No abstract

Clinical trials focusing on therapeutic candidates that modify β-amyloid (Aβ) have repeatedly failed to treat Alzheimer’s disease (AD), suggesting that Aβ may not be the optimal target for treating AD. The evaluation of Aβ, tau, and neurodegenerative (A/T/N) biomarkers has been proposed for classifying AD. However, it remains unclear whether disturbances in each arm of the A/T/N framework contribute equally throughout the progression of AD. Here, using the random forest machine learning method to analyze participants in the Alzheimer’s Disease Neuroimaging Initiative dataset, we show that A/T/N biomarkers show varying importance in predicting AD development, with elevated biomarkers of Aβ and tau better predicting early dementia status, and biomarkers of neurodegeneration, especially glucose hypometabolism, better predicting later dementia status. Our results suggest that AD treatments may also need to be disease stage-oriented with Aβ and tau as targets in early AD and glucose metabolism as a target in later AD.

Automated methods for breast cancer detection have focused on 2D mammography and have largely ignored 3D digital breast tomosynthesis (DBT), which is frequently used in clinical practice. The two key challenges in developing automated methods for DBT classification are handling the variable number of slices and retaining slice-to-slice changes. We propose a novel deep 2D convolutional neural network (CNN) architecture for DBT classification that simultaneously overcomes both challenges. Our approach operates on the full volume, regardless of the number of slices, and allows the use of pre-trained 2D CNNs for feature extraction, which is important given the limited amount of annotated training data. In an extensive evaluation on a real-world clinical dataset, our approach achieves 0.854 auROC, which is 28.80% higher than approaches based on 3D CNNs. We also find that these improvements are stable across a range of model configurations.

Breast cancer is the malignant tumor that causes the highest number of cancer deaths in females. Digital mammograms (DM or 2D mammogram) and digital breast tomosynthesis (DBT or 3D mammogram) are the two types of mammography imagery that are used in clinical practice for breast cancer detection and diagnosis. Radiologists usually read both imaging modalities in combination; however, existing computer-aided diagnosis tools are designed using only one imaging modality. Inspired by clinical practice, we propose an innovative convolutional neural network (CNN) architecture for breast cancer classification, which uses both 2D and 3D mammograms, simultaneously. Our experiment shows that the proposed method significantly improves the performance of breast cancer classification. By assembling three CNN classifiers, the proposed model achieves 0.97 AUC, which is 34.72% higher than the methods using only one imaging modality.

Background Over the past several decades, treatment development for Alzheimer’s disease (AD) has been largely focused on modifying amyloid‐beta (Aβ), but no drugs that modify the pathophysiological processes underlying the disease have been FDA approved; it is therefore possible that Aβ may not be the optimal target for treating AD. The NIA‐AA consortium has proposed the use of amyloid, tau, and neurodegenerative (A/T/N) biomarkers in diagnosis and treatment of AD. However, it remains unclear whether each arm of the A/T/N framework has an equally weighted contribution to the progression of AD or rather a stage‐dependent importance to AD development. Methods Here we use random forest, a machine learning algorithm, in participants from the ADNI dataset (Table 1) to predict AD cognitive decline using integrated biomarkers from the A/T/N framework: Aβ‐PET, CSF‐pTau, and FDG‐PET and MRI‐Structural, respectively (Table 2). We chose random forest for its high prediction accuracy and interpretability. We also analyzed the relationship between A/T/N biomarkers and memory composite and executive functioning composite scores. Results We show that the A/T/N biomarkers have stage‐dependent importance to AD development, with Aβ and phosphorylated‐tau (pTau) better predicting early dementia status (i.e. mild cognitive impairment) and neurodegeneration, especially low glucose uptake, better predicting later dementia status (i.e. clinical AD) (Table 3). We show a similar pattern when correlating markers to performance on memory and executive functioning tests. Conclusions Our results provide evidence that AD treatments may need to be stage‐oriented to match the natural disease progression. (Figure 1) Aβ and tau may be appropriate targets early in the disease course, but brain metabolic restoration should be explored as a treatment target later on in the disease process.