A Semiautomated Deep Learning Approach for Pancreas Segmentation

A deep learning detection method for pancreatic cystic neoplasm based on Mamba architecture

OBJECTIVE

Early diagnosis of pancreatic cystic neoplasm (PCN) is crucial for patient survival. This study proposes M-YOLO, a novel model combining Mamba architecture and YOLO, to enhance the detection of pancreatic cystic tumors. The model addresses the technical challenge posed by the tumors' complex morphological features in medical images.

METHODS

This study develops an innovative deep learning network architecture, M-YOLO (Mamba YOLOv10), which combines the advantages of Mamba and YOLOv10 and aims to improve the accuracy and efficiency of pancreatic cystic neoplasm(PCN) detection. The Mamba architecture, with its superior sequence modeling capabilities, is ideally suited for processing the rich contextual information contained in medical images. At the same time, YOLOv10's fast object detection feature ensures the system's viability for application in clinical practice.

RESULTS

M-YOLO has a high sensitivity of 0.98, a specificity of 0.92, a precision of 0.96, an F1 value of 0.97, an accuracy of 0.93, as well as a mean average precision (mAP) of 0.96 at 50% intersection-to-union (IoU) threshold on the dataset provided by Changhai Hospital.

CONCLUSIONS

M-YOLO(Mamba YOLOv10) enhances the identification performance of PCN by integrating the deep feature extraction capability of Mamba and the fast localization technique of YOLOv10.

Artificial Intelligence in Pancreatic Imaging: A Systematic Review

The rising incidence of pancreatic diseases, including acute and chronic pancreatitis and various pancreatic neoplasms, poses a significant global health challenge. Pancreatic ductal adenocarcinoma (PDAC) for example, has a high mortality rate due to late-stage diagnosis and its inaccessible location. Advances in imaging technologies, though improving diagnostic capabilities, still necessitate biopsy confirmation. Artificial intelligence, particularly machine learning and deep learning, has emerged as a revolutionary force in healthcare, enhancing diagnostic precision and personalizing treatment. This narrative review explores Artificial intelligence's role in pancreatic imaging, its technological advancements, clinical applications, and associated challenges. Following the PRISMA-DTA guidelines, a comprehensive search of databases including PubMed, Scopus, and Cochrane Library was conducted, focusing on Artificial intelligence, machine learning, deep learning, and radiomics in pancreatic imaging. Articles involving human subjects, written in English, and published up to March 31, 2024, were included. The review process involved title and abstract screening, followed by full-text review and refinement based on relevance and novelty. Recent Artificial intelligence advancements have shown promise in detecting and diagnosing pancreatic diseases. Deep learning techniques, particularly convolutional neural networks (CNNs), have been effective in detecting and segmenting pancreatic tissues as well as differentiating between benign and malignant lesions. Deep learning algorithms have also been used to predict survival time, recurrence risk, and therapy response in pancreatic cancer patients. Radiomics approaches, extracting quantitative features from imaging modalities such as CT, MRI, and endoscopic ultrasound, have enhanced the accuracy of these deep learning models. Despite the potential of Artificial intelligence in pancreatic imaging, challenges such as legal and ethical considerations, algorithm transparency, and data security remain. This review underscores the transformative potential of Artificial intelligence in enhancing the diagnosis and treatment of pancreatic diseases, ultimately aiming to improve patient outcomes and survival rates.

Main challenges on the curation of large scale datasets for pancreas segmentation using deep learning in multi-phase CT scans: Focus on cardinality, manual refinement, and annotation quality

Accurate segmentation of the pancreas in computed tomography (CT) holds paramount importance in diagnostics, surgical planning, and interventions. Recent studies have proposed supervised deep-learning models for segmentation, but their efficacy relies on the quality and quantity of the training data. Most of such works employed small-scale public datasets, without proving the efficacy of generalization to external datasets. This study explored the optimization of pancreas segmentation accuracy by pinpointing the ideal dataset size, understanding resource implications, examining manual refinement impact, and assessing the influence of anatomical subregions. We present the AIMS-1300 dataset encompassing 1,300 CT scans. Its manual annotation by medical experts required 938 h. A 2.5D UNet was implemented to assess the impact of training sample size on segmentation accuracy by partitioning the original AIMS-1300 dataset into 11 smaller subsets of progressively increasing numerosity. The findings revealed that training sets exceeding 440 CTs did not lead to better segmentation performance. In contrast, nnU-Net and UNet with Attention Gate reached a plateau for 585 CTs. Tests on generalization on the publicly available AMOS-CT dataset confirmed this outcome. As the size of the partition of the AIMS-1300 training set increases, the number of error slices decreases, reaching a minimum with 730 and 440 CTs, for AIMS-1300 and AMOS-CT datasets, respectively. Segmentation metrics on the AIMS-1300 and AMOS-CT datasets improved more on the head than the body and tail of the pancreas as the dataset size increased. By carefully considering the task and the characteristics of the available data, researchers can develop deep learning models without sacrificing performance even with limited data. This could accelerate developing and deploying artificial intelligence tools for pancreas surgery and other surgical data science applications.

