187 biopsy specimens with stage I and II LUAD. In 123 cases, subsequent resection specimens were also available. All specimens were evaluated for growth pattern, nuclear grade, fibrosis, inflammation, and genomic alterations. Findings were compared using non-parametric testing for categorical variables. Model performance was assessed using the area under the curve for both biopsies and resection specimens, and overall (OS) and disease-free survival (DFS) was calculated.

RESULTS

The overall growth pattern concordance between biopsies and resections was 73.9%. The dominant growth pattern correlated with OS and DFS in resected adenocarcinomas and for high-grade growth pattern in biopsies. Multivariate analysis of biopsy specimens revealed that T2-tumors, N1-status, KRAS mutations and a lack of other driver mutations were associated with poorer survival. Model performance using clinical, histological and genetic data from biopsy specimens for predicting OS and DSF demonstrated an AUC of 0.72 and 0.69, respectively.

CONCLUSIONS

Our data demonstrated the prognostic relevance of a high-grade growth pattern in biopsy specimens of LUAD. Combining clinical, histological and genetic information in one model demonstrated a suboptimal performance for DFS prediction and good performance for OS prediction. However, for daily practice, more robust (bio)markers are required to predict prognosis and stratify patients for therapy and follow-up.

Self-initialized active contours for microscopic cell image segmentation

Level set models are suitable for processing topological changes in different regions of images while performing segmentation. Active contour models require an empirical setting for initial parameters, which is tedious for the end-user. This study proposes an incremental level set model with the automatic initialization of contours based on local and global fitting energies that enable it to capture image regions containing intensity corruption or other light artifacts. The region-based area and the region-based length terms use signed pressure force (SPF) to strengthen the balloon force. SPF helps to achieve a smooth version of the gradient descent flow in terms of energy minimization. The proposed model is tested on multiple synthetic and real images. Our model has four advantages: first, there is no need for the end user to initialize the parameters; instead, the model is self-initialized. Second, it is more accurate than other methods. Third, it shows lower computational complexity. Fourth, it does not depend on the starting position of the contour. Finally, we evaluated the performance of our model on microscopic cell images (Coelho et al., in: 2009 IEEE international symposium on biomedical imaging: from nano to macro, IEEE, 2009) to confirm that its performance is superior to that of other state-of-the-art models.

TU6.8 An Audit of Day case surgery for cholecystectomy

Aims

To compare the trust-wide performance with the standard by the British Association of Day Surgery in the management of cholecystectomy

Methods

4 months of Electronic data of patients undergoing elective laparoscopic cholecystectomy in 2020 was analyzed. Those who had emergency cholecystectomy were excluded.

Results

112 of 145 total patients were female and 33 were male. The age range was 18–82 Around 65% of patients were sent home the same day. 51 Patients ended up being admitted. 33 of these were Pre-booked as inpatients' intent. 39% (13/33) had no specific reason for being booked as an inpatient. The rest Majority had medical issues quoted as the reason for booking.35% (18) of the 51 admitted patients were actually brought in as day-case lap-chole. 6 of these were admitted for perioperative surgical issues and 8 had no documented reason. The Mean length of stay was 2.56 days(0–13). Our Performance was noted to be 10% lower than the BADS standard.

Conclusion

Relatively more patients are being treated as inpatients than the recommended standard. About 1/4th of those who were inpatient had no specific/genuine grounds to be kept in. There is a need for improvement in pre and perioperative documentation to explain the reason for inpatient management. Development of inpatient surgery booking criteria and adherence to set criteria.

EP-503 An Audit of Day case surgery for Inguinal Hernia Repair

Aims

To compare the trust-wide performance with the standard by the British Association of Day Surgery in the management of inguinal hernias.

Methods

Electronic data of patients who underwent Inguinal Hernia Repairs in the trust from September 2019 to December 2019 was analyzed.

Results

A total of 122 male and 11 female patients had hernias repaired in this time period.18 were emergency while the rest of the cases were elective. The ages ranged from 19–91 with a mean age of 62. Of the 115 electives, 60% were performed as day-case. The mean length of stay was 1.7days (R 0–12).34 out of 46 (74%) patients who stayed inpatient were actually booked as day-case. 73% had no documented reason for their admission.4 patients were admitted for medical reasons 2 for post-operative surgical complications. Of patients pre-booked as inpatients,10 were quoted to have serious medical issues while 5 had no clear reason. The vast majority had open repairs while 26% of the 115 patients had laparoscopic repairs.

Conclusion

Our Performance was noted to be 30% lower than the BADS standard. There is a need of:

Development of inpatient surgery booking criteria and adherence.

Discussion with anesthetic colleagues to assist drive towards day-case surgery.

