SenoCAD Research GmbH is dedicated to:
- Performing algorithmic and applied research to design innovative, reliable and cost-effective healthcare applications, using state-of-the-art Computer Vision and Artificial Intelligence (AI) methods.
- Design innovative methods for challenging clinical problems, such as the prediction of the resistance to the Neoadjuvant Chemotherapy in Cancer.
- Offering our healthcare applications as services that can be used in the frame of multicentric clinical studies.
It is our endeavor to:
- Improve the radiologist workflow thanks to state-of-the-art machine learning and computer vision algorithms.
- Empower the radiologist by providing him predictive radiomic features and a therapy resistance score that cannot be obtained by simple visual inspection of medical imaging data.
- Design AI-powered methods that are reliable for acceptance in clinical routine, and cost-effective for acceptance by healthcare payers.
We have addressed two interrelated clinical problems:
- Computer-Aided Detection, Segmentation and Characterization of Tumors in 3D medical images.
- Early prediction of the resistance/response to NACT in Breast Cancer.
-1- Computer-Aided Detection, Segmentation and Characterization of Tumors in 3D medical images
Our computer-aided tool is a unique integration of tasks that must be performed to generate the training data of our method for the prediction of the resistance to NACT:
- Fast interactive tumor localization.
- Fast tumor 3D segmentation.
- Tumor functional and metabolic characterization.
-2- Early prediction of the resistance/response to NACT in Breast Cancer
The pathological complete response of neoadjuvant chemotherapy for breast cancer correlates with the prognosis for survival (Zhao 2015), and many papers about the “Prediction of the pathological complete response to NACT” have been published in peer-reviewed journals. However, the pathological complete response rate is only 6%–45% depending on breast cancer subtype and treatment regimen. Hence, it is important to identify the non-responders at an early stage so that their treatment regimen can be modified, sparing them the long and short-term toxicities from ineffective chemotherapies (Song 2019).
The prediction of the response to NACT is a challenging clinical problem. We have designed a unique AI-powered method for the early prediction of the response to NACT. The proof of concept of our prediction method has given promising results in the case of locally advanced breast cancer. Now, these results must be validated by a large-scale multicentric clinical validation. Later on, our prediction method will be applied in cancer of other organs.
For each of the envisaged clinical problems, the following phases will be considered:
- Algorithmic Research & Proof-of-Concept: the aim is to design reliable and cost-efficient AI-powered prediction methods. The realization of the proof-of-concept (phase I study) is performed using publicly available medical data, and/or data provided by medical partners.
- Clinical Research: the objective is to demonstrate the replicability of results obtained by the proof-of-concept, in the frame of a multicentric clinical study (phase II study) led by a consortium of medical/industrial partners.
Our reliable AI-powered healthcare applications will be commercialized as cost-efficient cloud services that can be used for research in the frame of clinical studies.
Please, contact us using our Contact form, if you are interested to participate in a collaborative research project.
[Song 2019] Early Prediction of Breast Cancer Therapy Response using Multiresolution Fractal Analysis of DCE-MRI Parametric Maps. A. Machireddy, G. Thibault, A. Tudorica, A. Afzal, M. Mishal, K. Kemmer, A. Naik, M. Troxell, E. Goranson, K. Oh, N. Roy, N. Jafarian, M. Holtorf, W. Huang, and X. Song. Tomography.org | Volume 5 Number 1 | March 2019. Available at: https://www.tomography.org/media/vol5/issue1/pdf/tomo-05-090.pdf
[Zhao 2015] Evaluation of the pathological response and prognosis following neoadjuvant chemotherapy in molecular subtypes of breast cancer. Yue Zhao, Xiaoqiu Dong, Rongguo Li, Xiao Ma, Jian Song Yingjie Li, and Dongwei Zhang. Onco Targets Ther. 2015; 8: 1511–1521. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4480585/