Validating polyp and instrument segmentation methods in colonoscopy through Medico 2020 and MedAI 2021 Challenges.

Automatic analysis of colonoscopy images has been an active field of research motivated by the importance of early detection of precancerous polyps. However, detecting polyps during the live examination can be challenging due to various factors such as variation of skills and experience among the endoscopists, lack of attentiveness, and fatigue leading to a high polyp miss-rate. Therefore, there is a need for an automated system that can flag missed polyps during the examination and improve patient care. Deep learning has emerged as a promising solution to this challenge as it can assist endoscopists in detecting and classifying overlooked polyps and abnormalities in real time, improving the accuracy of diagnosis and enhancing treatment. In addition to the algorithm's accuracy, transparency and interpretability are crucial to explaining the whys and hows of the algorithm's prediction. Further, conclusions based on incorrect decisions may be fatal, especially in medicine. Despite these pitfalls, most algorithms are developed in private data, closed source, or proprietary software, and methods lack reproducibility. Therefore, to promote the development of efficient and transparent methods, we have organized the "Medico automatic polyp segmentation (Medico 2020)" and "MedAI: Transparency in Medical Image Segmentation (MedAI 2021)" competitions. The Medico 2020 challenge received submissions from 17 teams, while the MedAI 2021 challenge also gathered submissions from another 17 distinct teams in the following year. We present a comprehensive summary and analyze each contribution, highlight the strength of the best-performing methods, and discuss the possibility of clinical translations of such methods into the clinic. Our analysis revealed that the participants improved dice coefficient metrics from 0.8607 in 2020 to 0.8993 in 2021 despite adding diverse and challenging frames (containing irregular, smaller, sessile, or flat polyps), which are frequently missed during a routine clinical examination. For the instrument segmentation task, the best team obtained a mean Intersection over union metric of 0.9364. For the transparency task, a multi-disciplinary team, including expert gastroenterologists, accessed each submission and evaluated the team based on open-source practices, failure case analysis, ablation studies, usability and understandability of evaluations to gain a deeper understanding of the models' credibility for clinical deployment. The best team obtained a final transparency score of 21 out of 25. Through the comprehensive analysis of the challenge, we not only highlight the advancements in polyp and surgical instrument segmentation but also encourage subjective evaluation for building more transparent and understandable AI-based colonoscopy systems. Moreover, we discuss the need for multi-center and out-of-distribution testing to address the current limitations of the methods to reduce the cancer burden and improve patient care.

Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge.

Polyps are well-known cancer precursors identified by colonoscopy. However, variability in their size, appearance, and location makes the detection of polyps challenging. Moreover, colonoscopy surveillance and removal of polyps are highly operator-dependent procedures and occur in a highly complex organ topology. There exists a high missed detection rate and incomplete removal of colonic polyps. To assist in clinical procedures and reduce missed rates, automated methods for detecting and segmenting polyps using machine learning have been achieved in past years. However, the major drawback in most of these methods is their ability to generalise to out-of-sample unseen datasets from different centres, populations, modalities, and acquisition systems. To test this hypothesis rigorously, we, together with expert gastroenterologists, curated a multi-centre and multi-population dataset acquired from six different colonoscopy systems and challenged the computational expert teams to develop robust automated detection and segmentation methods in a crowd-sourcing Endoscopic computer vision challenge. This work put forward rigorous generalisability tests and assesses the usability of devised deep learning methods in dynamic and actual clinical colonoscopy procedures. We analyse the results of four top performing teams for the detection task and five top performing teams for the segmentation task. Our analyses demonstrate that the top-ranking teams concentrated mainly on accuracy over the real-time performance required for clinical applicability. We further dissect the devised methods and provide an experiment-based hypothesis that reveals the need for improved generalisability to tackle diversity present in multi-centre datasets and routine clinical procedures.

Why Culture and Context Matters: Examining Differences in Mental Health Stigma and Social Distance Between Latino Individuals in the United States and Mexico.