Clear documentation in the clinical letters to explain the reason for inpatient management and booking.

Perioperative notes need improvement.

Protease production and molecular characterization of a protease dipeptidyl-aminopeptidase gene from different strains of Sordaria fimicola

The current research was designed to reach extracellular protease production potential in different strains of Sordaria fimicola which were previously obtained from Dr. Lamb (Imperial College, London) from North Facing Slope and South Facing Slope of Evolution Canyon. After initial and secondary screening, two hyper-producers strains S2 and N6 were selected for submerged fermentation and cultural conditions including temperature, pH, incubation period, inoculum size, substrate concentration, and different carbon and nitrogen sources were optimized for enzyme production. S2 strain showed maximum protease production of 3.291 U/mL after 14 days of incubation at 30 °C with 7 pH, 1% substrate concentration and 1 mL inoculum, While N6 strain showed maximum protease production of 1.929 U/mL under fermentation optimized conditions. Another aim of the present research was to underpin the biodiversity of genetics and post-translational modifications (PTMs) of protease DPAP (peptidyl-aminopeptidase) in Sordaria fimicola. Five polymorphic sites were observed in amino acid sequence of S. fimicola strains with reference to Neurospora crassa. PTMs prediction from bioinformatics tools predicted 38 phosphorylation sites on serine residues for protease peptidyl-aminopeptidase in S1 strain of S. fimicola while 45 phosphorylation sites on serine in N7 strain and 47 serine phosphorylation modifications were predicted in N. crassa. Current research gave an insight that change in genetic makeup effected PTMs which ultimately affected the production of protease enzyme in different strains of same organism (S. fimicola). The production and molecular data of the research revealed that environmental stress has strong effects on the specific genes through mutations which may cause genetic diversity. S. fimicola is non- pathogenic fungus and has a short life cycle. This fungus can be chosen to produce protease enzyme on a commercial scale.

Moral injury and the COVID-19 pandemic: A philosophical viewpoint

Introduction

Much has changed in healthcare during the coronavirus disease (COVID)-19 pandemic. Medicine, a profession of traditional principles and virtues, has faced unprecedented challenges in the light of scarce and unequal distribution of ventilators, testing, and personal protective equipment. Healthcare workers have been- and are increasingly likely to be- forced into situations that require difficult decision making under life-and-death conditions. Concepts of "medical necessity" and "maximum benefit" challenge healthcare systems that already struggle to manage unequal treatment and access to services, giving rise to moral distress and moral injury on the front lines.

Methods

This article focuses on moral injury in the context of coronavirus disease (COVID)-19 pandemic. I review recent literature to highlight the psychological impact of many morally-injurious events that have been reported during the COVID-19 pandemic. With the help of a clinical vignette, I point out how healthcare systems adopt many utilitarian policies in times of excessive healthcare burden. A viewpoint is offered that many morally injurious events happen when healthcare workers, traditionally practicing Kantian and virtue ethics, are forced to follow utilitarian policies of healthcare system.

Conclusion

One form of moral injury may arise from inherent conflicts between individual deontological moral judgments and organizational utilitarian moral judgments. More research is needed to validate the philosophical viewpoint as well as to explore whether increased awareness and education of key principles within moral philosophy can better equip healthcare workers in situations when public health takes precedence over individual health.

Association of plasma nitrite levels with obesity and metabolic syndrome in the Old Order Amish

OBJECTIVES

Plasma nitrite is a metabolite of nitric oxide and reflects endogenous nitric oxide synthase (NOS) activity. Although plasma nitrites were previously linked with obesity and metabolic syndrome (MetS), the direction of association remains inconsistent, possibly due to sample heterogeneity. In a relatively homogeneous population, we hypothesized that nitrite levels will be positively associated with overweight/obesity and MetS.

METHODS

Fasting nitrite levels were measured in 116 Old Order Amish (78% women). We performed age-and-sex-adjusted ancovas to compare nitrite levels between three groups (a) overweight/obese(-)MetS(-), (b) overweight/obese(+)MetS(-) and (c) overweight/obese(+)MetS)(+). Multivariate linear regressions were conducted on nitrite associations with continuous metabolic variables, with successive adjustments for demographics, body mass index, C-reactive protein and neopterin.

RESULTS

Nitrite levels were higher in the obese/overweight(+)MetS(+) group than in the other two groups (p < 0.001). Nitrites were positively associated with levels of triglycerides (p < 0.0001), total cholesterol (p = 0.048), high-density lipoprotein/cholesterol ratio (p < 0.0001) and fasting glucose (p < 0.0001), and negatively correlated with high-density lipoprotein-cholesterol (p < 0.0001). These associations were robust to adjustments for body mass index and inflammatory markers.

