Automatic Detection of Liver Cancer Using Hybrid Pre-Trained Models

AI for interpreting screening mammograms: implications for missed cancer in double reading practices and challenging-to-locate lesions

Although the value of adding AI as a surrogate second reader in various scenarios has been investigated, it is unknown whether implementing an AI tool within double reading practice would capture additional subtle cancers missed by both radiologists who independently assessed the mammograms. This paper assesses the effectiveness of two state-of-the-art Artificial Intelligence (AI) models in detecting retrospectively-identified missed cancers within a screening program employing double reading practices. The study also explores the agreement between AI and radiologists in locating the lesions, considering various levels of concordance among the radiologists in locating the lesions. The Globally-aware Multiple Instance Classifier (GMIC) and Global-Local Activation Maps (GLAM) models were fine-tuned for our dataset. We evaluated the sensitivity of both models on missed cancers retrospectively identified by a panel of three radiologists who reviewed prior examinations of 729 cancer cases detected in a screening program with double reading practice. Two of these experts annotated the lesions, and based on their concordance levels, cases were categorized as 'almost perfect,' 'substantial,' 'moderate,' and 'poor.' We employed Similarity or Histogram Intersection (SIM) and Kullback-Leibler Divergence (KLD) metrics to compare saliency maps of malignant cases from the AI model with annotations from radiologists in each category. In total, 24.82% of cancers were labeled as "missed." The performance of GMIC and GLAM on the missed cancer cases was 82.98% and 79.79%, respectively, while for the true screen-detected cancers, the performances were 89.54% and 87.25%, respectively (p-values for the difference in sensitivity < 0.05). As anticipated, SIM and KLD from saliency maps were best in 'almost perfect,' followed by 'substantial,' 'moderate,' and 'poor.' Both GMIC and GLAM (p-values < 0.05) exhibited greater sensitivity at higher concordance. Even in a screening program with independent double reading, adding AI could potentially identify missed cancers. However, the challenging-to-locate lesions for radiologists impose a similar challenge for AI.

Using hybrid pre-trained models for breast cancer detection

Breast cancer is a prevalent and life-threatening disease that affects women globally. Early detection and access to top-notch treatment are crucial in preventing fatalities from this condition. However, manual breast histopathology image analysis is time-consuming and prone to errors. This study proposed a hybrid deep learning model (CNN+EfficientNetV2B3). The proposed approach utilizes convolutional neural networks (CNNs) for the identification of positive invasive ductal carcinoma (IDC) and negative (non-IDC) tissue using whole slide images (WSIs), which use pre-trained models to classify breast cancer in images, supporting pathologists in making more accurate diagnoses. The proposed model demonstrates outstanding performance with an accuracy of 96.3%, precision of 93.4%, recall of 86.4%, F1-score of 89.7%, Matthew's correlation coefficient (MCC) of 87.6%, the Area Under the Curve (AUC) of a Receiver Operating Characteristic (ROC) curve of 97.5%, and the Area Under the Curve of the Precision-Recall Curve (AUPRC) of 96.8%, which outperforms the accuracy achieved by other models. The proposed model was also tested against MobileNet+DenseNet121, MobileNetV2+EfficientNetV2B0, and other deep learning models, proving more powerful than contemporary machine learning and deep learning approaches.

Evaluating Recalibrating AI Models for Breast Cancer Diagnosis in a New Context: Insights from Transfer Learning, Image Enhancement and High-Quality Training Data Integration

This paper investigates the adaptability of four state-of-the-art artificial intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n = 856 cancer cases and n = 856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish two sets: a 'high-concordances subset' with 99% agreement of cancer location and an 'entire dataset' with all cases included. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&H and End2End AI models, both in the pretrained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with the transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by the GLAM model (0.909), I&H (0.893) and End2End (0.875). There were significant differences (p < 0.05) in the performances of the four AI models between the high-concordance subset and the entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with a strong concordance with radiologists' annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models.

Bibliometric analysis of the global scientific production on machine learning applied to different cancer types

Cancer disease is one of the main causes of death in the world, with million annual cases in the last decades. The need to find a cure has stimulated the search for efficient treatments and diagnostic procedures. One of the most promising tools that has emerged against cancer in recent years is machine learning (ML), which has raised a huge number of scientific papers published in a relatively short period of time. The present study analyzes global scientific production on ML applied to the most relevant cancer types through various bibliometric indicators. We find that over 30,000 studies have been published so far and observe that cancers with the highest number of published studies using ML (breast, lung, and colon cancer) are those with the highest incidence, being the USA and China the main scientific producers on the subject. Interestingly, the role of China and Japan in stomach cancer is correlated with the number of cases of this cancer type in Asia (78% of the worldwide cases). Knowing the countries and institutions that most study each area can be of great help for improving international collaborations between research groups and countries. Our analysis shows that medical and computer science journals lead the number of publications on the subject and could be useful for researchers in the field. Finally, keyword co-occurrence analysis suggests that ML-cancer research trends are focused not only on the use of ML as an effective diagnostic method, but also for the improvement of radiotherapy- and chemotherapy-based treatments.

Mixed reality navigation training system for liver surgery based on a high-definition human cross-sectional anatomy data set

OBJECTIVES

This study aims to use the three-dimensional (3D) mixed-reality model of liver, entailing complex intrahepatic systems and to deeply study the anatomical structures and to promote the training, diagnosis and treatment of liver diseases.

METHODS

Vascular perfusion human specimens were used for thin-layer frozen milling to obtain liver cross-sections. The 104-megapixel-high-definition cross sectional data set was established and registered to achieve structure identification and manual segmentation. The digital model was reconstructed and data was used to print a 3D hepatic model. The model was combined with HoloLens mixed reality technology to reflect the complex relationships of intrahepatic systems. We simulated 3D patient specific anatomy for identification and preoperative planning, conducted a questionnaire survey, and evaluated the results.

RESULTS

The 3D digital model and 1:1 transparent and colored model of liver established truly reflected intrahepatic vessels and their complex relationships. The reconstructed model imported into HoloLens could be accurately matched with the 3D model. Only 7.7% participants could identify accessory hepatic veins. The depth and spatial-relationship of intrahepatic structures were better understandable for 92%. The 100%, 84.6%, 69% and 84% believed the 3D models were useful in planning, safer surgical paths, reducing intraoperative complications and training of young surgeons respectively.

CONCLUSIONS

A detailed 3D model can be reconstructed using the higher quality cross-sectional anatomical data set. When combined with 3D printing and HoloLens technology, a novel hybrid-reality navigation-training system for liver surgery is created. Mixed Reality training is a worthy alternative to provide 3D information to clinicians and its possible application in surgery. This conclusion was obtained based on a questionnaire and evaluation. Surgeons with extensive experience in surgical operations perceived in the questionnaire that this technology might be useful in liver surgery, would help in precise preoperative planning, accurate intraoperative identification, and reduction of hepatic injury.