Comparable prediction of breast cancer risk from a glimpse or a first impression of a mammogram

Expert radiologists can discern normal from abnormal mammograms with above-chance accuracy after brief (e.g. 500 ms) exposure. They can even predict cancer risk viewing currently normal images (priors) from women who will later develop cancer. This involves a rapid, global, non-selective process called “gist extraction”. It is not yet known whether prolonged exposure can strengthen the gist signal, or if it is available solely in the early exposure. This is of particular interest for the priors that do not contain any localizable signal of abnormality. The current study compared performance with brief (500 ms) or unlimited exposure for four types of mammograms (normal, abnormal, contralateral, priors). Groups of expert radiologists and untrained observers were tested. As expected, radiologists outperformed naïve participants. Replicating prior work, they exceeded chance performance though the gist signal was weak. However, we found no consistent performance differences in radiologists or naïves between timing conditions. Exposure time neither increased nor decreased ability to identify the gist of abnormality or predict cancer risk. If gist signals are to have a place in cancer risk assessments, more efforts should be made to strengthen the signal.

Comprehensive assessments of germline deletion structural variants reveal the association between prognostic MUC4 and CEP72 deletions and immune response gene expression in colorectal cancer patients

Background Functional disruptions by large germline genomic structural variants in susceptible genes are known risks for cancer. Few studies have used deletion structural variants (DSVs) to predict cancer risk with neural networks or studied the relationship between DSVs and immune gene expression to stratify prognosis.Methods Whole-genome sequencing (WGS) data was analyzed with the blood samples of 192 cancer and 499 noncancer subjects with or without family cancer history (FCH). Ninety-nine colorectal cancer (CRC) patients had immune response gene expression data. To build the cancer risk predictive model and identify DSVs in familial cancer, we used joint calling tools and attention-weighted model. The survival support vector machine (survival-SVM) was used to select prognostic DSVs. Results We identified 671 DSVs that could predict cancer risk. The area under the curve (AUC) of receiver operating characteristic curve (ROC) of attention-weighted model was 0.71. The 3 most frequent DSV genes observed in cancer patients were identified as ADCY9, AURKAPS1, and RAB3GAP2 (p < 0.05). We identified 65 immune-associated DSV markers for assessing cancer prognosis (P < 0.05). The functional protein of MUC4 DSV gene interacted with MAGE1expresssion, according to the STRING database. The causal inference model showed that deleting the CEP72 DSV gene could affect the recurrence-free survival (RFS) of IFIT1 expression. Conclusions We established an explainable attention-weighted model for cancer risk prediction and used the survival-SVM for prognostic stratification by using DSV and immune gene expression datasets. It can provide the genetic landscape of cancer patients and help predict the clinical outcome.

Developing global image feature analysis models to predict cancer risk and prognosis

In order to develop precision or personalized medicine, identifying new quantitative imaging markers and building machine learning models to predict cancer risk and prognosis has been attracting broad research interest recently. Most of these research approaches use the similar concepts of the conventional computer-aided detection schemes of medical images, which include steps in detecting and segmenting suspicious regions or tumors, followed by training machine learning models based on the fusion of multiple image features computed from the segmented regions or tumors. However, due to the heterogeneity and boundary fuzziness of the suspicious regions or tumors, segmenting subtle regions is often difficult and unreliable. Additionally, ignoring global and/or background parenchymal tissue characteristics may also be a limitation of the conventional approaches. In our recent studies, we investigated the feasibility of developing new computer-aided schemes implemented with the machine learning models that are trained by global image features to predict cancer risk and prognosis. We trained and tested several models using images obtained from full-field digital mammography, magnetic resonance imaging, and computed tomography of breast, lung, and ovarian cancers. Study results showed that many of these new models yielded higher performance than other approaches used in current clinical practice. Furthermore, the computed global image features also contain complementary information from the features computed from the segmented regions or tumors in predicting cancer prognosis. Therefore, the global image features can be used alone to develop new case-based prediction models or can be added to current tumor-based models to increase their discriminatory power.

A computational modelling approach for deriving biomarkers to predict cancer risk in premalignant disease

The lack of effective biomarkers for predicting cancer risk in premalignant disease is a major clinical problem. There is a near-limitless list of candidate biomarkers and it remains unclear how best to sample the tissue in space and time. Practical constraints mean that only a few of these candidate biomarker strategies can be evaluated empirically and there is no framework to determine which of the plethora of possibilities is the most promising. Here we have sought to solve this problem by developing a theoretical platform for in silico biomarker development. We construct a simple computational model of carcinogenesis in premalignant disease and use the model to evaluate an extensive list of tissue sampling strategies and different molecular measures of these samples. Our model predicts that: (i) taking more biopsies improves prognostication, but with diminishing returns for each additional biopsy; (ii) longitudinally-collected biopsies provide slightly more prognostic information than a single biopsy collected at the latest possible time-point; (iii) measurements of clonal diversity are more prognostic than measurements of the presence or absence of a particular abnormality and are particularly robust to confounding by tissue sampling; and (iv) the spatial pattern of clonal expansions is a particularly prognostic measure. This study demonstrates how the use of a mechanistic framework provided by computational modelling can diminish empirical constraints on biomarker development.