CONCLUSION

Further investigation of the connection between obesity/MetS and plasma nitrite levels may lead to novel dietary and pharmacological approaches that ultimately may contribute to reducing the increasing burden of obesity, MetS and cardiovascular morbidity and mortality.

Active contours driven by difference of Gaussians

In this paper, a novel edge-based active contour method is proposed based on the difference of Gaussians (DoG) to segment intensity inhomogeneous images. DoG is known as a feature enhancement tool, which can enhance the edges of an image. However, in the proposed energy functional it is used as an edge-indicator parameter, which acts like a balloon force during the level-set curve evolution process. In the proposed formulation, the internal energy term penalizes the deviation of the level-set function from a signed distance function and external energy term evolves the contour towards the boundaries of the objects. There are three main advantages of the proposed method. First, image difference computed using the DoG function provides the global structure of an image, which helps to segment the image globally that the traditional edge-based methods are unable to do. Second, it has a low time complexity compared to the state-of-the-art active contours developed in the context of intensity inhomogeneity. Third, it is not sensitive to the initial position of contour. Experimental results using both synthetic and real brain magnetic resonance (MR) images show that the proposed method yields better segmentation results compared to the state-of-the-art.

Segmentation of Left and Right Ventricles in Cardiac MRI Using Active Contours

Segmentation of left and right ventricles plays a crucial role in quantitatively analyzing the global and regional information in the cardiac magnetic resonance imaging (MRI). In MRI, the intensity inhomogeneity and weak or blurred object boundaries are the problems, which makes it difficult for the intensity-based segmentation methods to properly delineate the regions of interests (ROI). In this paper, a hybrid signed pressure force function (SPF) is proposed, which yields both local and global image fitted differences in an additive fashion. A characteristic term is also introduced in the SPF function to restrict the contour within the ROI. The overlapping dice index and Hausdorff-Distance metrics have been used over cardiac datasets for quantitative validation. Using 2009 LV MICCAI validation dataset, the proposed method yields DSC values of 0.95 and 0.97 for endocardial and epicardial contours, respectively. Using 2012 RV MICCAI dataset, for the endocardial region, the proposed method yields DSC values of 0.97 and 0.90 and HD values of 8.51 and 7.67 for ED and ES, respectively. For the epicardial region, it yields DSC values of 0.92 and 0.91 and HD values of 6.47 and 9.34 for ED and ES, respectively. Results show its robustness in the segmentation application of the cardiac MRI.

Active contours driven by local and global fitted image models for image segmentation robust to intensity inhomogeneity

This paper presents a region-based active contour method for the segmentation of intensity inhomogeneous images using an energy functional based on local and global fitted images. A square image fitted model is defined by using both local and global fitted differences. Moreover, local and global signed pressure force functions are introduced in the solution of the energy functional to stabilize the gradient descent flow. In the final gradient descent solution, the local fitted term helps extract regions with intensity inhomogeneity, whereas the global fitted term targets homogeneous regions. A Gaussian kernel is applied to regularize the contour at each step, which not only smoothes it but also avoids the computationally expensive re-initialization. Intensity inhomogeneous images contain undesired smooth intensity variations (bias field) that alter the results of intensity-based segmentation methods. The bias field is approximated with a Gaussian distribution and the bias of intensity inhomogeneous regions is corrected by dividing the original image by the approximated bias field. In this paper, a two-phase model is first derived and then extended to a four-phase model to segment brain magnetic resonance (MR) images into the desired regions of interest. Experimental results with both synthetic and real brain MR images are used for a quantitative and qualitative comparison with state-of-the-art active contour methods to show the advantages of the proposed segmentation technique in practical terms.

Segmentation of intensity inhomogeneous brain MR images using active contours

Segmentation of intensity inhomogeneous regions is a well-known problem in image analysis applications. This paper presents a region-based active contour method for image segmentation, which properly works in the context of intensity inhomogeneity problem. The proposed region-based active contour method embeds both region and gradient information unlike traditional methods. It contains mainly two terms, area and length, in which the area term practices a new region-based signed pressure force (SPF) function, which utilizes mean values from a certain neighborhood using the local binary fitted (LBF) energy model. In turn, the length term uses gradient information. The novelty of our method is to locally compute new SPF function, which uses local mean values and is able to detect boundaries of the homogenous regions. Finally, a truncated Gaussian kernel is used to regularize the level set function, which not only regularizes it but also removes the need of computationally expensive reinitialization. The proposed method targets the segmentation problem of intensity inhomogeneous images and reduces the time complexity among locally computed active contour methods. The experimental results show that the proposed method yields better segmentation result as well as less time complexity compared with the state-of-the-art active contour methods.