This study examines the influence of cultural context on social distance and perceptions of stigma towards mental health conditions among Latino populations in Houston, TX, USA and Mexico City, Mexico. We employed a community-based experimental vignette survey to assess perceptions towards individuals experiencing symptoms of alcohol misuse, depression, and psychosis. Participants (n = 513) from Houston and Mexico City were asked about their willingness to accept community members experiencing mental health symptoms in various social roles, their perceptions of stigma related to these symptoms, anticipated danger, possible positive outcomes, and the community member's ability to change. Findings demonstrate significant differences in stigma perceptions between Latino respondents in the US and in Mexico. Houston participants reported lower public stigma and perceived dangerousness of someone with mental health concerns compared to respondents in Mexico City. Furthermore, the cultural context may influence the association between various dimensions of stigma, with some inverse relationships occurring based on location of data collection. Findings illuminate the complex interplay between cultural context, mental health symptoms, and stigma, and underscores the need for culturally nuanced interventions to reduce mental health stigma and promote service utilization in Latino communities.

TransResU-Net: A Transformer based ResU-Net for Real-Time Colon Polyp Segmentation.

Colorectal cancer (CRC) is one of the most common causes of cancer and cancer-related mortality worldwide. Performing colon cancer screening in a timely fashion is the key to early detection. Colonoscopy is the primary modality used to diagnose colon cancer. However, the miss rate of polyps, adenomas and advanced adenomas remains significantly high. Early detection of polyps at the precancerous stage can help reduce the mortality rate and the economic burden associated with colorectal cancer. Deep learning-based computer-aided diagnosis (CADx) system may help gastroenterologists to identify polyps that may otherwise be missed, thereby improving the polyp detection rate. Additionally, CADx system could prove to be a cost-effective system that improves long-term colorectal cancer prevention. In this study, we proposed a deep learning-based architecture for automatic polyp segmentation called Transformer ResU-Net (TransResU-Net). Our proposed architecture is built upon residual blocks with ResNet-50 as the backbone and takes advantage of the transformer self-attention mechanism as well as dilated convolution(s). Our experimental results on two publicly available polyp segmentation benchmark datasets showed that TransResU-Net obtained a highly promising dice score and a real-time speed. With high efficacy in our performance metrics, we concluded that TransResU-Net could be a strong benchmark for building a real-time polyp detection system for the early diagnosis, treatment, and prevention of colorectal cancer. The source code of the proposed TransResU-Net is publicly available at https://github.com/nikhilroxtomar/TransResUNet.

FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation.

The increase of available large clinical and experimental datasets has contributed to a substantial amount of important contributions in the area of biomedical image analysis. Image segmentation, which is crucial for any quantitative analysis, has especially attracted attention. Recent hardware advancement has led to the success of deep learning approaches. However, although deep learning models are being trained on large datasets, existing methods do not use the information from different learning epochs effectively. In this work, we leverage the information of each training epoch to prune the prediction maps of the subsequent epochs. We propose a novel architecture called feedback attention network (FANet) that unifies the previous epoch mask with the feature map of the current training epoch. The previous epoch mask is then used to provide hard attention to the learned feature maps at different convolutional layers. The network also allows rectifying the predictions in an iterative fashion during the test time. We show that our proposed feedback attention model provides a substantial improvement on most segmentation metrics tested on seven publicly available biomedical imaging datasets demonstrating the effectiveness of FANet. The source code is available at https://github.com/nikhilroxtomar/FANet.

Differences in internalized stigma of mental illness among college students based on demographic characteristics.

Objective: To assess differences in internalized stigma of mental illness based on demographic characteristics and mental healthcare utilization among college students. Participants: Students with self-reported mental illness (n = 128) were recruited via random sampling. Methods: Participants completed an online survey, including questions related to demographic characteristics and mental healthcare utilization. The survey also included the Internalized Stigma of Mental Illness (ISMI) scale. Data were analyzed using descriptive and inferential statistics. Results: Students accessing mental healthcare (pharmacological and/or psychotherapeutic) reported higher ISMI scores than students who did not access services during past year. Students with sexual minority statuses also reported higher ISMI scores than their heterosexual counterparts. Conclusions: Results highlight differences in internalized stigma based on demographics characteristics and mental healthcare utilization among college students. More research is needed to better understand intersectional stigma. Further, universities need tailored and specific interventions to address internalized stigma among students with diverse backgrounds and needs.

An Intervention Framework for Addressing Stigma on College Campuses: Findings From a 3-Year-Long Intervention Program.

