Explainable 3D CNN based on baseline breast DCE-MRI to give an early prediction of pathological complete response to neoadjuvant chemotherapy

• Published in: Computers in biology and medicine Vol. 172; p. 108132
• Main Authors: Comes, Maria Colomba, Fanizzi, Annarita, Bove, Samantha, Didonna, Vittorio, Diotiaiuti, Sergio, Fadda, Federico, La Forgia, Daniele, Giotta, Francesco, Latorre, Agnese, Nardone, Annalisa, Palmiotti, Gennaro, Ressa, Cosmo Maurizio, Rinaldi, Lucia, Rizzo, Alessandro, Talienti, Tiziana, Tamborra, Pasquale, Zito, Alfredo, Lorusso, Vito, Massafra, Raffaella
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.04.2024; Elsevier Limited
• Subjects: Algorithms; Artificial intelligence; Artificial neural networks; Breast cancer; Cancer therapies; Chemotherapy; Cloning; Decision making; Deep learning; Identification; Information processing; Lymphatic system; Magnetic resonance imaging; Medical imaging; Neural networks; Patients; Surgery; Surgical outcomes; Italy
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108132

So far, baseline Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) has played a key role for the application of sophisticated artificial intelligence-based models using Convolutional Neural Networks (CNNs) to extract quantitative imaging information as earlier indicators of pathological Complete Response (pCR) achievement in breast cancer patients treated with neoadjuvant chemotherapy (NAC). However, these models did not exploit the DCE-MRI exams in their full geometry as 3D volume but analysed only few individual slices independently, thus neglecting the depth information. This study aimed to develop an explainable 3D CNN, which fulfilled the task of pCR prediction before the beginning of NAC, by leveraging the 3D information of post-contrast baseline breast DCE-MRI exams. Specifically, for each patient, the network took in input a 3D sequence containing the tumor region, which was previously automatically identified along the DCE-MRI exam. A visual explanation of the decision-making process of the network was also provided. To the best of our knowledge, our proposal is competitive than other models in the field, which made use of imaging data alone, reaching a median AUC value of 81.8%, 95%CI [75.3%; 88.3%], a median accuracy value of 78.7%, 95%CI [74.8%; 82.5%], a median sensitivity value of 69.8%, 95%CI [59.6%; 79.9%] and a median specificity value of 83.3%, 95%CI [82.6%; 84.0%], respectively. The median and CIs were computed according to a 10-fold cross-validation scheme for 5 rounds. Finally, this proposal holds high potential to support clinicians on non-invasively early pursuing or changing patient-centric NAC pathways. •The 3D information of baseline breast DCE-MRI exams is leveraged.•Our proposal outperforms other models in the field which made use of imaging data alone.•A median AUC of 81.8% on a 10-fold cross-validation scheme for 5 rounds is reached.•The peritumoral area is revealed as the most relevant zone for non-pCR class prediction.•The intratumoral area is revealed as the most informative zone for pCR class prediction.