Improved Pancreatic Cancer Detection and Localization on CT Scans: A Computer-Aided Detection Model Utilizing Secondary Features

The early detection of pancreatic ductal adenocarcinoma (PDAC) is essential for optimal treatment of pancreatic cancer patients. We propose a tumor detection framework to improve the detection of pancreatic head tumors on CT scans. In this retrospective research study, CT images of 99 patients with pancreatic head cancer and 98 control cases from the Catharina Hospital Eindhoven were collected. A multi-stage 3D U-Net-based approach was used for PDAC detection including clinically significant secondary features such as pancreatic duct and common bile duct dilation. The developed algorithm was evaluated using a local test set comprising 59 CT scans. The model was externally validated in 28 pancreatic cancer cases of a publicly available medical decathlon dataset. The tumor detection framework achieved a sensitivity of 0.97 and a specificity of 1.00, with an area under the receiver operating curve (AUROC) of 0.99, in detecting pancreatic head cancer in the local test set. In the external test set, we obtained similar results, with a sensitivity of 1.00. The model provided the tumor location with acceptable accuracy obtaining a DICE Similarity Coefficient (DSC) of 0.37. This study shows that a tumor detection framework utilizing CT scans and secondary signs of pancreatic cancer can detect pancreatic tumors with high accuracy.

Automated image analysis method to detect and quantify fat cell infiltration in hematoxylin and eosin stained human pancreas histology images

Fatty infiltration in pancreas leading to steatosis is a major risk factor in pancreas transplantation. Hematoxylin and eosin (H and E) is one of the common histological staining techniques that provides information on the tissue cytoarchitecture. Adipose (fat) cells accumulation in pancreas has been shown to impact beta cell survival, its endocrine function and pancreatic steatosis and can cause non-alcoholic fatty pancreas disease (NAFPD). The current automated tools (E.g. Adiposoft) available for fat analysis are suited for white fat tissue which is homogeneous and easier to segment unlike heterogeneous tissues such as pancreas where fat cells continue to play critical physiopathological functions. The currently, available pancreas segmentation tool focuses on endocrine islet segmentation based on cell nuclei detection for diagnosis of pancreatic cancer. In the current study, we present a fat quantifying tool, Fatquant, which identifies fat cells in heterogeneous H and E tissue sections with reference to diameter of fat cell. Using histological images from a public database, we observed an intersection over union of 0.797 to 0.962 and 0.675 to 0.937 for manual versus Fatquant analysis of pancreas and liver, respectively.

A Novel Extra Tree Ensemble Optimized DL Framework (ETEODL) for Early Detection of Diabetes

Diabetes has been recognized as a global medical problem for more than half a century. Patients with diabetes can benefit from the Internet of Things (IoT) devices such as continuous glucose monitoring (CGM), intelligent pens, and similar devices. Smart devices generate continuous data streams that must be processed in real-time to benefit the users. The amount of medical data collected is vast and heterogeneous since it is gathered from various sources. An accurate diagnosis can be achieved through a variety of scientific and medical techniques. It is necessary to process this streaming data faster to obtain relevant and significant knowledge. Recently, the research has concentrated on improving the prediction model's performance by using ensemble-based and Deep Learning (DL) approaches. However, the performance of the DL model can degrade due to overfitting. This paper proposes the Extra-Tree Ensemble feature selection technique to reduce the input feature space with DL (ETEODL), a predictive framework to predict the likelihood of diabetes. In the proposed work, dropout layers follow the hidden layers of the DL model to prevent overfitting. This research utilized a dataset from the UCI Machine learning (ML) repository for an Early-stage prediction of diabetes. The proposed scheme results have been compared with state-of-the-art ML algorithms, and the comparison validates the effectiveness of the predictive framework. This proposed work, which outperforms the other selected classifiers, achieves a 97.38 per cent accuracy rate. F1-Score, precision, and recall percent are 96, 97.7, and 97.7, respectively. The comparison unveils the superiority of the suggested approach. Thus, the proposed method effectively improves the performance against the earlier ML techniques and recent DL approaches and avoids overfitting.