ABSTRACT: The ongoing COVID-19 pandemic will only exacerbate the rising mental health concerns among college students. However, stigma toward such concerns continues to hinder mental health care utilization among the students, requiring urgent evidence that can help guide college campuses in implementing effective antistigma interventions. We propose and provide evidence for an intervention based on findings from a 3-year-long antistigma intervention that was implemented on a Southeastern college campus in the United States. Unique random samples of college students, totaling N = 1727 across 3 years, were recruited as participants. Each year, participants completed a preintervention and postintervention survey comprising of questions related to demographics, stigma, and mental health care knowledge. Findings indicate that the stakeholder-led intervention decreased personal stigma and increased mental health care knowledge among students who were exposed to the intervention. Further research is needed to assess feasibility and efficacy of the proposed intervention framework on other campuses.

Automatic Polyp Segmentation with Multiple Kernel Dilated Convolution Network.

The detection and removal of precancerous polyps through colonoscopy is the primary technique for the prevention of colorectal cancer worldwide. However, the miss rate of colorectal polyp varies significantly among the endoscopists. It is well known that a computer-aided diagnosis (CAD) system can assist endoscopists in detecting colon polyps and minimize the variation among endoscopists. In this study, we introduce a novel deep learning architecture, named MKDCNet, for automatic polyp segmentation robust to significant changes in polyp data distribution. MKDCNet is simply an encoder-decoder neural network that uses the pre-trained ResNet50 as the encoder and novel multiple kernel dilated convolution (MKDC) block that expands the field of view to learn more robust and heterogeneous representation. Extensive experiments on four publicly available polyp datasets and cell nuclei dataset show that the proposed MKDCNet outperforms the state-of-the-art methods when trained and tested on the same dataset as well when tested on unseen polyp datasets from different distributions. With rich results, we demonstrated the robustness of the proposed architecture. From an efficiency perspective, our algorithm can process at (≈ 45) frames per second on RTX 3090 GPU. MKDCNet can be a strong benchmark for building real-time systems for clinical colonoscopies. The code of the proposed MKDCNet is available at https://github.com/nikhilroxtomar/MKDCNet.

Video Capsule Endoscopy Classification using Focal Modulation Guided Convolutional Neural Network.

Video capsule endoscopy is a hot topic in computer vision and medicine. Deep learning can have a positive impact on the future of video capsule endoscopy technology. It can improve the anomaly detection rate, reduce physicians' time for screening, and aid in real-world clinical analysis. Computer-Aided diagnosis (CADx) classification system for video capsule endoscopy has shown a great promise for further improvement. For example, detection of cancerous polyp and bleeding can lead to swift medical response and improve the survival rate of the patients. To this end, an automated CADx system must have high throughput and decent accuracy. In this study, we propose FocalConvNet, a focal modulation network integrated with lightweight convolutional layers for the classification of small bowel anatomical landmarks and luminal findings. FocalConvNet leverages focal modulation to attain global context and allows global-local spatial interactions throughout the forward pass. Moreover, the convolutional block with its intrinsic inductive/learning bias and capacity to extract hierarchical features allows our FocalConvNet to achieve favourable results with high throughput. We compare our FocalConvNet with other state-of-the-art (SOTA) on Kvasir-Capsule, a large-scale VCE dataset with 44,228 frames with 13 classes of different anomalies. We achieved the weighted F1-score, recall and Matthews correlation coefficient (MCC) of 0.6734, 0.6373 and 0.2974, respectively, outperforming SOTA methodologies. Further, we obtained the highest throughput of 148.02 images/second rate to establish the potential of FocalConvNet in a real-time clinical environment. The code of the proposed FocalConvNet is available at https://github.com/NoviceMAn-prog/FocalConvNet.

TGANet: Text-guided attention for improved polyp segmentation.

Colonoscopy is a gold standard procedure but is highly operator-dependent. Automated polyp segmentation, a precancerous precursor, can minimize missed rates and timely treatment of colon cancer at an early stage. Even though there are deep learning methods developed for this task, variability in polyp size can impact model training, thereby limiting it to the size attribute of the majority of samples in the training dataset that may provide sub-optimal results to differently sized polyps. In this work, we exploit size-related and polyp number-related features in the form of text attention during training. We introduce an auxiliary classification task to weight the text-based embedding that allows network to learn additional feature representations that can distinctly adapt to differently sized polyps and can adapt to cases with multiple polyps. Our experimental results demonstrate that these added text embeddings improve the overall performance of the model compared to state-of-the-art segmentation methods. We explore four different datasets and provide insights for size-specific improvements. Our proposed text-guided attention network (TGANet) can generalize well to variable-sized polyps in different datasets. Codes are available at https://github.com/nikhilroxtomar/TGANet.

Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning.

