We hypothesize that convolutional neural networks (CNN) can be used to predict neoadjuvant chemotherapy (NAC) response using a breast MRI tumor dataset prior to initiation of chemotherapy. An institutional review board-approved retrospective review of our database from January 2009 to June 2016 identified 141 locally advanced breast cancer patients who (1) underwent breast MRI prior to the initiation of NAC, (2) successfully completed adriamycin/taxane-based NAC, and (3) underwent surgical resection with available final surgical pathology data. Patients were classified into three groups based on their NAC response confirmed on final surgical pathology: complete (group 1), partial (group 2), and no response/progression (group 3). A total of 3107 volumetric slices of 141 tumors were evaluated. Breast tumor was identified on first T1 postcontrast dynamic images and underwent 3D segmentation. CNN consisted of ten convolutional layers, four max-pooling layers, and dropout of 50% after a fully connected layer. Dropout, augmentation, and L2 regularization were implemented to prevent overfitting of data. Non-linear functions were modeled by a rectified linear unit (ReLU). Batch normalization was used between the convolutional and ReLU layers to limit drift of layer activations during training. A three-class neoadjuvant prediction model was evaluated (group 1, group 2, or group 3). The CNN achieved an overall accuracy of 88% in three-class prediction of neoadjuvant treatment response. Three-class prediction discriminating one group from the other two was analyzed. Group 1 had a specificity of 95.1% ± 3.1%, sensitivity of 73.9% ± 4.5%, and accuracy of 87.7% ± 0.6%. Group 2 (partial response) had a specificity of 91.6% ± 1.3%, sensitivity of 82.4% ± 2.7%, and accuracy of 87.7% ± 0.6%. Group 3 (no response/progression) had a specificity of 93.4% ± 2.9%, sensitivity of 76.8% ± 5.7%, and accuracy of 87.8% ± 0.6%. It is feasible for current deep CNN architectures to be trained to predict NAC treatment response using a breast MRI dataset obtained prior to initiation of chemotherapy. Larger dataset will likely improve our prediction model.

UNLABELLED: MYCN-amplified neuroblastoma often presents as a highly aggressive metastatic disease with a poor prognosis. Activating transcription factor 5 (ATF5) is implicated in neural cell differentiation and cancer cell survival. Here, we show that ATF5 is highly expressed in patients with stage 4 high-risk neuroblastoma, with increased expression correlating with a poorer prognosis. We demonstrated that ATF5 promotes the metastasis of neuroblastoma cell lines in vivo. Functionally, ATF5 depletion significantly reduced xenograft tumor growth and metastasis of neuroblastoma cells to the bone marrow and liver. Mechanistically, ATF5 endows tumor cells with resistance to anoikis, thereby increasing their survival in systemic circulation and facilitating metastasis. We identified the proapoptotic BCL-2 modifying factor (BMF) as a critical player in ATF5-regulated neuroblastoma anoikis. ATF5 suppresses BMF under suspension conditions at the transcriptional level, promoting anoikis resistance, whereas BMF knockdown significantly prevents ATF5 depletion-induced anoikis. Therapeutically, we showed that a cell-penetrating dominant-negative ATF5 peptide, CP-d/n-ATF5, inhibits neuroblastoma metastasis to the bone marrow and liver by inducing anoikis sensitivity in circulating tumor cells. Our study identified ATF5 as a metastasis promoter and CP-d/n-ATF5 as a potential antimetastatic therapeutic agent for neuroblastoma. SIGNIFICANCE: This study shows that resistance to anoikis in neuroblastoma is mediated by ATF5 and offers a rationale for targeting ATF5 to treat metastatic neuroblastoma.