Classification and Visualization of Chemotherapy-Induced Cognitive Impairment in Volumetric Convolutional Neural Networks

Breast cancer is the most common female cancer worldwide, and breast cancer accounts for 30% of female cancers. Of all the treatment modalities, breast cancer survivors who have undergone chemotherapy might complain about cognitive impairment during and after cancer treatment. This phenomenon, chemo-brain, is used to describe the alterations in cognitive functions after receiving systemic chemotherapy. Few reports detect the chemotherapy-induced cognitive impairment (CICI) by performing functional MRI (fMRI) and a deep learning analysis. In this study, we recruited 55 postchemotherapy breast cancer survivors (C+ group) and 65 healthy controls (HC group) and extracted mean fractional amplitudes of low-frequency fluctuations (mfALFF) from resting-state fMRI as our input feature. Two state-of-the-art deep learning architectures, ResNet-50 and DenseNet-121, were transformed to 3D, embedded with squeeze and excitation (SE) blocks and then trained to differentiate cerebral alterations based on the effect of chemotherapy. An integrated gradient was applied to visualize the pattern that was recognized by our model. The average performance of SE-ResNet-50 models was an accuracy of 80%, precision of 78% and recall of 70%; on the other hand, the SE-DenseNet-121 model reached identical results with an average of 80% accuracy, 86% precision and 80% recall. The regions with the greatest contributions highlighted by the integrated gradients algorithm for differentiating chemo-brain were the frontal, temporal, parietal and occipital lobe. These regions were consistent with other studies and strongly associated with the default mode and dorsal attention networks. We constructed two volumetric state-of-the-art models and visualized the patterns that are critical for identifying chemo-brains from normal brains. We hope that these results will be helpful in clinically tracking chemo-brain in the future.

Doxorubicin-Induced Cognitive Impairment: The Mechanistic Insights

Chemotherapy can significantly prolong the survival of patients with breast cancer; Nevertheless, the majority of patients receiving chemotherapy such as doxorubicin may have cognitive deficits that manifest as impairments in learning, reasoning, attention, and memory. The phenomenon of chemotherapy-induced cognitive decline is termed as chemotherapy-related cognitive impairment (CRCI) or chemo-brain. Doxorubicin (DOX), a commonly used drug in adjuvant chemotherapy for patients with breast cancer, has been reported to induce chemo-brain through a variety of mechanisms including DNA damage, oxidative stress, inflammation, dysregulation of apoptosis and autophagy, changes in neurotransmitter levels, mitochondrial dysfunction, glial cell interactions, neurogenesis inhibition, and epigenetic factors. These mechanisms do not operate independently but are inter-related, coordinately contributing to the development of chemo-brain. Here we review the relationships of these mechanisms and pathways in attempt to provide mechanistic insights into the doxorubicin-induced cognitive impairment.

Functional and Structural Connectome Features for Machine Learning Chemo-Brain Prediction in Women Treated for Breast Cancer with Chemotherapy

Breast cancer is the leading cancer among women worldwide, and a high number of breast cancer patients are struggling with psychological and cognitive disorders. In this study, we aim to use machine learning models to discriminate between chemo-brain participants and healthy controls (HCs) using connectomes (connectivity matrices) and topological coefficients. Nineteen female post-chemotherapy breast cancer (BC) survivors and 20 female HCs were recruited for this study. Participants in both groups received resting-state functional magnetic resonance imaging (rs-fMRI) and generalized q-sampling imaging (GQI). Logistic regression (LR), decision tree classifier (CART), and xgboost (XGB) were the models we adopted for classification. In connectome analysis, LR achieved an accuracy of 79.49% with the functional connectomes and an accuracy of 71.05% with the structural connectomes. In the topological coefficient analysis, accuracies of 87.18%, 82.05%, and 83.78% were obtained by the functional global efficiency with CART, the functional global efficiency with XGB, and the structural transitivity with CART, respectively. The areas under the curves (AUCs) were 0.93, 0.94, 0.87, 0.88, and 0.84, respectively. Our study showed the discriminating ability of functional connectomes, structural connectomes, and global efficiency. We hope our findings can contribute to an understanding of the chemo brain and the establishment of a clinical system for tracking chemo brain.

Stem cell therapies as a therapeutic option to counter chemo brain: a negative effect of cancer treatment

Chemo brain, a constellation of cognitive deficiencies followed by chemotherapy drugs, used to treat different types of cancers and adversely impacts the quality of life of a cancer survivor. The underlying mechanism of chemo brain remains vague, thus delaying the advancement of efficient treatments. Unfortunately, there is no US FDA approved medicine for chemo brain and often medicines considered for chemo brain are already the ones approved for other diseases. Nevertheless, researches exploring stem cell transplantation in different neurodegenerative diseases demonstrate that cellular transplantation could reverse chemotherapy-induced chemo brain. This review talks about the mechanism behind the cognitive impairments instigated by different chemotherapy drugs used in cancer treatment, and how stem cell therapy could be advantageous to overcome this disease.

The chemo-brain effect in colorectal cancer patients.

e24095 Background: The chemo-brain effect associated with systemic chemotherapy results in cognitive disturbances impacting the capacity to engage in tasks and quality of life (QOL). Patients with colorectal cancer (CRC) who receive adjuvant chemotherapy generally have long survival times. The long-term effect of chemotherapy on cognition is uncertain. We aimed to ascertain the frequency of long-term cognitive impairment using neuropsychological assessments and correlating with neuroimaging. Methods: In this prospective pilot study, patients (n=22) with stage II to III CRC between 45 to 75 years old, who were planned to receive adjuvant chemotherapy, were recruited. 3 visits were scheduled for each subject – pre-chemotherapy (V1), at 1 month post chemotherapy (V2), and at 6 months post chemotherapy (V3). Serial tests were performed – the Cambridge Neuropsychological Test Automated Battery (CANTAB), QOL questionnaires (Hospital Anxiety and Depression Scale (HADS), Perceived Deficits Questionnaire (PDQ), EORTC QLQ-C30, FACT-ES), 3 item pocket smell test, functional PET/MRI brain imaging, and blood biomarker studies. Results: 18/22 subjects (13 male, 5 female) had completed tests at all 3 visits; the median age was 62 years (range 51 – 69). 9/18 had an initial decline (median -0.033) of Rapid Visual Information processing (RVP) at V2; 3/9 showed improvement to baseline at V3. 8/18 had a persistent decline in RVP scores at V3 (median -0.054). This was associated with increased HADS depression scores (mean 3.63 at V2 vs 4.63 at V1), worsening attention scores (mean 4.38 at V3 and 3.63 at V1), prospective memory scores (mean 3.75 at V3 vs 3.38 at V1), and total scores (mean 14.63 at V3 vs 13.75 at V1) on the PDQ. 7/18 had an increase in Paired Associates Learning (PAL) errors (median +6) at V2. 3/7 improved to baseline at V3, while 4/7 continued to have a persistent decline. PAL scores were not associated with worsening retrospective or prospective PDQ memory scores, changes in HADS depression or EORTC QLQ-C30 scores. There was no difference in baseline CANTAB scores for patients reporting declining vs stable QLQ-C30 scores. Conclusions: Only half of patients with initial RVP A and PAL decline improved at 6 months post chemotherapy. Further efforts should be placed to identify those at risk of poor recovery, and develop strategies to manage the chemo-brain effect. The correlation of cognitive decline with neuroimaging will be presented in the final analysis.