Computer-aided detection, localisation, and segmentation methods can help improve colonoscopy procedures. Even though many methods have been built to tackle automatic detection and segmentation of polyps, benchmarking of state-of-the-art methods still remains an open problem. This is due to the increasing number of researched computer vision methods that can be applied to polyp datasets. Benchmarking of novel methods can provide a direction to the development of automated polyp detection and segmentation tasks. Furthermore, it ensures that the produced results in the community are reproducible and provide a fair comparison of developed methods. In this paper, we benchmark several recent state-of-the-art methods using Kvasir-SEG, an open-access dataset of colonoscopy images for polyp detection, localisation, and segmentation evaluating both method accuracy and speed. Whilst, most methods in literature have competitive performance over accuracy, we show that the proposed ColonSegNet achieved a better trade-off between an average precision of 0.8000 and mean IoU of 0.8100, and the fastest speed of 180 frames per second for the detection and localisation task. Likewise, the proposed ColonSegNet achieved a competitive dice coefficient of 0.8206 and the best average speed of 182.38 frames per second for the segmentation task. Our comprehensive comparison with various state-of-the-art methods reveals the importance of benchmarking the deep learning methods for automated real-time polyp identification and delineations that can potentially transform current clinical practices and minimise miss-detection rates.

Principle of gradient rationality: Revisiting stigma and conceptualizing its guiding mechanism.

OBJECTIVE: Historically, much of the stigma research has relied on a language of attributes, using survey methodology for assessment, and the consumers' perspectives on stigma are also inadequate, hindering an in-depth understanding of social processes related to stigma. Thus, this study aims to understand the social processes guiding experiences of stigma among adults with serious mental illness. METHODS: Ethnographic methodology was employed to collect data for this study. Methods included interviews and participant observation. Participants included adults with serious mental illness (n = 18) and mental healthcare providers (n = 16), along with policy stakeholders/experts (n = 7). Data analysis was conducted via open and focused coding along with analytic interpretation. RESULTS: A social process guiding experiences of stigma, termed as the principle of gradient rationality (PoGR), is proposed. Three components to the principle are: 1) categorization via stigma or status symbols, 2) movement within hierarchy via exchange of social capital, and 3) institutionalization of stigma via interactional stigma. Briefly, the principle suggests that, during an interaction, individuals can be placed in a hierarchy of three roles/categories ("unreasonable," "high-functioning," or "normal") based on their measure of non-normative behavior. The lower one's position in the hierarchy, the more likely one is to experience stigma. Findings can help develop stigma measures that are sensitive to the variability of individuals experiencing mental illness and to the variability of stigma experiences on a personal/contextual level. Research in other settings is required to further study the applicability of this principle across contexts.

Statewide mental health training for probation officers: improving knowledge and decreasing stigma.

BACKGROUND: The large and growing number of probationers with mental illnesses pose significant challenges to the probationer officers who supervise them. Stigma towards mental illnesses among probation officers is largely unstudied and the effectiveness of training initiatives designed to educate probation officers about mental illness is unknown. To address these gaps in the literature, we report findings from a statewide mental health training initiative designed to improve probation officers' knowledge of mental illnesses. A single-group pretest posttest design was used and data about stigma towards mental illnesses and knowledge of mental illnesses were collected from 316 probation officers. Data were collected prior to and shortly after officers viewed a series of educational training modules about mental illnesses. RESULTS: Officers' knowledge of mental illnesses increased and officers demonstrated lower levels of stigma towards persons with mental illnesses as evidenced by scores on a standardized scale. CONCLUSION: Mental health education can help decrease stigma and increase knowledge of mental illnesses among probation officers. More research is needed to assess the impact of these trainings on probationers' mental health and criminal justice outcomes.

Examining the lived experience and factors influencing education of two student veterans using photovoice methodology.

OBJECTIVE. We sought to understand the lived experience of 2 student veterans and identify factors influencing their higher education. METHOD. A qualitative research design was used with 2 student veterans who engaged in photovoice methodology. We analyzed their photographs, accompanying narratives, and discussion session transcripts using descriptive coding and thematic analysis. RESULTS. Data analysis revealed four themes: (1) reminiscence of past duty and reflections on military life, (2) transition from military life to civilian student life, (3) entry to a new stage of life, and (4) influence of the university and community environment. CONCLUSION. Findings from this study revealed factors influencing student veterans' education and can be used to develop occupation-based interventions to assist veterans who engage in higher education.